{
  "abstract": "Reliable, timely crop-yield forecasts are essential for market stability and risk management, yet many approaches rely on costly or hard-to-scale inputs. We present a frugal, transferable, and architecture-agnostic deep learning framework that uses routine weather as the only time-varying input plus two lightweight static context inputs (crop year and an agro-environmental label) to capture long-run change and regional heterogeneity, while supporting multiple sequence encoders under identical data requirements. Using a 20-season Brazilian soybean case study (2001/02-2020/21) with leave-one-year-out cross-validation, we benchmark MLP, CNN, LSTM, CNN-LSTM, a Transformer encoder and the Mamba state-space model against linear ridge regression and a five-year moving-average \"farmer\" baseline. All deep learning variants outperform ridge, and all sequential encoders surpass the non-sequential MLP. The Transformer achieves the best national accuracy (RMSE 149 kg ha^-1; rRMSE 5.3%; R^2 = 0.784), reducing error by 47.6% relative to the farmer baseline. In-season forecasts improve monotonically from early- to late-season issuance, reaching approximately 50% lower error than the baseline at the latest forecast point. Ablations indicate that the agro-environmental label and spatial instance expansion (multiple grid-node weather sequences per municipality-year) contribute positively without increasing input complexity. SHAP diagnostics suggest crop year explains most of the long-run trajectory, whereas within-season weather and agro-environmental context primarily drive interannual deviations, with moisture/cloud and thermal-demand variables dominating. Overall, the framework is straightforward to deploy across other crops and geographic regions and is naturally compatible with operational weather forecasts for routine monitoring.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.38447",
  "author_total": 3,
  "authors": [
    {
      "name": "Fernando Dupin da Cunha Mello"
    },
    {
      "name": "Prashant Kumar"
    },
    {
      "name": "Erick G. Sperandio Nascimento"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9mpgyy9rswb0n.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.38447",
  "fulltext_url": null,
  "id": "9mpgyy9rswb0n",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.38447",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "openalex",
      "1110|Smart Agriculture and AI"
    ]
  ],
  "openalex": "W7215111187",
  "pdf_url": "https://arxiv.org/pdf/2609.38447",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9mpgyy9rswb0n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:58Z",
      "native_id": "2609.38447",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.38447"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean",
  "title_text": "An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:58Z",
  "url": "https://research.draconitic.com/paper/9mpgyy9rswb0n",
  "venue": "arXiv",
  "versions": []
}