Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales

Abstract

Recent observations with varied schedules and types (moving average, snapshot, or regularly spaced) can help to improve streamflow forecasts, but it is challenging to integrate them effectively. Based on a long short-term memory (LSTM) streamflow model, we tested multiple versions of a flexible procedure we call data integration (DI) to leverage recent discharge measurements to improve forecasts. DI accepts lagged inputs either directly or through a convolutional neural network (CNN) unit. DI ubiquitously elevated streamflow forecast performance to unseen levels, reaching a record continental-scale median Nash-Sutcliffe Efficiency coefficient value of 0.86. Integrating moving-average discharge, discharge from the last few days, or even average discharge from the previous calendar month could all improve daily forecasts. Directly using lagged observations as inputs was comparable in performance to using the CNN unit. Importantly, we obtained valuable insights regarding hydrologic processes impacting LSTM and DI performance. Before applying DI, the base LSTM model worked well in mountainous or snow-dominated regions, but less well in regions with low discharge volumes (due to either low precipitation or high precipitation-energy synchronicity) and large inter-annual storage variability. DI was most beneficial in regions with high flow autocorrelation: it greatly reduced baseflow bias in groundwater-dominated western basins and also improved peak prediction for basins with dynamical surface water storage, such as the Prairie Potholes or Great Lakes regions. However, even DI cannot elevate high-aridity basins with one-day flash peaks. Despite this limitation, there is much promise for a deep-learning-based forecast paradigm due to its performance, automation, efficiency, and flexibility.

References in corpus (5)

• Deep Learning in Neural Networks: An Overview
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• A trans-disciplinary review of deep learning research for water resources scientists
• Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
• NeuralHydrology -- Interpreting LSTMs in Hydrology

Cited by in corpus (8)

• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling
• Differentiable, learnable, regionalized process-based models with physical outputs can approach state-of-the-art hydrologic prediction accuracy
• The data synergy effects of time-series deep learning models in hydrology
• Prediction in ungauged regions with sparse flow duration curves and input-selection ensemble modeling
• Continental-scale streamflow modeling of basins with reservoirs: towards a coherent deep-learning-based strategy
• Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions
• DRUM: Diffusion-based runoff model for probabilistic flood forecasting