Metraipolis › archive › dc_e56c786238da

An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean — arXiv:2609.38447

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38447
License (as archived)
CC0-1.0
Archived
2026-10-07T13:45:18.131Z
SHA-256 of the archived text
cbecac19e283110747e3fd522d9373f18d9924dde636f88b760dca68ed49454f
Stable URL of this page
https://metraipolis.com/documento/dc_e56c786238da

How to cite

An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean — arXiv:2609.38447 — arXiv (en), https://arxiv.org/abs/2609.38447 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e56c786238da (Metraipolis archive dc_e56c786238da, sha256 cbecac19e283110747e3fd522d9373f18d9924dde636f88b760dca68ed49454f)
BibTeX
@misc{dce56c786238da,
  title = {An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean — arXiv:2609.38447},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38447},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e56c786238da; sha256 cbecac19e283110747e3fd522d9373f18d9924dde636f88b760dca68ed49454f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38447. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Applications (stat.AP).
Pagina del lavoro: https://arxiv.org/abs/2609.38447 — 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 2026-10-07T13:18:10.209Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).