MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms

The Loess Plateau, with its fragile ecological environment and frequent landslides, poses severe risks to both ecological safety and human life. Accurate and efficient landslide detection is essential for disaster prevention and sustainable regional development. This study proposes an enhanced targe...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yuan Liang, Zhe Chen, Zhengbo Yu, Zhong Wang, Qingyun Ji, Ziqiong He, Dongsheng Zhong, Zhongchang Sun, Huadong Guo
Format: Article
Langue:anglais
Publié: Taylor & Francis Group 2025-12-01
Collection:International Journal of Digital Earth
Sujets:
Accès en ligne:https://www.tandfonline.com/doi/10.1080/17538947.2025.2536666
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1839619470583136256
author Yuan Liang
Zhe Chen
Zhengbo Yu
Zhong Wang
Qingyun Ji
Ziqiong He
Dongsheng Zhong
Zhongchang Sun
Huadong Guo
author_facet Yuan Liang
Zhe Chen
Zhengbo Yu
Zhong Wang
Qingyun Ji
Ziqiong He
Dongsheng Zhong
Zhongchang Sun
Huadong Guo
author_sort Yuan Liang
collection DOAJ
description The Loess Plateau, with its fragile ecological environment and frequent landslides, poses severe risks to both ecological safety and human life. Accurate and efficient landslide detection is essential for disaster prevention and sustainable regional development. This study proposes an enhanced target detection architecture, MAH-YOLO, designed for the precise identification of eolian landslides in complex environments. The MAH-YOLO model integrates multi-attention mechanisms (Halo Attention and Global Attention) with a lightweight design (MobileNetv3) to timely optimise landslide detection with high precision. Performance evaluations against Faster-RCNN and YOLOv8n demonstrated substantial improvements in key metrics, including precision (95.68%), recall (80.13%), and mean average precision (mAP) at 88.25%. These metrics were 5.43, 6.01 percentage points, 10.88, 4.96 percentage points, and 5.04, 4.87 percentage points higher than Faster-RCNN and YOLOv8n, respectively. Additionally, MAH-YOLO, a low complexity model with only 3.35M parameters and 16.1G FLOPs was used, balancing efficiency and accuracy. The ablation experiments confirmed the effectiveness of both the multi-attention mechanism and lightweight design. The proposed MAH-YOLO architecture excels at capturing intricate textures and detailed features, offering reliable support for accurate landslide detection. Our work provides valuable insights for intelligent monitoring and early warning systems of geological disasters on the Loess Plateau.
format Article
id doaj-art-bcc4a3aee4994e21a565cc153ea4615e
institution Matheson Library
issn 1753-8947
1753-8955
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-bcc4a3aee4994e21a565cc153ea4615e2025-07-23T07:16:21ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-12-0118110.1080/17538947.2025.2536666MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanismsYuan Liang0Zhe Chen1Zhengbo Yu2Zhong Wang3Qingyun Ji4Ziqiong He5Dongsheng Zhong6Zhongchang Sun7Huadong Guo8School of Mathematical Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaSchool of Mathematical Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaSchool of Earth Science and Resources, China University of Geosciences (Beijing), Beijing, People’s Republic of ChinaCollege of Management Science, Chengdu University of Technology, Chengdu, People’s Republic of ChinaSchool of Mathematical Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Management Science, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Earth and Planetary Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaInternational Research Centre of Big Data for Sustainable Development Goals, Beijing, People’s Republic of ChinaInternational Research Centre of Big Data for Sustainable Development Goals, Beijing, People’s Republic of ChinaThe Loess Plateau, with its fragile ecological environment and frequent landslides, poses severe risks to both ecological safety and human life. Accurate and efficient landslide detection is essential for disaster prevention and sustainable regional development. This study proposes an enhanced target detection architecture, MAH-YOLO, designed for the precise identification of eolian landslides in complex environments. The MAH-YOLO model integrates multi-attention mechanisms (Halo Attention and Global Attention) with a lightweight design (MobileNetv3) to timely optimise landslide detection with high precision. Performance evaluations against Faster-RCNN and YOLOv8n demonstrated substantial improvements in key metrics, including precision (95.68%), recall (80.13%), and mean average precision (mAP) at 88.25%. These metrics were 5.43, 6.01 percentage points, 10.88, 4.96 percentage points, and 5.04, 4.87 percentage points higher than Faster-RCNN and YOLOv8n, respectively. Additionally, MAH-YOLO, a low complexity model with only 3.35M parameters and 16.1G FLOPs was used, balancing efficiency and accuracy. The ablation experiments confirmed the effectiveness of both the multi-attention mechanism and lightweight design. The proposed MAH-YOLO architecture excels at capturing intricate textures and detailed features, offering reliable support for accurate landslide detection. Our work provides valuable insights for intelligent monitoring and early warning systems of geological disasters on the Loess Plateau.https://www.tandfonline.com/doi/10.1080/17538947.2025.2536666MAH-YOLOloess landslide detectionmulti-attention mechanismYOLOv8lightweight models
spellingShingle Yuan Liang
Zhe Chen
Zhengbo Yu
Zhong Wang
Qingyun Ji
Ziqiong He
Dongsheng Zhong
Zhongchang Sun
Huadong Guo
MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms
International Journal of Digital Earth
MAH-YOLO
loess landslide detection
multi-attention mechanism
YOLOv8
lightweight models
title MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms
title_full MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms
title_fullStr MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms
title_full_unstemmed MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms
title_short MAH-YOLO: an enhanced YOLOv8n framework for loess landslide detection with multi-attention mechanisms
title_sort mah yolo an enhanced yolov8n framework for loess landslide detection with multi attention mechanisms
topic MAH-YOLO
loess landslide detection
multi-attention mechanism
YOLOv8
lightweight models
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2536666
work_keys_str_mv AT yuanliang mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT zhechen mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT zhengboyu mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT zhongwang mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT qingyunji mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT ziqionghe mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT dongshengzhong mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT zhongchangsun mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms
AT huadongguo mahyoloanenhancedyolov8nframeworkforloesslandslidedetectionwithmultiattentionmechanisms