【摘要】 长白山保护开发区崩塌灾害频发，对保护区的人民生命财产造成了破坏，阻碍了区域经济发展，为了降低崩塌灾害给区域内人民生命财产造成的损失程度并提高开发区人们防灾减灾能力，进行有效的地质灾害危险性评价是防灾减灾的重要组成部分。但常见的二元分类崩塌灾害危险评价模型存在分类速度慢、分类误差大及样本类型单一等问题，因此，按照地质灾害规模等级规范对灾害点进行分类，运用基于灾害规模等级的多分类支持向量机构建危险性评价模型对研究区进行危险性评价，避免了传统危险性评价受主观权重影响的局限性。结果表明，极高和高危险性区主要集中在研究区的中东部区域，运用实际灾害点对危险性评价结果进行验证，评价结果与实际情况吻合，验证了模型的有效性，其可以为区域内地质灾害的防治和开发灾害监测预警技术平台及开发旅游提供参考。更多还原

【Abstract】 The frequent occurrence of collapse disasters in the Changbai Mountain Protection and Development Zone has caused damage to the lives and property of the people in the area, and the economic development in the area has been hindered.In order to reduce the damage caused by collapse disasters to the lives and property of the people and improve the disaster prevention and reduction ability in the area, it is an important component of disaster prevention and reduction to take geological hazard risk evaluation effectively.The common binary classification collapse hazard evaluation models have problems such as slow classification speed, large classification error, and single sample type.Therefore, the disaster points are classified according to the specifications of geological disaster scale, a multi-classification support vector mechanism based on hazard scale level is used to build a risk evaluation model for the study area, avoiding the limitations of traditional risk evaluation being influenced by subjective weights.The results show that the extremely high and high-risk areas are mainly concentrated in the central and eastern regions of the study area.The actual disaster points are used to verify the hazard evaluation results, which are consistent with the actual situation and verifies the effectiveness of the model.It can provide references for the prevention and control of geological disasters in the region, the development of disaster monitoring and early warning technology platforms, and the development of tourism.更多还原