Flood Forecasting System Based on Integrated Big and Crowdsource Data by Using Machine Learning Techniques

• Published in: IEEE access Vol. 8; pp. 5885 - 5905
• Main Authors: Puttinaovarat, Supattra, Horkaew, Paramate
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Big Data; crowdsource; deep learning; Disaster management; Flood forecasting; Flood forecasting system; Floods; Forecasting; Geographical locations; Geospatial analysis; Hydrology; Machine learning; Property damage; Real-time systems
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2963819

Flood is one of the most disruptive natural hazards, responsible for loss of lives and damage to properties. A number of cities are subject to monsoons influences and hence face the disaster almost every year. Early notification of flood incident could benefit the authorities and public to devise both short and long terms preventive measures, to prepare evacuation and rescue mission, and to relieve the flood victims. Geographical locations of affected areas and respective severities, for instances, are among the key determinants in most flood administration. Thus far, an effective means of anticipating flood in advance remains lacking. Existing tools were typically based on manually input and prepared data. The processes were tedious and thus prohibitive for real-time and early forecasts. Furthermore, these tools did not fully exploit more comprehensive information available in current big data platforms. Therefore, this paper proposes a novel flood forecasting system based on fusing meteorological, hydrological, geospatial, and crowdsource big data in an adaptive machine learning framework. Data intelligence was driven by state-of-the-art learning strategies. Subjective and objective evaluations indicated that the developed system was able to forecast flood incidents, happening in specific areas and time frames. It was also later revealed by benchmarking experiments that the system configured with an MLP ANN gave the most effective prediction, with correct percentage, Kappa, MAE and RMSE of 97.93, 0.89, 0.01 and 0.10, respectively.