SEN2DWATER: A Novel Multispectral and Multitemporal Dataset and Deep Learning Benchmark for Water Resources Analysis

Climate change has caused disruption in certain weather patterns, leading toextreme weather events like flooding and drought in different parts of theworld. In this paper, we propose machine learning methods for analyzing changesin water resources over a time period of six years, by focusing on lakes andrivers in Italy and Spain. Additionally, we release open-access code to enablethe expansion of the study to any region of the world. We create a novel multispectral and multitemporal dataset, SEN2DWATER, whichis freely accessible on GitHub. We introduce suitable indices to monitorchanges in water resources, and benchmark the new dataset on three differentdeep learning frameworks: Convolutional Long Short Term Memory (ConvLSTM),Bidirectional ConvLSTM, and Time Distributed Convolutional Neural Networks(TD-CNNs). Future work exploring the many potential applications of thisresearch is also discussed.