The third generation of high resolution 10-m wetland inventory map of Canada, covering an approximate area of one billion hectares, was generated using multi-year (2016-2020), multi-source imagery (Sentinel-1, Sentinel-2, ALOS PALSAR-2, and SRTM) Earth Observation (EO) data as well as environmental features. Over 8800 wetland polygons were processed within an object-based random forest classification scheme on the Google Earth Engine cloud computing platform. The average overall accuracy of 90.5% is an increase of 4.7% over CWIM2. CWIM Versions: The Canadian Wetland Inventory Map (CWIM) is an extension of work started at Memorial University to produce a Newfoundland and Labrador wetland inventory during 2015-2018 which was significantly funded by Environment and Climate Change Canada. The first national CWIM was produced 2018-2019 as a collaboration between Memorial University, C-CORE, and Natural Resources Canada. Dr. Brian Brisco was instrumental in connecting ground truth from multiple sources to the project and providing guidance. Version 2 was produced in 2020 which included more training data and processing by Canada’s ecozones rather than provinces to take advantage of the commonality of landscape ecological features within ecozones to improve the accuracy. Version 3 produced in 2021 continued adding more data sources to further improve accuracy specifically an overestimation of wetland area as well as introducing a confidence map. Version 3A completed in 2022 updates only the arctic ecozones due to their relatively lower accuracy and added hydro-physiographic data layers. Currently work is underway to create a northern circumpolar wetland inventory map to be published in 2025. Paper on Newfoundland and Labrador Wetland Inventory: Mahdianpari, M.; Salehi, B.; Mohammadimanesh, F.; Homayouni, S.; Gill, E. The First Wetland Inventory Map of Newfoundland at a Spatial Resolution of 10 m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform. Remote Sens. 2019, 11, 43. https://doi.org/10.3390/rs11010043 Paper on CWIM1: Mahdianpari, M., Salehi, B., Mohammadimanesh, F., Brisco, B., Homayouni, S., Gill, E., … Bourgeau-Chavez, L. (2020). Big Data for a Big Country: The First Generation of Canadian Wetland Inventory Map at a Spatial Resolution of 10-m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform. Canadian Journal of Remote Sensing, 46(1), 15–33. https://doi.org/10.1080/07038992.2019.1711366 Paper on CWIM2: Mahdianpari, M., Brisco, B., Granger, J. E., Mohammadimanesh, F., Salehi, B., Banks, S., … Weng, Q. (2020). The Second Generation Canadian Wetland Inventory Map at 10 Meters Resolution Using Google Earth Engine. Canadian Journal of Remote Sensing, 46(3), 360–375. https://doi.org/10.1080/07038992.2020.1802584 Paper on CWIM3: M. Mahdianpari et al., "The Third Generation of Pan-Canadian Wetland Map at 10 m Resolution Using Multisource Earth Observation Data on Cloud Computing Platform," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 8789-8803, 2021, doi: 10.1109/JSTARS.2021.3105645. Paper on Arctic ecoregion enhancement for CWIM3A: Michael Merchant, et al., ”Leveraging google earth engine cloud computing for large-scale arctic wetland mapping,” in International Journal of Applied Earth Observation and Geoinformation, vol. 125, 2023, https://doi.org/10.1016/j.jag.2023.103589.

This dataset maps the distribution of crop types in Northeast China with the 30-m resolution with reliable accuracies. We believe our dataset can be helpful for relevant studies on regional agricultural production management.

If you want to use this dataset, please cite our paper.

Xuan, F., Dong, Y., Li, J., Li, X., Su, W., Huang, X., ... & Zhang, Y. (2023). Mapping crop type in Northeast China during 2013–2021 using automatic sampling and tile-based image classification. International Journal of Applied Earth Observation and Geoinformation, 117, 103178.

This dataset includes data and codes underlying the PhD thesis of Stefanie Steinbach: Sustainable Use of African Wetlands for Food Security: A Spatial Evaluation Approach. The dataset uses and complements the data published in the four articles constituting the core part of the thesis. Chapter 2: Dataset containing four wetland data layers that were created and analyzed in the study - https://doi.org/10.5281/zenodo.4326702 Steinbach, S., Cornish, N., Franke, J., Hentze, K., Strauch, A., Thonfeld, F., Zwart, S.J., Nelson, A., 2021. A New Conceptual Framework for Integrating Earth Observation in Large-scale Wetland Management in East Africa. Wetlands 41, 93. https://doi.org/10.1007/s13157-021-01468-9 Chapter 3: Dataset with the layer that was created and analyzed in the study - https://doi.org/10.5281/zenodo.14247305 Steinbach, S., Hentschel, E., Hentze, K., Rienow, A., Umulisa, V., Zwart, S.J., Nelson, A., 2023. Automatization and evaluation of a remote sensing-based indicator for wetland health assessment in East Africa on national and local scales. Ecol. Inform. 75, 102032. https://doi.org/10.1016/j.ecoinf.2023.102032 Chapter 4: Dataset with measurement locations and in-situ turbidity measurement values - https://doi.org/10.5281/zenodo.14275713 Steinbach, S., Rienow, A., Chege, M.W., Dedring, N., Kipkemboi, W., Thiong’o, B.K., Zwart, S.J., Nelson, A., 2024. Low-Cost Sensors and Multitemporal Remote Sensing for Operational Turbidity Monitoring in an East African Wetland Environment. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 17, 8490–8508. https://doi.org/10.1109/JSTARS.2024.3381756 Chapter 5: Scripts and workflow applied to retrieve and analyze remote sensing-based small reservoir turbidity - https://doi.org/10.5281/zenodo.14245504 Steinbach, S., Bartels, A., Rienow, A., Thiong’o, B.K., Zwart, S.J., Nelson, A. Predicting Turbidity Dynamics in Small Reservoirs in Central Kenya Using Remote Sensing and Machine Learning. International Journal of Applied Earth Observation and Geoinformation - Under review

The Government of Lesotho, with support of international partners, has embarked on an ambitious national programme for Integrated Catchment Management (ICM) under the name ReNOKA – ‘We are a river’. Its aim is to rehabilitate degraded watersheds across the country and to put in place prevention measures that will halt further degradation of Lesotho’s catchment areas. GIZ is commissioned by the European Union and the German Federal Ministry for Economic Cooperation and Development (BMZ) to support the Government of Lesotho in the implementation of ICM. Wetlands Invasive Species MappingDegradation of wetlands can be caused by the concomitant effects of different factors and can be measured through a variety of empirical indicators. Among these, there is the presence of invasive species, encroaching the wetland healthy vegetation. The effect of invasive species in wetlands poses a threat to the existing native species. Invasive species populations exhibit unique characteristics that allow them to outcompete the native species for nutrients, light, water, and space to nourish[1]. The early detection of the invasive populations is crucial for better management, control, and eradication efforts. Information about the distribution and abundance of the invasive populations is thus very important in assessing the impact of the spread in wetlands. To achieve this, mapping of vegetation is essential to obtain the distribution of healthy and invasive species vegetation to ensure restoration and protection. Some of the traditional methods such as literature reviews, field surveys and auxiliary data analysis are not sufficient to map the spread of the native and invasive species. These methods are date lagged, expensive and time consuming. Remote sensing has proven to be a reliable tool for detecting the invasion of their populations in wetlands. It provides consistent assessment and monitoring of the vegetation cover over time. It also provides sufficient information and allows collection of information over large areas. Plants have characteristics such as canopy structure, biochemical and biophysical properties, leaf pigment properties for example water content, chlorophyll content and nitrogen concentration[2]. These characteristics are different between the native and invasive species that can be distinguished by use of remote sensing. Remote sensing sensors measures spectral responses for different vegetation canopy cover on the earth surface. It has spectral bands with that lie on different wavelength regions of the electromagnetic spectrum that make it possible to distinguish different types of targets on the earth surface, including vegetation species. One of the most efficient ways of detecting and quantifying the presence of invasive plant species is the use of very high-resolution images. In this study, very high resolution and in-situ data gathered through an ad-hoc field survey campaign are used in mapping presence of invasive plant species for reference year 2021. Mapping of invasive plant species was performed in wetland areas of six sub catchment areas in Lesotho. The availability of the visible and near infra-red bands together with various band combinations for deriving vegetation indices makes it reliable in mapping vegetation species.[1] Dao, P. D., Axiotis, A., & He, Y. (2021). Mapping native and invasive grassland species and characterizing topography-driven species dynamics using high spatial resolution hyperspectral imagery. International Journal of Applied Earth Observation and Geoinformation, 104, 102542.[2] Lu, B., He, Y., & Dao, P. D. (2019). Comparing the performance of multispectral and hyperspectral images for estimating vegetation properties. IEEE Journal of selected topics in applied earth observations and remote sensing, 12(6), 1784-1797.