T. Bhuvaneswari, R. Chandra Guru Sekar, M. Chengathir Selvi, J. Jemima Rubavathi, V. Kaviyaa
{"title":"Robust Deep Learning for Accurate Landslide Identification and Prediction","authors":"T. Bhuvaneswari, R. Chandra Guru Sekar, M. Chengathir Selvi, J. Jemima Rubavathi, V. Kaviyaa","doi":"10.1134/s1028334x23602961","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Landslide is the most common natural risk in mountainous regions on all five continents and they can pose a serious threat in these areas. Strong earthquakes, unusual weather events such as storms and eruptions of volcanoes, and human-caused events such as creating roadways that crossed the slopes are the main causes of landslides and they cause significant dangers to residential properties and society as a whole. The Landslide4sense dataset is used for identifying landslides, which contains 3799 training samples and 245 testing samples. These image patches are taken from the Sentinel-2 sensor, while the slope and Digital Elevation Model (DEM) are from the ALOS PALSAR sensor. Data was gathered from four distinct geographical areas namely Kodagu, Iburi, Taiwan, and Gorkha. We use Deep Learning (DL) models such as ResNet18, U-Net, and VGG16 to predict the landslide. By comparing the above models with the evaluation metrics like loss, precision, recall, F1 score and accuracy, ResNet18 model is selected as the best model for landslide identification.</p>","PeriodicalId":11352,"journal":{"name":"Doklady Earth Sciences","volume":"20 1","pages":""},"PeriodicalIF":0.7000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Doklady Earth Sciences","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1134/s1028334x23602961","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Landslide is the most common natural risk in mountainous regions on all five continents and they can pose a serious threat in these areas. Strong earthquakes, unusual weather events such as storms and eruptions of volcanoes, and human-caused events such as creating roadways that crossed the slopes are the main causes of landslides and they cause significant dangers to residential properties and society as a whole. The Landslide4sense dataset is used for identifying landslides, which contains 3799 training samples and 245 testing samples. These image patches are taken from the Sentinel-2 sensor, while the slope and Digital Elevation Model (DEM) are from the ALOS PALSAR sensor. Data was gathered from four distinct geographical areas namely Kodagu, Iburi, Taiwan, and Gorkha. We use Deep Learning (DL) models such as ResNet18, U-Net, and VGG16 to predict the landslide. By comparing the above models with the evaluation metrics like loss, precision, recall, F1 score and accuracy, ResNet18 model is selected as the best model for landslide identification.
期刊介绍：
Doklady Earth Sciences is a journal that publishes new research in Earth science of great significance. Initially the journal was a forum of the Russian Academy of Science and published only best contributions from Russia. Now the journal welcomes submissions from any country in the English or Russian language. Every manuscript must be recommended by Russian or foreign members of the Russian Academy of Sciences.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
