The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery
The scientific outcomes of the 2022 Landslide4Sense (L4S) competition organized by the Institute of Advanced Research in Artificial Intelligence are presented here. The objective of the competition is to automatically detect landslides based on large-scale multiple sources of satellite imagery colle...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9944085/ |
| _version_ | 1811307079031324672 |
|---|---|
| author | Omid Ghorbanzadeh Yonghao Xu Hengwei Zhao Junjue Wang Yanfei Zhong Dong Zhao Qi Zang Shuang Wang Fahong Zhang Yilei Shi Xiao Xiang Zhu Lin Bai Weile Li Weihang Peng Pedram Ghamisi |
| author_facet | Omid Ghorbanzadeh Yonghao Xu Hengwei Zhao Junjue Wang Yanfei Zhong Dong Zhao Qi Zang Shuang Wang Fahong Zhang Yilei Shi Xiao Xiang Zhu Lin Bai Weile Li Weihang Peng Pedram Ghamisi |
| author_sort | Omid Ghorbanzadeh |
| collection | DOAJ |
| description | The scientific outcomes of the 2022 Landslide4Sense (L4S) competition organized by the Institute of Advanced Research in Artificial Intelligence are presented here. The objective of the competition is to automatically detect landslides based on large-scale multiple sources of satellite imagery collected globally. The 2022 L4S aims to foster interdisciplinary research on recent developments in deep learning (DL) models for the semantic segmentation task using satellite imagery. Over the past few years, DL-based models have achieved performance that meets expectations on image interpretation due to the development of convolutional neural networks. The main objective of this article is to present the details and the best-performing algorithms featured in this competition. The winning solutions are elaborated with state-of-the-art models, such as the Swin Transformer, SegFormer, and U-Net. Advanced machine learning techniques and strategies, such as hard example mining, self-training, and mix-up data augmentation, are also considered. Moreover, we describe the L4S benchmark dataset in order to facilitate further comparisons and report the results of the accuracy assessment online. The data are accessible on <italic>Future Development Leaderboard</italic> for future evaluation at <uri>https://www.iarai.ac.at/landslide4sense/challenge/</uri>, and researchers are invited to submit more prediction results, evaluate the accuracy of their methods, compare them with those of other users, and, ideally, improve the landslide detection results reported in this article. |
| first_indexed | 2024-04-13T08:57:06Z |
| format | Article |
| id | doaj.art-e36c52023a174ec5be325cd238ff473a |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-13T08:57:06Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-e36c52023a174ec5be325cd238ff473a2022-12-22T02:53:15ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01159927994210.1109/JSTARS.2022.32208459944085The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite ImageryOmid Ghorbanzadeh0https://orcid.org/0000-0002-9664-8770Yonghao Xu1https://orcid.org/0000-0002-6857-0152Hengwei Zhao2https://orcid.org/0000-0001-5878-5152Junjue Wang3https://orcid.org/0000-0002-9500-3399Yanfei Zhong4https://orcid.org/0000-0001-9446-5850Dong Zhao5https://orcid.org/0000-0001-9880-8822Qi Zang6Shuang Wang7https://orcid.org/0000-0003-4940-1211Fahong Zhang8https://orcid.org/0000-0003-0209-8841Yilei Shi9Xiao Xiang Zhu10https://orcid.org/0000-0001-5530-3613Lin Bai11Weile Li12Weihang Peng13https://orcid.org/0000-0002-9798-8750Pedram Ghamisi14https://orcid.org/0000-0003-1203-741XInstitute of Advanced Research in Artificial Intelligence, Vienna, AustriaInstitute of Advanced Research in Artificial Intelligence, Vienna, AustriaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaSchool of Artificial Intelligence, Xidian University, Xi'an, ChinaSchool of Artificial Intelligence, Xidian University, Xi'an, ChinaSchool of Artificial Intelligence, Xidian University, Xi'an, ChinaData Science in Earth Observation, Technical University of Munich, Munich, GermanyRemote Sensing Technology, Technical University of Munich, Munich, GermanyRemote Sensing Technology Institute, German Aerospace Center, Wessling, GermanyState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu, ChinaInstitute of Advanced Research in Artificial Intelligence, Vienna, AustriaThe scientific outcomes of the 2022 Landslide4Sense (L4S) competition organized by the Institute of Advanced Research in Artificial Intelligence are presented here. The objective of the competition is to automatically detect landslides based on large-scale multiple sources of satellite imagery collected globally. The 2022 L4S aims to foster interdisciplinary research on recent developments in deep learning (DL) models for the semantic segmentation task using satellite imagery. Over the past few years, DL-based models have achieved performance that meets expectations on image interpretation due to the development of convolutional neural networks. The main objective of this article is to present the details and the best-performing algorithms featured in this competition. The winning solutions are elaborated with state-of-the-art models, such as the Swin Transformer, SegFormer, and U-Net. Advanced machine learning techniques and strategies, such as hard example mining, self-training, and mix-up data augmentation, are also considered. Moreover, we describe the L4S benchmark dataset in order to facilitate further comparisons and report the results of the accuracy assessment online. The data are accessible on <italic>Future Development Leaderboard</italic> for future evaluation at <uri>https://www.iarai.ac.at/landslide4sense/challenge/</uri>, and researchers are invited to submit more prediction results, evaluate the accuracy of their methods, compare them with those of other users, and, ideally, improve the landslide detection results reported in this article.https://ieeexplore.ieee.org/document/9944085/Deep learning (DL)landslide detectionmultispectral imagerynatural hazardremote sensing (RS) |
| spellingShingle | Omid Ghorbanzadeh Yonghao Xu Hengwei Zhao Junjue Wang Yanfei Zhong Dong Zhao Qi Zang Shuang Wang Fahong Zhang Yilei Shi Xiao Xiang Zhu Lin Bai Weile Li Weihang Peng Pedram Ghamisi The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning (DL) landslide detection multispectral imagery natural hazard remote sensing (RS) |
| title | The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery |
| title_full | The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery |
| title_fullStr | The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery |
| title_full_unstemmed | The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery |
| title_short | The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection From Multisource Satellite Imagery |
| title_sort | outcome of the 2022 landslide4sense competition advanced landslide detection from multisource satellite imagery |
| topic | Deep learning (DL) landslide detection multispectral imagery natural hazard remote sensing (RS) |
| url | https://ieeexplore.ieee.org/document/9944085/ |
| work_keys_str_mv | AT omidghorbanzadeh theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT yonghaoxu theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT hengweizhao theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT junjuewang theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT yanfeizhong theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT dongzhao theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT qizang theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT shuangwang theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT fahongzhang theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT yileishi theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT xiaoxiangzhu theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT linbai theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT weileli theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT weihangpeng theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT pedramghamisi theoutcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT omidghorbanzadeh outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT yonghaoxu outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT hengweizhao outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT junjuewang outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT yanfeizhong outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT dongzhao outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT qizang outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT shuangwang outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT fahongzhang outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT yileishi outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT xiaoxiangzhu outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT linbai outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT weileli outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT weihangpeng outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery AT pedramghamisi outcomeofthe2022landslide4sensecompetitionadvancedlandslidedetectionfrommultisourcesatelliteimagery |