Debris-flow disasters occurred frequently after the Mw 8.0 Wenchuan earthquake on 12 May 2008 in Sichuan Province, China. Based on historical accounts of debris-flow disaster events, it found that debris flow occurren...Debris-flow disasters occurred frequently after the Mw 8.0 Wenchuan earthquake on 12 May 2008 in Sichuan Province, China. Based on historical accounts of debris-flow disaster events, it found that debris flow occurrence is closely related to the impact of earthquakes and droughts, because earthquakedrought activities can increase the loose solid materials, which can transform into debris flows under the effect of rainstorms. Based on the analysis of historical earthquake activity(frequency, magnitude and location), drought indexes and the trend of climate change(amount of rainfall), a prediction method was established, and the regional debris flow susceptibility was predicted. Furthermore, in a debris flow-susceptible site, effective warning and monitoring are essential not only from an economicpoint of view but are also considered as a frontline approach to alleviate hazards. The advantages of the prediction and early monitoring include(1) the acquired results being sent to the central government for policy making;(2) lives and property in mountainous areas can be protected, such as the 570 residents in the Aizi valley, who evacuated successfully before debris flows in 2012;(3) guiding the government to identify the areas of disasters and the preparation for disaster prevention and mitigation, such as predicting disasters in high-risk areas in the period 2012-2017, helping the government to recognize the development trend of disasters;(4) the quantitative prediction of regional debris-flow susceptibility, such as after the Wenchuan earthquake, can promote scientific and sustainable development and socioeconomic planning in earthquake-struck areas.展开更多
针对当前研究中泥石流诱发因子敏感度各异导致的预测准确度不高、数据集样本有限造成的模型训练和预测效果不佳、非线性过程严重引起的参数难以确定等问题,利用改进的核主成分分析算法(kernel principal component analysis,KPCA)筛选...针对当前研究中泥石流诱发因子敏感度各异导致的预测准确度不高、数据集样本有限造成的模型训练和预测效果不佳、非线性过程严重引起的参数难以确定等问题,利用改进的核主成分分析算法(kernel principal component analysis,KPCA)筛选出相关性一般的因子,结合宽度学习(broad learning,BL)建立泥石流概率预测模型,再通过引入正弦因子的粒子群算法(TFPSO)对模型进行优化,最终建立基于KPCA-TFPSO-BL的泥石流预测模型。通过实验对比了经典BL模型、KPCAPSO-BL模型以及KPCA-TFPSO-BL模型的性能,结果表明,KPCA-TFPSO-BL的均方根误差为4.92,平均绝对误差为4.60,训练时间为7.22 s,该模型在预测误差和训练时间方面综合表现最佳。本研究为泥石流预测领域提供了一种新的思路和借鉴。展开更多
基金funded by National Natural Science Foundation of China(Grant No.41671112 and 41861134008)National Key Research and Development Plan(Grant No.2018YFC1505202)Sichuan Province Science and Technology Plan Project Key research and development projects(Grant No.18ZDYF0329)
文摘Debris-flow disasters occurred frequently after the Mw 8.0 Wenchuan earthquake on 12 May 2008 in Sichuan Province, China. Based on historical accounts of debris-flow disaster events, it found that debris flow occurrence is closely related to the impact of earthquakes and droughts, because earthquakedrought activities can increase the loose solid materials, which can transform into debris flows under the effect of rainstorms. Based on the analysis of historical earthquake activity(frequency, magnitude and location), drought indexes and the trend of climate change(amount of rainfall), a prediction method was established, and the regional debris flow susceptibility was predicted. Furthermore, in a debris flow-susceptible site, effective warning and monitoring are essential not only from an economicpoint of view but are also considered as a frontline approach to alleviate hazards. The advantages of the prediction and early monitoring include(1) the acquired results being sent to the central government for policy making;(2) lives and property in mountainous areas can be protected, such as the 570 residents in the Aizi valley, who evacuated successfully before debris flows in 2012;(3) guiding the government to identify the areas of disasters and the preparation for disaster prevention and mitigation, such as predicting disasters in high-risk areas in the period 2012-2017, helping the government to recognize the development trend of disasters;(4) the quantitative prediction of regional debris-flow susceptibility, such as after the Wenchuan earthquake, can promote scientific and sustainable development and socioeconomic planning in earthquake-struck areas.
