A Sustainable Early Warning System Using Rolling Forecasts Based on ANN and Golden Ratio Optimization Methods to Accurately Predict Real-Time Water Levels and Flash Flood.

Feras Alasali,Zahra Ghanem,Rula Tawalbeh,Mohammad Alghazzawi,Fatima Mohammad

doi:10.3390/s21134598

Abstract

Remote monitoring sensor systems play a significant role in the evaluation and minimization of natural disasters and risk. This article presents a sustainable and real-time early warning system of sensors employed in flash flood prediction by using a rolling forecast model based on Artificial Neural Network (ANN) and Golden Ratio Optimization (GROM) methods. This Early Flood Warning System (EFWS) aims to support decision makers by providing reliable and accurate information and warning about any possible flood events within an efficient lead-time to reduce any damages due to flash floods. In this work, to improve the performance of the EFWS, an ANN forecast model based on a new optimization method, GROM, is developed and compared to the traditional ANN model. Furthermore, due to the lack of literature regarding the optimal ANN structural model for forecasting the flash flood, this paper is one of the first extensive investigations into the impact of using different exogenous variables and parameters on the ANN structure. The effect of using a rolling forecast model compared to fixed model on the accuracy of the forecasts is investigated as well. The results indicate that the rolling ANN forecast model based on GROM successfully improved the model accuracy by 40% compared to the traditional ANN model and by 93.5% compared to the fixed forecast model.

Highlights

Flash flood events occurred in the downtown/Amman area (2018, 2019 and 2020)
One of the objectives in this study is to develop a novel rolling Early Flood Warning System (EFWS) for flash floods in streets using real-time measurement based on ultrasonic sensors and the Artificial Neural Network (ANN) model
One of the objectives of this study is to develop a novel rolling EFWS for flash floods in streets using real-time measurement based on ultrasonic sensors and the ANN model

Summary

Introduction

Climate change, with its related phenomena such as flash floods, has shown high negative impacts on both environmental and human society [1]. The flash flood problem is a natural hazard and one of the most frequent events, which is caused mainly by heavy rains within a short duration of time (heavy rainfall) and the limited water drainage infrastructure [1,2,3]. The flash flood events are related to the frequency of rainfall, the properties of drainage basins, the physical properties of the land, the land use and cover characteristics [3,4]. The increase in urbanization with limited spaces to absorb and hold rainwater will increase the risk and possibility of flash floods. Floods disasters which occurred between 2001 and 2018 were responsible for 504 billion USD financial losses and a 94,000 death toll [5]

Objectives

Methods

Results

Conclusion