基于LSTM_TCN模型的降雨型滑坡时间概率预测及气象预警建模

Temporal probability prediction and meteorological early warning modeling of rainfall-induced landslide based on LSTM_TCN model

如果滑坡发生时间信息不完备则会导致滑坡与降雨时序关系错误,以至于降雨阈值模型精度偏低。以重庆市万州区1995-2015年所发生的降雨型滑坡为研究对象,将区内严重缺失历史滑坡时间信息的恒合乡作为验证区,提出了一种基于长短时记忆网络(LSTM)融合时域卷积网络(TCN)的模型方法。该方法通过模拟降雨型滑坡发生时间与降雨量间的非线性关系,重建降雨型滑坡事件在某日发生的时间概率。将重建时间信息后的滑坡事件进行了验证与筛选,应用于累积有效降雨量-降雨历时曲线的合理划分,构建了滑坡气象预警模型。结果表明,本方法所预测滑坡时间概率平均值达到90.33%,高于人工神经网络(ANN)(71.17%)、LSTM(72.75%)和TCN(86.91%)的概率。利用预测概率高于90%的滑坡,将验证区18个时间信息扩充至201个。基于扩充时间信息后的滑坡数据所构建的气象预警模型比仅利用历史滑坡事件具有更合理的预警分级,在严重警告级别上有效预警率提升了42.86%。结果说明该方法可弥补野外调查中灾害数据时间信息不足的问题,为降雨型滑坡气象预警工作提供数据支撑,由此提高气象预警准确率。

[Objective] Incomplete landslide timing information can result in inaccuracies in the temporal relationship between landslides and rainfall,consequently affecting the precision of a critical rainfall threshold model.[Methods] To address this issue,this study focuses on rainfall-induced landslides in the Wanzhou District of Chongqing from 1995 to 2015.The Henghe Township,lacking historical landslide data,serves as the verification area.We proposed a prediction model for the daily temporal probability of landslide occurrence on a certain day based on long short-term memory(LSTM) and a temporal convolutional network(TCN).This method was used to reconstruct the temporal information of rainfall-induced landslide events by simulating the nonlinear relationship between the duration of landslides and rainfall.After the reconstruction of temporal information,the landslide events were verified and selected and subsequently applied to a reasonable division of the E-D effective rainfall threshold curve to establish the landslide meteorological warning model.[Results] The results showed that the average temporal probability of rainfall-induced landslides predicted by the proposed method reached 90.33%,which was higher than that of the ANN(71.17%),LSTM(72.75%),and TCN(86.91%) models.Using temporal probabilities exceeding a 90% threshold,18 data points,including 42 landslides in the verification area,are expanded to 201.Compared with using solely historical landslide events,the meteorological warning model based on expanded temporal information provides a more reasonable warning classification,and the effective warning rate at the severe warning level is increased by 42.86%.[Conclusion] This method can compensate for the shortage of landslide time information in field investigations and provide data support for early meteorological warning systems for rainfall-induced landslides,thus improving the accuracy of early meteorological warning systems.