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.

In considering projections that flooding will increase in the future years due to factors such as climate change and urbanization, the need for dependable and accurate water sensors systems is greater than ever. In this study, the performance of four different water level sensors, including ultrasonic, infrared (IR), and pressure sensors, is analyzed based on innovative characterization and comparative analysis, to determine whether or not these sensors have the ability to detect rising water levels and flash floods at an earlier stage under different conditions. During our exhaustive tests, we subjected the device to a variety of conditions, including clean and contaminated water, light and darkness, and an analogue connection to a display. When it came to monitoring water levels, the ultrasonic sensors stood out because of their remarkable precision and consistency. To address this issue, this study provides a novel and comparative examination of four water level sensors to determine which is the most effective and cost-effective in detecting floods and water level fluctuations. The IR sensor delivered accurate findings; however, it demonstrated some degree of variability throughout the course of the experiment. In addition, the results of our research show that the pressure sensor is a legitimate alternative to ultrasonic sensors. This presents a possibility that is more advantageous financially when it comes to the development of effective water level monitoring systems. The findings of this study are extremely helpful in improving the dependability and accuracy of flood detection systems and, eventually, in lessening the devastation caused by natural catastrophes.