Forecast of flood disaster emergency material demand based on IACO-BP algorithm

The frequent occurrence of various sudden natural disasters in the world has caused heavy losses to human beings. It is very important to forecast the demand of emergency materials in order to protect people's safety and property. The purpose of this study is to use IACO-BP algorithm to forecast the demand of emergency supplies in the case of flood disaster. In this study, the flood disaster situation in recent years published by the Ministry of Water Resources of China is selected as the experimental data set. The data are sorted and analyzed by a variety of theoretical comprehensive operation, qualitative and quantitative research method, analytic hierarchy process and system dynamics method. The improved ant colony optimization algorithm is used to model the emergency material demand, and the population, flood level, flood level of the disaster area are analyzed. As the network input, the material situation outputs the material demand, so as to forecast. The results show that the iteration times of IACO-BP algorithm are 11 and the running time is 3S. The fluctuation of IACO-BP algorithm is the least and the most stable among the three algorithms. The material satisfaction degree predicted by IACO-BP algorithm is improved by 15% from the original 80.9%. It is concluded that this algorithm is very accurate and efficient in the prediction of emergency material demand, which can better assist the disaster situation. This study contributes to the prediction of emergency material demand for emergency disaster.

[1]  Establishing flood damage functions for agricultural crops using estimated inundation depth and flood disaster statistics in data-scarce regions , 2017 .

[2]  G. Aneiros,et al.  Short-term forecast of daily curves of electricity demand and price , 2016 .

[3]  Yun-Hu He,et al.  Applied prospect of modern information technology in relation to mountain flood disaster monitoring and early warning system , 2017 .

[4]  K. Clarke,et al.  Integrating human behaviour dynamics into flood disaster risk assessment , 2018, Nature Climate Change.

[5]  Riccardo Rizzo,et al.  Analysis and visualization of meteorological emergencies , 2017, J. Ambient Intell. Humaniz. Comput..

[6]  Jing Zuo,et al.  Research on the Process Supervision and Forecasting Model of Railway Emergency Based on GERTS , 2019, Int. J. Pattern Recognit. Artif. Intell..

[7]  C. Chinnarasri,et al.  Appropriate Engineering Measures with Participation of Community for Flood Disaster Reduction: Case of the Tha Chin Basin, Thailand , 2016 .

[8]  Mohammad Nazir Ahmad,et al.  An Ontology for Sharing and Managing Information in Disaster Response: In Flood Response Usage Scenarios , 2019, Journal on Data Semantics.

[9]  Megan S. Ryerson,et al.  Forecast to grow: Aviation demand forecasting in an era of demand uncertainty and optimism bias , 2019, Transportation Research Part E: Logistics and Transportation Review.

[10]  Albert Y. Chen,et al.  Demand Forecast Using Data Analytics for the Preallocation of Ambulances , 2016, IEEE Journal of Biomedical and Health Informatics.

[11]  Youngok Kang,et al.  Risk analysis and visualization for detecting signs of flood disaster in Twitter , 2016, Spatial Information Research.

[12]  M. Su,et al.  The influence of landscape pattern on the risk of urban water-logging and flood disaster , 2017, Ecological Indicators.

[13]  J. Chung.  Conflicts and natural disaster management: a comparative study of flood control in the Republic of Korea and the United States. , 2016, Disasters.

[14]  C. Zhu,et al.  Spatio-temporal evolution of drought and flood disaster chains in Baoji area from 1368 to 1911 , 2018, Journal of Geographical Sciences.

[15]  Grazziela P. Figueredo,et al.  Short and Long term predictions of Hospital emergency department attendances , 2019, Int. J. Medical Informatics.