LEViM-Net: A Lightweight EfficientViM Network for Earthquake Building Damage Assessment.
Saved in:
| Title: | LEViM-Net: A Lightweight EfficientViM Network for Earthquake Building Damage Assessment. |
|---|---|
| Authors: | Ma, Qing1,2 (AUTHOR) maqing24@mails.jlu.edu.cn, Wu, Dongpu1,2 (AUTHOR), Zhang, Yichen1,3 (AUTHOR), Zhang, Jiquan1,3 (AUTHOR), Xu, Jinyuan1,2 (AUTHOR), Yao, Yechi1,3 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 10, p1592. 25p. |
| Subjects: | State-space methods, Deep learning, Remote sensing, Earthquake hazard analysis, Building protection, Disaster relief, Artificial neural networks |
| Abstract: | Highlights: What are the main findings? LEViM-Net, a lightweight state-space-based encoder–decoder network, effectively integrates EfficientViM and the HSM-SSD module to capture long-range dependencies and multi-scale damage features, achieving a favorable balance between recognition accuracy and computational efficiency. LEViM-Net performs exceptionally well on four earthquake events in the BRIGHT dataset, demonstrating strong cross-event generalization capabilities. What are the implications of the main findings? State-space modeling provides an effective paradigm for unifying global context modeling and computational efficiency. This framework has the potential to facilitate rapid post-earthquake assessments and the deployment of practical emergency response measures. Building damage and collapse are the main sources of serious casualties and financial losses during earthquakes, which are among the most destructive natural disasters that endanger human life and property. Therefore, quick and precise post-earthquake building damage assessment is essential for risk assessment and emergency action. Convolutional neural networks (CNNs) primarily concentrate on local features and frequently ignore global contextual information within and across buildings, despite the fact that deep learning-based techniques allow automated damage identification. Transformer-based approaches, on the other hand, are good at capturing global dependencies, but their large memory and processing costs restrict their usefulness. As a result, existing networks still struggle to achieve an effective balance between accuracy and efficiency. To address this issue, this study proposes a lightweight and efficient network for post-earthquake building damage assessment. Specifically, we develop a two-stage method based on EfficientViM with an encoder–decoder architecture. In the encoder, Mamba is introduced to extract multi-scale change features with long-range dependencies, leveraging the state space model to preserve global modeling capability while significantly reducing computational complexity. In the decoder, two lightweight modules are designed to further enhance discriminative capability and computational efficiency. The network finally outputs building localization and pixel-level building damage, respectively. Experiments were conducted on four earthquake events from the BRIGHT dataset using a three-for-training and one-for-testing cross-event rotation evaluation strategy. The results demonstrate that LEViM-Net requires only 30.94 M parameters and 27.10 G FLOPs. In addition, for the Türkiye earthquake event, the proposed method achieves an F1 score of 80.49%, an overall accuracy (OA) of 88.17%, and a mean intersection over union (mIoU) of 49.73%. The proposed model enables efficient remote-sensing-based mapping of macroscopic and image-visible building damage, providing timely support for early-stage emergency response. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? LEViM-Net, a lightweight state-space-based encoder–decoder network, effectively integrates EfficientViM and the HSM-SSD module to capture long-range dependencies and multi-scale damage features, achieving a favorable balance between recognition accuracy and computational efficiency. LEViM-Net performs exceptionally well on four earthquake events in the BRIGHT dataset, demonstrating strong cross-event generalization capabilities. What are the implications of the main findings? State-space modeling provides an effective paradigm for unifying global context modeling and computational efficiency. This framework has the potential to facilitate rapid post-earthquake assessments and the deployment of practical emergency response measures. Building damage and collapse are the main sources of serious casualties and financial losses during earthquakes, which are among the most destructive natural disasters that endanger human life and property. Therefore, quick and precise post-earthquake building damage assessment is essential for risk assessment and emergency action. Convolutional neural networks (CNNs) primarily concentrate on local features and frequently ignore global contextual information within and across buildings, despite the fact that deep learning-based techniques allow automated damage identification. Transformer-based approaches, on the other hand, are good at capturing global dependencies, but their large memory and processing costs restrict their usefulness. As a result, existing networks still struggle to achieve an effective balance between accuracy and efficiency. To address this issue, this study proposes a lightweight and efficient network for post-earthquake building damage assessment. Specifically, we develop a two-stage method based on EfficientViM with an encoder–decoder architecture. In the encoder, Mamba is introduced to extract multi-scale change features with long-range dependencies, leveraging the state space model to preserve global modeling capability while significantly reducing computational complexity. In the decoder, two lightweight modules are designed to further enhance discriminative capability and computational efficiency. The network finally outputs building localization and pixel-level building damage, respectively. Experiments were conducted on four earthquake events from the BRIGHT dataset using a three-for-training and one-for-testing cross-event rotation evaluation strategy. The results demonstrate that LEViM-Net requires only 30.94 M parameters and 27.10 G FLOPs. In addition, for the Türkiye earthquake event, the proposed method achieves an F1 score of 80.49%, an overall accuracy (OA) of 88.17%, and a mean intersection over union (mIoU) of 49.73%. The proposed model enables efficient remote-sensing-based mapping of macroscopic and image-visible building damage, providing timely support for early-stage emergency response. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18101592 |
