Hydrological Early Warning System Based on a Deep Learning Runoff Model Coupled with a Meteorological Forecast

Abstract

The intensification of the hydrological cycle because of global warming raises concerns about future floods and their impact on large cities where exposure to these events has also increased. The development of adequate adaptation solutions such as early warning systems is crucial. Here, we used deep learning (DL) for weather-runoff forecasting in región Metropolitana of Chile, a large urban area in a valley at the foot of the Andes Mountains, with more than 7 million inhabitants. The final goal of this research is to develop an effective forecasting system to provide timely information and support in real-time decision making. For this purpose, we implemented a coupled model of a near-future global meteorological forecast with a short-range runoff forecasting system. Starting from a traditional hydrological conceptual model, we defined the hydro-meteorological and geomorphological variables that were used in the data-driven weather-runoff forecast models. The meteorological variables were obtained through statistical scaling of the Global Forecast System (GFS), thus enabling near-future prediction, and two data-driven approaches were implemented for predicting the entire hourly flow time-series in the near future (3 days), a simple Artificial Neural Networks (ANN) and a Deep Learning (DL) approach based on Long-Short Term Memory (LSTM) cells. We show that the coupling between meteorological forecasts and data-driven weather-runoff forecast models are able to satisfy two basic requirements that any early warning system should have: The forecast should be given in advance, and it should be accurate and reliable. In this context, DL significantly improves runoff forecast when compared with a traditional data-driven approach such as ANN, being accurate in predicting time-evolution of output variables, with an error of 5% for DL, measured in terms of the root mean square error (RMSE) for predicting the peak flow, compared to 15.5% error for ANN, which is adequate to warn communities at risk and initiate disaster response operations.

Transferring Hydrologic Data Across Continents – Leveraging Data‐Rich Regions to Improve Hydrologic Prediction in Data‐Sparse Regions

“…The Global Runoff Data Center (GRDC, available at http://grdc.bafg.de/), for example, shows that a large portion of basins around the world have fewer than 3 years’ worth of daily streamflow observations. In these scenarios, machine learning models have still been employed but mostly in a local model setting, where a model is fitted to the data from one basin or a few neighboring basins (S. Zhu et al., ​2020; Yaseen et al., 2015; Liang et al., 2018; Bowes et al., 2019; de la Fuente et al., 2019). Shen (2018) provided a summary and an entry point into a vast body of work in this realm, with many other papers also attesting to the huge demand for solutions (Beven, 2020; Guillon et al., 2020).…”

Application of Long Short-Term Memory (LSTM) on the Prediction of Rainfall-Runoff in Karst Area

“…Due to the complex structure of the hydrological model and the complex evolution characteristics and spatiotemporal evolution trend of a basin water cycle system, in order to accurately describe the hydrological cycle process of the basin, most hydrological model parameters are difficult to determine. How to determine the runoff parameters that can adapt to the heterogeneity of the underlying surface and the size of runoff level of different basins is the key to obtain high-precision short-term runoff forecast information of the basin [23,24]. Including basin spatial data, basin meteorological data, runoff simulation data, and other information, through data collection, data processing, parameter estimation, and optimization, hydrological runoff relationship modeling and analysis are realized [25].…”

Water-Level Prediction Analysis for the Three Gorges Reservoir Area Based on a Hybrid Model of LSTM and Its Variants

“…X. Y. Liu et al [20] used an LSTM model to predict hourly scale changes in water levels in front of the Three Gorges Dam, applicable for real-time reservoir management, flood warning, and hydropower generation scheduling. de la Fuente et al [21] developed a hydrological early-warning system that integrates a deep-learning model for runoff prediction with meteorological forecasts, significantly enhancing the prediction accuracy and timeliness of flood warnings. Hrnjica et al [22] and Baek et al [23] made breakthroughs in time series predictions of water levels and water quality by applying LSTM and GRU models.…”