Deep Convolutional LSTM for improved flash flood prediction

Abstract

Flooding remains one of the most devastating and costly natural disasters. As flooding events grow in frequency and intensity, it has become increasingly important to improve flood monitoring, prediction, and early warning systems. Recent efforts to improve flash flood forecasts using deep learning have shown promise, yet commonly-used techniques such as long short term memory (LSTM) models are unable to extract potentially significant spatial relationships among input datasets. Here we propose a hybrid approach using a Convolutional LSTM (ConvLSTM) network to predict stream stage heights using multi-modal hydrometeorological remote sensing and in-situ inputs. Results suggest the hybrid network can more effectively capture the specific spatiotemporal landscape dynamics of a flash flood-prone catchment relative to the current state-of-the-art, leading to a roughly 26% improvement in model error when predicting elevated stream conditions. Furthermore, the methodology shows promise for improving prediction accuracy and warning times for supporting local decision making.