Measurement and analysis of regional flood disaster resilience based on a support vector regression model refined by
Dong Liu1, Chunqing Wang2, Yi Ji2
1School of Water Conservancy & Civil Engineering, Northeast Agricultural University, Harbin, Heilongjiang, 150030, China; Key Laboratory of Effective Utilization of Agricultural Water Resources of Ministry of Agriculture, Northeast Agricultural University, Harbin, Heilongjiang, 150030, China; Heilongjiang Provincial Key Laboratory of Water Resources and Water Conservancy Engineering in Cold Region, Northeast Agricultural University, Harbin, Heilongjiang, 150030, China; Key Laboratory of Water-Saving Agriculture of Ordinary University in Heilongjiang Province, Northeast Agricultural University, Harbin, Heilongjiang, 150030, China.
Abstract:
Flood disasters are sudden, frequent, uncertain and highly hazardous natural disasters. The precise identification of the spatiotemporal evolution characteristics, key driving factors and influencing mechanisms of resilience has become a hot spot in disaster risk reduction research. Therefore, the cumulative information contribution rate-Pearson correlation coefficient (CICR- PCC) model is used in this paper to construct a flood disaster resilience index system by quantitative methods, and a support vector regression model refined by the selfish herd optimizer with elite opposition-based learning (EO-SHO-SVR) is built to improve the accuracy of flood disaster resilience evaluation. On this basis, the EO-SHO-SVR model is used to analyze the spatiotemporal evolution of flood disaster resilience in the Jiansanjiang branch of China Beidahuang Agricultural Reclamation Group Co., Ltd. over the past 22 years. In addition, to verify the comprehensive performance of the EO-SHO-SVR model, support vector regression (SVR), imperial competition algorithm-improved support vector regression (ICA-SVR), and unimproved selfish herd optimizer support vector regression (SHO-SVR) models were selected for comparative analysis. The results show that during the study period, the resilience levels reached a plateau of high levels from 1997 to 2018 after experiencing a state of steady low levels followed by increased volatility. Among the investigated factors, land-average flood prevention investment, GDP per capita, agricultural machinery power per unit of arable land, water conservancy project investment as a percentage of GDP, and rainfall are the main driving factors that cause spatiotemporal differences in flood disaster resilience in the study area. Spatially, the resilience levels in the Jiansanjiang branch are ordered as northern farms > southern farms > central farms, and the comprehensive index of resilience shows an increasing trend from west to east. In the model comparison, the EO-SHO-SVR model has outstanding advantages in fitting performance, reliability, rationality and stability, which fully demonstrates that the EO-SHO-SVR model is highly advanced and practical in the measurement of flood disaster resilience. These research results can provide a more accurate evaluation model of regional flood disaster resilience. In addition, they can also provide valuable information for regional flood resilience improvement and flood risk avoidance.
Related Concept Videos
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
02:41Responses to Drought and Flooding
01:29Applications of GIS: Disaster Management and Emergency Response
01:19Survival Tree
Building a Survival Tree
Constructing a...
01:16Response Surface Methodology
The process of RSM involves several key steps:
01:11Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...