{
  "abstract": "Despite substantial progress in short-to-medium-range weather forecasting, predicting high-impact events such as flash droughts remains a key challenge for both early warning operations and physically-based subseasonal-to-seasonal (S2S) prediction systems. Here we demonstrate that, for S2S soil-moisture forecasting over Europe, forecast skill depends as much on how the prediction problem is formulated as on the forecasting model itself. Using a Vision Transformer-based architecture with dual-pathway temporal and spatial attention, we show that residual learning is essential to outperform persistence. This advantage is realized only when forecasting root-zone soil moisture in physical units rather than standardized anomalies, revealing that the target representation itself constrains predictability. A probabilistic extension via quantile-head fine-tuning further provides well-calibrated predictive distributions. Benchmarked against deep-learning and operational ECMWF S2S baselines over 2021-2022, our model achieves the highest deterministic and probabilistic skill at all lead times and reliably detects anomalously dry root-zone states (below the 20th percentile). Yet flash drought onset, defined by multi-pentad intensification criteria, remains a fundamental challenge shared across all current S2S systems. These findings advance data-driven S2S soil-moisture forecasting while highlighting the remaining challenge of predicting rapid drought development.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.07060",
  "author_total": 4,
  "authors": [
    {
      "name": "Noelia Otero"
    },
    {
      "name": "Atahan Özer"
    },
    {
      "name": "Miguel-Ángel Fernández-Torres"
    },
    {
      "name": "Jackie Ma"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8021q0f73d151.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.07060",
  "fulltext_url": null,
  "id": "8021q0f73d151",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.07060",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.ao-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.07060",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8021q0f73d151.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:22Z",
      "native_id": "2610.07060",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.07060"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    }
  ],
  "title": "Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction",
  "title_text": "Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:22Z",
  "url": "https://research.draconitic.com/paper/8021q0f73d151",
  "venue": "arXiv",
  "versions": []
}