ReaLSAT: A new Reservoir and Lake Surface Area Timeseries Dataset created using machine learning and satellite imagery [preprint]
Preprint date
November 4, 2020
Authors
Ankush Khandelwal (Ph.D. 2019), Rahul Ghosh (Ph.D. student), Zhihao Wei, Huangying Kuang (undergraduate research assistant), Hilary Dugan, Paul Hanson, Anuj Karpatne, Vipin Kumar (professor)
Abstract
Lakes and reservoirs, as most humans experience and use them, are dynamic three-dimensional bodies of water, with surface levels that rise and fall with seasonal precipitation patterns, long-term changes in climate, and human management decisions. A global dataset that provides the location and dynamics of water bodies can be of great importance to the ecological community as it enables the study of the impact of human actions and climate change on fresh water availability. This paper presents a new database, ReaLSAT (Reservoir and Lake Surface Area Timeseries) that has been created by analyzing spectral data from Earth Observation (EO) Satellites using novel machine learning (ML) techniques. These ML techniques can construct highly accurate surface area extents of water bodies at regular intervals despite the challenges arising from heterogeneity and missing or poor quality spectral data. The ReaLSAT dataset provides information for 669107 lakes and reservoirs between 0.1 and 100 square kilometers in size. The visualization of these water bodies and their surface area time series is also available online. The aim of this paper is to provide an overview of the dataset and a summary of some of the key insights that can be derived from the dataset.
Link to full paper
Keywords
data mining, machine learning, environmental data science