In this course, you will learn to work within the free and open-source R environment with a specific focus on working with and analyzing geospatial data. We will cover a wide variety of data and spatial data analytics topics, and you will learn how to code in R along the way. The Introduction module provides more background info about the course and course set up. This course is designed for someone with some prior GIS knowledge. For example, you should know the basics of working with maps, map projections, and vector and raster data. You should be able to perform common spatial analysis tasks and make map layouts. If you do not have a GIS background, we would recommend checking out the West Virginia View GIScience class. We do not assume that you have any prior experience with R or with coding. So, don't worry if you haven't developed these skill sets yet. That is a major goal in this course. Background material will be provided using code examples, videos, and presentations. We have provided assignments to offer hands-on learning opportunities. Data links for the lecture modules are provided within each module while data for the assignments are linked to the assignment buttons below. Please see the sequencing document for our suggested order in which to work through the material. After completing this course you will be able to: prepare, manipulate, query, and generally work with data in R. perform data summarization, comparisons, and statistical tests. create quality graphs, map layouts, and interactive web maps to visualize data and findings. present your research, methods, results, and code as web pages to foster reproducible research. work with spatial data in R. analyze vector and raster geospatial data to answer a question with a spatial component. make spatial models and predictions using regression and machine learning. code in the R language at an intermediate level.

This data repository hosts datasets that are used for students to practice spatial operations introduced in R-as-GIS lectures and workshops.

The Digital Geomorphic-GIS Map of Gulf Islands National Seashore (5-meter accuracy and 1-foot resolution 2006-2007 mapping), Mississippi and Florida is composed of GIS data layers and GIS tables, and is available in the following GRI-supported GIS data formats: 1.) a 10.1 file geodatabase (guis_geomorphology.gdb), a 2.) Open Geospatial Consortium (OGC) geopackage, and 3.) 2.2 KMZ/KML file for use in Google Earth, however, this format version of the map is limited in data layers presented and in access to GRI ancillary table information. The file geodatabase format is supported with a 1.) ArcGIS Pro map file (.mapx) file (guis_geomorphology.mapx) and individual Pro layer (.lyrx) files (for each GIS data layer), as well as with a 2.) 10.1 ArcMap (.mxd) map document (guis_geomorphology.mxd) and individual 10.1 layer (.lyr) files (for each GIS data layer). The OGC geopackage is supported with a QGIS project (.qgz) file. Upon request, the GIS data is also available in ESRI 10.1 shapefile format. Contact Stephanie O'Meara (see contact information below) to acquire the GIS data in these GIS data formats. In addition to the GIS data and supporting GIS files, three additional files comprise a GRI digital geologic-GIS dataset or map: 1.) A GIS readme file (guis_geology_gis_readme.pdf), 2.) the GRI ancillary map information document (.pdf) file (guis_geomorphology.pdf) which contains geologic unit descriptions, as well as other ancillary map information and graphics from the source map(s) used by the GRI in the production of the GRI digital geologic-GIS data for the park, and 3.) a user-friendly FAQ PDF version of the metadata (guis_geomorphology_metadata_faq.pdf). Please read the guis_geology_gis_readme.pdf for information pertaining to the proper extraction of the GIS data and other map files. Google Earth software is available for free at: https://www.google.com/earth/versions/. QGIS software is available for free at: https://www.qgis.org/en/site/. Users are encouraged to only use the Google Earth data for basic visualization, and to use the GIS data for any type of data analysis or investigation. The data were completed as a component of the Geologic Resources Inventory (GRI) program, a National Park Service (NPS) Inventory and Monitoring (I&M) Division funded program that is administered by the NPS Geologic Resources Division (GRD). For a complete listing of GRI products visit the GRI publications webpage: For a complete listing of GRI products visit the GRI publications webpage: https://www.nps.gov/subjects/geology/geologic-resources-inventory-products.htm. For more information about the Geologic Resources Inventory Program visit the GRI webpage: https://www.nps.gov/subjects/geology/gri,htm. At the bottom of that webpage is a "Contact Us" link if you need additional information. You may also directly contact the program coordinator, Jason Kenworthy (jason_kenworthy@nps.gov). Source geologic maps and data used to complete this GRI digital dataset were provided by the following: U.S. Geological Survey. Detailed information concerning the sources used and their contribution the GRI product are listed in the Source Citation section(s) of this metadata record (guis_geomorphology_metadata.txt or guis_geomorphology_metadata_faq.pdf). Users of this data are cautioned about the locational accuracy of features within this dataset. Based on the source map scale of 1:26,000 and United States National Map Accuracy Standards features are within (horizontally) 13.2 meters or 43.3 feet of their actual location as presented by this dataset. Users of this data should thus not assume the location of features is exactly where they are portrayed in Google Earth, ArcGIS, QGIS or other software used to display this dataset. All GIS and ancillary tables were produced as per the NPS GRI Geology-GIS Geodatabase Data Model v. 2.3. (available at: https://www.nps.gov/articles/gri-geodatabase-model.htm).

This dataset was created to be used in my Capstone Project for the Google Data Analytics Professional Certificate. Data was web scraped from the state websites to combine the GIS information like FIPS, latitude, longitude, and County Codes by both number and Mailing Number.

RStudio was used for this web scrape and join. For details on how it was done you can go to the following link for my Github repository.

Feel free to follow my Github or LinkedIn profile to see what I end up doing with this Dataset.

Today, deep neural networks are widely used in many computer vision problems, also for geographic information systems (GIS) data. This type of data is commonly used for urban analyzes and spatial planning. We used orthophotographic images of two residential districts from Kielce, Poland for research including urban sprawl automatic analysis with Transformer-based neural network application.Orthophotomaps were obtained from Kielce GIS portal. Then, the map was manually masked into building and building surroundings classes. Finally, the ortophotomap and corresponding classification mask were simultaneously divided into small tiles. This approach is common in image data preprocessing for machine learning algorithms learning phase. Data contains two original orthophotomaps from Wietrznia and Pod Telegrafem residential districts with corresponding masks and also their tiled version, ready to provide as a training data for machine learning models.Transformed-based neural network has undergone a training process on the Wietrznia dataset, targeted for semantic segmentation of the tiles into buildings and surroundings classes. After that, inference of the models was used to test model's generalization ability on the Pod Telegrafem dataset. The efficiency of the model was satisfying, so it can be used in automatic semantic building segmentation. Then, the process of dividing the images can be reversed and complete classification mask retrieved. This mask can be used for area of the buildings calculations and urban sprawl monitoring, if the research would be repeated for GIS data from wider time horizon.Since the dataset was collected from Kielce GIS portal, as the part of the Polish Main Office of Geodesy and Cartography data resource, it may be used only for non-profit and non-commertial purposes, in private or scientific applications, under the law "Ustawa z dnia 4 lutego 1994 r. o prawie autorskim i prawach pokrewnych (Dz.U. z 2006 r. nr 90 poz 631 z późn. zm.)". There are no other legal or ethical considerations in reuse potential.Data information is presented below.wietrznia_2019.jpg - orthophotomap of Wietrznia districtmodel's - used for training, as an explanatory imagewietrznia_2019.png - classification mask of Wietrznia district - used for model's training, as a target imagewietrznia_2019_validation.jpg - one image from Wietrznia district - used for model's validation during training phasepod_telegrafem_2019.jpg - orthophotomap of Pod Telegrafem district - used for model's evaluation after training phasewietrznia_2019 - folder with wietrznia_2019.jpg (image) and wietrznia_2019.png (annotation) images, divided into 810 tiles (512 x 512 pixels each), tiles with no information were manually removed, so the training data would contain only informative tilestiles presented - used for the model during training (images and annotations for fitting the model to the data)wietrznia_2019_vaidation - folder with wietrznia_2019_validation.jpg image divided into 16 tiles (256 x 256 pixels each) - tiles were presented to the model during training (images for validation model's efficiency); it was not the part of the training datapod_telegrafem_2019 - folder with pod_telegrafem.jpg image divided into 196 tiles (256 x 265 pixels each) - tiles were presented to the model during inference (images for evaluation model's robustness)Dataset was created as described below.Firstly, the orthophotomaps were collected from Kielce Geoportal (https://gis.kielce.eu). Kielce Geoportal offers a .pst recent map from April 2019. It is an orthophotomap with a resolution of 5 x 5 pixels, constructed from a plane flight at 700 meters over ground height, taken with a camera for vertical photos. Downloading was done by WMS in open-source QGIS software (https://www.qgis.org), as a 1:500 scale map, then converted to a 1200 dpi PNG image.Secondly, the map from Wietrznia residential district was manually labelled, also in QGIS, in the same scope, as the orthophotomap. Annotation based on land cover map information was also obtained from Kielce Geoportal. There are two classes - residential building and surrounding. Second map, from Pod Telegrafem district was not annotated, since it was used in the testing phase and imitates situation, where there is no annotation for the new data presented to the model.Next, the images was converted to an RGB JPG images, and the annotation map was converted to 8-bit GRAY PNG image.Finally, Wietrznia data files were tiled to 512 x 512 pixels tiles, in Python PIL library. Tiles with no information or a relatively small amount of information (only white background or mostly white background) were manually removed. So, from the 29113 x 15938 pixels orthophotomap, only 810 tiles with corresponding annotations were left, ready to train the machine learning model for the semantic segmentation task. Pod Telegrafem orthophotomap was tiled with no manual removing, so from the 7168 x 7168 pixels ortophotomap were created 197 tiles with 256 x 256 pixels resolution. There was also image of one residential building, used for model's validation during training phase, it was not the part of the training data, but was a part of Wietrznia residential area. It was 2048 x 2048 pixel ortophotomap, tiled to 16 tiles 256 x 265 pixels each.

ObjectivesXinjiang is one of the high TB burden provinces of China. A spatial analysis was conducted using geographical information system (GIS) technology to improve the understanding of geographic variation of the pulmonary TB occurrence in Xinjiang, its predictors, and to search for targeted interventions.MethodsNumbers of reported pulmonary TB cases were collected at county/district level from TB surveillance system database. Population data were extracted from Xinjiang Statistical Yearbook (2006~2014). Spatial autocorrelation (or dependency) was assessed using global Moran’s I statistic. Anselin’s local Moran’s I and local Getis-Ord statistics were used to detect local spatial clusters. Ordinary least squares (OLS) regression, spatial lag model (SLM) and geographically-weighted regression (GWR) models were used to explore the socio-demographic predictors of pulmonary TB incidence from global and local perspectives. SPSS17.0, ArcGIS10.2.2, and GeoDA software were used for data analysis.ResultsIncidence of sputum smear positive (SS+) TB and new SS+TB showed a declining trend from 2005 to 2013. Pulmonary TB incidence showed a declining trend from 2005 to 2010 and a rising trend since 2011 mainly caused by the rising trend of sputum smear negative (SS-) TB incidence (p

**THIS NEWER 2016 DIGITAL MAP REPLACES THE OLDER 2014 VERSION OF THE GRI GATE Geomorphological-GIS data. The Unpublished Digital Pre-Hurricane Sandy Geomorphological-GIS Map of the Gateway National Recreation Area: Sandy Hook, Jamaica Bay and Staten Island Units, New Jersey and New York is composed of GIS data layers and GIS tables in a 10.1 file geodatabase (gate_geomorphology.gdb), a 10.1 ArcMap (.MXD) map document (gate_geomorphology.mxd), individual 10.1 layer (.LYR) files for each GIS data layer, an ancillary map information (.PDF) document (gate_geomorphology.pdf) which contains source map unit descriptions, as well as other source map text, figures and tables, metadata in FGDC text (.TXT) and FAQ (.HTML) formats, and a GIS readme file (gate_gis_readme.pdf). Please read the gate_gis_readme.pdf for information pertaining to the proper extraction of the file geodatabase and other map files. To request GIS data in ESRI 10.1 shapefile format contact Stephanie O’Meara (stephanie.omeara@colostate.edu; see contact information below). The data is also available as a 2.2 KMZ/KML file for use in Google Earth, however, this format version of the map is limited in data layers presented and in access to GRI ancillary table information. Google Earth software is available for free at: http://www.google.com/earth/index.html. Users are encouraged to only use the Google Earth data for basic visualization, and to use the GIS data for any type of data analysis or investigation. The data were completed as a component of the Geologic Resources Inventory (GRI) program, a National Park Service (NPS) Inventory and Monitoring (I&M) Division funded program that is administered by the NPS Geologic Resources Division (GRD). Source geologic maps and data used to complete this GRI digital dataset were provided by the following: Rutgers University Institute of Marine and Coastal Sciences. Detailed information concerning the sources used and their contribution the GRI product are listed in the Source Citation section(s) of this metadata record (gate_metadata_faq.html; available at http://nrdata.nps.gov/geology/gri_data/gis/gate/gate_pre-sandy_metadata_faq.html). Users of this data are cautioned about the locational accuracy of features within this dataset. Based on the source map scale of 1:6,000 and United States National Map Accuracy Standards features are within (horizontally) 5.08 meters or 16.67 feet of their actual location as presented by this dataset. Users of this data should thus not assume the location of features is exactly where they are portrayed in Google Earth, ArcGIS or other software used to display this dataset. All GIS and ancillary tables were produced as per the NPS GRI Geology-GIS Geodatabase Data Model v. 2.3. (available at: http://science.nature.nps.gov/im/inventory/geology/GeologyGISDataModel.cfm). The GIS data projection is NAD83, UTM Zone 18N, however, for the KML/KMZ format the data is projected upon export to WGS84 Geographic, the native coordinate system used by Google Earth. The data is within the area of interest of Gateway National Recreation Area.

This dataset reflects reported incidents of crime (with the exception of murders where data exists for each victim) that occurred in the City of Chicago from 2001 to present, minus the most recent seven days. Data is extracted from the Chicago Police Department's CLEAR (Citizen Law Enforcement Analysis and Reporting) system. In order to protect the privacy of crime victims, addresses are shown at the block level only and specific locations are not identified. Should you have questions about this dataset, you may contact the Research & Development Division of the Chicago Police Department at 312.745.6071 or RandD@chicagopolice.org. Disclaimer: These crimes may be based upon preliminary information supplied to the Police Department by the reporting parties that have not been verified. The preliminary crime classifications may be changed at a later date based upon additional investigation and there is always the possibility of mechanical or human error. Therefore, the Chicago Police Department does not guarantee (either expressed or implied) the accuracy, completeness, timeliness, or correct sequencing of the information and the information should not be used for comparison purposes over time. The Chicago Police Department will not be responsible for any error or omission, or for the use of, or the results obtained from the use of this information. All data visualizations on maps should be considered approximate and attempts to derive specific addresses are strictly prohibited. The Chicago Police Department is not responsible for the content of any off-site pages that are referenced by or that reference this web page other than an official City of Chicago or Chicago Police Department web page. The user specifically acknowledges that the Chicago Police Department is not responsible for any defamatory, offensive, misleading, or illegal conduct of other users, links, or third parties and that the risk of injury from the foregoing rests entirely with the user. The unauthorized use of the words "Chicago Police Department," "Chicago Police," or any colorable imitation of these words or the unauthorized use of the Chicago Police Department logo is unlawful. This web page does not, in any way, authorize such use. Data is updated daily Tuesday through Sunday. The dataset contains more than 65,000 records/rows of data and cannot be viewed in full in Microsoft Excel. Therefore, when downloading the file, select CSV from the Export menu. Open the file in an ASCII text editor, such as Wordpad, to view and search. To access a list of Chicago Police Department - Illinois Uniform Crime Reporting (IUCR) codes, go to http://data.cityofchicago.org/Public-Safety/Chicago-Police-Department-Illinois-Uniform-Crime-R/c7ck-438e

Crowther_Nature_Files.zip This description pertains to the original download. Details on revised (newer) versions of the datasets are listed below. When more than one version of a file exists in Figshare, the original DOI will take users to the latest version, though each version technically has its own DOI. -- Two global maps (raster files) of tree density. These maps highlight how the number of trees varies across the world. One map was generated using biome-level models of tree density, and applied at the biome scale. The other map was generated using ecoregion-level models of tree density, and applied at the ecoregion scale. For this reason, transitions between biomes or between ecoregions may be unrealistically harsh, but large-scale estimates are robust (see Crowther et al 2015 and Glick et al 2016). At the outset, this study was intended to generate reliable estimates at broad spatial scales, which inherently comes at the cost of fine-scale precision. For this reason, country-scale (or larger) estimates are generally more robust than individual pixel-level estimates. Additionally, due to data limitations, estimates for Mangroves and Tropical coniferous forest (as identified by WWF and TNC) were generated using models constructed from Topical moist broadleaf forest data and Temperate coniferous forest data, respectively. Because we used ecological analogy, the estimates for these two biomes should be considered less reliable than those of other biomes . These two maps initially appeared in Crowther et al (2015), with the biome map being featured more prominently. Explicit publication of the data is associated with Glick et al (2016). As they are produced, updated versions of these datasets, as well as alternative formats, will be made available under Additional Versions (see below).

Methods: We collected over 420,000 ground-sources estimates of tree density from around the world. We then constructed linear regression models using vegetative, climatic, topographic, and anthropogenic variables to produce forest tree density estimates for all locations globally. All modeling was done in R. Mapping was done using R and ArcGIS 10.1.

Viewing Instructions: Load the files into an appropriate geographic information system (GIS). For the original download (ArcGIS geodatabase files), load the files into ArcGIS to view or export the data to other formats. Because these datasets are large and have a unique coordinate system that is not read by many GIS, we suggest loading them into an ArcGIS dataframe whose coordinate system matches that of the data (see File Format). For GeoTiff files (see Additional Versions), load them into any compatible GIS or image management program.

Comments: The original download provides a zipped folder that contains (1) an ArcGIS File Geodatabase (.gdb) containing one raster file for each of the two global models of tree density – one based on biomes and one based on ecoregions; (2) a layer file (.lyr) for each of the global models with the symbology used for each respective model in Crowther et al (2015); and an ArcGIS Map Document (.mxd) that contains the layers and symbology for each map in the paper. The data is delivered in the Goode homolosine interrupted projected coordinate system that was used to compute biome, ecoregion, and global estimates of the number and density of trees presented in Crowther et al (2015). To obtain maps like those presented in the official publication, raster files will need to be reprojected to the Eckert III projected coordinate system. Details on subsequent revisions and alternative file formats are list below under Additional Versions.----------

Additional Versions: Crowther_Nature_Files_Revision_01.zip contains tree density predictions for small islands that are not included in the data available in the original dataset. These predictions were not taken into consideration in production of maps and figures presented in Crowther et al (2015), with the exception of the values presented in Supplemental Table 2. The file structure follows that of the original data and includes both biome- and ecoregion-level models.

Crowther_Nature_Files_Revision_01_WGS84_GeoTiff.zip contains Revision_01 of the biome-level model, but stored in WGS84 and GeoTiff format. This file was produced by reprojecting the original Goode homolosine files to WGS84 using nearest neighbor resampling in ArcMap. All areal computations presented in the manuscript were computed using the Goode homolosine projection. This means that comparable computations made with projected versions of this WGS84 data are likely to differ (substantially at greater latitudes) as a product of the resampling. Included in this .zip file are the primary .tif and its visualization support files.

References:

Crowther, T. W., Glick, H. B., Covey, K. R., Bettigole, C., Maynard, D. S., Thomas, S. M., Smith, J. R., Hintler, G., Duguid, M. C., Amatulli, G., Tuanmu, M. N., Jetz, W., Salas, C., Stam, C., Piotto, D., Tavani, R., Green, S., Bruce, G., Williams, S. J., Wiser, S. K., Huber, M. O., Hengeveld, G. M., Nabuurs, G. J., Tikhonova, E., Borchardt, P., Li, C. F., Powrie, L. W., Fischer, M., Hemp, A., Homeier, J., Cho, P., Vibrans, A. C., Umunay, P. M., Piao, S. L., Rowe, C. W., Ashton, M. S., Crane, P. R., and Bradford, M. A. 2015. Mapping tree density at a global scale. Nature, 525(7568): 201-205. DOI: http://doi.org/10.1038/nature14967Glick, H. B., Bettigole, C. B., Maynard, D. S., Covey, K. R., Smith, J. R., and Crowther, T. W. 2016. Spatially explicit models of global tree density. Scientific Data, 3(160069), doi:10.1038/sdata.2016.69.

This collection of gridded data layers provides the extent of inundation in May 2020 resulting from the cyclone Amphan in 39 coastal districts in India and Bangladesh.

Input data:

These geospatial data layers are derived from Sentinel-1 dual-polarization C-band Synthetic Aperture Radar (SAR) data for pre-Amphan (May 5-18, 2020) and post-Amphan (May 22-30, 2020) periods. We accessed ready-to-use SAR data on Google Earth Engine (GEE). These input data were preprocessed using Ground Range Detected (GRD) border-noise removal, thermal noise removal, radiometric calibration, and terrain correction, to derive backscatter coefficients (σ°) in decibels (dB). We used VH polarisation instead of VV, since the latter is known to be affected by windy conditions as compared to VH.

Methods:

We developed a binary water/non-water classification scheme for the pre- and post-Amphan images using the automated Otsu thresholding approach that finds optimum threshold values based on clusters found in the histograms of pixel values. This analysis resulted in eight images: four each for pre-Amphan and post-Amphan periods (one each for coastal districts of Odisha and West Bengal and two for Bangladesh for each period). The pixels in these images have two values: 0 for non-water and 1 for water.

We then used a decision rule to identify areas that changed from ‘non-water’ to ‘water’ after the cyclone. The decision rule generated the ‘inundation layer’ with the permanent water bodies such as river, lakes, oceans and aquaculture masked out. This analysis resulted in four images, each with pixels with a value of 1 for inundated regions.

Data set format:

The spatial resolution of all the derived datasets is 10m. These georeferenced datasets are distributed in GEOTIFF format, and are compatible with GIS and/or image processing software, such as R and ArcGIS. The GIS-ready raster files can be used directly in mapping and geospatial analysis.

Data set for download:

A. Three data layers for Odisha, India:

OD_pre_binary.tif

OD_post_binary.tif

OD_inundation.tif

These data layers cover 10 districts: Baleshwar, Bhadrak, Cuttack, Jagatsinghpur, Jajpur, Kendrapara, Keonjhar, Khordha, Mayurbhanj and Puri.

B. Three data layers for West Bengal, India:

WB_pre_binary.tif

WB_post_binary.tif

WB_inundation.tif

These data layers cover 9 districts: Barddhaman, East Midnapore, Haora, Hugli, Kolkata, Nadia, North 24 Parganas, South 24 Parganas, and West Midnapore.

C. Six data layers for Bangladesh – three each for lower (L) region and upper (U) region.

BNG_L_pre_binary.tif

BNG_L_post_binary.tif

BNG_L_inundation.tif

BNG_U_pre_binary.tif

BNG_U_post_binary.tif

BNG_U_inundation.tif

The data layers for the lower region cover 11 districts: Bagerhat, Barguna, Barisal, Bhola, Jhalokati, Khulna, Lakshmipur, Noakhali, Patuakhali, Pirojpur, and Satkhira.

The data layers for the upper region cover 9 districts: Chuadanga, Jessore, Jhenaidah, Kushtia, Meherpur, Naogaon, Natore, Pabna, and Rajshahi.

This seminar is an applied study of deep learning methods for extracting information from geospatial data, such as aerial imagery, multispectral imagery, digital terrain data, and other digital cartographic representations. We first provide an introduction and conceptualization of artificial neural networks (ANNs). Next, we explore appropriate loss and assessment metrics for different use cases followed by the tensor data model, which is central to applying deep learning methods. Convolutional neural networks (CNNs) are then conceptualized with scene classification use cases. Lastly, we explore semantic segmentation, object detection, and instance segmentation. The primary focus of this course is semantic segmenation for pixel-level classification. The associated GitHub repo provides a series of applied examples. We hope to continue to add examples as methods and technologies further develop. These examples make use of a vareity of datasets (e.g., SAT-6, topoDL, Inria, LandCover.ai, vfillDL, and wvlcDL). Please see the repo for links to the data and associated papers. All examples have associated videos that walk through the process, which are also linked to the repo. A variety of deep learning architectures are explored including UNet, UNet++, DeepLabv3+, and Mask R-CNN. Currenlty, two examples use ArcGIS Pro and require no coding. The remaining five examples require coding and make use of PyTorch, Python, and R within the RStudio IDE. It is assumed that you have prior knowledge of coding in the Python and R enviroinments. If you do not have experience coding, please take a look at our Open-Source GIScience and Open-Source Spatial Analytics (R) courses, which explore coding in Python and R, respectively. After completing this seminar you will be able to: explain how ANNs work including weights, bias, activation, and optimization. describe and explain different loss and assessment metrics and determine appropriate use cases. use the tensor data model to represent data as input for deep learning. explain how CNNs work including convolutional operations/layers, kernel size, stride, padding, max pooling, activation, and batch normalization. use PyTorch, Python, and R to prepare data, produce and assess scene classification models, and infer to new data. explain common semantic segmentation architectures and how these methods allow for pixel-level classification and how they are different from traditional CNNs. use PyTorch, Python, and R (or ArcGIS Pro) to prepare data, produce and assess semantic segmentation models, and infer to new data.

Overview:
The Copernicus DEM is a Digital Surface Model (DSM) which represents the surface of the Earth including buildings, infrastructure and vegetation. The original GLO-30 provides worldwide coverage at 30 meters (refers to 10 arc seconds). Note that ocean areas do not have tiles, there one can assume height values equal to zero. Data is provided as Cloud Optimized GeoTIFFs. Note that the vertical unit for measurement of elevation height is meters.

The Copernicus DEM for Europe at 3 arcsec (0:00:03 = 0.00083333333 ~ 90 meter) in COG format has been derived from the Copernicus DEM GLO-30, mirrored on Open Data on AWS, dataset managed by Sinergise (https://registry.opendata.aws/copernicus-dem/).

Processing steps:
The original Copernicus GLO-30 DEM contains a relevant percentage of tiles with non-square pixels. We created a mosaic map in VRT format and defined within the VRT file the rule to apply cubic resampling while reading the data, i.e. importing them into GRASS GIS for further processing. We chose cubic instead of bilinear resampling since the height-width ratio of non-square pixels is up to 1:5. Hence, artefacts between adjacent tiles in rugged terrain could be minimized:

gdalbuildvrt -input_file_list list_geotiffs_MOOD.csv -r cubic -tr 0.000277777777777778 0.000277777777777778 Copernicus_DSM_30m_MOOD.vrt

In order to reduce the spatial resolution to 3 arc seconds, weighted resampling was performed in GRASS GIS (using r.resamp.stats -w and the pixel values were scaled with 1000 (storing the pixels as integer values) for data volume reduction. In addition, a hillshade raster map was derived from the resampled elevation map (using r.relief, GRASS GIS). Eventually, we exported the elevation and hillshade raster maps in Cloud Optimized GeoTIFF (COG) format, along with SLD and QML style files.

Projection + EPSG code:
Latitude-Longitude/WGS84 (EPSG: 4326)

Spatial extent:
north: 82:00:30N
south: 18N
west: 32:00:30W
east: 70E

Spatial resolution:
3 arc seconds (approx. 90 m)

Pixel values:
meters * 1000 (scaled to Integer; example: value 23220 = 23.220 m a.s.l.)

Software used:
GDAL 3.2.2 and GRASS GIS 8.0.0 (r.resamp.stats -w; r.relief)

Original dataset license:
https://spacedata.copernicus.eu/documents/20126/0/CSCDA_ESA_Mission-specific+Annex.pdf

Processed by:
mundialis GmbH & Co. KG, Germany (https://www.mundialis.de/)

Catholic Carbon Footprint Story Map Map:DataBurhans, Molly A., Cheney, David M., Gerlt, R.. . “PerCapita_CO2_Footprint_InDioceses_FULL”. Scale not given. Version 1.0. MO and CT, USA: GoodLands Inc., Environmental Systems Research Institute, Inc., 2019.Map Development: Molly BurhansMethodologyThis is the first global Carbon footprint of the Catholic population. We will continue to improve and develop these data with our research partners over the coming years. While it is helpful, it should also be viewed and used as a "beta" prototype that we and our research partners will build from and improve. The years of carbon data are (2010) and (2015 - SHOWN). The year of Catholic data is 2018. The year of population data is 2016. Care should be taken during future developments to harmonize the years used for catholic, population, and CO2 data.1. Zonal Statistics: Esri Population Data and Dioceses --> Population per dioceses, non Vatican based numbers2. Zonal Statistics: FFDAS and Dioceses and Population dataset --> Mean CO2 per Diocese3. Field Calculation: Population per Diocese and Mean CO2 per diocese --> CO2 per Capita4. Field Calculation: CO2 per Capita * Catholic Population --> Catholic Carbon FootprintAssumption: PerCapita CO2Deriving per-capita CO2 from mean CO2 in a geography assumes that people's footprint accounts for their personal lifestyle and involvement in local business and industries that are contribute CO2. Catholic CO2Assumes that Catholics and non-Catholic have similar CO2 footprints from their lifestyles.Derived from:A multiyear, global gridded fossil fuel CO2 emission data product: Evaluation and analysis of resultshttp://ffdas.rc.nau.edu/About.htmlRayner et al., JGR, 2010 - The is the first FFDAS paper describing the version 1.0 methods and results published in the Journal of Geophysical Research.Asefi et al., 2014 - This is the paper describing the methods and results of the FFDAS version 2.0 published in the Journal of Geophysical Research.Readme version 2.2 - A simple readme file to assist in using the 10 km x 10 km, hourly gridded Vulcan version 2.2 results.Liu et al., 2017 - A paper exploring the carbon cycle response to the 2015-2016 El Nino through the use of carbon cycle data assimilation with FFDAS as the boundary condition for FFCO2."S. Asefi‐Najafabady P. J. Rayner K. R. Gurney A. McRobert Y. Song K. Coltin J. Huang C. Elvidge K. BaughFirst published: 10 September 2014 https://doi.org/10.1002/2013JD021296 Cited by: 30Link to FFDAS data retrieval and visualization: http://hpcg.purdue.edu/FFDAS/index.phpAbstractHigh‐resolution, global quantification of fossil fuel CO2 emissions is emerging as a critical need in carbon cycle science and climate policy. We build upon a previously developed fossil fuel data assimilation system (FFDAS) for estimating global high‐resolution fossil fuel CO2 emissions. We have improved the underlying observationally based data sources, expanded the approach through treatment of separate emitting sectors including a new pointwise database of global power plants, and extended the results to cover a 1997 to 2010 time series at a spatial resolution of 0.1°. Long‐term trend analysis of the resulting global emissions shows subnational spatial structure in large active economies such as the United States, China, and India. These three countries, in particular, show different long‐term trends and exploration of the trends in nighttime lights, and population reveal a decoupling of population and emissions at the subnational level. Analysis of shorter‐term variations reveals the impact of the 2008–2009 global financial crisis with widespread negative emission anomalies across the U.S. and Europe. We have used a center of mass (CM) calculation as a compact metric to express the time evolution of spatial patterns in fossil fuel CO2 emissions. The global emission CM has moved toward the east and somewhat south between 1997 and 2010, driven by the increase in emissions in China and South Asia over this time period. Analysis at the level of individual countries reveals per capita CO2 emission migration in both Russia and India. The per capita emission CM holds potential as a way to succinctly analyze subnational shifts in carbon intensity over time. Uncertainties are generally lower than the previous version of FFDAS due mainly to an improved nightlight data set."Global Diocesan Boundaries:Burhans, M., Bell, J., Burhans, D., Carmichael, R., Cheney, D., Deaton, M., Emge, T. Gerlt, B., Grayson, J., Herries, J., Keegan, H., Skinner, A., Smith, M., Sousa, C., Trubetskoy, S. “Diocesean Boundaries of the Catholic Church” [Feature Layer]. Scale not given. Version 1.2. Redlands, CA, USA: GoodLands Inc., Environmental Systems Research Institute, Inc., 2016.Using: ArcGIS. 10.4. Version 10.0. Redlands, CA: Environmental Systems Research Institute, Inc., 2016.Boundary ProvenanceStatistics and Leadership DataCheney, D.M. “Catholic Hierarchy of the World” [Database]. Date Updated: August 2019. Catholic Hierarchy. Using: Paradox. Retrieved from Original Source.Catholic HierarchyAnnuario Pontificio per l’Anno .. Città del Vaticano :Tipografia Poliglotta Vaticana, Multiple Years.The data for these maps was extracted from the gold standard of Church data, the Annuario Pontificio, published yearly by the Vatican. The collection and data development of the Vatican Statistics Office are unknown. GoodLands is not responsible for errors within this data. We encourage people to document and report errant information to us at data@good-lands.org or directly to the Vatican.Additional information about regular changes in bishops and sees comes from a variety of public diocesan and news announcements.GoodLands’ polygon data layers, version 2.0 for global ecclesiastical boundaries of the Roman Catholic Church:Although care has been taken to ensure the accuracy, completeness and reliability of the information provided, due to this being the first developed dataset of global ecclesiastical boundaries curated from many sources it may have a higher margin of error than established geopolitical administrative boundary maps. Boundaries need to be verified with appropriate Ecclesiastical Leadership. The current information is subject to change without notice. No parties involved with the creation of this data are liable for indirect, special or incidental damage resulting from, arising out of or in connection with the use of the information. We referenced 1960 sources to build our global datasets of ecclesiastical jurisdictions. Often, they were isolated images of dioceses, historical documents and information about parishes that were cross checked. These sources can be viewed here:https://docs.google.com/spreadsheets/d/11ANlH1S_aYJOyz4TtG0HHgz0OLxnOvXLHMt4FVOS85Q/edit#gid=0To learn more or contact us please visit: https://good-lands.org/Esri Gridded Population Data 2016DescriptionThis layer is a global estimate of human population for 2016. Esri created this estimate by modeling a footprint of where people live as a dasymetric settlement likelihood surface, and then assigned 2016 population estimates stored on polygons of the finest level of geography available onto the settlement surface. Where people live means where their homes are, as in where people sleep most of the time, and this is opposed to where they work. Another way to think of this estimate is a night-time estimate, as opposed to a day-time estimate.Knowledge of population distribution helps us understand how humans affect the natural world and how natural events such as storms and earthquakes, and other phenomena affect humans. This layer represents the footprint of where people live, and how many people live there.Dataset SummaryEach cell in this layer has an integer value with the estimated number of people likely to live in the geographic region represented by that cell. Esri additionally produced several additional layers World Population Estimate Confidence 2016: the confidence level (1-5) per cell for the probability of people being located and estimated correctly. World Population Density Estimate 2016: this layer is represented as population density in units of persons per square kilometer.World Settlement Score 2016: the dasymetric likelihood surface used to create this layer by apportioning population from census polygons to the settlement score raster.To use this layer in analysis, there are several properties or geoprocessing environment settings that should be used:Coordinate system: WGS_1984. This service and its underlying data are WGS_1984. We do this because projecting population count data actually will change the populations due to resampling and either collapsing or splitting cells to fit into another coordinate system. Cell Size: 0.0013474728 degrees (approximately 150-meters) at the equator. No Data: -1Bit Depth: 32-bit signedThis layer has query, identify, pixel, and export image functions enabled, and is restricted to a maximum analysis size of 30,000 x 30,000 pixels - an area about the size of Africa.Frye, C. et al., (2018). Using Classified and Unclassified Land Cover Data to Estimate the Footprint of Human Settlement. Data Science Journal. 17, p.20. DOI: http://doi.org/10.5334/dsj-2018-020.What can you do with this layer?This layer is unsuitable for mapping or cartographic use, and thus it does not include a convenient legend. Instead, this layer is useful for analysis, particularly for estimating counts of people living within watersheds, coastal areas, and other areas that do not have standard boundaries. Esri recommends using the Zonal Statistics tool or the Zonal Statistics to Table tool where you provide input zones as either polygons, or raster data, and the tool will summarize the count of population within those zones. https://www.esri.com/arcgis-blog/products/arcgis-living-atlas/data-management/2016-world-population-estimate-services-are-now-available/

This map displays projected visible surface smoke across the contiguous United States for the next 48 hours in 1 hour increments. It is updated every 24 hours by NWS. Concentrations are reported in micrograms per cubic meter.Where is the data coming from?The National Digital Guidance Database (NDGD) is a sister to the National Digital Forecast Database (NDFD). Information in NDGD may be used by NWS forecasters as guidance in preparing official NWS forecasts in NDFD. The experimental/guidance NDGD data is not an official NWS forecast product.Source: https://tgftp.nws.noaa.gov/SL.us008001/ST.opnl/DF.gr2/DC.ndgd/GT.aq/AR.conus/ds.smokes01.binSource data archive can be found here: https://www.ncei.noaa.gov/products/weather-climate-models/national-digital-guidance-database look for 'LXQ...' files by date. These are the Binary GRIB2 files that can be decoded via DeGRIB tool.Where can I find other NDGD data?The Source data is downloaded and parsed using the Aggregated Live Feeds methodology to return information that can be served through ArcGIS Server as a map service or used to update Hosted Feature Services in Online or Enterprise.What can you do with this layer?This map service is suitable for data discovery and visualization. Identify features by clicking on the map to reveal the pre-configured pop-ups. View the time-enabled data using the time slider by Enabling Time Animation.RevisionsJuly 11, 2022: Feed updated to leverage forecast model change by NOAA, whereby the Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) forecast model system was replaced with the Rapid Refresh (RAP) forecast model system. Key differences: higher accuracy with RAP now concentrated at 0-8 meter detail vs HYSPLIT at 0-100 meter; earlier data delivery by 6 hrs; forecast output extended to 51 hrs.This map is provided for informational purposes and is not monitored 24/7 for accuracy and currency.If you would like to be alerted to potential issues or simply see when this Service will update next, please visit our Live Feed Status Page!

This abstract contains links to public ArcGIS maps that include locations of carbonate springs and some of their characteristics. Information for accessing and navigating through the maps are included in a PowerPoint presentation IN THE FILE UPLOAD SECTION BELOW. Three separate data sets are included in the maps:

1. Geochemistry data from the US Water Quality Portal (WQP), which compiles geochemistry data from the USGS and other federal agencies.
2. Discharge data from WoKaS, a world wide spring discharge data set (Olarinoye et al., 2020).
3. Regional karst data from selected US state agencies.

Several base maps are included in the links. The US carbonate map describes and categorizes carbonates (e.g., depth from surface, overlying geology/ice, climate). The carbonate springs map categorizes springs as being urban, specifically within 1000 ft of a road, or rural. The basis for this categorization was that the heat island effect defines urban as within a 1000 ft of a road. There are other methods for defining urban versus rural to consider. Map links and details of the information they contain are listed below.

Map set 1: The WQP map provides three mapping options separated by the parameters available at each spring site. These maps summarize discrete water quality samples, but not data logger availability. Information at each spring provides links for where users can explore further data.

Option 1: WQP data with urban and rural springs labeled, with highlight of springs with or without NWIS data https://www.arcgis.com/home/item.html?id=2ce914ec01f14c20b58146f5d9702d8a

Options 2: WQP data by major ions and a few other solutes https://www.arcgis.com/home/item.html?id=5a114d2ce24c473ca07ef9625cd834b8

Option 3:WQP data by various carbon species https://www.arcgis.com/home/item.html?id=ae406f1bdcd14f78881905c5e0915b96

Map 2: The worldwide carbonate map in the WoKaS data set (citation below) includes a description of carbonate purity and distribution of urban and rural springs, for which discharge data are available: https://www.arcgis.com/apps/mapviewer/index.html?webmap=5ab43fdb2b784acf8bef85b61d0ebcbe.

Reference: Olarinoye, T., Gleeson, T., Marx, V., Seeger, S., Adinehvand, R., Allocca, V., Andreo, B., Apaéstegui, J., Apolit, C., Arfib, B. and Auler, A., 2020. Global karst springs hydrograph dataset for research and management of the world’s fastest-flowing groundwater. Scientific Data, 7(1), pp.1-9.

Map 3: Karst and spring data from selected states: This map includes sites that members of the RCN have suggested to our group.

https://uageos.maps.arcgis.com/apps/mapviewer/index.html?webmap=28ed22a14bb749e2b22ece82bf8a8177

This data set is incomplete (as of October 13, 2022 it includes Florida and Missouri). We are looking for more information. You can share data links to additional data by typing them into the hydroshare page created for our group. Then new sites will periodically be added to the map: https://www.hydroshare.org/resource/0cf10e9808fa4c5b9e6a7852323e6b11/

Acknowledgements: These maps were created by Michael Jones, University of Arkansas and Shishir Sarker, University of Kentucky with help from Laura Toran and Francesco Navarro, Temple University.

TIPS FOR NAVIGATING THE MAPS ARE IN THE POWERPOINT DOCUMENT IN THE FILE UPLOAD SECTION BELOW.

Read me – Schimmelradar manuscript

The code in this repository was written to analyse the data and generate figures for the manuscript “Land use drives spatial structure of drug resistance in a fungal pathogen”.

This repository consists of two original .csv raw data files, 2 .tif files that are minimally reformatted after being downloaded from LGN.nl and www.pdok.nl/introductie/-/article/basisregistratie-gewaspercelen-brp-, and 9 scripts using the R language. The remaining files include intermediate .tif and .csv files to skip more computationally heavy steps of the analysis and facilitate the reproduction of the analysis.

Data files:§1

Schimmelradar_360_submission.csv: The raw phenotypic resistance spatial data from the air sample

• Sample: an arbitrary sample code given to each of the participants

• Area: A random number assigned to each of the 100 areas the Netherlands was split up into to facilitate an even spread of samples across the country during participant selection.

• Logistics status: Variable used to indicate whether the sample was returned in good order, not otherwise used in the analysis.

• Arrived back on: The date by which the sample arrived back at Wageningen University

• Quality seals: quality of the seals upon sample return, only samples of a quality designated as good seals were processed. (also see Supplement file – section A).

• Start sampling: The date on which the trap was deployed and the stickers exposed to the air, recorded by the participant

• End sampling: The date on which the trap was taken down and the stickers were re-covered and no longer exposed to the air, recorded by the participant

• 3 back in area?: Binary indicating whether at least three samples have been returned in the respective area (see Area)

• Batch: The date on which processing of the sample was started. To be more specific, the date at which Flamingo medium was poured over the seals of the sample and incubation was started.

• Lab processing: Binary indication completion of lab processing

• Tot ITR: A. fumigatus CFU count in the permissive layer of the itraconazole-treated plate

• RES ITR: CFU count of colonies that had breached the surface of the itraconazole-treated layer after incubation and were visually (with the unaided eye) sporulating.

• RF ITR: The itraconazole (~4 mg/L) resistance fraction = RES ITR/Tot ITR

• Muccor ITR: Indication of the presence of Mucorales spp. growth on the itraconazole treatment plate

• Tot VOR: A. fumigatus CFU count in the permissive layer of the voriconazole-treated plate

• RES VOR: CFU count of colonies that had breached the surface of the voriconazole-treated layer after incubation and were visually (with the unaided eye) sporulating.

• RF VOR: The voriconazole (~2 mg/L) resistance fraction = RES VOR/Tot VOR

• Muccor VOR: Indication of the presence of Mucorales spp. growth on the voriconazole treatment plate

• Tot CON: CFU count on the untreated growth control plate Note: note on the sample based on either information given by the participant or observations in the lab. The exclude label was given if the sample had either too little (<25) or too many (>300) CFUs on one or more of the plates (also see Supplement file – section A).

• Lat: Exact latitude of the address where the sample was taken. Not used in the published version of the code and hidden for privacy reasons.

• Long: Exact longitude of the address where the sample was taken. Not used in the published version of the code and hidden for privacy reasons.

• Round_Lat: Rounded latitude of the address where the sample was taken. Rounded down to two decimals (the equivalent of a 1 km2 area), so they could not be linked to a specific address. Used in the published version of the code.

• Round_Long: Rounded longitude of the address where the sample was taken. Rounded down to two decimals (the equivalent of a 1 km2 area), so they could not be linked to a specific address. Used in the published version of the code.

Analysis_genotypic_schimmelradar_TR_types.csv: The genotype data inferred from gel electrophoresis for all resistant isolates

• TR type: Indicates the length of the tandem repeats in bp, as judged from a gel. 34 bp, 46 bp, or multiples of 46.

• Plate: 96-well plate on which the isolate was cultured

• 96-well: well in which the isolate was cultured

• Azole: Azole on which the isolate was grown and resistant to. Itraconazole (ITRA) or Voriconazole (VORI).

• Sample: The air sample the isolate was taken from, corresponds to “Sample” in “Schimmelradar_360_submission.csv”.

• Strata: The number that equates to “Area” in “Schimmelradar_360_submission.csv”.

• WT: A binary that indicates whether an isolate had a wildtype cyp51a promotor.

• TR34: A binary that indicates whether an isolate had a TR34 cyp51a promotor.

• TR46: A binary that indicates whether an isolate had a TR46 cyp51a promotor.

• TR46_3: A binary that indicates whether an isolate had a TR46*3 cyp51a promotor.

• TR46_4: A binary that indicates whether an isolate had a TR46*4 cyp51a promotor.

Script 1 - generation_100_equisized_areas_NL

NOTE: Running this code is not necessary for the other analyses, it was used primarily for sample selection. The area distribution was used during the analysis in script 2B, yet each sample is already linked to an area in “Schimmelradar_360_submission.csv". This script was written to generate a spatial polygons data frame of 100 equisized areas of the Netherlands. The registrations for the citizen science project Schimmelradar were binned into these areas to facilitate a relatively even distribution of samples throughout the country which can be seen in Figure S1. The spatial polygons data frame can be opened and displayed in open-source software such as QGIS. The package “spcosa” used to generate the areas has RJava as a dependency, so having Java installed is required to run this script. The R script uses a shapefile of the Netherlands from the tmap package to generate the areas within the Netherlands. Generating a similar distribution for other countries will require different shape files!

Script 2 - Spatial_data_integration_fungalradar

This script produces 4 data files that describe land use in the Netherlands: The three focal.RData files with land use and resistant/colony counts, as well as the “Predictor_raster_NL.tif” land use file.

In this script, both the phenotypic and genotypic resistance spatial data from the air samples taken during the Fungal radar citizen science project are integrated with the land use and weather data used to model them. It is not recommended to run this code because the data extraction is fairly computationally demanding and it does not itself contain key statistical analyses. Rather it is used to generate the objects used for modelling and spatial predictions that are also included in this repository.

The phenotypic resistance is summarised in Table 1, which is generated in this script. Subsequently, the spatial data from the LNG22 and BRP datasets are integrated into the data. These dataset can be loaded from the "LGN2022.tif" and "Gewas22rast.tiff" raster files, respectively. Link to webpages where these files can be downloaded can found in the code.

Once the raster files are loaded, the code generates heatmaps and calculates the proportions of all the land use classes in both a 5 and 10-km radius around every sample and across the country to make spatial predictions. Only the 10 km radius data are used in the later analysis, but the 5 km radius was generated to test if that radius would be more appropriate, during an earlier stage of the analyses, and was left in for completeness. For documentation of the LGN22 data set, we refer to https://lgn.nl/documentatie and for BRP to https://nationaalgeoregister.nl/geonetwork/srv/dut/catalog.search#/metadata/44e6d4d3-8fc5-47d6-8712-33dd6d244eef, both of these online resources are in Dutch but can be readily translated. A list of the variables that were included from these datasets during model selection can be found in Table S3. Alongside land-use data, the code extracts weather data from datafiles that can be downloaded from https://cds.climate.copernicus.eu/datasets/sis-agrometeorological-indicators?tab=download for the Netherlands during the sampling window, dates and dimensions are listed within the code. The Weather_schimmelradar folder contains four subfolders for each weather variable that was considered during modelling: temperature, wind speed, precipitation and humidity. Each of these subfolders contains 44 .nc files that each cover the daily mean of the respective weather variable across the Netherlands for each of the 44 days of the sampling window the citizen scientists were given.

All spatial objects weather + land use are eventually merged into one predictor raster "Predictor_raster_NL.tif". The land use fractions and weather data are subsequently integrated with the air sample data into a single spatial data frame along with the resistance data and saved into an R object "Schimmelradar360spat_focal.RData". The script concludes by merging the cyp51a haplotype data with this object as well, to create two different objects: "Schimmelradar360spat_focal_TR_VORI.RData" for the haplotype data of the voriconazole resistant isolates and "Schimmelradar360spat_focal_TR_ITRA.RData" including the haplotype data of itraconazole resistant isolates. These two datasets are modeled separately in scripts 5,9 and 6,8, respectively. This final section of the script also generates summary table S2, which summarises the frequency of the cyp51a haplotypes per azole treatment.

If the relevant objects are loaded

scripts.zip

arcgisTools.atbx: terrainDerivatives: make terrain derivatives from digital terrain model (Band 1 = TPI (50 m radius circle), Band 2 = square root of slope, Band 3 = TPI (annulus), Band 4 = hillshade, Band 5 = multidirectional hillshades, Band 6 = slopeshade). rasterizeFeatures: convert vector polygons to raster masks (1 = feature, 0 = background).

makeChips.R: R function to break terrain derivatives and chips into image chips of a defined size. makeTerrainDerivatives.R: R function to generated 6-band terrain derivatives from digital terrain data (same as ArcGIS Pro tool). merge_logs.R: R script to merge training logs into a single file. predictToExtents.ipynb: Python notebook to use trained model to predict to new data. trainExperiments.ipynb: Python notebook used to train semantic segmentation models using PyTorch and the Segmentation Models package. assessmentExperiments.ipynb: Python code to generate assessment metrics using PyTorch and the torchmetrics library. graphs_results.R: R code to make graphs with ggplot2 to summarize results. makeChipsList.R: R code to generate lists of chips in a directory. makeMasks.R: R function to make raster masks from vector data (same as rasterizeFeatures ArcGIS Pro tool).

terraceDL.zip

dems: LiDAR DTM data partitioned into training, testing, and validation datasets based on HUC8 watershed boundaries. Original DTM data were provided by the Iowa BMP mapping project: https://www.gis.iastate.edu/BMPs. extents: extents of the training, testing, and validation areas as defined by HUC 8 watershed boundaries. vectors: vector features representing agricultural terraces and partitioned into separate training, testing, and validation datasets. Original digitized features were provided by the Iowa BMP Mapping Project: https://www.gis.iastate.edu/BMPs.

Here we provide a mosaic of the Copernicus DEM 30m for Europe and the corresponding hillshade derived from the GLO-30 public instance of the Copernicus DEM. The CRS is the same as the original Copernicus DEM CRS: EPSG:4326. Note that GLO-30 Public provides limited coverage at 30 meters because a small subset of tiles covering specific countries are not yet released to the public by the Copernicus Programme. Note that ocean areas do not have tiles, there one can assume height values equal to zero. Data is provided as Cloud Optimized GeoTIFFs. The Copernicus DEM is a Digital Surface Model (DSM) which represents the surface of the Earth including buildings, infrastructure and vegetation. The original GLO-30 provides worldwide coverage at 30 meters (refers to 10 arc seconds). Note that ocean areas do not have tiles, there one can assume height values equal to zero. Data is provided as Cloud Optimized GeoTIFFs. Note that the vertical unit for measurement of elevation height is meters. The Copernicus DEM for Europe at 30 m in COG format has been derived from the Copernicus DEM GLO-30, mirrored on Open Data on AWS, dataset managed by Sinergise (https://registry.opendata.aws/copernicus-dem/). Processing steps: The original Copernicus GLO-30 DEM contains a relevant percentage of tiles with non-square pixels. We created a mosaic map in https://gdal.org/drivers/raster/vrt.html format and defined within the VRT file the rule to apply cubic resampling while reading the data, i.e. importing them into GRASS GIS for further processing. We chose cubic instead of bilinear resampling since the height-width ratio of non-square pixels is up to 1:5. Hence, artefacts between adjacent tiles in rugged terrain could be minimized: gdalbuildvrt -input_file_list list_geotiffs_MOOD.csv -r cubic -tr 0.000277777777777778 0.000277777777777778 Copernicus_DSM_30m_MOOD.vrt The pixel values were scaled with 1000 (storing the pixels as integer values) for data volume reduction. In addition, a hillshade raster map was derived from the resampled elevation map (using r.relief, GRASS GIS). Eventually, we exported the elevation and hillshade raster maps in Cloud Optimized GeoTIFF (COG) format, along with SLD and QML style files.

Note: This LCMS CONUS Cause of Change image service has been deprecated. It has been replaced by the LCMS CONUS Annual Change image service, which provides updated and consolidated change data.Please refer to the new service here: https://usfs.maps.arcgis.com/home/item.html?id=085626ec50324e5e9ad6323c050ac84dThis product is part of the Landscape Change Monitoring System (LCMS) data suite. It shows LCMS change attribution classes for each year. See additional information about change in the Entity_and_Attribute_Information or Fields section below.LCMS is a remote sensing-based system for mapping and monitoring landscape change across the United States. Its objective is to develop a consistent approach using the latest technology and advancements in change detection to produce a "best available" map of landscape change. Because no algorithm performs best in all situations, LCMS uses an ensemble of models as predictors, which improves map accuracy across a range of ecosystems and change processes (Healey et al., 2018). The resulting suite of LCMS change, land cover, and land use maps offer a holistic depiction of landscape change across the United States over the past four decades.Predictor layers for the LCMS model include outputs from the LandTrendr and CCDC change detection algorithms and terrain information. These components are all accessed and processed using Google Earth Engine (Gorelick et al., 2017). To produce annual composites, the cFmask (Zhu and Woodcock, 2012), cloudScore, and TDOM (Chastain et al., 2019) cloud and cloud shadow masking methods are applied to Landsat Tier 1 and Sentinel 2a and 2b Level-1C top of atmosphere reflectance data. The annual medoid is then computed to summarize each year into a single composite. The composite time series is temporally segmented using LandTrendr (Kennedy et al., 2010; Kennedy et al., 2018; Cohen et al., 2018). All cloud and cloud shadow free values are also temporally segmented using the CCDC algorithm (Zhu and Woodcock, 2014). LandTrendr, CCDC and terrain predictors can be used as independent predictor variables in a Random Forest (Breiman, 2001) model. LandTrendr predictor variables include fitted values, pair-wise differences, segment duration, change magnitude, and slope. CCDC predictor variables include CCDC sine and cosine coefficients (first 3 harmonics), fitted values, and pairwise differences from the Julian Day of each pixel used in the annual composites and LandTrendr. Terrain predictor variables include elevation, slope, sine of aspect, cosine of aspect, and topographic position indices (Weiss, 2001) from the USGS 3D Elevation Program (3DEP) (U.S. Geological Survey, 2019). Reference data are collected using TimeSync, a web-based tool that helps analysts visualize and interpret the Landsat data record from 1984-present (Cohen et al., 2010).Outputs fall into three categories: change, land cover, and land use. Change relates specifically to vegetation cover and includes slow loss (not included for PRUSVI), fast loss (which also includes hydrologic changes such as inundation or desiccation), and gain. These values are predicted for each year of the time series and serve as the foundational products for LCMS. References: Breiman, L. (2001). Random Forests. In Machine Learning (Vol. 45, pp. 5-32). https://doi.org/10.1023/A:1010933404324Chastain, R., Housman, I., Goldstein, J., Finco, M., and Tenneson, K. (2019). Empirical cross sensor comparison of Sentinel-2A and 2B MSI, Landsat-8 OLI, and Landsat-7 ETM top of atmosphere spectral characteristics over the conterminous United States. In Remote Sensing of Environment (Vol. 221, pp. 274-285). https://doi.org/10.1016/j.rse.2018.11.012Cohen, W. B., Yang, Z., and Kennedy, R. (2010). Detecting trends in forest disturbance and recovery using yearly Landsat time series: 2. TimeSync - Tools for calibration and validation. In Remote Sensing of Environment (Vol. 114, Issue 12, pp. 2911-2924). https://doi.org/10.1016/j.rse.2010.07.010Cohen, W. B., Yang, Z., Healey, S. P., Kennedy, R. E., and Gorelick, N. (2018). A LandTrendr multispectral ensemble for forest disturbance detection. In Remote Sensing of Environment (Vol. 205, pp. 131-140). https://doi.org/10.1016/j.rse.2017.11.015Foga, S., Scaramuzza, P.L., Guo, S., Zhu, Z., Dilley, R.D., Beckmann, T., Schmidt, G.L., Dwyer, J.L., Hughes, M.J., Laue, B. (2017). Cloud detection algorithm comparison and validation for operational Landsat data products. Remote Sensing of Environment, 194, 379-390. https://doi.org/10.1016/j.rse.2017.03.026Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., and Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. In Remote Sensing of Environment (Vol. 202, pp. 18-27). https://doi.org/10.1016/j.rse.2017.06.031Healey, S. P., Cohen, W. B., Yang, Z., Kenneth Brewer, C., Brooks, E. B., Gorelick, N., Hernandez, A. J., Huang, C., Joseph Hughes, M., Kennedy, R. E., Loveland, T. R., Moisen, G. G., Schroeder, T. A., Stehman, S. V., Vogelmann, J. E., Woodcock, C. E., Yang, L., and Zhu, Z. (2018). Mapping forest change using stacked generalization: An ensemble approach. In Remote Sensing of Environment (Vol. 204, pp. 717-728). https://doi.org/10.1016/j.rse.2017.09.029Kennedy, R. E., Yang, Z., and Cohen, W. B. (2010). Detecting trends in forest disturbance and recovery using yearly Landsat time series: 1. LandTrendr - Temporal segmentation algorithms. In Remote Sensing of Environment (Vol. 114, Issue 12, pp. 2897-2910). https://doi.org/10.1016/j.rse.2010.07.008Kennedy, R., Yang, Z., Gorelick, N., Braaten, J., Cavalcante, L., Cohen, W., and Healey, S. (2018). Implementation of the LandTrendr Algorithm on Google Earth Engine. In Remote Sensing (Vol. 10, Issue 5, p. 691). https://doi.org/10.3390/rs10050691Olofsson, P., Foody, G. M., Herold, M., Stehman, S. V., Woodcock, C. E., and Wulder, M. A. (2014). Good practices for estimating area and assessing accuracy of land change. In Remote Sensing of Environment (Vol. 148, pp. 42-57). https://doi.org/10.1016/j.rse.2014.02.015Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M. and Duchesnay, E. (2011). Scikit-learn: Machine Learning in Python. In Journal of Machine Learning Research (Vol. 12, pp. 2825-2830).Pengra, B. W., Stehman, S. V., Horton, J. A., Dockter, D. J., Schroeder, T. A., Yang, Z., Cohen, W. B., Healey, S. P., and Loveland, T. R. (2020). Quality control and assessment of interpreter consistency of annual land cover reference data in an operational national monitoring program. In Remote Sensing of Environment (Vol. 238, p. 111261). https://doi.org/10.1016/j.rse.2019.111261U.S. Geological Survey. (2019). USGS 3D Elevation Program Digital Elevation Model, accessed August 2022 at https://developers.google.com/earth-engine/datasets/catalog/USGS_3DEP_10mWeiss, A.D. (2001). Topographic position and landforms analysis Poster Presentation, ESRI Users Conference, San Diego, CAZhu, Z., and Woodcock, C. E. (2012). Object-based cloud and cloud shadow detection in Landsat imagery. In Remote Sensing of Environment (Vol. 118, pp. 83-94). https://doi.org/10.1016/j.rse.2011.10.028Zhu, Z., and Woodcock, C. E. (2014). Continuous change detection and classification of land cover using all available Landsat data. In Remote Sensing of Environment (Vol. 144, pp. 152-171). https://doi.org/10.1016/j.rse.2014.01.011This record was taken from the USDA Enterprise Data Inventory that feeds into the https://data.gov catalog. Data for this record includes the following resources: ISO-19139 metadata ArcGIS Hub Dataset ArcGIS GeoService For complete information, please visit https://data.gov.

The Grid Garage Toolbox is designed to help you undertake the Geographic Information System (GIS) tasks required to process GIS data (geodata) into a standard, spatially aligned format. This format is required by most, grid or raster, spatial modelling tools such as the Multi-criteria Analysis Shell for Spatial Decision Support (MCAS-S). Grid Garage contains 36 tools designed to save you time by batch processing repetitive GIS tasks as well diagnosing problems with data and capturing a record of processing step and any errors encountered.\r \r Grid Garage provides tools that function using a list based approach to batch processing where both inputs and outputs are specified in tables to enable selective batch processing and detailed result reporting. In many cases the tools simply extend the functionality of standard ArcGIS tools, providing some or all of the inputs required by these tools via the input table to enable batch processing on a 'per item' basis. This approach differs slightly from normal batch processing in ArcGIS, instead of manually selecting single items or a folder on which to apply a tool or model you provide a table listing target datasets. In summary the\r Grid Garage allows you to:\r \r * List, describe and manage very large volumes of geodata.\r * Batch process repetitive GIS tasks such as managing (renaming, describing etc.) or processing (clipping, resampling, reprojecting etc.) many geodata inputs such as time-series geodata derived from satellite imagery or climate models.\r * Record any errors when batch processing and diagnose errors by interrogating the input geodata that failed.\r * Develop your own models in ArcGIS ModelBuilder that allow you to automate any GIS workflow utilising one or more of the Grid Garage tools that can process an unlimited number of inputs.\r * Automate the process of generating MCAS-S TIP metadata files for any number of input raster datasets.\r \r The Grid Garage is intended for use by anyone with an understanding of GIS principles and an intermediate to advanced level of GIS skills. Using the Grid Garage tools in ArcGIS ModelBuilder requires skills in the use of the ArcGIS ModelBuilder tool.\r \r Download Instructions: Create a new folder on your computer or network and then download and unzip the zip file from the GitHub Release page for each of the following items in the 'Data and Resources' section below. There is a folder in each zip file that contains all the files. See the Grid Garage User Guide for instructions on how to install and use the Grid Garage Toolbox with the sample data provided. \r \r