EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A multi-modal deep learning framework with GAN-based fusion for enhanced landslide detection

R Srivats, Deepika Roselind Johnson iD, G Logeswari, R Saimirra, Muskaan Siddiqui, Abhiram Sharma

PLOS One · 30.04.2026 · 21 (4) · e0347324

DOI: 10.1371/journal.pone.0347324 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 30.04.2026. Verfasst von R Srivats und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India. Hauptthemen laut MEDLINE: Deep Learning, Landslides, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proposed work presents a hybrid deep learning framework that integrates four pre-trained Convolutional Neural Networks that include VGG16, DenseNet201, ResNet50 and InceptionV3. The pre-trained CNNs are combined with a GAN-based adversarial refinement module for accurate landslide detection and segmentation. Unlike traditional single-CNN or ensemble models, the proposed model performs multi-backbone feature fusion to accurately capture global level terrain context and fine-grained spatial details. The GAN component sharpens boundaries and suppresses noisy predictions through discriminator-guided refinement. The proposed system generates GIS-ready probability maps with confidence layers. They are also optimized for low-latency inference, making it suitable for rapid post-disaster decision support. The proposed work is evaluated on three benchmark datasets - CAS Landslide (high-resolution GF-2/UAV imagery), MS2LandsNet (medium-resolution Sentinel-2) and GDCLD (coseismic landslides). The proposed framework achieves F1-scores of 97.24%, 93.70% and 94.75% across the three datasets. These results correspond to improvements of 1.4 to 2.9% over fusion baselines and 4–7% over single-CNN models such as VGG16, DenseNet201,ResNet50 andInceptionV3. The results highlight consistent IoU gains and improved boundary delineation. The cross-dataset experiments further demonstrate strong generalization across varying resolutions, terrain types and triggering mechanisms. To our knowledge, this is the first landslide segmentation study to combine multi-backbone feature fusion with adversarial mask refinement in an operational monitoring context. The results confirm that the proposed framework delivers high accuracy, scalability and deployment readiness making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLandslidesImage Processing, Computer-AssistedGenerative Adversarial NetworksConvolutional Neural NetworksAlgorithmsDetection Algorithms

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India.

ORCID-Profile: Deepika Roselind Johnson

Zitieren

APA

Srivats, R., Johnson, D. R., Logeswari, G., Saimirra, R., Siddiqui, M., & Sharma, A. (2026). A multi-modal deep learning framework with GAN-based fusion for enhanced landslide detection. PLOS One, 21(4), e0347324. https://doi.org/10.1371/journal.pone.0347324

Vancouver

Srivats R, Johnson DR, Logeswari G, Saimirra R, Siddiqui M, Sharma A. A multi-modal deep learning framework with GAN-based fusion for enhanced landslide detection. PLOS One. 2026;21(4):e0347324. doi:10.1371/journal.pone.0347324

BibTeX
@article{Srivats2026,
  author = {Srivats, R and Johnson, Deepika Roselind and Logeswari, G and Saimirra, R and Siddiqui, Muskaan and Sharma, Abhiram},
  title = {A multi-modal deep learning framework with GAN-based fusion for enhanced landslide detection},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0347324},
  doi = {10.1371/journal.pone.0347324}
}
Kostenlos starten →