EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MAD-SAR: A Multi-Agent Agentic Engineering Framework for Landslide Detection Using Sentinel-1 SAR Imagery

Kohei Arai

Information · 15.06.2026 · 17 (6) · 597

DOI: 10.3390/info17060597 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 15.06.2026. Verfasst von Kohei Arai. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid and accurate detection of landslide-affected areas is critical for disaster response and risk mitigation. Sentinel-1 SAR imagery offers all-weather, day-and-night observation capability, but existing deep learning approaches treat landslide detection as a single-pass segmentation problem, which limits performance in complex terrain where backscatter changes are confounded by soil moisture, surface roughness, urban double bounce, shadow, and layover effects. MAD-SAR, a rule-based agentic framework that coordinates anomaly detection, super-resolution, object detection, and semantic segmentation under a planning orchestrator and a physics-aware validation engine is proposed. The orchestrator selects specialist modules, their execution order, and the number of refinement iterations according to a scene complexity score computed from SAR-derived statistics. The physics-aware validation engine cross-checks every candidate detection against backscatter change thresholds, DEM-derived slope constraints, and radar geometry masks before any detection is committed to the output. MAD-SAR is evaluated on three Japanese disaster datasets: Hiroshima 2018, Kumamoto 2016, and Ibaraki 2019. On the held-out Ibaraki test event, the framework achieves an F1-score of 0.863 and IoU of 0.759, outperforming all baselines and reducing false alarms by 45% relative to standalone SegFormer. Ablation results confirm that each module contributes to the final performance. These results suggest that multi-module orchestration with embedded physical validation can meaningfully improve SAR-based landslide mapping, though broader validation across regions, sensor configurations, and failure mechanisms remains necessary.

Zitieren

APA

Arai, K. (2026). MAD-SAR: A Multi-Agent Agentic Engineering Framework for Landslide Detection Using Sentinel-1 SAR Imagery. Information, 17(6), 597. https://doi.org/10.3390/info17060597

Vancouver

Arai K. MAD-SAR: A Multi-Agent Agentic Engineering Framework for Landslide Detection Using Sentinel-1 SAR Imagery. Information. 2026;17(6):597. doi:10.3390/info17060597

BibTeX
@article{Arai2026,
  author = {Arai, Kohei},
  title = {MAD-SAR: A Multi-Agent Agentic Engineering Framework for Landslide Detection Using Sentinel-1 SAR Imagery},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {6},
  pages = {597},
  doi = {10.3390/info17060597}
}
Kostenlos starten →