Inductive predictions of hydrologic events using a Long Short-Term Memory network and the Soil and Water Assessment Tool

We present machine learning methods to predict hydrologic features such as streamflow and soil moisture from spatially and temporally varying hydrological and meteorological data. We used a temporal reduction technique to reduce computation and memory requirements and trained a Long Short-Term Memory (LSTM) network to predict soil moisture and streamflow over multiple watersheds. We show LSTM networks can be trained in a fraction of the time required by complex process-based and attention-based models such as Soil and Water Assessment Tool (SWAT) and GeoMAN without sacrificing accuracy. We also demonstrate that outside data sourced from a watershed other than the target can be used to train LSTM to comparable or even superior prediction accuracy. The success of LSTM in such spatially-inductive settings shows hydrologic features can be predicted with minimal prior knowledge of the watershed in question. Finally, we make all methodologies of this work publicly available as an end-to-end software pipeline that facilitates rapid prototyping of hydrologic learners.

Automated summary

This study presents machine learning methods to predict hydrologic features such as streamflow and soil moisture based on hydrological and meteorological data. Temporal reduction technique and Long Short-Term Memory (LSTM) network are utilized to reduce computation and memory requirements and improve accuracy. The research demonstrates the effectiveness of LSTM in predicting hydrologic features with minimal prior knowledge of the watershed. The methodologies are shared as an end-to-end software pipeline for rapid prototyping of hydrologic learners.