Due to limited evidence and complex causes of regional climate change, the confidence in predicting fluvial floods remains low. Understanding the fundamental mechanisms intrinsic to geo-spatiotemporal information is crucial to improve the prediction accuracy. This paper demonstrates a hybrid neural network architecture - HydroDeep, that couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network. HydroDeep outperforms the independent CNN's and LSTM's performance by 1.6% and 10.5% respectively in Nash-Sutcliffe efficiency. Also, we show that HydroDeep pre-trained in one region is adept at passing on its knowledge to distant places via unique transfer learning approaches that minimize HydroDeep's training duration for a new region by learning its regional geo-spatiotemporal features in a reduced number of iterations.
@article{arxiv.2010.04328,
title = {HydroDeep -- A Knowledge Guided Deep Neural Network for Geo-Spatiotemporal Data Analysis},
author = {Aishwarya Sarkar and Jien Zhang and Chaoqun Lu and Ali Jannesari},
journal= {arXiv preprint arXiv:2010.04328},
year = {2021}
}