Streamflow modelling and forecasting for Canadian watersheds using LSTM networks with attention mechanism

Abstract

This study investigates the capability of sequence-to-sequence machine learning (ML) architectures in an effort to develop streamflow forecasting tools for Canadian watersheds. Such tools are useful to inform local and region-specific water management and flood forecasting related activities. Two powerful deep-learning variants of the Recurrent Neural Network were investigated, namely the standard and attention-based encoder-decoder long short-term memory (LSTM) models. Both models were forced with past hydro-meteorological states and daily meteorological data with a look-back time window of several days. These models were tested for 10 different watersheds from the Ottawa River watershed, located within the Great Lakes Saint-Lawrence region of Canada, an economic powerhouse of the country. The results of training and testing phases suggest that both models are able to simulate overall hydrograph patterns well when compared to observational records. Between the two models, the attention model significantly outperforms the standard model in all watersheds, suggesting the importance and usefulness of the attention mechanism in ML architectures, not well explored for hydrological applications. The mean performance accuracy of the attention model on unseen data, when assessed in terms of mean Nash–Sutcliffe Efficiency and Kling-Gupta Efficiency is, respectively, found to be 0.985 and 0.954 for these watersheds. Streamflow forecasts with lead times of up to 5 days with the attention model demonstrate overall skillful performance with well above the benchmark accuracy of 70%. The results of the study suggest that the encoder–decoder LSTM, with attention mechanism, is a powerful modelling choice for developing streamflow forecasting systems for Canadian watersheds.

An End‐To‐End Flood Stage Prediction System Using Deep Neural Networks

“…To simplify the notation in this section, we denote x to be the number of time steps, which each model has the objective to predict in advance. We used a dynamic sliding window method on each output (see Girihagama et al., 2022). When a neural network produces an output then this output was appended to the end of the input and the first value of the input is removed.…”

Using Deep Learning Algorithms for Intermittent Streamflow Prediction in the Headwaters of the Colorado River, Texas

“…The self-attention mechanism is known as an effective technique for improving LSTMs and enhancing the model's performance by "paying attention" and assigning attention scores (weights) to each observation [106,107]. Attention-based LSTM models are among the most recent developments in machine learning that have found application for streamflow prediction [39,108,109].…”

Physics-informed deep learning framework to model intense precipitation events at super resolution

“…In addition, ensembles of climate simulations are generally required to quantify uncertainty in climate projections and that further amplifies the required resources. The recent advances in machine learning (Brenowitz and Bretherton 2018 ; Reichstein et al 2019 ) and its applications in various fields (e.g., Chung and Shin 2018 ; Ding et al 2020 ; Pradhan et al 2020 ; Stengel et al 2020 ; Van et al 2020 ; Ray and Chattopadhyay 2021 ; Barrera-Animas et al 2022 ; Girihagama et al 2022 ) provide an opportunity for developing hybrid approaches, combining physical understanding of atmospheric processes with machine learning architectures, to overcome this obstacle and advance studies on climate−urban infrastructure interactions (Wu et al 2021 ) and informing design methodologies. In the recent years, deep learning-based image super-resolution (SR) models built using convolutional neural networks (CNNs) have been developed (e.g., Wang et al 2015 ; Dong et al 2016 ; Lai et al 2017 ; Zhang et al 2018 ) and applied to produce high-resolution physical fields in various domains (Li et al 2009 ; Trinh et al 2014 ; Vandal et al 2017 ; Xie et al 2018 ; Stengel et al 2020 ).…”