The European Space Agency (ESA) WorldCover 10 m 2020 product provides a global land cover map for 2020 at 10 m resolution based on Sentinel-1 and Sentinel-2 data. The WorldCover product comes with 11 land cover classes and has been generated in the framework of the ESA WorldCover project, part …

Sentinel2GlobalLULC is a deep learning-ready dataset of RGB images from the Sentinel-2 satellites designed for global land use and land cover (LULC) mapping. Sentinel2GlobalLULC v2.1 contains 194,877 images in GeoTiff and JPEG format corresponding to 29 broad LULC classes. Each image has 224 x 224 pixels at 10 m spatial resolution and was produced by assigning the 25th percentile of all available observations in the Sentinel-2 collection between June 2015 and October 2020 in order to remove atmospheric effects (i.e., clouds, aerosols, shadows, snow, etc.). A spatial purity value was assigned to each image based on the consensus across 15 different global LULC products available in Google Earth Engine (GEE).

Our dataset is structured into 3 main zip-compressed folders, an Excel file with a dictionary for class names and descriptive statistics per LULC class, and a python script to convert RGB GeoTiff images into JPEG format. The first folder called "Sentinel2LULC_GeoTiff.zip" contains 29 zip-compressed subfolders where each one corresponds to a specific LULC class with hundreds to thousands of GeoTiff Sentinel-2 RGB images. The second folder called "Sentinel2LULC_JPEG.zip" contains 29 zip-compressed subfolders with a JPEG formatted version of the same images provided in the first main folder. The third folder called "Sentinel2LULC_CSV.zip" includes 29 zip-compressed CSV files with as many rows as provided images and with 12 columns containing the following metadata (this same metadata is provided in the image filenames):

• Land Cover Class ID: is the identification number of each LULC class
• Land Cover Class Short Name: is the short name of each LULC class
• Image ID: is the identification number of each image within its corresponding LULC class
• Pixel purity Value: is the spatial purity of each pixel for its corresponding LULC class calculated as the spatial consensus across up to 15 land-cover products
• GHM Value: is the spatial average of the Global Human Modification index (gHM) for each image
• Latitude: is the latitude of the center point of each image
• Longitude: is the longitude of the center point of each image
• Country Code: is the Alpha-2 country code of each image as described in the ISO 3166 international standard. To understand the country codes, we recommend the user to visit the following website where they present the Alpha-2 code for each country as described in the ISO 3166 international standard:https: //www.iban.com/country-codes
• Administrative Department Level1: is the administrative level 1 name to which each image belongs
• Administrative Department Level2: is the administrative level 2 name to which each image belongs
• Locality: is the name of the locality to which each image belongs
• Number of S2 images : is the number of found instances in the corresponding Sentinel-2 image collection between June 2015 and October 2020, when compositing and exporting its corresponding image tile

For seven LULC classes, we could not export from GEE all images that fulfilled a spatial purity of 100% since there were millions of them. In this case, we exported a stratified random sample of 14,000 images and provided an additional CSV file with the images actually contained in our dataset. That is, for these seven LULC classes, we provide these 2 CSV files:

• A CSV file that contains all exported images for this class
• A CSV file that contains all images available for this class at spatial purity of 100%, both the ones exported and the ones not exported, in case the user wants to export them. These CSV filenames end with "including_non_downloaded_images".

To clearly state the geographical coverage of images available in this dataset, we included in the version v2.1, a compressed folder called "Geographic_Representativeness.zip". This zip-compressed folder contains a csv file for each LULC class that provides the complete list of countries represented in that class. Each csv file has two columns, the first one gives the country code and the second one gives the number of images provided in that country for that LULC class. In addition to these 29 csv files, we provided another csv file that maps each ISO Alpha-2 country code to its original full country name.

© Sentinel2GlobalLULC Dataset by Yassir Benhammou, Domingo Alcaraz-Segura, Emilio Guirado, Rohaifa Khaldi, Boujemâa Achchab, Francisco Herrera & Siham Tabik is marked with Attribution 4.0 International (CC-BY 4.0)

The Terra and Aqua combined Moderate Resolution Imaging Spectroradiometer (MODIS) Land Cover Type (MCD12Q1) Version 6.1 data product provides global land cover types at yearly intervals. The MCD12Q1 Version 6.1 data product is derived using supervised classifications of MODIS Terra and Aqua reflectance data. Land cover types are derived from the International Geosphere-Biosphere Programme (IGBP), University of Maryland (UMD), Leaf Area Index (LAI), BIOME-Biogeochemical Cycles (BGC), and Plant Functional Types (PFT) classification schemes. The supervised classifications then underwent additional post-processing that incorporate prior knowledge and ancillary information to further refine specific classes. Additional land cover property assessment layers are provided by the Food and Agriculture Organization (FAO) Land Cover Classification System (LCCS) for land cover, land use, and surface hydrology. Layers for Land Cover Type 1-5, Land Cover Property 1-3, Land Cover Property Assessment 1-3, Land Cover Quality Control (QC), and a Land Water Mask are also provided. Documentation: User's Guide Algorithm Theoretical Basis Document (ATBD) General Documentation

This dataset contains continental (Africa) land cover and impervious surface changes over a long period of time (15 years) using high resolution Landsat satellite observations and Google Earth Engine cloud computing platform. The approach applied here to overcome the computational challenges of handling big earth observation data by using cloud computing can help scientists and practitioners who lack high-performance computational resources. The dataset contains seven classes, prepared annually from 2000 to 2015, using high‐resolution Landsat 7 images (ETM+) and analyzed by Google Earth Engine cloud computing method. The model that generated the LULC classification was evaluated for predictive accuracy across classes as well as overall accuracy. The model achieved an overall accuracy of 88% with class-specific user’s and producer’s accuracies ranged from 84-94% and 79-96% respectively (Midekisa et al., 2017).

Using 335,709 Landsat images on the Google Earth Engine, we built the first Landsat-derived annual land cover product of China (CLCD) from 1985 to 2019. We collected the training samples by combining stable samples extracted from China's Land-Use/Cover Datasets (CLUD), and visually-interpreted samples from satellite time-series data, Google Earth and Google Map. Several temporal metrics were constructed via all available Landsat data and fed to the random forest classifier to obtain classification results. A post-processing method incorporating spatial-temporal filtering and logical reasoning was further proposed to improve the spatial-temporal consistency of CLCD.

"*_albert.tif" are projected files via proj4 string "+proj=aea +lat_1=25 +lat_2=47 +lat_0=0 +lon_0=105 +x_0=0 +y_0=0 +datum=WGS84 +units=m +no_defs".

CLCD in 2021 is now available; Filling possible gaps between provinces; Building internal overviews for each file.

This dataset supports the generation of figures and conclusions in the article "An online GEE-CA tool for seamlessly simulating global urban expansion with high resolutions". It includes simulated urban expansion from 2020 to 2050 under 5 SSP scenarios, projected urban demands, and other data for model performance analysis.

The objectives of this study are to map the past and present LULC accurately, ensure the precision of classification and prediction models, and estimate future LULC changes using Google Earth Engine. LULC classification from 2014-2024 was performed using robust SmileCART and future LULC prediction for 2024, 2030, 2040, 2050, 2060 and 2070 was conducted using the Smile Random Forest (RF) algorithm incorporating various socio-economic variables. The classification model SmileCART was trained by using the European Space Agency World Cover data and validated through Landsat 8 satellite imagery, achieving training and test accuracies of 83% and 84% respectively. SmileRF prediction model showed an accuracy of 87% with a kappa coefficient of 0.86. The results indicate a decline in vegetation cover, snow & ice and water bodies, and an increase in built-up areas and cropland, with other classes showing fluctuations in the Jhelum and Chenab River basins from 2014 to 2070. These insights contribute to a deeper understanding of these critical watersheds, informing sustainable land management, water resource planning, and decision-making for the future sustainable development of the Jhelum and Chenab River basins using GEE and remote sensing data.

TimeSpec4LULC is a smart open-source global dataset of multi-spectral time series for 29 Land Use and Land Cover (LULC) classes ready to train machine learning models. It was built based on the seven spectral bands of the MODIS sensors at 500 m resolution from 2000 to 2021 (262 observations in each time series). Then, was annotated using spatial-temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE).

TimeSpec4LULC contains two datasets: the original dataset distributed over 6,076,531 pixels, and the balanced subset of the original dataset distributed over 29000 pixels.

The original dataset contains 30 folders, namely "Metadata", and 29 folders corresponding to the 29 LULC classes. The folder "Metadata" holds 29 different CSV files describing the metadata of the 29 LULC classes. The remaining 29 folders contain the time series data for the 29 LULC classes. Each folder holds 262 CSV files corresponding to the 262 months. Inside each CSV file, we provide the seven values of the spectral bands as well as the coordinates for all the LULC class-related pixels.

The balanced subset of the original dataset contains the metadata and the time series data for 1000 pixels per class representative of the globe. It holds 29 different JSON files following the names of the 29 LULC classes.

The features of the dataset are:

- ".geo": the geometry and coordinates (longitude and latitude) of the pixel center.

- "ADM0_Code": the GAUL country code.

- "ADM1_Code": the GAUL first-level administrative unit code.

- GHM_Index": the average of the global human modification index.

- "Products_Agreement_Percentage": the agreement percentage over the 15 global LULC products available in GEE.

- "Temporal_Availability_Percentage": the percentage of non-missing values in each band.

- "Pixel_TS": the time series values of the seven spectral bands.

MSZSI: Multi-Scale Zonal Statistics [AgriClimate] Inventory -------------------------------------------------------------------------------------- MSZSI is a data extraction tool for Google Earth Engine that aggregates time-series remote sensing information to multiple administrative levels using the FAO GAUL data layers. The code at the bottom of this page (metadata) can be pasted into the Google Earth Engine JavaScript code editor and ran at https://code.earthengine.google.com/. Please refer to the associated publication: Peter, B.G., Messina, J.P., Breeze, V., Fung, C.Y., Kapoor, A. and Fan, P., 2024. Perspectives on modifiable spatiotemporal unit problems in remote sensing of agriculture: evaluating rice production in Vietnam and tools for analysis. Frontiers in Remote Sensing, 5, p.1042624. https://www.frontiersin.org/journals/remote-sensing/articles/10.3389/frsen.2024.1042624 Input options: [1] Country of interest [2] Start and end year [3] Start and end month [4] Option to mask data to a specific land-use/land-cover type [5] Land-use/land-cover type code from CGLS LULC [6] Image collection for data aggregation [7] Desired band from the image collection [8] Statistics type for the zonal aggregations [9] Statistic to use for annual aggregation [10] Scaling options [11] Export folder and label suffix Output: Two CSVs containing zonal statistics for each of the FAO GAUL administrative level boundaries Output fields: system:index, 0-ADM0_CODE, 0-ADM0_NAME, 0-ADM1_CODE, 0-ADM1_NAME, 0-ADMN_CODE, 0-ADMN_NAME, 1-AREA_PERCENT_LULC, 1-AREA_SQM_LULC, 1-AREA_SQM_ZONE, 2-X_2001, 2-X_2002, 2-X_2003, ..., 2-X_2020, .geo PREPROCESSED DATA DOWNLOAD The datasets available for download contain zonal statistics at 2 administrative levels (FAO GAUL levels 1 and 2). Select countries from Southeast Asia and Sub-Saharan Africa (Cambodia, Indonesia, Lao PDR, Myanmar, Philippines, Thailand, Vietnam, Burundi, Kenya, Malawi, Mozambique, Rwanda, Tanzania, Uganda, Zambia, Zimbabwe) are included in the current version, with plans to extend the dataset to contain global metrics. Each zip file is described below and two example NDVI tables are available for preview. Key: [source, data, units, temporal range, aggregation, masking, zonal statistic, notes] Currently available: MSZSI-V2_V-NDVI-MEAN.tar: [NASA-MODIS, NDVI, index, 2001–2020, annual mean, agriculture, mean, n/a] MSZSI-V2_T-LST-DAY-MEAN.tar: [NASA-MODIS, LST Day, °C, 2001–2020, annual mean, agriculture, mean, n/a] MSZSI-V2_T-LST-NIGHT-MEAN.tar: [NASA-MODIS, LST Night, °C, 2001–2020, annual mean, agriculture, mean, n/a] MSZSI-V2_R-PRECIP-SUM.tar: [UCSB-CHG-CHIRPS, Precipitation, mm, 2001–2020, annual sum, agriculture, mean, n/a] MSZSI-V2_S-BDENS-MEAN.tar: [OpenLandMap, Bulk density, g/cm3, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_S-ORGC-MEAN.tar: [OpenLandMap, Organic carbon, g/kg, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_S-PH-MEAN.tar: [OpenLandMap, pH in H2O, pH, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_S-WATER-MEAN.tar: [OpenLandMap, Soil water, % at 33kPa, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_S-SAND-MEAN.tar: [OpenLandMap, Sand, %, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_S-SILT-MEAN.tar: [OpenLandMap, Silt, %, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_S-CLAY-MEAN.tar: [OpenLandMap, Clay, %, static, n/a, agriculture, mean, at depths 0-10-30-60-100-200] MSZSI-V2_E-ELEV-MEAN.tar: [MERIT, [elevation, slope, flowacc, HAND], [m, degrees, km2, m], static, n/a, agriculture, mean, n/a] Coming soon MSZSI-V2_C-STAX-MEAN.tar: [OpenLandMap, Soil taxonomy, category, static, n/a, agriculture, area sum, n/a] MSZSI-V2_C-LULC-MEAN.tar: [CGLS-LC100-V3, LULC, category, 2015–2019, mode, none, area sum, n/a] Data sources: https://developers.google.com/earth-engine/datasets/catalog/MODIS_006_MOD13Q1 https://developers.google.com/earth-engine/datasets/catalog/MODIS_006_MOD11A2 https://developers.google.com/earth-engine/datasets/catalog/UCSB-CHG_CHIRPS_PENTAD https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_BULKDENS-FINEEARTH_USDA-4A1H_M_v02 https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_ORGANIC-CARBON_USDA-6A1C_M_v02 https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_PH-H2O_USDA-4C1A2A_M_v02 https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_WATERCONTENT-33KPA_USDA-4B1C_M_v01 https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_CLAY-WFRACTION_USDA-3A1A1A_M_v02 https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_SAND-WFRACTION_USDA-3A1A1A_M_v02 https://developers.google.com/earth-engine/datasets/catalog/OpenLandMap_SOL_SOL_GRTGROUP_USDA-SOILTAX_C_v01...

Land use/land cover (LULC) mapping in fragmented landscapes, characterized by multiple and small land uses, is still a challenge. This study aims to evaluate the effectiveness of Synthetic Aperture Radar (SAR) and multispectral optical data in land cover mapping using Google Earth Engine (GEE), a cloud computing platform allowing big geospatial data analysis. The proposed approach combines multi-source satellite imagery for accurate land cover classification in a fragmented municipal territory in Southern Italy over a 5-month vegetative period. Within the GEE platform, a set of Sentinel-1, Sentinel-2, and Landsat 8 data was acquired and processed to generate a land cover map for the 2021 greenness period. A supervised pixel-based classification was performed, using a Random Forest (RF) machine learning algorithm, to classify the imagery and derived spectral indices into eight land cover classes. Classification accuracy was assessed using Overall Accuracy (OA), Producer’s and User’s accuracies (PA, UA), and F-score. McNemar’s test was applied to assess the significance of difference between classification results. The optical integrated datasets in combination with SAR data and derivate indices (NDVI, GNDVI, NDBI, VHVV) produce the most accurate LULC map among those produced (OA: 89.64%), while SAR-only datasets performed the lowest accuracy (OA: 61.30%). The classification process offers several advantages, including widespread spectral information, SAR’s ability to capture almost all-weather, day-and-night imagery, and the computation of vegetation indices in the near infrared spectrum interval, in a short revisit time. The proposed digital techniques for processing multi-temporal satellite data provide useful tools for understanding territorial and environmental dynamics, supporting decision-making in land use planning, agricultural expansion, and environmental management in fragmented landscapes.

TimeSpec4LULC is archived in 30 different ZIP files owning the name of the 29 LULC classes (one class is divided into two files since it is too large). Within each ZIP file, there exists a set of seven CSV files, each one corresponding to one of the seven spectral bands. The naming of each file follows this structure: IdOfTheClass_NameOfTheClass_ModisBand.csv For example, for band 1 of the Barren Lands class, the filename is: 01_BarrenLands_MCD09A1b01.csv Inside each CSV file, rows represent the collected pixels for that class. The first 11 columns contain the following metadata: - ���IdOfTheClass���: Id of the class. - ���NameOfTheClass���: Name of the class. - ���IdOfTheLevel0���: Id of the FAO-L0 (i.e., countries). - ���IdOfTheLevel1���: Id of the FAO-L1 (i.e., departments, states, or provinces depending on the country). - ���IdOfThePixel���: Id of the pixel. - ���PurityOfThePixel���: Spatial and inter-annual consensus for this class across multiple land-cover products, i.e., Purity of the pixel. - ���DataAvailability���: percentage of non-missing data per band throughout the time series. - ���Index_GHM���: average of Global Human Modification index (gHM). - ���Lat���: Latitude of the pixel center. - ���Lon���: Longitude of the pixel center. - ���.geo���: (Longitude, Latitude) of the pixel center with more precision. And, the last 223 columns contain the 223 monthly observations of the time series for one spectral band from 2002-07 to 2021-01. Along with the dataset, an Excel file named 'Countries_Departments_FAO-GAUL' containing the FAO-L0 and the FAO-L1 Ids and names (following the FAO-GAUL standards) is provided. This research has been supported by DETECTOR (A-RNM-256-UGR18 Universidad de Granada/FEDER), LifeWatch SmartEcomountains (LifeWatch-2019-10-UGR-01 Ministerio de Ciencia e Innovaci��n/Universidad de Granada/FEDER), BBVA DeepSCOP (Ayudas Fundaci��n BBVA a Equipos de Investigaci��n Cient��fica 2018), Ram��n y Cajal Programme (RYC-2015-18136), DeepL-ISCO (A-TIC-458-UGR18 Ministerio de Ciencia e Innovaci��n/FEDER), SMART-DASCI (TIN2017-89517-P Ministerio de Ciencia e Innovaci��n/Universidad de Granada/FEDER), BigDDL-CET (P18-FR-4961 Ministerio de Ciencia e Innovaci��n/Universidad de Granada/FEDER), RESISTE (P18-RT-1927 Consejer��a de Econom��a, Conocimiento, y Universidad from the Junta de Andaluc��a/FEDER), and Ecopotential (641762 European Commission).

The Iran-wide land cover map was generated by processing Sentinel imagery within the Google Earth Engine Cloud platform. For this purpose, over 2,500 Sentinel-1 and over 11,000 Sentinel-2 images were processed to produce a single mosaic dataset for the year 2017. Then, an object-based Random Forest classification method was trained by a large number of reference samples for 13 classes to generate the Iran-wide land cover map.

Annual (1986-2020) land-use/land cover maps at 30-meter resolution of the Tucson metropolitan area, Arizona and the greater Santa Cruz Watershed including Nogales, Sonora, Mexico. Maps were created using a combination of Landsat imagery, derived transformation and indices, texture analysis and other ancillary data fed to a Random Forest classifier in Google Earth Engine. The maps contain 13 classes based on the National Land Cover Classification scheme and modified to reflect local land cover types. Data are presented as a stacked, multi-band raster with one "band" for each year (Band 1 = 1986, Band 2 = 1987 and so on). Note that the year 2012 was left out of our time series because of lack of quality Landsat data. A color file (.clr) is included that can be imported to match the color of the National Land Cover Classification scheme. This data release also contains two JavaScript files with the Google Earth Engine code developed for pre-processing Landsat imagery and for image classification, and a zip folder "Accuracy Data" with five excel files: 1) Accuracy Statistics describing overall accuracy for each LULC year, 2) Confusion Matrices for each LULC year, 3) Land Cover Evolution - changes in pixel count for each class per year, 4) LULC Change Matrix - to and from class changes over the period, and 5) Variable Importance - results of the Random Forest Classification.

Predicted areas of LULC classes and their percentage of change in BMNP (2023–2053).

The annual land cover data of Nepal (2000-2022) have been created through the National Land Cover Monitoring System (NLCMS) for Nepal. The system uses freely available remote-sensing data (Landsat) and a cloud-based machine learning architecture in the Google Earth Engine (GEE) platform to generate land cover maps on an annual basis using a harmonized and consistent classification system.

The NLCMS is developed by the Forest Research and Training Centre (FRTC), Ministry of Forests and Environment, Government of Nepal with support from the International Centre for Integrated Mountain Development (ICIMOD) through SERVIR Hindu Kush Himalaya (SERVIR-HKH), a joint initiative in partnership with the National Aeronautics and Space Administration (NASA) and the United States Agency for International Development (USAID). Collaborators include SERVIR–Mekong at the Asian Disaster Preparedness Center (ADPC), SilvaCarbon, Global Land Analysis and Discovery (GLAD) group at the University of Maryland, and the US Forest Service.

The annual land cover data of Nepal for 2000-2019 was first published in 2022 while the data for 2020-2022 was released in 2024.

This research aimed to assess the observed land use and land cover (LULC) changes of Bale Mountains National Park (BMNP) from 1993 to 2023 and its future projections for the years (2033 and 2053). The study utilized multi-date Landsat imagery from 1993, 2003, 2013, and 2023, leveraging Landsat 5 TM, Landsat 7 ETM+, and Landsat 8 OLI-TIRS sensors for LULC classification. Standard image pre-processing techniques were applied, and composite images were created using yearly median values in Google Earth Engine (GEE). In addition to satellite data, both physical and socioeconomic variables were used as input for future LULC modeling. The Random Forest (RF) classification algorithm was used for image classification, while the Cellular Automata Artificial Neural Networks (CA-ANN) model within the Modules for Land Use Change Simulations (MOLUSCE) plugin of QGIS was employed for future LULC projection. The analysis revealed significant LULC changes in BMNP, from 1993 to 2023, primarily due to anthropogenic activities, with further changes anticipated between 2023 and 2053.The results showed a notable increase in woodland and shrubs at the expense of grassland and Erica forest. While woodland and shrubs increased by 87.18% and 36.7%, areas of Erica forest and grassland lost about 25% and 22% of their area, respectively, during this period. The LULC model results also indicated that areas covered by woodland and shrubs are expected to increase by 15.97% and 15.57%, respectively, between 2023 and 2053. Conversely, land areas occupied by cultivated land, Erica forest, grassland, and herbaceous plants are projected to decrease by 28.52%, 3.28%, 19.03%, and 6.55%, respectively. Proximity to roads and urban areas combined with rising temperatures and altered precipitation patterns emerged as critical factors influencing land use conversion patterns in BMNP. These findings underscore the complex interplay between environmental factors and human activities in shaping land cover dynamics. Hence, promoting sustainable land management practices among the park administration and local community as well as enhancing habitat protection efforts are recommended. Additionally, integrating advanced remote sensing technologies with ground truthing efforts will be essential for accurate assessments of LULC dynamics in this critical area of biodiversity.

This image classification of forest cover in the MAV was created using Google Dynamic World (https://www.nature.com/articles/s41597-022-01307-4 - https://dynamicworld.app/) to determine what was classified as forest. This dataset is a result of an automated land classification for every Sentinel image that is released. The code used for this process is as follows. ee.ImageCollection('GOOGLE/DYNAMICWORLD/V1') \ .filterBounds(geometry) \ .filterDate(oldstartDate, oldendDate) \ .select('label') \ .mode() \ .eq(1) \ .updateMask(urban) We selected the Dynamic World dataset and filtered by our area of interest by the extents of the Lower Mississippi Joint Venture boundary (i.e. Mississippi Alluvial Valley and West Gulf Coastal Plain ecological bird conservation regions (BCRs).We filtered the dataset based on a start and end date which is the first of 2021 and the last day of 2021.With this dataset each class has a band that represents probability of that pixel having complete coverage of that class (https://developers.google.com/earth-engine/datasets/catalog/GOOGLE_DYNAMICWORLD_V1#bands)Data accuracy was assessed at @82% accuracy and data resolution is 10m. Each image has a ‘label’ band with a discrete classification of LULC, but also 9 probability bands with class-specific probability scores generated by the deep learning model on the basis of the pixel’s spatial context. To generate an annual LULC composite comparable with WC and Esri, we calculated the mode of the predicted LULC class in the ‘label’ band of all DW images for 2020.Michael Mitchell with Ducks Unlimited Southern Regional Office led the development of this effort, in coordination and collaboration with Lower Mississippi Valley Joint Venture staff.

Accuracy assessments of classified LULC classes for the years (1993, 2003, 2013 and 2023).

Areas of LULC classes of BMNP in the years (1993, 2003, 2013, and 2023).

This project leveraged sentinel 2 datasets from Google Earth Engine (GEE) to generate forest products for 2016 and 2020. LULC forest products were generated based on the IPCC classes; Forest (Natural, Plantation & Bamboo), Grassland (Open & Wooded), Cropland and Bareland. Forest and non-forest products were then masked out of the LULC products for the two study years to quantify the approximate changes occurring within the specified areas of interest.