Enhancing Streamflow Forecast and Extracting Insights Using Long‐Short Term Memory Networks With Data Integration at Continental Scales. Issue 9 (16th September 2020)

• Record Type: Journal Article
• Authors: Feng, Dapeng; Fang, Kuai; Shen, Chaopeng
• Is Part Of: Water resources research. Volume 56:Issue 9(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-09-16
• Subjects: Hydrology -- Periodicals; 333.91
• DOI: 10.1029/2019WR026793
• Languages: English
• ISSNs: 0043-1397

Abstract

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 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 convolutional neural network 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 interannual 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 performance in high‐aridity basins with 1‐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. Key Points: We propose flexible data integration (DI), which can use various types of observations to improve discharge forecast at continental scales Adding a convolutional neural network unit to LSTM reduces overfitting but cannot outperform directly accepting lagged discharge as inputs Benefits of DI are strong in regions with high autocorrelation in streamflow, due to either groundwater dominance or surface water storage