基于原型网络的云南怒江州泥石流灾害易发性评价与区划

韩俊; 王保云

doi:10.16031/j.cnki.issn.1003-8035.202207023

基于原型网络的云南怒江州泥石流灾害易发性评价与区划

doi: 10.16031/j.cnki.issn.1003-8035.202207023

韩俊^{1, 2},
王保云^{2, 3, ,}

1.
云南师范大学信息学院，云南昆明　650500
2.
云南师范大学数学学院，云南昆明　650500
3.
云南省高校复杂系统建模及应用重点实验室，云南昆明　650500

基金项目: 国家自然科学基金项目（61966040）

详细信息

作者简介:
韩俊：韩　俊（1990-），男，云南寻甸人，硕士研究生，研究方向为图像处理和深度学习。E-mail：455804886@qq.com

通讯作者:
王保云（1977-），男，云南华宁人，副教授，研究方向为机器学习及图像处理。E-mail：wspbmly@163.com

中图分类号: P642.23
计量
- 文章访问数: 1114
- HTML全文浏览量: 1034
- PDF下载量: 132
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-18
- 录用日期: 2023-05-26
- 修回日期: 2022-12-17
- 网络出版日期: 2023-05-29
- 刊出日期: 2023-10-31

A case study on the susceptibility assessment of debris flows disasters based on prototype network in Nujiang Prefecture, Yunnan Province

Jun HAN^{1, 2},
Baoyun WANG^{2, 3
, ,}

1.
Yunnan Normal University, School of Information Science and Technology, Kunming, Yunnan　650500, China
2.
Yunnan Normal University, School of Mathematics, Kunming, Yunnan　650500, China
3.
Key Laboratory of Complex System Modeling and Application for Universities in Yunnan, Kunming, Yunnan　650500, China

摘要

摘要: 针对基于泥石流因子评价方法中选取因子不一及训练样本少的问题，提出了一种基于原型网络的沟谷泥石流灾害易发性评价方法。首先，通过元学习方式组织训练数据，计算每一类沟谷的原型中心。其次，计算未知样本与每一类原型中心的距离，得到其从属类别的概率。最后，根据类别概率计算沟谷的泥石流易发性指数，得到泥石流易发性评价等级。运用模型对怒江州的沟谷进行评价，并与历史灾害数据进行比对，分类正确率达到67.39%，历史事件中泥石流灾害严重程度与模型的评价等级吻合度较好。相比传统实地勘测和因子评价等方法，文章方法能够通过遥感影像进行泥石流灾害区域的快速识别与评价，为泥石流灾害的预警预测研究带来新的思路。
- 泥石流 /
- 遥感影像 /
- 小样本学习 /
- 原型网络 /
- 易发性评价
Abstract: In response to the issues of inconsistent factor selection and limited training samples in debris flow factor-based evaluation methods, this study proposed a prototypical network-based approach for assessing the susceptibility of valley debris flow disasters. The method involves organizing the training data through meta-learning and calculating the prototype center for each valley type, serving as a representative of that category. Subsequently, the distance between the features of unknown samples and the prototype center of each class is computed to determine the probability of their classification. Based on the category probabilities, the debris flow susceptibility index of the valley is calculated to obtain the evaluation grade for debris flow susceptibility. The model was applied to evaluate the valleys in Nujiang Prefecture, and its results were compared with historical disaster data, yielding a classification accuracy rate of 67.39%. The evaluation levels provided by the model align well with the severity of debris flow disasters in historical events. Compared to traditional methods such as field surveys and factor evaluation, the method proposed in this paper allows for the rapid identification and evaluation of debris flow disaster areas using remote sensing imagery, presenting new insights for research on early warning and prediction of debris flow disasters.
- debris flow /
- remote sensing image /
- few-shot learning /
- prototype network /
- susceptibility assessment

HTML全文

图 1 怒江州地理位置和地形分布情况

Figure 1. Geographical location and topographical distribution of Nujiang Prefecture

下载: 全尺寸图片幻灯片

图 2 Google Earth遥感数据的提取与处理

Figure 2. Extraction and processing of Google Earth remote sensing data

下载: 全尺寸图片幻灯片

图 3 基于原型网络的沟谷泥石流易发性评价流程

Figure 3. Chartflow of susceptibility assessment of debris flow based on prototype networks

下载: 全尺寸图片幻灯片

图 4 原型网络及分类模型

Figure 4. Prototype network classification model

下载: 全尺寸图片幻灯片

图 5 怒江州泥石流易发性分区图

Figure 5. Susceptibility zoning map of debris flow in Nujiang Prefecture

下载: 全尺寸图片幻灯片

图 6 怒江州泥石流易发性分区中沟谷高程差、沟长、面积、坡降比的分布情况

Figure 6. Distribution of the valley elevation difference, valley length, area, and slope ratio in the debris flow susceptibility zone in Nujiang prefecture

下载: 全尺寸图片幻灯片

图 7 4条泥石流沟谷的地理位置、Google Earth遥感图像和泥石流堆积物情况

Figure 7. Geographical location, Google Earth remote sensing images and debris flow deposits in four debris flow valleys

下载: 全尺寸图片幻灯片

表 1 Google Earth遥感和DEM数据信息

Table 1. Information on Google Earth remote sensing and DEM data

数据信息	Google Earth	DEM
数据来源	Google Earth软件	地理空间数据云 http://www.gscloud.cn/home
数据类型	遥感图像	数字高程模型
空间分辨率	2～15 m 按照DEM采样为30 m	ASTER GDEM V2 垂直精度20m，水平精度30m
通道数	3	1
时相	泥石流沟谷/与发生时间后最近时间分辨率影像图像负样本及评测沟谷/最新遥感图像	2015年1月6日发布的ASTER GDEM V2版本

下载: 导出CSV

表 2 多个特征提取器的分类性能

Table 2. Classification performance of multiple feature extractors

特征提取器	6分类/%	2分类/%
VGG	55.43	59.78
GoogleNet	51.09	56.52
ShuffleNetV2	47.82	51.09
MobileNetV2	53.26	55.43
ResNet12	40.22	44.57
ResNet18	44.57	48.91
DenseNet	50.00	64.13
Rir	51.08	57.61
Conv4	58.70	67.39

下载: 导出CSV

表 3 6分类测试混淆矩阵

Table 3. Confusion matrix of six-classification

6分类混淆矩阵		预测值
6分类混淆矩阵		0	1	2	3	4	5
真实值	0	9	2	0	2	1	0
	1	0	10	1	0	2	6
	2	0	2	12	0	0	3
	3	2	2	0	9	0	0
	4	0	8	0	0	5	2
	5	0	0	4	0	1	9

下载: 导出CSV

表 4 正负2分类测试混淆矩阵

Table 4. Confusion matrix for positive and negative binary-classification test

2分类混淆矩阵		预测值
2分类混淆矩阵		正样本	负样本
真实值	正样本	36	14
真实值	负样本	16	26

下载: 导出CSV

表 5 2分类和6分类指标表

Table 5. Binary-classification and six-classification indicator table

Accuracy/%	Precision/%	Recall/%	F1 Score	Kappa
67.39	69.23	72.00	0.71	0.50

下载: 导出CSV

表 6 4条泥石流沟谷原型网络计算的所属概率和易发性指数

Table 6. Probability and susceptibility index of four debris flow valleys with prototype networks

沟谷流域	编号	所属概率$ {S}_{i} $						易发性指数$ {I}_{i} $
沟谷流域	编号	0	1	2	3	4	5	易发性指数$ {I}_{i} $
普拉底乡东月谷	A	0.000 4	0.966 3	0.002 7	0	0.014 5	0.016 2	0.966 3
普拉底乡咪谷河	B	0.000 7	0.999 3	0	0	0	0	0.999 3
独龙江乡巴坡村沟谷	C	0.863 4	0.105 7	0.006 2	0.001 9	0.009 4	0.013 3	0.863 4
金顶镇七联村练登大沟	D	0.315 3	0.504 2	0.002 4	0.060 3	0.113 9	0.003 9	0.504 2

下载: 导出CSV

表 7 4条泥石流沟谷因子分析方法计算的所属概率和易发性指数

Table 7. Probability and susceptibility index of four debris flow valleys with factor analysis methods

沟谷流域	编号	所属概率$ {S}_{i} $						易发性指数$ {I}_{i} $
沟谷流域	编号	0	1	2	3	4	5	易发性指数$ {I}_{i} $
普拉底乡东月谷	A	0	0.08	0.79	0	0.01	0.12	0.79
普拉底乡咪谷河	B	0.53	0	0.04	0.41	0.02	0	0.53
独龙江乡巴坡村沟谷	C	0.31	0	0	0.69	0	0	−0.69
金顶镇七联村练登大沟	D	0.68	0.02	0.04	0.11	0.13	0.02	0.68

下载: 导出CSV

表 8 4条泥石流沟谷的地貌条件和物质条件因子分析

Table 8. Factors analysis of geomorphological and material conditions of four debris flow valleys

地貌条件和物源条件	泥石流沟谷
地貌条件和物源条件	东月谷	咪谷河	巴坡村沟谷	练登大沟
主沟长度/km	16.52	14.70	2.45	10.30
面积/km²	45.90	47.22	1.10	16.26
高程差/m	2 854	2 548	1 244	1 386
坡降比	0.17	0.17	0.51	0.13
平均坡度/（°）	15.46	26.49	33.64	16.17
Melton指数	0.42	0.37	1.18	0.34
植被覆盖^[35]	有林地41.66% 灌木林10.42% 疏林地31.25% 中覆盖度草地16.67%	有林地55.55% 灌木林8.88% 疏林地15.52% 中覆盖度草地5.03% 低覆盖度草地15.02%	有林地50.00% 灌木林50.00%	疏林地47.06% 高覆盖度草地47.06% 其它建设用地5.88%
土壤性质^[36]	松软薄层土简育高活性淋溶土	松软薄层土简育高活性淋溶土	简育高活性强酸土简育高活性淋溶土	不饱和雏形土简育高活性淋溶土
地层岩性^[36]	花岗岩、板岩、千枚岩、片岩	花岗岩、板岩、千枚岩、片岩	花岗岩、石灰岩和其他碳酸盐岩	板岩、千枚岩、杂砂岩、长石砂岩、砂岩石灰岩和其他碳酸盐岩

下载: 导出CSV

参考文献(44)

[1]	唐邦兴,杜榕桓,康志成,等. 我国泥石流研究[J]. 地理学报,1980(3):259 − 264. [TANG Bangxing,DU Rongheng,KANG Zhicheng,et al. Study on debris flow in China[J]. Acta Geographica Sinica,1980(3):259 − 264. (in Chinese) TANG Bangxing, DU Rongheng, KANG Zhicheng, et al. Study on debris flow in China[J]. Acta Geographica Sinica, 1980（03）: 259-264. （in Chinese）
[2]	唐邦兴,柳素清,刘世建. 我国山地灾害的研究[J]. 山地研究,1984(1):1 − 7. [TANG Bangxing,LIU Suqing,LIU Shijian. Study on mount ain cal amities in CHINA[J]. Mountain Research,1984(1):1 − 7. (in Chinese with English abstract) TANG Bangxing, LIU Suqing, LIU Shijian. Study on mount ain cal amities in CHINA[J]. Mountain Research, 1984（01）: 1-7. （in Chinese with English abstract）
[3]	陈宁生, 杨成林, 李战鲁, 等. 汶川地震次生泥石流形成发展趋势与防治对策[C]//汶川大地震工程震害调查分析与研究, 2009: 315 − 321 CHEN Ningsheng, YANG Chenglin, LI Zhanlu, et al. Formation and development trend of debris flow induced by Wenchuan earthquake and countermeasures[C]//Analysis and Investigation on Seismic Damages of Projects Subjected to Wenchuan Earthquake, 2009: 315 − 321. （in Chinese）
[4]	陈宁生,谢万银,李战鲁. 中国西南山区的泥石流分区与预测[J]. 高原气象,2004(增刊 1):134 − 140. [CHEN Ningsheng,XIE Wangyin,LI Zhanlu. Division and prediction of debris flow in mountain area of south west China[J]. Plateau Meteorology,2004(Sup 1):134 − 140. (in Chinese with English abstract) CHEN Ningsheng, XIE Wangyin, LI Zhanlu. Division and prediction of debris flow in mountain area of south west China[J]. Plateau Meteorology, 2004（S1）: 134-140. （in Chinese with English abstract）
[5]	陈宁生,胡桂胜. 天山天池景区地质灾害防治与生态环境保护关键技术研究及应用[J]. 科技促进发展,2015(3):380 − 384. [CHEN Ningsheng,HU Guisheng. Research and application on Tianshan Tianchi scenic geological disaster prevention and environment protection key technology[J]. Science & Technology for Development,2015(3):380 − 384. (in Chinese with English abstract) CHEN Ningsheng, HU Guisheng. Research and application on Tianshan Tianchi scenic geological disaster prevention and environment protection key technology[J]. Science & Technology for Development, 2015（03）: 380-384. （in Chinese with English abstract）
[6]	崔鹏,陈晓清,程尊兰,等. 西藏泥石流滑坡监测与防治[J]. 自然杂志,2010,32(1):19 − 25. [CUI Peng,CHEN Xiaoqing,CHENG Zunlan,et al. Monitoring and prevention of debris-flows and landslides in Tibet[J]. Chinese Journal of Nature,2010,32(1):19 − 25. (in Chinese with English abstract) CUI Peng, CHEN Xiaoqing, CHENG Zunlan, et al. Monitoring and prevention of debris-flows and landslides in Tibet[J]. Chinese Journal of Nature, 2010, 32（01）: 19-25. （in Chinese with English abstract）
[7]	崔鹏,庄建琦,陈兴长,等. 汶川地震区震后泥石流活动特征与防治对策[J]. 四川大学学报(工程科学版),2010,42(5):10 − 19. [CUI Peng,ZHUANG Jianqi,CHEN Xingchang,et al. Characteristics and countermeasures of debris flow in Wenchuan area after the earthquake[J]. Advanced Engineering Sciences,2010,42(5):10 − 19. (in Chinese with English abstract) CUI Peng, ZHUANG Jianqi, CHEN Xingchang, et al. Characteristics and countermeasures of debris flow in Wenchuan area after the earthquake[J]. Advanced Engineering Sciences, 2010, 42（05）: 10-19. （in Chinese with English abstract）
[8]	崔鹏,杨坤,陈杰. 前期降雨对泥石流形成的贡献—以蒋家沟泥石流形成为例[J]. 中国水土保持科学,2003(1):11 − 15. [CUI Peng,YANG Kun,CHEN Jie. Relationship between occurrence of debris flow and antecedent precipitation:Taking the Jiangjia gully as an example[J]. Science of Soil and Water Conservation,2003(1):11 − 15. (in Chinese with English abstract) CUI Peng, YANG Kun, CHEN Jie. Relationship between occurrence of debris flow and antecedent precipitation: Taking the Jiangjia gully as an Example[J]. Science of Soil and Water Conservation, 2003（01）: 11-15. （in Chinese with English abstract）
[9]	李益敏,杨蕾,魏苏杭. 基于小流域单元的怒江州泥石流易发性评价[J]. 长江流域资源与环境,2019,28(10):2419 − 2428. [LI Yimin,YANG Lei,WEI Suhang. Susceptibility assessment of debris flow in Nujiang befecture based on the catchment[J]. Resources and Environment in The Yangtze Basin\| Resour Environ Yangtze Basin,2019,28(10):2419 − 2428. (in Chinese with English abstract) LI Yimin, YANG Lei, WEI Suhang. Susceptibility assessment of debris flow in Nujiang befecture based on the catchment[J]. Resources and Environment in The Yangtze Basin\| Resour Environ Yangtze Basin, 2019, 28（10）: 2419-2428. （in Chinese with English abstract）
[10]	孙滨,祝传兵,康晓波,等. 基于信息量模型的云南东川泥石流易发性评价[J]. 中国地质灾害与防治学报,2022,33(5):39 − 47. [SUN Bin,ZHU Chuanbing,KANG Xiaobo,et al. Susceptibility assessment of debris flows based on information model in Dongchuan,Yunnan Province[J]. The Chinese Journal of Geological Hazard and Control,2022,33(5):39 − 47. (in Chinese with English abstract) SUN Bin, ZHU Chuanbing, KANG Xiaobo, et al. Susceptibility assessment of debris flows based on information model in Dongchuan, Yunnan Province[J]. The Chinese Journal of Geological Hazard and Control, 2022, 33（5）: 39-47. （in Chinese with English abstract）
[11]	赵岩. 基于机器学习的白龙江流域潜在低频泥石流沟识别[D]. 兰州: 兰州大学, 2020 ZHAO yan. Machine learning based identification of potential low-frequency debris flow catchments in the Bailong River basin[D]. Lanzhou: Lanzhou University, 2020. （in Chinese with English abstract）
[12]	刘坤香,王保云,徐繁树,等. 基于残差注意力机制的泥石流沟谷识别[J]. 中国地质灾害与防治学报,2022,33(6):134 − 141. [LIU Kunxiang,WANG Baoyun,XU Fanshu,et al. Debris flow gully recognition based on residual attention mechanism[J]. The Chinese Journal of Geological Hazard and Control,2022,33(6):134 − 141. (in Chinese with English abstract) LIU Kun-xiang, WANG Bao-yun, XU Fan-shu, et al. Debris flow gully recognition based on residual attention mechanism[J]. The Chinese Journal of Geological Hazard and Control, 2022, 33（6）: 134-141. （in Chinese with English abstract）
[13]	杨小兵,王登贵. 基于多光谱影像和DEM的泥石流堆积扇识别研究—以白龙江流域武都段为例[J]. 测绘与空间地理信息,2016,39(4):118 − 121. [YANG Xiaobing,WANG Denggui. Debris flow fan recognition study based on multi-spectral image and DEM:Wudu segment of Bailong river basin as a case study[J]. Geomatics & Spatial Information Technology,2016,39(4):118 − 121. (in Chinese with English abstract) doi: 10.3969/j.issn.1672-5867.2016.04.032 YANG Xiao-bing, WANG Deng-gui. Debris flow fan recognition study based on multi-spectral image and DEM: Wudu segment of Bailong river basin as a case study[J]. Geomatics & Spatial Information Technology, 2016, 39（4）: 118-121. （in Chinese with English abstract） doi: 10.3969/j.issn.1672-5867.2016.04.032
[14]	茹颖. 基于标签传播与小样本学习的高光谱图像分类方法[D]. 西安: 西安电子科技大学, 2021 RU Ying. Hyperspectral image classification method based on label propagation and few shot learning[D]. Xi’an: Xidian University, 2021. （in Chinese with English abstract）
[15]	张萌月. 小样本光学遥感影像目标检测识别技术研究[D]. 北京: 中国电子科技集团公司电子科学研究院, 2021 ZHANG Mengyue. Research on few-shot detection and recognition in optical remote sensing image[D]. Beijing: China Academic of Electronics and Information Techn. , 2021. （in Chinese with English abstract）
[16]	SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[J]. Advances in neural information processing systems,2017,30:1 − 11.
[17]	HERSBACH H, BELL B, BERRISFORD P, et al. ERA5 monthly averaged data on single levels from 1979 to present[J]. Copernicus Climate Change Service (C3S) Climate Data Store (CDS),2019,10:252 − 266.
[18]	刘晓,郑家文,张照录,等. Google Earth在遥感地质教学中的应用[J]. 中国地质教育,2017,26(2):52 − 55. [LIU Xiao,ZHENG Jiawen,ZHANG Zhaolu,et al. Application of Google Earth software in remote sensing geology teaching[J]. Chinese Geological Education Chin Geol Edu,2017,26(2):52 − 55. (in Chinese with English abstract) LIU Xiao, ZHENG Jiawen, ZHANG Zhaolu, et al. Application of Google Earth software in remote sensing geology teaching[J]. Chinese Geological Education Chin Geol Edu, 2017, 26（02）: 52-55. （in Chinese with English abstract）
[19]	陈勤主编, 云南减灾年鉴[M]. 昆明: 云南出版集团云南科技出版社, 2018 CHEN qin. Yunnan yearbook for disaster reduction[M]. Kunming: Yunnan Science and Technology Press. 2018. （in Chinese with English abstract）
[20]	姚振国,刘建周,牛贝贝,等. 流域面积对沟道泥石流发育的影响分析[J]. 资源环境与工程,2019,33(2):217 − 219. [YAO Zhenguo,LIU Jianzhou,NIU Beibei,et al. Influence of drainage area on development of debris flow in gully[J]. Resources Environment & Engineering,2019,33(2):217 − 219. Yao Zhenguo, Liu Jianzhou, Niu Beibei, et al. Influence of drainage area on development of debris flow in gully[J]. Resources Environment & EngineerinYAO Zhenguo, LIU Jianzhou, NIU Beibei, et alith English abstract）
[21]	WANG Y, YAO Q, KWOK J T, et al. Generalizing from a few examples: A survey on few-shot learning[J]. ACM computing surveys (csur),2020,53(3):1 − 34.
[22]	SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science, 2014: 1-14.
[23]	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1 − 9.
[24]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770 − 778.
[25]	MA N, ZHANG X, ZHENG H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 116 − 131.
[26]	SANDLER M, HOWARD A, ZHU M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510 − 4520.
[27]	WERTHEIMER D, TANG L, HARIHARAN B. Few-shot classification with feature map reconstruction networks[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 8012 − 8021.
[28]	HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700 − 4708.
[29]	TARG S, ALMEIDA D, LYMAN K. Resnet in Resnet: Generalizing Residual Architectures［J］. 2016: 1 − 7.
[30]	MELTON M A. The geomorphic and paleoclimatic significance of alluvial deposits in southern Arizona[J]. Journal of Geology,1965,73(1):1 − 38. doi: 10.1086/627044
[31]	邹翔,崔鹏,韦方强,等. 灰色关联度法在泥石流活动性评价中的应用[J]. 山地学报,2003(3):360 − 364. [ZOU Xiang,CUI Peng,WEI Fangqiang,et al. Application of grey-correiation method to activity evaluation of debris flow[J]. Mountain Research,2003(3):360 − 364. (in Chinese with English abstract) ZOU Xiang, CUI Peng, WEI Fangqiang, et al. Application of grey-correiation method to activity evaluation of debris flow[J]. Mountain Research, 2003（03）: 360-364. （in Chinese with English abstract）
[32]	张书豪,吴光,张乔,等. 基于子流域特征的泥石流易发性评价[J]. 水文地质工程地质,2018,45(2):142 − 149. [ZHANG Shuhao,WU Guang,ZHANG Qiao,et al. Debris-flow susceptibility assessment using the characteristic factors of a catchment[J]. Hydrogeology & Engineering Geology,2018,45(2):142 − 149. (in Chinese with English abstract) ZHANG Shuhao, WU Guang, ZHANG Qiao, et al. Debris-flow susceptibility assessment using the characteristic factors of a catchment[J]. Hydrogeology & Engineering Geology, 2018, 45（02）: 142-149. （in Chinese with English abstract）
[33]	蒋德明,李益敏,鲍华姝. 泸水县滑坡孕灾环境因素敏感性研究[J]. 自然灾害学报,2016,25(4):109 − 119. [JIANG Deming,LI Yimin,BAO Huashu. Study on sensitivity in disaster-pregnant environmental factors of landslide in Lushui County[J]. Journal of Natural Disasters,2016,25(4):109 − 119. (in Chinese with English abstract) JIANG Deming, LI Yimin, BAO Huashu. Study on sensitivity in disaster-pregnant environmental factors of landslide in Lushui County[J]. Journal of Natural Disasters J Nat Disaster, 2016, 25（04）: 109-119. （in Chinese with English abstract）
[34]	唐川,马国超. 基于地貌单元的小区域地质灾害易发性分区方法研究[J]. 地理科学,2015,35(1):91 − 98. [TANG Chuan,MA Guochao. Small regional geohazards susceptibility mapping based on geomorphic unit[J]. Scientia Geographica Sinica,2015,35(1):91 − 98. (in Chinese with English abstract) TANG Chuan, MA Guochao. Small regional geohazards susceptibility mapping based on geomorphic unit[J]. Scientia Geographica Sinica, 2015, 35（01）: 91-98. （in Chinese with English abstract）
[35]	徐新良,刘纪远,张树文, 等,吴世新.中国多时期土地利用遥感监测数据集[EB/OL]. https://www.resdc.cn/DOI/DOI.aspx?DOIid=54 XU Xinliang, LIU Jiyuan, ZHANG Shuwen, et al. Remote sensing data set of multi-period land use monitoring in China[EB/OL]. https://www.resdc.cn/DOI/DOI.aspx?DOIid=54
[36]	DIJKSHOORN K, VAN ENGELEN V, HUTING J. Soil and landform properties for LADA partner countries[J]. ISRIC report,2008,6:1 − 28.
[37]	唐川. 云南怒江流域泥石流敏感性空间分析[J]. 地理研究,2005(2):178 − 185. [TANG Chuan. Susceptibility spatial analysis of debris flows in the Nujiang River basin of Yunnan[J]. Geographical Research,2005(2):178 − 185. (in Chinese with English abstract) TANG Chuan. Susceptibility spatial analysis of debris flows in the Nujiang River basin of Yunnan[J]. Geographical Research, 2005（02）: 178-185. （in Chinese with English abstract）
[38]	王欢,陈廷方,丁明涛. 泥石流对岩性的敏感性分析及其在危险性评价中的应用[J]. 长江流域资源与环境,2012,21(3):385 − 390. [WANG Huan,CHEN Tingfang,DING Mingtao. Sensitivity analysis to lithology and a pplication in risk assessment of debris flow[J]. Resources and Environment in The Yangtze Basin,2012,21(3):385 − 390. (in Chinese with English abstract) WANG Huan, CHEN Tingfang, DING Mingtao. Sensitivity analysis to lithology and a pplication in risk assessment of debris flow[J]. Resources and Environment in The Yangtze basin Resour Environ Yangtze Basin, 2012, 21（03）: 385-390. （in Chinese with English abstract）
[39]	张桥. 泥石流流域岩性坚硬系数与暴发频率的关系分析—以云南滇北地区泥石流为例[J]. 低碳世界,2016(27):107 − 108. [ZHANG Qiao. Analysis on the relationship between lithological hardness coefficient and outbreak frequency in debris flow watershed:A case study of debris flow in Yunnan and northern Yunnan[J]. Low-Carbon World,2016(27):107 − 108. (in Chinese) ZHANG Qiao. Analysis on the relationship between lithological hardness coefficient and outbreak frequency in debris flow watershed: A case study of debris flow in Yunnan and northern Yunnan[J]. Low-Carbon World, 2016（27）: 107-108. （in Chinese）
[40]	王猛,王宁,王军,等. 不同岩性区泥石流堆积物颗粒组成特征—以新疆塔什库尔干河中上游为例[J]. 四川地质学报,2018,38(4):680 − 684. [WANG Meng,WANG Ning,WANG Jun,et al. On particle composition characteristics of debris flow deposits in different lithologic regions:By the example of middle and upper reaches of the Taxkorgan River[J]. Acta Geologica Sichuan,2018,38(4):680 − 684. (in Chinese with English abstract) doi: 10.3969/j.issn.1006-0995.2018.04.032 WANG Meng, WANG Ning, WANG Jun, et al. On Particle Composition Characteristics of Debris Flow Deposits in Different Lithologic Regions ——By the Example of Middle and Upper Reaches of the Taxkorgan River[J]. Acta Geologica Sichuan, 2018, 38（04）: 680-684. （in Chinese with English abstract） doi: 10.3969/j.issn.1006-0995.2018.04.032
[41]	李松阳,林静远,潘佳虹,等. 泥石流频发区不同土地利用类型土壤粒径分布多重分形特征[J]. 应用与环境生物学报,2021,27(4):893 − 900. [LI Songyang,LIN Jingyuan,PAN Jiahong,et al. Multifractal characteristics of soil particle-size distribution under different land-use types in an area with high frequency debris flow[J]. Chinese Journal of Applied and Environmental Biology,2021,27(4):893 − 900. (in Chinese with English abstract) LI Songyang, LIN Jingyuan, PAN Jiahong, et al. Multifractal characteristics of soil particle-size distribution under different land-use types in an area with high frequency debris flow[J]. Chinese Journal of Applied and Environmental Biology, 2021, 27（04）: 893-900. （in Chinese with English abstract）
[42]	李松阳, 刘康妮, 余杭, 等. 云南省蒋家沟不同植被类型土壤物理性质对水分入渗特征的影响[J]. 山地学报, 2021, 39（6）: 867 − 878 LI Songyang, LIU Kangni, YU Hang, et al. The influence of soil physical properties on the infiltration of soil covered by different vegetation types in the Jiangjia gully Yunnan Province, China[J], Mountain Research, 2021, 39（6）: 867 − 878. （in Chinese with English abstract）
[43]	李鸿雁,原若溪,王小军,等. 吉林省泥石流易发区的降雨特征分析[J]. 自然资源学报,2016,31(7):1222 − 1230. [LI Hongyan,YUAN Ruoxi,WANG Xiaojun,et al. Rainfall characteristics in debris flow prone areas of Jilin Province[J]. Journal of Natural Resources,2016,31(7):1222 − 1230. (in Chinese with English abstract) LI Hongyan, YUAN Ruoxi, WANG Xiaojun, et al. Rainfall characteristics in debris flow prone areas of Jilin Province[J]. Journal of Natural Resources, 2016, 31（07）: 1222-1230. （in Chinese with English abstract）
[44]	周振华. 泥石流中的超孔隙水压力及其形成机理[D]. 昆明: 昆明理工大学, 2018 ZHOU Zhenhua. Excess pore pressure and its formation mechanism in debris flow[D]. Kunming: Kunming University of Science and Technology, 2018. （in Chinese with English abstract）