Risk-based Decision Support System for Early Warning of Chemical Emissions in Flood Event: A Case Study of Crystallization Factories in Liberec City, Czech Republic

Based on the reports presented in various studies, it appears that in the Czech Republic, in 2002, as a result of a fluvial flood, chlorine and other chemicals in a factory were washed away and led to various epidemiological effects [1]. This paper presents a Decision Support System (DSS) based on Random Forest (RF) artificial intelligence technique and Failure Modes and Effects Analysis (FMEA) [2] to minimize the chemical risks in industrial factories and control possible pollution from crystallization plants. The methodology is demonstrated by its application on real crystallization plant in Liberec, Czech Republic. The investigations demonstrated that the RF algorithm has the ability to predict the severity of the occurrence and the Risk Probability Number (RPN) of spreading pollution with more than 90% regression coefficient. On the other hand, combining the machine learning method with the risk analysis has the possibility of heavy metal emission risk detection as well as the presentation of available solutions using the classic Delphi technique [3,4]. The evaluations of this research proved that the proposed methdology can significantly increase the biological security of citizens in crisis conditions.

Keywords: Flood; Decision Support System; Machine Learning; Risk Analysis; Czech Republic.

 

Reference

[1] Gautam, K.P. and Van Der Hoek, E.E., 2003. Literature study on environmental impact of floods. DC1-233-13.

[2] Gheibi, M., Karrabi, M. and Eftekhari, M., 2019. Designing a smart risk analysis method for gas chlorination units of water treatment plants with combination of Failure Mode Effects Analysis, Shannon Entropy, and Petri Net Modeling. Ecotoxicology and Environmental Safety, 171, pp.600-608.

[3] Zabihi, O., Siamaki, M., Gheibi, M., Akrami, M. and Hajiaghaei-Keshteli, M., 2023. A smart sustainable system for flood damage management with the application of artificial intelligence and multi-criteria decision-making computations. International Journal of Disaster Risk Reduction, 84, p.103470.

[4] Akbarian, H., Gheibi, M., Hajiaghaei-Keshteli, M. and Rahmani, M., 2022. A hybrid novel framework for flood disaster risk control in developing countries based on smart prediction systems and prioritized scenarios. Journal of environmental management, 312, p.114939.