Find research datasets worth reusing

ReaLSAT, a global dataset of reservoir and lake surface area variations

<p>Reservoir and Lake Surface Area Timeseries (ReaLSAT) dataset provides an unprecedented reconstruction of surface area variations of lakes and reservoirs at a global scale using Earth Observation (EO) data and novel machine learning techniques. The dataset provides monthly scale surface area variations (1984 to 2020) of 681,137 water bodies below 50&deg;N and sizes greater than 0.1 square kilometers.</p> <p>&nbsp;The dataset contains the following&nbsp;files:</p> <p>1) ReaLSAT.zip: A shapefile that contains the reference shape of waterbodies in the dataset.</p> <p>2) monthly_timeseries.zip: contains one CSV file for each water body. The CSV file provides monthly surface area variation values. The CSV files are stored in a subfolder corresponding to each 10 degree&nbsp;by 10 degree cell. For example, monthly_timeseries_60_-50 folders contain CSV files of lakes that lie between 60 E and 70&nbsp;E longitude, and 50S and 40&nbsp;S.&nbsp;</p> <p>3) monthly_shapes_&lt;bottom_left_lon&gt;_&lt;bottom_left_lat&gt;.zip: contains a geotiff for each water body that lie within the 10 degree by 10 degree cell. Please refer to the visualization notebook on how to use these geotiffs.&nbsp;</p> <p>4) evaluation_data.zip: contains the random subsets of the dataset used for evaluation. The zip file contains a README file that describes the evaluation data.</p> <p>6) generate_realsat_timeseries.ipynb: a Google Colab notebook that provides the code to generate timerseries and surface extent maps for any waterbody.</p> <p>Please refer to the following papers to learn more about the processing pipeline used to create ReaLSAT dataset:</p> <p>[1] Khandelwal, Ankush, Anuj Karpatne, Praveen Ravirathinam, Rahul Ghosh, Zhihao Wei, Hilary A. Dugan, Paul C. Hanson, and Vipin Kumar. &quot;ReaLSAT, a global dataset of reservoir and lake surface area variations.&quot;&nbsp;<em>Scientific data</em>&nbsp;9, no. 1 (2022): 1-12.</p> <p>[2]&nbsp;Khandelwal, Ankush. &quot;ORBIT (Ordering Based Information Transfer): A Physics Guided Machine Learning Framework to Monitor the Dynamics of Water Bodies at a Global Scale.&quot; (2019).</p> <p>&nbsp;</p> <p><strong>Version Updates</strong></p> <p>Version 2.0:</p> <p>- extends the datasets to 2020.</p> <p>- provides geotiffs instead of shapefiles for individual lakes to reduce dataset size.</p> <p>- provides a notebook to visualize the updated dataset.&nbsp;</p> <p>Version 1.4: added 1120 large lakes to the dataset and removed partial lakes that overlapped with these large lakes.</p> <p>Version 1.3: fixed visualization related bug in generate_realsat_timeseries.ipynb</p> <p>Version 1.2: added a Google Colab notebook that provides the code to generate timerseries and surface extent maps for any waterbody in ReaLSAT database.</p>