September 10, 2025Remote SensingOpen Access

Rapid Detection and Segmentation of Landslide Hazards in Loess Tableland Areas Using Deep Learning: A Case Study of the 2023 Jishishan Ms 6.2 Earthquake in Gansu, China

View Full Paper

Ask AI

Bookmark

The enhanced deep learning algorithm detected 417 landslides with 94.1% recognition accuracy.
The model achieved mAP50(M) = 0.747 within a 500-epoch training strategy, emphasizing its improved capabilities.
Utilized 20 km2 of high-precision UAV imagery post-earthquake, supporting rapid and accurate analysis.
Spatial analysis revealed high-density clustering and diverse configurations, highlighting loess landslide characteristics.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

This study demonstrates enhanced deep learning improved landslide detection and segmentation, suggesting effective methods for managing loess tableland hazards.

Cite This Study

Bai et al. (2025) studied this question.

synapsesocial.com/papers/68c2404eb210217d6479a3bb https://doi.org/10.3390/rs17152667

View Full Paper

Ask AI

Bookmark

Implication

This study demonstrates enhanced deep learning improved landslide detection and segmentation, suggesting effective methods for managing loess tableland hazards.

Rapid Detection and Segmentation of Landslide Hazards in Loess Tableland Areas Using Deep Learning: A Case Study of the 2023 Jishishan Ms 6.2 Earthquake in Gansu, China

Key Points

Discussion

Implication

Cite This Study

Rapid Detection and Segmentation of Landslide Hazards in Loess Tableland Areas Using Deep Learning: A Case Study of the 2023 Jishishan Ms 6.2 Earthquake in Gansu, China

Key Points

Discussion

Implication

Cite This Study

Keep reading

Keep reading