arXiv subjects

Yongshuang Zhang

Publications and source records attributed to Yongshuang Zhang.

2 recordsLinked to original sources

arXiv2026

Knowledge-Data Dually Driven Paradigm for Accurate Landslide Susceptibility Prediction under Data-Scarce Conditions Using Geomorphic Priors and Tabular Foundation Model

Landslide susceptibility prediction is critical for geohazard risk assessment and mitigation. Conventional data-driven paradigm achieves high predictive accuracy but require sufficient conditioning factors and large-scale landslide inventories. However, in practical engineering applications across mountainous and plateau regions, data-scarce conditions are commonly observed, where such data requirements are rarely satisfied, rendering conventional data-driven paradigm inapplicable. To address this issue, we propose a knowledge-data dually driven paradigm for accurate landslide susceptibility prediction under data-scarce conditions. The essential idea behind the proposed novel paradigm is the integration of the geomorphic prior knowledge with scarce landslide data. To validate the proposed paradigm, we first applied it to a data-rich region in central Italy, where a conventional data-driven paradigm trained on the full dataset served as the baseline. By utilizing only 30% of the available landslide data, the proposed paradigm achieved comparable predictive accuracy to the baseline, demonstrating its effectiveness under data-scarce conditions. The paradigm was further evaluated in a genuinely data-scarce environment for application, the Qilian Permafrost Region of the Tibetan Plateau, where it also yielded reliable susceptibility predictions, confirming its applicability under data-scarce conditions.

cs.LG↗

arXiv2025

Rainfall-induced Mass Movement as Self-organization Process

Self-organizing processes shape Earth's surface, creating complex patterns from simple rules in most landforms. Rainfall-induced mass movements dramatically reshape landscapes through rapid sediment transfer, but whether they self-organize remains unknown. Here we decode their organizational principles by treating spatial changes in scar geometries as fingerprints of the movement process. In 65,936 scars worldwide, we discovered three geometric signals from width, sinuosity and curvature converge on shared patterns and identify a slow-to-fast hierarchy characteristic of self-organizing landforms: long-range correlations show width retaining spatial memory while curvature decorrelates quickly; power spectra quantify a 4-3-2 hierarchy (width-sinuosity-curvature) in scaling exponents; and information flow confirms a top-down organization (width-sinuosity-curvature). Although entropy increases toward finer scales, phase-space reconstructions settle on low-dimensional attractors, revealing hidden order. Together, the evidence shows that width establishes flow corridors through slow dynamics, sinuosity mediates momentum and gravity by intermediate adjustments, and curvature responds rapidly to the terrain. We also developed a model based on simple terrain-inertia trade-offs, demonstrating how mass movements maintain large-scale coherence while flexibly navigating obstacles, potentially extending run-out distances. This organizing rule offers a fundamental mechanism for predicting the destructive reach of mass movements, which are intensifying in our warming, wetter world.

physics.geo-ph↗