EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Independent Multi-Sensor Validation of Machine-Learning Landslide Susceptibility: Footprint Construction Decides the Verdict—May 2023 Emilia-Romagna Event

Lucian Necula, Liviu Porumb, Andreea Florina Jocea, Dan Raducanu

Remote Sensing · 10.07.2026 · 18 (14) · 2318

DOI: 10.3390/rs18142318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.07.2026. Verfasst von Lucian Necula und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Research, Innovation and Digiti-zation, CCCDI – UEFISCDI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine-learning landslide-susceptibility maps are almost always judged by inventory-split skill (the area under the receiver-operating-characteristic curve, AUC, and Cohen’s κ), not by model-independent physical observation of where an event caused ground disturbance. For the May 2023 Emilia-Romagna event (>80,000 landslides; RER2023 inventory), we confront an open-data, event-conditioned susceptibility model (trigger rainfall is among its predictors) with a co-event disturbance footprint built from two satellites: phenology-matched Sentinel-2 change in the Normalized Difference Vegetation Index (ΔNDVI) and Normalized Burn Ratio (ΔNBR), and a 12-day Sentinel-1A C-band coherence-and-backscatter layer used as a cloud-independent coverage check (C-band 12-day decorrelation is the a priori expectation in this setting); neither enters the model. Apparent geomorphic plausibility depends critically on how the independent footprint is constructed. Against a raw co-event footprint (contaminated by flooding and agriculture), a model with AUC ≈ 0.945 is indistinguishable from a random mask. On a landslide-relevant footprint, the same model captures optically detectable disturbance at roughly twice the chance (bootstrap median 1.94×, 95% CI 1.25–2.72, excluding 1; ≈1.46× above a vegetation-phenology null), but the aggregate is driven by an upper-tail minority of 10 km blocks—the majority of blocks have per-block median lift 0.67× (below chance). The map is therefore a regional, not a per-place, statement. Results are a within-event consistency test; cross-event transferability is not claimed. Footprint construction is decisive and currently neglected. The open-source pipeline is released upon acceptance.

Förderung

  • Ministry of Research, Innovation and Digiti-zation, CCCDI – UEFISCDI

Zitieren

APA

Necula, L., Porumb, L., Jocea, A. F., & Raducanu, D. (2026). Independent Multi-Sensor Validation of Machine-Learning Landslide Susceptibility: Footprint Construction Decides the Verdict—May 2023 Emilia-Romagna Event. Remote Sensing, 18(14), 2318. https://doi.org/10.3390/rs18142318

Vancouver

Necula L, Porumb L, Jocea AF, Raducanu D. Independent Multi-Sensor Validation of Machine-Learning Landslide Susceptibility: Footprint Construction Decides the Verdict—May 2023 Emilia-Romagna Event. Remote Sensing. 2026;18(14):2318. doi:10.3390/rs18142318

BibTeX
@article{Necula2026,
  author = {Necula, Lucian and Porumb, Liviu and Jocea, Andreea Florina and Raducanu, Dan},
  title = {Independent Multi-Sensor Validation of Machine-Learning Landslide Susceptibility: Footprint Construction Decides the Verdict—May 2023 Emilia-Romagna Event},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {14},
  pages = {2318},
  doi = {10.3390/rs18142318}
}
Kostenlos starten →