EUVIMEDEUVIMED entdecken
Crossref

Spatially varying deep functional neural network: application in large-scale crop yield prediction

Yeonjoo Park, Bo Li, Yehua Li

Journal of the Royal Statistical Society Series C: Applied Statistics · 16.11.2026 · 75 (5) · 1324-1344

DOI: 10.1093/jrsssc/qlag023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Royal Statistical Society Series C: Applied Statistics, online erschienen am 06.04.2026. Verfasst von Yeonjoo Park und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: Division of Mathematical Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of crop yield is critical for supporting food security, agricultural planning, and economic decision-making. However, yield forecasting remains a significant challenge due to the complex and nonlinear relationships between weather variables and crop production, as well as spatial heterogeneity across agricultural regions. We propose a Spatially Varying Deep Functional Neural Network (SVD-funNet), a deep neural network architecture that integrates functional and scalar predictors with spatially varying coefficients and spatial random effects. The method is designed to flexibly model spatially indexed functional data, such as daily temperature curves, and their relationship to variability in the response, while accounting for spatial correlation. SVD-funNet mitigates the curse of dimensionality through a low-rank structure inspired by the spatially varying functional index model (SVFIM). Through comprehensive simulations, we demonstrate that SVD-funNet outperforms state-of-the-art functional regression models for spatial data, when the functional predictors exhibit complex structure and their relationship with the response varies spatially in a potentially nonstationary manner. Application to corn yield data from the U.S. Midwest demonstrates that SVD-funNet achieves superior predictive accuracy compared to both leading machine learning approaches and parametric statistical models. These results highlight the model’s robustness and its potential applicability to other weather-sensitive crops.

Förderung

  • Division of Mathematical Sciences

Zitieren

APA

Park, Y., Li, B., & Li, Y. (2026). Spatially varying deep functional neural network: application in large-scale crop yield prediction. Journal of the Royal Statistical Society Series C: Applied Statistics, 75(5), 1324-1344. https://doi.org/10.1093/jrsssc/qlag023

Vancouver

Park Y, Li B, Li Y. Spatially varying deep functional neural network: application in large-scale crop yield prediction. Journal of the Royal Statistical Society Series C: Applied Statistics. 2026;75(5):1324-1344. doi:10.1093/jrsssc/qlag023

BibTeX
@article{Park2026,
  author = {Park, Yeonjoo and Li, Bo and Li, Yehua},
  title = {Spatially varying deep functional neural network: application in large-scale crop yield prediction},
  journal = {Journal of the Royal Statistical Society Series C: Applied Statistics},
  year = {2026},
  volume = {75},
  number = {5},
  pages = {1324--1344},
  doi = {10.1093/jrsssc/qlag023}
}
Kostenlos starten →