Qiongqiong Lan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Qiongqiong Lan has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Binbin Zhao
State Grid Electric Power Engineering Research Institute Co., Ltd., Beijing 100031, China
1 shared publication - Chong Xu
National Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing, China
1 shared publication - Hao Yuan
The College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
1 shared publication - Hengqian Zhao
The College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
1 shared publication - Jielin Liu
National Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing 100085, China
1 shared publication - Jinming Li
The College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (21) , 3856
MFM-TransUNet: Multi-Scale Feature Modeling Network for Remote Sensing-Based Surface Water Extraction
Accurate extraction of surface water is of great significance for water resource management, ecological conservation, and flood disaster monitoring. However, water bodies in high-resolution remote sensing imagery are often obscured by building shadows, vegetation, complex backgrounds, or spectral confusion. Consequently, traditional semantic segmentation methods frequently struggle with global feature modeling and the preservation of boundary details. To address these challenges, this paper proposes MFM-TransUNet, a remote sensing water extraction network based on multi-scale feature modeling. The network employs an encoder–feature modeling–decoder architecture. A Ghost-SE encoder is utilized to extract multi-scale hierarchical features, while a High-Performance Sequence Modeling Module (HPSM) is introduced to aggregate local contextual information from high-level features through depthwise 1D convolutions, with a feed-forward network enhancing nonlinear feature representations along the channel dimension. During the decoding phase, a learnable weight-fusion strategy is applied to balance the contributions of features from different levels, and an Edge-enhanced Feature Attention (EFA) is incorporated to strengthen boundary-related information within the decoded features. The proposed method was evaluated in terms of segmentation accuracy, module ablation, and cross-dataset performance. Experiments on the GID dataset demonstrate that MFM-TransUNet achieves an Overall Accuracy (OA) of 96.27%, a Mean Intersection over Union (Mean IoU) of 89.24%, an F1-Score of 94.20%, and a Boundary IoU of 63.52%, showing competitive performance compared with several mainstream baseline models. Ablation studies evaluate the contributions of the key modules, while experiments on the LJ-Water and Water-CD datasets assess the model’s performance across different datasets. These results suggest that MFM-TransUNet achieves a favorable trade-off between segmentation accuracy, boundary-related performance, and computational cost, providing a potential approach for surface water extraction in complex remote sensing scenarios.
- 9 November 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (21) , 3856
Open AccessMFM-TransUNet: Multi-Scale Feature Modeling Network for Remote Sensing-Based Surface Water Extraction
Accurate extraction of surface water is of great significance for water resource management, ecological conservation, and flood disaster monitoring. However, water bodies in high-resolution remote sensing imagery are often obscured by building shadows, vegetation, complex backgrounds, or spectral confusion. Consequently, traditional semantic segmentation methods frequently struggle with global feature modeling and the preservation of boundary details. To address these challenges, this paper proposes MFM-TransUNet, a remote sensing water extraction network based on multi-scale feature modeling. The network employs an encoder–feature modeling–decoder architecture. A Ghost-SE encoder is utilized to extract multi-scale hierarchical features, while a High-Performance Sequence Modeling Module (HPSM) is introduced to aggregate local contextual information from high-level features through depthwise 1D convolutions, with a feed-forward network enhancing nonlinear feature representations along the channel dimension. During the decoding phase, a learnable weight-fusion strategy is applied to balance the contributions of features from different levels, and an Edge-enhanced Feature Attention (EFA) is incorporated to strengthen boundary-related information within the decoded features. The proposed method was evaluated in terms of segmentation accuracy, module ablation, and cross-dataset performance. Experiments on the GID dataset demonstrate that MFM-TransUNet achieves an Overall Accuracy (OA) of 96.27%, a Mean Intersection over Union (Mean IoU) of 89.24%, an F1-Score of 94.20%, and a Boundary IoU of 63.52%, showing competitive performance compared with several mainstream baseline models. Ablation studies evaluate the contributions of the key modules, while experiments on the LJ-Water and Water-CD datasets assess the model’s performance across different datasets. These results suggest that MFM-TransUNet achieves a favorable trade-off between segmentation accuracy, boundary-related performance, and computational cost, providing a potential approach for surface water extraction in complex remote sensing scenarios.
- Open Access
- 5 January 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (1) , 156
Deformation Slope Extraction and Influencing Factor Analysis Using LT-1 Satellite Data: A Case Study of Chongqing and Surrounding Areas, China
The use of satellite imagery for surface deformation monitoring has been steadily increasing. However, the study of extracting deformation slopes from deformation data requires further advancement. This limitation not only poses challenges for subsequent studies but also restricts the potential for deeper exploration and utilization of deformation data. The LT-1 satellite, China’s largest L-band synthetic aperture radar satellite, offers a new perspective for monitoring. In this study, we extracted deformation slopes in Chongqing and its surrounding areas of China based on deformation data generated by LT-1. Twelve factors were selected to analyze their influence on slope deformation, including elevation, topographic position, slope, landcover, soil, lithology, relief, average rainfall intensity, and distances to rivers, roads, railways, and active faults. A total of 5863 deformation slopes were identified, covering an area of 140 km2, mainly concentrated in the central part of the study area, with the highest area density reaching 0.22%. Among these factors, average rainfall intensity was found to have the greatest impact on deformation slope. These findings provide valuable information for geological disaster early warning and management in Chongqing and surrounding areas, while also demonstrating the practical value of the LT-1 satellite in deformation monitoring.
- 5 January 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (1) , 156
Open AccessDeformation Slope Extraction and Influencing Factor Analysis Using LT-1 Satellite Data: A Case Study of Chongqing and Surrounding Areas, China
The use of satellite imagery for surface deformation monitoring has been steadily increasing. However, the study of extracting deformation slopes from deformation data requires further advancement. This limitation not only poses challenges for subsequent studies but also restricts the potential for deeper exploration and utilization of deformation data. The LT-1 satellite, China’s largest L-band synthetic aperture radar satellite, offers a new perspective for monitoring. In this study, we extracted deformation slopes in Chongqing and its surrounding areas of China based on deformation data generated by LT-1. Twelve factors were selected to analyze their influence on slope deformation, including elevation, topographic position, slope, landcover, soil, lithology, relief, average rainfall intensity, and distances to rivers, roads, railways, and active faults. A total of 5863 deformation slopes were identified, covering an area of 140 km2, mainly concentrated in the central part of the study area, with the highest area density reaching 0.22%. Among these factors, average rainfall intensity was found to have the greatest impact on deformation slope. These findings provide valuable information for geological disaster early warning and management in Chongqing and surrounding areas, while also demonstrating the practical value of the LT-1 satellite in deformation monitoring.