Transfer Learning Approaches for Knowledge Discovery in Grid-based Geo-Spatiotemporal DataDownload PDF

Published: 22 Oct 2021, Last Modified: 05 May 2023NeurIPS-AI4Science PosterReaders: Everyone
Keywords: geo-spatiotemporal, hydrology, transfer learning, data analysis, knowledge-guided neural network
Abstract: Extracting and meticulously analyzing geo-spatiotemporal features is crucial to recognize intricate underlying causes of natural events, such as floods. Limited evidence about hidden factors leading to climate change makes it challenging to predict regional water discharge accurately. In addition, the explosive growth in complex geo-spatiotemporal environment data that requires repeated learning by the state-of-the-art neural networks for every new region emphasizes the need for new computationally efficient methods, advanced computational resources, and extensive training on a massive amount of available monitored data. We, therefore, propose HydroDeep, an effectively reusable pretrained model to address this problem of transferring knowledge from one region to another by effectively capturing their intrinsic geo-spatiotemporal variance. Further, we present four transfer learning approaches on HydroDeep for spatiotemporal interpretability that improve Nash–Sutcliffe efficiency by 9% to 108% in new regions with a 95% reduction in time
Track: Original Research Track
TL;DR: This paper presents a new application of transfer learning techniques in interpreting geo-spatiotemporal features
1 Reply