摘要
近年来全球气候变化加剧,台风风暴潮灾害的频率、强度和损失逐渐加大,台风风暴潮灾害损失的预评估对海洋防灾减灾工作有重大现实意义。作者选用广东省1995年—2020年间的50组台风风暴潮数据进行研究,量化气候变化数据,建立台风风暴潮损失评估体系并通过主成分分析进行降维。采用麻雀搜索算法优化极限学习机建立预评估模型,分别对台风风暴潮损失等级、受灾人口和直接经济损失进行预测,结果表明,优化后的模型正确率更高,且具有更好的预测精确性和适用性,为防灾减灾事业提供了有效的损失评估方式。
In recent years,global climate change has intensified,and the frequency,intensity,and loss of typhoon storm surge disasters have gradually increased.Pre-assessing typhoon storm surge disaster losses has a considerable practical significance for marine disaster prevention and mitigation.This paper selects 50 sets of typhoon storm surge data in Guangdong Province from 1995 to 2020,quantifies climate change data,establishes a typhoon storm surge loss assessment system,and reduces the dimensionality through principal component analysis.The sparrow search algorithm is used to optimize the extreme learning machine to establish a pre-evaluation model,which pre-dicts the typhoon storm surge loss level,the affected population,and the direct economic loss.The results show that the optimized model has a higher accuracy rate and better prediction accuracy and applicability.Further,this paper provides an effective loss assessment method for disaster prevention and mitigation.
作者
郝婧
刘强
HAO Jing;LIU Qiang(College of Engineering,Ocean University of China,Qingdao 266100,China)
出处
《海洋科学》
CAS
CSCD
北大核心
2022年第2期55-63,共9页
Marine Sciences
基金
国家自然科学基金项目(41072176,41371496)
国家科技支撑计划项目(2013BAK05B04)。