LGAO-PHJul 13, 2021

Fast-Slow Streamflow Model Using Mass-Conserving LSTM

arXiv:2107.06057v13 citations
Originality Incremental advance
AI Analysis

This work addresses water resource management and disaster preparedness for communities affected by climate change, but it appears incremental as it builds on existing LSTM methods.

The authors tackled streamflow forecasting by developing a new mass-conserving LSTM model that incorporates fast and slow flow components, resulting in preliminary improvements in skill scores compared to recent literature.

Streamflow forecasting is key to effectively managing water resources and preparing for the occurrence of natural calamities being exacerbated by climate change. Here we use the concept of fast and slow flow components to create a new mass-conserving Long Short-Term Memory (LSTM) neural network model. It uses hydrometeorological time series and catchment attributes to predict daily river discharges. Preliminary results evidence improvement in skills for different scores compared to the recent literature.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes