A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data

Abstract Landslides are frequent all over the world, posing serious threats to human life, infrastructure, and economic operations, making them chronic disasters. This study proposes a novel landslide detection methodology that is automated and based on a hybrid deep learning approach. Currently, De...

Full description

Saved in:
Bibliographic Details
Main Authors: Arush Kaushal, Ashok Kumar Gupta, Vivek Kumar Sehgal
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-79266-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850169186445164544
author Arush Kaushal
Ashok Kumar Gupta
Vivek Kumar Sehgal
author_facet Arush Kaushal
Ashok Kumar Gupta
Vivek Kumar Sehgal
author_sort Arush Kaushal
collection DOAJ
description Abstract Landslides are frequent all over the world, posing serious threats to human life, infrastructure, and economic operations, making them chronic disasters. This study proposes a novel landslide detection methodology that is automated and based on a hybrid deep learning approach. Currently, Deep Learning is constrained by the lack of applicability, lack of data, and low efficiency in landslide detection but with recent advancement in deep learning-based solutions for landslide detection has sparked considerable advantages over traditional techniques. In order to prevent and mitigate disaster, we introduced a hybrid model based on remote sensing technologies such as satellite images. Specifically, the proposed approach consists hybrid U-Net model integrated with a pyramid pooling layer for landslide detection, which uses high-resolution landslide images from the Landslide4Sense dataset. The UNet-Pyramid model has the following modifications: To improve feature acquisition and advancements to strengthen the model’s attention U-Net architecture is integrated with the pyramid pooling layers and OBIA technique. The UNet-Pyramid model was trained and validated using labeled images taken from the Landslide4Sense dataset and the validated set using OBIA to improve its efficacy. The overall Precision, Recall, and F1 Score of the UNet-pyramid model for landslide detection are 91%, 84%, and 87%, respectively.
format Article
id doaj-art-1e35eb781dbb4ed680915e9bf798e76e
institution OA Journals
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1e35eb781dbb4ed680915e9bf798e76e2025-08-20T02:20:48ZengNature PortfolioScientific Reports2045-23222024-12-0114112310.1038/s41598-024-79266-6A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing dataArush Kaushal0Ashok Kumar Gupta1Vivek Kumar Sehgal2Jaypee University of Information Technology, Computer ScienceJaypee University of Information Technology, Civil EngineeringJaypee University of Information Technology, Computer ScienceAbstract Landslides are frequent all over the world, posing serious threats to human life, infrastructure, and economic operations, making them chronic disasters. This study proposes a novel landslide detection methodology that is automated and based on a hybrid deep learning approach. Currently, Deep Learning is constrained by the lack of applicability, lack of data, and low efficiency in landslide detection but with recent advancement in deep learning-based solutions for landslide detection has sparked considerable advantages over traditional techniques. In order to prevent and mitigate disaster, we introduced a hybrid model based on remote sensing technologies such as satellite images. Specifically, the proposed approach consists hybrid U-Net model integrated with a pyramid pooling layer for landslide detection, which uses high-resolution landslide images from the Landslide4Sense dataset. The UNet-Pyramid model has the following modifications: To improve feature acquisition and advancements to strengthen the model’s attention U-Net architecture is integrated with the pyramid pooling layers and OBIA technique. The UNet-Pyramid model was trained and validated using labeled images taken from the Landslide4Sense dataset and the validated set using OBIA to improve its efficacy. The overall Precision, Recall, and F1 Score of the UNet-pyramid model for landslide detection are 91%, 84%, and 87%, respectively.https://doi.org/10.1038/s41598-024-79266-6LandslideDeep Neural Network (DNN)Hybrid ModelLandslide PredictionMachine Learning
spellingShingle Arush Kaushal
Ashok Kumar Gupta
Vivek Kumar Sehgal
A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data
Scientific Reports
Landslide
Deep Neural Network (DNN)
Hybrid Model
Landslide Prediction
Machine Learning
title A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data
title_full A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data
title_fullStr A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data
title_full_unstemmed A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data
title_short A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data
title_sort semantic segmentation framework with unet pyramid for landslide prediction using remote sensing data
topic Landslide
Deep Neural Network (DNN)
Hybrid Model
Landslide Prediction
Machine Learning
url https://doi.org/10.1038/s41598-024-79266-6
work_keys_str_mv AT arushkaushal asemanticsegmentationframeworkwithunetpyramidforlandslidepredictionusingremotesensingdata
AT ashokkumargupta asemanticsegmentationframeworkwithunetpyramidforlandslidepredictionusingremotesensingdata
AT vivekkumarsehgal asemanticsegmentationframeworkwithunetpyramidforlandslidepredictionusingremotesensingdata
AT arushkaushal semanticsegmentationframeworkwithunetpyramidforlandslidepredictionusingremotesensingdata
AT ashokkumargupta semanticsegmentationframeworkwithunetpyramidforlandslidepredictionusingremotesensingdata
AT vivekkumarsehgal semanticsegmentationframeworkwithunetpyramidforlandslidepredictionusingremotesensingdata