Metraipolis › archive › dc_a423eae884f5
State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting — arXiv:2610.02248
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02248
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:08:27.445Z
- SHA-256 of the archived text
818d4bfac43512e7e68601913d6f29f71f7e5f5b7b386eeb2c4c44b7c0900d30- Stable URL of this page
https://metraipolis.com/documento/dc_a423eae884f5
How to cite
State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting — arXiv:2610.02248 — arXiv, https://arxiv.org/abs/2610.02248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a423eae884f5 (Metraipolis archive dc_a423eae884f5, sha256 818d4bfac43512e7e68601913d6f29f71f7e5f5b7b386eeb2c4c44b7c0900d30)
BibTeX
@misc{dca423eae884f5,
title = {State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting — arXiv:2610.02248},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02248},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a423eae884f5; sha256 818d4bfac43512e7e68601913d6f29f71f7e5f5b7b386eeb2c4c44b7c0900d30},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Operational land surface forecasting systems built on Mamba-family Structured State Space Models absorb non-stationary confounding events (unrecorded irrigation booms, dam-operation shifts, sensor recalibrations) into their state-transition matrices, silently biasing NDVI, LST, and crop phenology predictions long after the physical cause ends. This paper introduces SSU-LSF (State-Space Unlearning for Land Surface Forecasting), the first machine-unlearning framework purpose-built for geoscientific Mamba-based SSMs. We develop EKFac influence functions specialized to the Mamba state matrices via a closed-form matrix-exponential gradient, use spectral-radius-weighted elbow thresholding to localize a temporal confounding footprint $\Phi$, and apply Hessian-free projected gradient ascent within a KL-divergence trust region augmented by spatial total-variation (TV) regularization. Proposition 1 establishes that residual confounding is bounded by $\mathcal{O}\big((1-\rho(\bar{A})^{T_c})/((1-\rho(\bar{A}))\mu)\big)$, which grows with the window length $T_c$. Across three heterogeneous benchmarks and eleven baselines, SSU-LSF achieves confounding reduction rates of $0.773$ (CropHarvest), $0.821$ (NDVI-LST), and $0.859$ (ERA5), with worst-case clean-domain RMSE degradation of $4.2\%$ on ERA5, converging in 3--5 epochs at $8.4\times$ lower GPU-cost per unlearning request than full retraining. Code: this https URL
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.02248 — 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 2026-10-05T23:01:38.546Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).