Landslide Susceptibility Assessment Based on Multitemporal Landslide Inventories and TrAdaBoost Transfer Learning
-
摘要: 为了解决震区不同时期易发性评价中滑坡编录样本不足问题，以汶川地震震区汶川-映秀区域为研究区，基于TrAdaBoost迁移学习算法，利用2011-2013年滑坡数据集辅助训练2013-2015年滑坡数据集的滑坡易发性模型，分别建立了以决策树（DT）和随机森林（RF）为单体学习器的TrAdaBoost-DT和TrAdaBoost-RF滑坡易发性模型.通过所建立的模型对研究区的滑坡易发性进行预测，并将预测结果与仅用2013-2015年滑坡数据集所建立的DT和RF模型的预测结果进行对比.以受试者工作曲线下方面积（AUC）为评价指标，TrAdaBoost模型使得DT和RF模型的AUC分别提高了0.03和0.01.为了进一步验证所提方法有效性，以2013-2015年滑坡数据集辅助训练2015-2018年滑坡数据集中的易发性模型.结果表明，基于TrAdaBoost模型优化DT和RF模型的AUC均提高了0.13；TrAdaBoost模型能够有效提高传统基于机器学习滑坡易发性模型的预测性能，且对小数据集下的滑坡易发性模型的预测性能提升更为显著.Abstract: To overcome the shortcoming of insufficient landslide inventories, TrAdaboost-DT and TrAdaBoost-RF models with decision tree and random forest as basic learners respectively in 2013-2015 were built, by taking the Wenchuan-Yingxiu, Sichuan Province as the study area and the landslide inventory in 2011-2013 as an auxiliary data set. The proposed models were used to predict landslide susceptibility and prediction results were compared with those of DT and RF models trained by the landslide inventory in 2013-2015. The comparison results show that areas of under receiver operating characteristic curve (AUC) of TrAdaBoost-DT and TrAdaBoost-RF models were more than 0.03 and 0.01 than those of DT and RF models, respectively. To validate the prediction performance of the proposed models, the landslide inventory in 2013-2015 was used to build LS model in 2015-2018. The results indicate that the AUC of both DT and RF models increased by 0.13 using the proposed model. TrAdaBoost algorithm can improve the prediction performance of LS model based on machine learning algorithm and show significant improvement for those under small data sets.
-
Key words:
- landslide susceptibility /
- landslide inventory /
- transfer learning /
- TrAdaBoost /
- decision tree /
- random forest /
- engineering geology
-
萤石是许多金属和非金属矿床的主要脉石矿物之一.特别是由于火成岩可能富集具有经济价值的Be、Mo、Sn、U, 研究与之共生的萤石矿物成为近年来的热点[1~3].另一方面, 世界上报道的300多个与火成碳酸岩有关的萤石中, 达到经济价值的仅几个(印度Amba Dongar, 纳米比亚Okorusu, 巴西Mato Preto, 安哥拉Tchiviva, Bol'shaya Tagna, 图瓦卢Karasugsiy和Choakhol'skiy[4]).四川牦牛坪稀土矿床是中国仅次于白云鄂博矿床的大型稀土矿床.萤石不仅是该矿床中主要的脉石矿物, 具有可开采的工业价值, 同时萤石与正长岩-碳酸岩的共生关系显示了它们成矿流体来源的密切联系.
过去中外学者对不同矿床中的萤石做了许多Sr、Nd同位素的工作, 研究显示萤石Sr同位素是示踪成矿流体来源的有力工具[3, 5], Nd同位素初始值能较好地反映成矿流体的初始成分并提供可靠的成矿年龄[2, 6, 7].遗憾的是, 大多数矿床中萤石的成矿年龄晚于围岩, 成矿流体主要来源于大气降水或晚期岩浆热液活动, 容易受到地壳物质的混染[8], Sr同位素初始值偏高, 很难反映源区的地球化学性质, 特别是地幔源区的性质.牛贺才等[9, 10]在矿区萤石中发现了熔融包裹体, 均一温度较高, 为岩浆成因.许成等[11]分析了矿区50余件萤石样品的REE, 发现萤石表现出连续变化的REE配分模式, 分为LREE富集型、LREE平坦型和LREE亏损型.3种类型的萤石是同源不同阶段的产物, 其形成贯穿了整个REE成矿过程.在REE研究的基础上, 本文分析了矿床中3种REE配分模式萤石的Sr、Nd同位素组成, 探讨了萤石和稀土成矿流体的来源及演化.
1. 地质概况及萤石的基本地质特征
牦牛坪稀土矿床位于攀西裂谷北部.南河断裂带和锦屏山断裂将这一地区划分为东部裂谷区、西部地槽褶皱区和中部过渡区3个各具特色的大地构造单元.牦牛坪矿区位于中部过渡带, 处于攀西裂谷与龙门山-锦屏山幔坡陡倾带转折部位, 为陆壳脆弱活动带, 岩浆活动频繁.区内岩浆岩分布广泛, 有燕山期侵入的花岗岩(冕西花岗岩), 还有喜山期的碱性岩体(正长岩和碳酸岩), 以及少量时代不明的玄武岩和流纹岩, 其中喜山期的正长岩和碳酸岩与稀土矿化时空密切相关.矿床的矿石类型主要为重晶石伟晶岩型和方解石伟晶岩型, 少量为细网脉型, 矿石矿物主要为氟碳铈矿, 脉石矿物以萤石、重晶石、方解石、石英、云母和霓辉石为主[14, 15].
萤石是牦牛坪稀土矿中最重要的脉石矿物之一, 每种矿石类型中均有分布, 颜色多种多样, 颗粒大小悬殊.重晶石伟晶岩型矿石中的萤石主要呈断续条带产出, 少数呈微脉网状分布于其他矿物颗粒之间, 颜色主要为深紫色、紫色、浅紫色、浅绿色和无色, 粒度多在1~10 mm; 方解石伟晶岩型矿石中的萤石主要沿方解石和重晶石颗粒间不均匀充填分布, 形态极不规则, 有时集中呈团块状分布.颜色主要为紫色、浅紫色、浅绿色和无色, 粒度变化较大, 多在1~20 mm; 细网脉型矿石中萤石相对较少, 主要呈细脉状与重晶石和霓石-霓辉石脉体相伴分布, 颜色主要为紫色、浅紫色和无色, 粒度多在0.5~5.0 mm.此外, 在远离矿体的地区还有呈伟晶状产出的萤石, 颜色主要为绿色、浅绿色和无色, 粒度一般 > 5 mm.
2. 样品及分析方法
本次工作分析了牦牛坪矿区3种REE配分模式的萤石Sr、Nd同位素组成.样品由中国科学院地质与地球物理研究所分析, 利用MAT262热电离质谱.Sr、Nd同位素分析流程相似, 首先将样品加入HF+HClO4混合酸溶解, 然后分别用AGW50×12(100~200目)阳离子交换柱将Rb、Sr分离, 用萃淋树脂离子交换柱将Sm、Nd分离.化学分析在净化实验室的超净工作台内完成, 实验全流程空白w(Rb)=50×10-11、w(Sr)=50×10-11、w(Sm)=7×10-11、w(Nd)=8×10-11.分析标样NBS987的w(87Sr)/w(86Sr)=0.710 234±7×10-6, LA的w(143Nd)/w(144Nd)=0.511 838±8×10-6.
3. 结果分析
表 1列出牦牛坪稀土矿床萤石的Sr、Nd同位素组成, 萤石的w(87Rb)/w(86Sr)和w(147Sm)/w(144Nd)比值较低, 由成矿年龄t=30 Ma计算的[w(87Sr)/w(86Sr)] 0和[w(143Nd)/w(144Nd)]0与测定的w(87Sr)/w(86Sr)和w(143Nd)/w(144Nd)(现代值)不存在明显的差别(表 1).
表 1 牦牛坪稀土矿床萤石Sr、Nd同位素组成Table Supplementary Table Sr-Nd isotope of fluorite in Maoniuping REE deposit
从表 1中可见, 5件不同颜色、产于不同矿石类型、不同REE特征萤石的Sr、Nd同位素组成基本一致, 其w(87Sr)/w(86Sr)和w(143Nd)/w(144Nd)变化范围分别为0.706 031~0.706 237和0.512 409~0.512 437, εSr和εNd也不具明显差别, 分别为22.22~25.15和-4.48~-3.65;1件远离矿体萤石的w(87Sr)/w(86Sr)、w(143Nd)/w(144Nd)、εSr和εNd均在矿体萤石相应值变化范围之内, 这些特征表明矿区萤石具有同源性.与该区萤石REE地球化学研究结果[11]一致.
根据围岩的划分[8], 笔者总结了花岗岩型、火山岩型和碳酸岩或碳酸盐岩型3种萤石类型Sr同位素的初始比值, 显示不同类型的萤石Sr初始值不同, 火山岩型高于花岗岩型, 高于碳酸岩或碳酸盐岩型(图 1), 表明萤石Sr同位素与围岩关系密切, 这一点已得到学者的认可[25].矿区萤石Sr初始值相对较低, 具有幔源特征.
4. 讨论
4.1 萤石成矿流体来源
萤石Sr-Nd同位素组成是示踪成矿流体来源的重要手段之一.由于Sr与Ca相似的地球化学特征, 两者易于发生类质同象置换, 而Rb则相反, 不易与Ca发生类质同象, 因而萤石是一种相对富Sr而贫Rb的矿物, 笔者测定了四川冕宁稀土矿床中20件萤石样品的微量元素含量, 其中w(Sr)在2 042×10-6~6 173×10-6, 平均3 210×10-6, 而w(Rb)大都低于检测限, 最高仅为1.79×10-6; Deer等[26]的研究结果表明, 萤石中Ca的位置只接受少量的Sr而不接受Rb.正因为萤石是一种相对富Sr而贫Rb的矿物, 在成矿过程中这种矿物的Sr同位素组成不受87Rb衰变的影响, 较好地保存了成矿流体本身的Sr同位素组成信息, 因而萤石Sr同位素组成能较好地示踪成矿流体的来源.同时萤石中的稀土主要来源于成矿流体中的F-REE络合物, 所以其Nd同位素组成也是判别成矿流体(尤其是F)来源的有力工具之一[2].
对比矿区主要围岩分析[29]可见, 牦牛坪稀土矿床萤石的Sr、Nd同位素组成与矿区出露的碳酸岩和正长岩两者基本一致, 明显不同于花岗岩; 且萤石Sr初始值相对较低, 低于花岗岩型萤石(图 1), 说明矿区萤石成矿流体主要来源于正长岩-碳酸岩.
4.2 REE成矿流体来源
图 2b中, 矿区萤石位于EM1-EM2轨迹上, 靠近EM1地幔端元, 具有明显的幔源特征.包裹体研究也显示其形成温度较高, 并发现了熔融包裹体[9].对比同种类型的印度Amba Dongar碱性岩(碳酸岩-硅酸岩)矿区萤石发现, 两者Nd同位素比值相似(图 2a).Amba Dongar矿区萤石Sr-Nd同位素研究表明[2], 萤石Nd初始值与矿区碱性岩相似, 说明F的来源与碱性岩的岩浆活动有关.研究显示[30]: F是REE的主要载体, F-REE络合常数大于其他络合剂.Wendlandt等[31]的实验也证实: 富CO2的碱性硅酸岩熔体通过分离结晶或液态不混溶作用分异出硅酸岩熔体和碳酸岩熔体的过程中, 也分异出富REE(尤其是LREE)的流体.因此可以认为牦牛坪稀土矿床的稀土成矿流体来源具有幔源特征, 与碳酸岩-正长岩岩浆活动有关.以下证据也支持这种观点.
图 2 不同地区萤石[w(87Sr)/w(86Sr)] 0-[w(143Nd)/w(144Nd)]0图a中, MNP为牦牛坪稀土矿区萤石; ★为矿区花岗岩; AD为产于印度Amba Dongar碱性岩(硅酸岩-碳酸岩)地区萤石[2]; Ar、Ir、Sp引自文献[16~18], 其成矿流体主要来源于花岗岩.图b中方框为矿区萤石, 椭圆为碱性岩(正长岩-碳酸岩); DMM、HIMU、EM1和EM2引自文献[27], [w(87Sr)/w(86Sr)]Bulk Earth=0.704 5、[3(143Nd)/w(144Nd)]CHUR=0.512 363 8引自文献[28]Fig. 2. [w(87Sr)/w(86Sr)]0-[w(143Nd)/w(144Nd)]0 of different regional fluorites(1) 牦牛坪稀土矿床与碳酸岩-正长岩时空密切共生.空间上: 矿床与碳酸岩-正长岩分布规律一致, 碳酸岩-正长岩是矿区最主要的赋矿岩石; 时间上: 两者均形成于喜山期, 蒲广平[32]报道了矿区正长岩的K-Ar稀释法年龄为28~48 Ma, 碳酸岩为(31.7±0.7) Ma, 施泽民[33]利用矿脉中钍石、钠铁闪石和黑云母测得同位素年龄分别为23 Ma和(27~40±0.7) Ma.而花岗岩为燕山期产物[34], 两者时间相差较大.
(2) 本文测得矿区石英δ(D)=-77×10-3~-52×10-3, δ(18O)=7.8×10-3~9.4×10-3组成显示: 牦牛坪矿区成矿流体具有幔源特征, 萤石w(87Sr)/w(86Sr)比值(变化范围0.706 031~0.706 237)大体在地幔[w(87Sr)/w(86Sr)] 0比值范围(0.704±0.002)之内也可证实这一点.
(3) 燕山期冕西花岗岩为牦牛坪稀土矿床及碱性岩体(碳酸岩-正长岩)主要围岩之一.本文测得2件花岗岩样品, w(87Sr)/w(86Sr)为0.743 765和0.744 440, w(143Nd)/w(144Nd)为0.512 419和0.512 485, 取原始地幔w(87Sr)/w(86Sr)=0.704 5, w(143Nd)/w(144Nd)=0.512 64[35], 按Zhu等[36]提出的二元混合模式计算公式: x=(Rm-R1)/(R2-R1), X=Cm×x/K.(Rm为样品测定的同位素比值; R1为原始地幔的同位素比值; R2为混合端元同位素比值; X为混合体积比; Cm为样品Sr、Nd的测定浓度; K为综合常数, 计算Sr和Nd分别为15 000和900[36]).以矿区花岗岩w(87Sr)/w(86Sr)=0.744 102, w(143Nd)/w(144Nd)=0.512 457(均值)为混合端元, 计算萤石中锶、钕分别有98.2%~99.4%和83.7%~88.8%为幔源锶、钕, 只有0.6%~1.8%, 11.2%~16.3%为壳源锶、钕.如果将地壳作为混合端元, 取其w(87Sr)/w(86Sr)=0.717, w(143Nd)/w(144Nd)=0.512 0[35], 计算结果显示: 94.3%~98.0%, 95.3%~96.8%为幔源锶、钕; 壳源锶、钕仅占2.0%~5.7%, 3.2%~4.7%.2种计算结果均表明该区成矿流体具有明显的幔源特征.
(4) 另据攀西裂谷地球物理研究成果[37], 攀西地区上地幔顶部遗存裂谷期“异常地幔体”, 根据大地热流值和爆炸地震测深给出的模型, “异常地幔体”是壳幔混熔体部分熔融引起的.张云湘等[37]指出“如遇到合适的板块活动条件, 推测将会又一次出现构造岩浆活化”, 而印度-欧亚块板碰撞缝合引起强大的喜山运动提供了这一契机, 使其可能局部活化, 成为本区稀土成矿的发源地.
致谢: 野外地质工作中得到四川省地矿厅109地质队蒲广平高级工程师的大力帮助, 中科院地质与地球物理研究所黄萱研究员完成了Sr、Nd同位素组成测定, 中科院地化所裘愉卓研究员、彭建堂副研究员韩润生博士后、张辉博士对该文提出了宝贵意见, 中国地科院矿床所王登红研究员、袁忠信研究员提供了宝贵资料, 在此表示感谢. -
图 2 基于多时期滑坡编录和TrAdaBoost迁移学习的滑坡易发性模型构建流程
Fig. 2. Flowchart of landslide susceptibility model using the multitemporal landslide inventories and TrAdaBoost transfer learning
图 4 滑坡影响因子
a.高程；b.坡度；c.坡向；d.剖面曲率；e.地层岩性；f.距断层距离
Fig. 4. The landslide influence factors in the study area
图 5 基于TrAdaBoost-DT (a)和DT (b)模型的研究区滑坡易发性分布图（2013‒2015）
Fig. 5. Landslide susceptibility maps using TrAdaBoost-DT (a) and DT (b) models (2013‒2015)
图 6 不同滑坡易发性模型的ROC曲线（2013‒2015）
Fig. 6. ROC of different landslide susceptibility models (2013‒2015)
图 7 基于TrAdaBoost-RF和RF模型的研究区2013‒2015年期间滑坡易发性分布
Fig. 7. Landslide susceptibility maps using TrAdaBoost-RF and RF models in 2013‒2015
a. TrAdaBoost-RF; b. RF
图 8 基于TrAdaBoost-DT、DT、TrAdaBoost-RF和RF模型的研究区2015‒2018年期间滑坡易发性分布
Fig. 8. Landslide susceptibility maps using TrAdaBoost-DT, DT, TrAdaBoost-RF and RF models in 2015‒2018
a. TrAdaBoost-DT; b. DT; c. TrAdaBoost-RF; d. RF
图 9 不同滑坡易发性模型的ROC曲线（2015‒2018）
Fig. 9. ROC of different landslide susceptibility models (2015‒2018)
表 1 研究区不同时期滑坡数据集样本数量
Table 1. The number of landslide in different periods in the study area
时间 2005‒2007 2008‒2011 2011‒2013 2013‒2015 2015‒2017 2017‒2018 滑坡数量 71 8 830 3 690 1 074 20 17 
下载: 导出CSV
表 2 研究区数据来源、分辨率和类型
Table 2. The source, resolution and type of data
数据 来源 分辨率/比例 格式类型 滑坡目录 公开数据集 https://zenodo.org/record/1484667#.Yz5QG3ZByiM 25 m 矢量点 区域DEM Google Earth Engine 30 m 栅格 地层岩性 四川基础地理信息中心 1:100 000 矢量面
下载: 导出CSV
表 3 滑坡影响因子与滑坡发育相关性检测结果
Table 3. q values of landslide influencing factors
滑坡影响因子 地层岩性 坡向 坡度 高程 剖面曲率 距断层距离 q 0.007 0.068 0.031 0.020 0.003 0.012 p value 0.014 0.000 0.000 0.000 0.334 0.000
下载: 导出CSV
表 4 不同模型预测性能的检验结果（2013‒2015）
Table 4. Prediction performance of different models (2013‒2015)
2013‒2015 TrAdaBoost-DT DT TrAdaBoost-RF RF 滑坡预测 0.58 0.58 0.75 0.67 非滑坡预测 0.81 0.72 0.54 0.63 总体准确率 0.7 0.65 0.65 0.65 AUC 0.65 0.62 0.62 0.61
下载: 导出CSV
表 5 不同模型预测性能的检验结果（2015‒2018）
Table 5. Prediction performance of different models (2015‒2018)
2017‒2018 TrAdaBoost-DT DT TrAdaBoost-RF RF 滑坡预测 0.69 0.67 0.67 0.66 非滑坡预测 0.57 0.54 0.54 0.53 总体准确率 0.68 0.65 0.65 0.65 AUC 0.76 0.63 0.73 0.6
下载: 导出CSV
-
Breiman, L., 2001. Random Forests. Machine Learning, 45(1): 5-32. doi: 10.1023/A:1010933404324 Chen, Y., Fan, X. M., 2020. Susceptibility Assessment of Post-Earthquake Geo-Hazard in the Epicentral Area of the 2008 Wenchuan Eearthquake near Yingxiu Town. Science Technology and Engineering, 20(9): 3516-3527 (in Chinese with English abstract). doi: 10.3969/j.issn.1671-1815.2020.09.021 Criss, R. E., Yao, W. M., Li, C. D., et al., 2020. A Predictive, Two-Parameter Model for the Movement of Reservoir Landslides. Journal of Earth Science, 31(6): 1051-1057. doi: 10.1007/s12583-020-1331-9 Dai, W. Y., Yang, Q., Xue, G. R., et al., 2007. Boosting for Transfer Learning. In: Proceedings of the 24th International Conference on Machine Learning. ACM Press, New York, 193-200. Dou, J., Xiang, Z. L., Xu, Q., et al., 2023. Application and Development Trend of Machine Learning in Landslide Intelligent Disaster Prevention and Mitigation. Earth Science, 48(5): 1657-1674 (in Chinese with English abstract). Dou, J., Yunus, A. P., Tien Bui, D., et al., 2019. Assessment of Advanced Random Forest and Decision Tree Algorithms for Modeling Rainfall-Induced Landslide Susceptibility in the Izu-Oshima Volcanic Island, Japan. The Science of the Total Environment, 662: 332-346. https://doi.org/10.1016/j.scitotenv.2019.01.221 Fan, X. M., Yunus, A. P., Scaringi, G., et al., 2021. Rapidly Evolving Controls of Landslides after a Strong Earthquake and Implications for Hazard Assessments. Geophysical Research Letters, 48(1): 1-12. doi: 10.1029/2020GL090509 Formetta, G., Rago, V., Capparelli, G., et al., 2014. Integrated Physically Based System for Modeling Landslide Susceptibility. The Third Italian Workshop on Landslides: Hydrological Response of Slopes through Physical Experiments, Field Monitoring and Mathematical Modeling, 9: 74-82. Guo, C., Xu, Q., Dong, X.J., et al., 2021. Geohazard Recognition and Inventory Mapping Using Airborne LiDAR Data in Complex Mountainous Areas. Journal of Earth Science, 32(5): 1079-1091. doi: 10.1007/s12583-021-1467-2 Guzzetti, F., Mondini, A. C., Cardinali, M., et al., 2012. Landslide Inventory Maps: New Tools for an Old Problem. Earth-Science Reviews, 112: 42-66. doi: 10.1016/j.earscirev.2012.02.001 Huang, F. M., Pan, L. H., Yao, C., et al., 2021. Landslide Susceptibility Prediction Modeling Based on Semi- Supervised Machine Learning. Journal of Zhejiang University (Engineering Science), 55(9): 1705-1713 (in Chinese with English abstract). Huang, W.B., Ding, M.T., Wang, D., et al., 2022. Evaluation of Landslide Susceptibility Based on Layer Adaptive Weighted Convolutional Neural Network Model along Sichuan-Tibet Traffic Corridor. Earth Science, 47(6): 2015-2030 (in Chinese with English abstract). Jiang, S. H., Liu, X., Huang, F. M., et al., 2020. Failure Mechanism and Reliability Analysis of Soil Slopes under Rainfall Infiltration Considering Spatial Variability of Multiple Soil Parameters. Chinese Journal of Geotechnical Engineering, 42(5): 900-907 (in Chinese with English abstract). Lee, S., Ryu, J. H., Kim, I.S., 2007. Landslide Susceptibility Analysis and Its Verification Using Likelihood Ratio, Logistic Regression, and Artificial Neural Network Models: Case Study of Youngin, Korea. Landslides, 4(4): 327-338. doi: 10.1007/s10346-007-0088-x Li, C. D., Fu, Z. Y., Wang, Y., et al., 2019. Susceptibility of Reservoir-Induced Landslides and Strategies for Increasing the Slope Stability in the Three Gorges Reservoir Area: Zigui Basin as an Example. Engineering Geology, 261: 105279. doi: 10.1016/j.enggeo.2019.105279 Li, Y. W., Xu, L. Y., Zhang, L. L., et al., 2023. Study on Development Patterns and Susceptibility Evaluation of Coseismic Landslides within Mountainous Regions Influenced by Strong Earthquakes. Earth Science, 48(5): 1960-1976 (in Chinese with English abstract). Ling, P., Niu, R. Q., Huang, B., et al., 2014. Landslide Susceptibility Mapping Based on Rough Set Theory and Support Vector Machines: A Case of the Three Gorges Area, China. Geomorphology, 204(1): 287-301. Liu, J., Li, S. L., Chen, T., 2018. Landslide Susceptibility Assesment Based on Optimized Random Forest Model. Geomatics and Information Science of Wuhan University, 43(7): 1085-1091 (in Chinese with English abstract). Long, J. J., Liu, Y., Li, C. D., et al., 2021. A Novel Model for Regional Susceptibility Mapping of Rainfall-Reservoir Induced Landslides in Jurassic Slide-Prone Strata of Western Hubei Province, Three Gorges Reservoir Area. Stochastic Environmental Research and Risk Assessment, 35(7): 1403-1426. doi: 10.1007/s00477-020-01892-z Pan, S. J., Yang, Q., 2010. A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10): 1345-1359. doi: 10.1109/TKDE.2009.191 Shao, L., Zhu, F., Li, X. L., 2015. Transfer Learning for Visual Categorization: A Survey. IEEE Transactions on Neural Networks and Learning Systems, 26(5): 1019-1034. https://doi.org/10.1109/TNNLS.2014.2330900 Spackman, K. A., 1989. Signal Detection Theory: Valuable Tools for Evaluating Inductive Learning. In: Proceedings of the 6th International Workshop on Machine Learning (IWML). MICCAI, Ithaca, 160-163. Tang, H. M., Wasowski, J., Juang, C. H., 2019. Geohazards in the Three Gorges Reservoir Area, China: Lessons Learned from Decades of Research. Engineering Geology, 261: 105267. doi: 10.1016/j.enggeo.2019.105267 Tien Bui, D., Pradhan, B., Lofman, O., et al., 2012. Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models. Mathematical Problems in Engineering, 2012: 974638. http://siba-sinmemis.unile.it/journals/HOA/MPE/Volume2012/974638.pdf Wang, F. W., Zhang, Y. M., Huo, Z. T., et al., 2004. The July 14, 2003 Qianjiangping Landslide, Three Gorges Reservoir, China. Landslides, 1: 157-162. http://www.onacademic.com/detail/journal_1000034488354610_0b33.html Wang, H. J., Wang, L., Zhang, L. M., et al., 2022. Transfer Learning Improves Landslide Susceptibility Assessment. Gondwana Research. https://doi.org/10.1016/j.gr.2022.07.008 Wang, J. F., Li, X. H., Christakos, G., et al., 2010. Geographical Detectors-Based Health Risk Assessment and Its Application in the Neural Tube Defects Study of the Heshun Region, China. International Journal of Geographical Information Science, 24(1): 107-127. doi: 10.1080/13658810802443457 Wang, J. J., Yin, K. L., Xiao, L. L., 2014. Landslide Susceptibility Assessment Based on GIS and Weighted Information Value: A Case Study of Wanzhou District, Three Gorges Reservoir. Chinese Journal of Rock Mechanics and Engineering, 33(4): 797-808 (in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTOTAL-YSLX201404018.htm Wang, Y., Fang, Z. C., Hong, H. Y., 2019. Comparison of Convolutional Neural Networks for Landslide Susceptibility Mapping in Yanshan County, China. The Science of the Total Environment, 666: 975-993. https://doi.org/10.1016/j.scitotenv.2019.02.263 Wu, R. Z., Hu, X. D., Mei, H. B., et al., 2021. Spatial Sususceptibility Assessment of Landslides Based on Random Forest: A Case Study from Hubei Section in the Three Gorges Reservoir Area. Earth Science, 46(1): 321-330 (in Chinese with English abstract). Xu, C., Dai, F. C., Xu, X. W., 2011. Earthquake Triggered Landslide Susceptibility Evaluation Based on GIS Platform and Weight-of-Evidence Modeling. Earth Science, 36(6): 1155-1164 (in Chinese with English abstract). Xu, C., Dai, F. C., Yao, X., et al., 2009. GIS-Based Landslide Susceptibility Assessment Using Analytical Hierarchy Process in Wenchuan Earthquake Region. Chinese Journal of Rock Mechanics and Engineering, 28(S2): 3978-3985 (in Chinese with English abstract). Xu, Q., Li, W. L., Dong, X. J., et al., 2017. The Xinmocun Landslide on June 24, 2017 in Maoxian, Sichuan: Characteristics and Failure Mechanism. Chinese Journal of Rock Mechanics and Engineering, 36(11): 2612-2628 (in Chinese with English abstract). http://www.cqvip.com/QK/96026X/201711/673848535.html Yang, Q., 2018. Study on Temporal and Spatial Evolution Law and Susceptibility Evaluation of Geological Disasters after Wenchuan Earthquake (Dissertation). Chengdu University of Technology, Chengdu (in Chinese with English abstract). Yin, K. L., Zhu, L., 2001. Landslide Hazard Zonation and Application of GIS. Earth Science Frontiers, 8(2): 279-284 (in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTOTAL-DXQY200102012.htm Yin, Y. P., 2008. Researches on the Geo-Hazards Triggered by Wenchuan Earthquake, Sichuan. Journal of Engineering Geology, 16(4): 433-444 (in Chinese with English abstract). http://d.wanfangdata.com.cn/Conference/7822071 陈怡, 范宣梅, 2020. 震后地质灾害易发性评价: 以映秀震区为例. 科学技术与工程, 20(9): 3516-3527. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202009021.htm 窦杰, 向子林, 许强, 等, 2023. 机器学习在滑坡智能防灾减灾中的应用与发展趋势. 地球科学, 48(5): 1657-1674. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305001.htm 黄发明, 潘李含, 姚池, 等, 2021. 基于半监督机器学习的滑坡易发性预测建模. 浙江大学学报(工学版), 55(9): 1705-1713. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC202109012.htm 黄武彪, 丁明涛, 王栋, 等, 2022. 基于层数自适应加权卷积神经网络的川藏交通廊道沿线滑坡易发性评价. 地球科学, 47(6): 2015-2030. doi: 10.3799/dqkx.2021.243 蒋水华, 刘贤, 黄发明, 等, 2020. 考虑多参数空间变异性的降雨入渗边坡失稳机理及可靠度分析. 岩土工程学报, 42(5): 900-907. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC202005017.htm 李永威, 徐林荣, 张亮亮, 等, 2023. 强震山区地震诱发滑坡发育规律与易发性评估. 地球科学, 48(5): 1960-1976. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305020.htm 刘坚, 李树林, 陈涛, 2018. 基于优化随机森林模型的滑坡易发性评价. 武汉大学学报(信息科学版), 43(7): 1085-1091. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201807017.htm 王佳佳, 殷坤龙, 肖莉丽, 2014. 基于GIS和信息量的滑坡灾害易发性评价: 以三峡库区万州区为例. 岩石力学与工程学报, 33(4): 797-808. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201404018.htm 吴润泽, 胡旭东, 梅红波, 等, 2021. 基于随机森林的滑坡空间易发性评价: 以三峡库区湖北段为例. 地球科学, 46(1): 321-330. doi: 10.3799/dqkx.2020.032 许冲, 戴福初, 徐锡伟, 2011. 基于GIS平台与证据权的地震滑坡易发性评价. 地球科学, 36(6): 1155-1164. doi: 10.3799/dqkx.2011.122 许冲, 戴福初, 姚鑫, 等, 2009. GIS支持下基于层次分析法的汶川地震区滑坡易发性评价. 岩石力学与工程学报, 28(S2): 3978-3985. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2009S2104.htm 许强, 李为乐, 董秀军, 等, 2017. 四川茂县叠溪镇新磨村滑坡特征与成因机制初步研究. 岩石力学与工程学报, 36(11): 2612-2628. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201711002.htm 杨琴, 2018. 汶川震后地质灾害时空演化规律及易发性评价研究(硕士学位论文). 成都: 成都理工大学. 殷坤龙, 朱良峰, 2001. 滑坡灾害空间区划及GIS应用研究. 地学前缘, 8(2): 279-284. https://www.cnki.com.cn/Article/CJFDTOTAL-DXQY200102012.htm 殷跃平, 2008. 汶川八级地震地质灾害研究. 工程地质学报, 16(4): 433-444. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ200804000.htm -
下载:
点击查看大图
计量
- 文章访问数: 1304
- HTML全文浏览量: 647
- PDF下载量: 99
- 被引次数: 0
