Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data
Using data sourced from 15 periglacial debris flow gullies in the Parlung Zangbo Basin of southeast Tibet, the importance of 26 potential indicators to the development of debris flows was analyzed quantitatively. Three machine learning approaches combined with the borderline resampling technique wer...
Published in: | Water |
---|---|
Main Authors: | , , , , |
Format: | Report |
Language: | English |
Published: |
MDPI
2023
|
Subjects: | |
Online Access: | http://ir.imde.ac.cn/handle/131551/57139 https://doi.org/10.3390/w15020310 |
id |
ftchinacadscimhe:oai:ir.imde.ac.cn:131551/57139 |
---|---|
record_format |
openpolar |
spelling |
ftchinacadscimhe:oai:ir.imde.ac.cn:131551/57139 2023-05-15T17:57:53+02:00 Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data Du, Jun Zhang, Hong-ya Hu, Kai-heng Wang, Lin Dong, Lin-yao 2023 http://ir.imde.ac.cn/handle/131551/57139 https://doi.org/10.3390/w15020310 英语 eng MDPI WATER http://ir.imde.ac.cn/handle/131551/57139 doi:10.3390/w15020310 periglacial debris flow southeast Tibet small sample imbalanced data prediction model random forest RAINFALL INTENSITY MODEL SVM CLASSIFICATION PERMAFROST INITIATION LANDSLIDE PLATEAU SMOTE Environmental Sciences & Ecology Water Resources Environmental Sciences 期刊论文 2023 ftchinacadscimhe https://doi.org/10.3390/w15020310 2023-03-03T01:14:39Z Using data sourced from 15 periglacial debris flow gullies in the Parlung Zangbo Basin of southeast Tibet, the importance of 26 potential indicators to the development of debris flows was analyzed quantitatively. Three machine learning approaches combined with the borderline resampling technique were introduced for predicting debris flow occurrences, and several scenarios were tested and compared. The results indicated that temperature and precipitation, as well as vegetation coverage, were closely related to the development of periglacial debris flow in the study area. Based on seven selected indicators, the Random Forest-based model, with its weighted recall rate and Area Under the ROC Curve (AUC) greater than 0.76 and 0.77, respectively, performed the best in predicting debris flow events. Scenario tests indicated that the resampling was necessary to the improvement of model performance in the context of data scarcity. The new understandings obtained may enrich existing knowledge of the effects of main factors on periglacial debris flow development, and the modeling method could be promoted as a prediction scheme of regional precipitation-related debris flow for further research. Report permafrost IMHE OpenIR (Institute of Mountain Hazards and Environment, Chinese Academy of Sciences) Water 15 2 310 |
institution |
Open Polar |
collection |
IMHE OpenIR (Institute of Mountain Hazards and Environment, Chinese Academy of Sciences) |
op_collection_id |
ftchinacadscimhe |
language |
English |
topic |
periglacial debris flow southeast Tibet small sample imbalanced data prediction model random forest RAINFALL INTENSITY MODEL SVM CLASSIFICATION PERMAFROST INITIATION LANDSLIDE PLATEAU SMOTE Environmental Sciences & Ecology Water Resources Environmental Sciences |
spellingShingle |
periglacial debris flow southeast Tibet small sample imbalanced data prediction model random forest RAINFALL INTENSITY MODEL SVM CLASSIFICATION PERMAFROST INITIATION LANDSLIDE PLATEAU SMOTE Environmental Sciences & Ecology Water Resources Environmental Sciences Du, Jun Zhang, Hong-ya Hu, Kai-heng Wang, Lin Dong, Lin-yao Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data |
topic_facet |
periglacial debris flow southeast Tibet small sample imbalanced data prediction model random forest RAINFALL INTENSITY MODEL SVM CLASSIFICATION PERMAFROST INITIATION LANDSLIDE PLATEAU SMOTE Environmental Sciences & Ecology Water Resources Environmental Sciences |
description |
Using data sourced from 15 periglacial debris flow gullies in the Parlung Zangbo Basin of southeast Tibet, the importance of 26 potential indicators to the development of debris flows was analyzed quantitatively. Three machine learning approaches combined with the borderline resampling technique were introduced for predicting debris flow occurrences, and several scenarios were tested and compared. The results indicated that temperature and precipitation, as well as vegetation coverage, were closely related to the development of periglacial debris flow in the study area. Based on seven selected indicators, the Random Forest-based model, with its weighted recall rate and Area Under the ROC Curve (AUC) greater than 0.76 and 0.77, respectively, performed the best in predicting debris flow events. Scenario tests indicated that the resampling was necessary to the improvement of model performance in the context of data scarcity. The new understandings obtained may enrich existing knowledge of the effects of main factors on periglacial debris flow development, and the modeling method could be promoted as a prediction scheme of regional precipitation-related debris flow for further research. |
format |
Report |
author |
Du, Jun Zhang, Hong-ya Hu, Kai-heng Wang, Lin Dong, Lin-yao |
author_facet |
Du, Jun Zhang, Hong-ya Hu, Kai-heng Wang, Lin Dong, Lin-yao |
author_sort |
Du, Jun |
title |
Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data |
title_short |
Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data |
title_full |
Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data |
title_fullStr |
Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data |
title_full_unstemmed |
Prediction of the Periglacial Debris Flow in Southeast Tibet Based on Imbalanced Small Sample Data |
title_sort |
prediction of the periglacial debris flow in southeast tibet based on imbalanced small sample data |
publisher |
MDPI |
publishDate |
2023 |
url |
http://ir.imde.ac.cn/handle/131551/57139 https://doi.org/10.3390/w15020310 |
genre |
permafrost |
genre_facet |
permafrost |
op_relation |
WATER http://ir.imde.ac.cn/handle/131551/57139 doi:10.3390/w15020310 |
op_doi |
https://doi.org/10.3390/w15020310 |
container_title |
Water |
container_volume |
15 |
container_issue |
2 |
container_start_page |
310 |
_version_ |
1766166390985719808 |