Metraipolis › archive › dc_383fde4b0ecf
PhyRestore: Physics-Structured Latent-Factor Restoration — arXiv:2609.19776
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19776
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:08:44.580Z
- SHA-256 of the archived text
54ef0ecedd86e10d121047634185747ece0e8e797c2cf649ae4391ddb4ea6e6a- Stable URL of this page
https://metraipolis.com/documento/dc_383fde4b0ecf
How to cite
PhyRestore: Physics-Structured Latent-Factor Restoration — arXiv:2609.19776 — arXiv (en), https://arxiv.org/abs/2609.19776 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_383fde4b0ecf (Metraipolis archive dc_383fde4b0ecf, sha256 54ef0ecedd86e10d121047634185747ece0e8e797c2cf649ae4391ddb4ea6e6a)
BibTeX
@misc{dc383fde4b0ecf,
title = {PhyRestore: Physics-Structured Latent-Factor Restoration — arXiv:2609.19776},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19776},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_383fde4b0ecf; sha256 54ef0ecedd86e10d121047634185747ece0e8e797c2cf649ae4391ddb4ea6e6a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19776. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Estimating temporal soil-loss change is challenging when physically meaningful input factors are noisy or corrupted, particularly because substantial changes are rare relative to the large number of locations exhibiting little change. We study this problem through the Revised Universal Soil Loss Equation (RUSLE) and introduce PhyRestore, a physics-structured latent-factor restoration framework. Rather than directly predicting soil-loss change or correcting a degraded physical estimate, PhyRestore restores corrupted physical factors and reconstructs temporal change through the known physical relationship. We evaluate PhyRestore in a watershed-scale bitemporal raster setting under isolated and simultaneous corruption of rainfall erosivity and cover management, comparing it with the degraded RUSLE estimate and Direct RF, XGBoost, MLP, and CNN models. Factor restoration improves high-magnitude recovery when the corrupted factors remain identifiable, but its advantage weakens under joint corruption, sparse positive extremes, and factor values outside the training support. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.19776 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:48:18.287Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).