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

Alberto De La Fuente,Viviana Meruane,Carolina Meruane

doi:10.3390/w11091808

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.

Highlights

In the last decade, a series of unprecedented extreme hydrological events have occurred, some of which have been attributed to climate change [1]
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
As far as we know, the novelties of this contribution that have not been previously published are: (i) We present an approach based on a Deep Learning (DL) model that is coupled a near-future global meteorological forecast with a short-range runoff forecasting system. (ii) We use the complete set of hydro-meteorological and geomorphological variables of a complex hydrological model for training the data-driven models

Summary

Introduction

A series of unprecedented extreme hydrological events have occurred, some of which have been attributed to climate change [1]. Given that the early warning systems give more importance to the simplicity and robustness of the forecasting model rather than an accurate description of the various internal sub-processes, it is certainly worth considering hybrid models that combine physical-based models with data-driven approaches for improving real-time runoff forecasts [7,8,9,10]. Another difficulty in predicting hydrological extremes is that to get ahead of an extreme event requires the implementation of weather forecasting models coupled to hydrological models. Today there are high resolution global weather forecast models, which in conjunction with novel downscaling techniques, allows the development of model-generated weather input data for hydrological forecasting models [12,13]

Objectives

Methods

Results

Conclusion