Local Intrinsic Dimensionality of Ground Motion Data for Early Detection of Catastrophic Slope Failure
arXiv:2601.03569v3 Announce Type: replace Abstract: Local Intrinsic Dimensionality (LID) has shown strong potential for anomaly detection in high-dimensional data, including landslide failure detection in granular media, where early and accurate identification of failure zones is crucial for effective geohazard mitigation. However, this task is still challenging due to the spatial correlations and temporal dynamics that are inherently present in surface displacement data. To address this gap, we propose a novel unsupervised framework called spatiotemporal LID (st-LID) that generalizes the LID
The increasing availability of high-dimensional sensor data and advancements in AI/ML techniques for unsupervised anomaly detection are converging to address complex geotechnical challenges.
Early and accurate detection of catastrophic slope failures directly impacts infrastructure safety, resource extraction, and reduces loss of life and economic disruption from geohazards.
The development of spatiotemporal LID offers a more robust method for identifying critical zones in ground motion data, improving the reliability and timeliness of landslide prediction.
- · Geospatial monitoring companies
- · Mining sector
- · Infrastructure development
- · AI/ML research in geohazards
- · Regions prone to landslides
- · Traditional, less data-driven geological surveying
Improved early warning systems for natural disasters, particularly landslides.
Reduced insurance costs and infrastructure project risks in geologically unstable areas.
Potential for integration into autonomous monitoring and response systems, enhancing resilience to environmental hazards.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG