EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Kriging prior regression: A case for kriging-based spatial features with TabPFN in soil mapping

Jonas Schmidinger, Viacheslav Barkov, Sebastian Vogel, Martin Atzmueller, Gerard B.M. Heuvelink

Computers and Electronics in Agriculture · 2026-03 · 243 · 111352

DOI: 10.1016/j.compag.2025.111352 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers and Electronics in Agriculture, 2026-03. Verfasst von Jonas Schmidinger und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Volkswagen Foundation, Niedersächsische Ministerium für Wissenschaft und Kultur, Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning and geostatistics are two fundamentally different frameworks for predicting and spatially mapping soil properties. Geostatistics leverages the spatial structure of soil properties, while machine learning captures the relationship between available environmental features and soil properties. We propose a hybrid framework that enriches ML with spatial context through engineering of'spatial lag'features from ordinary kriging. We call this approach'kriging prior regression'(KpR), as it follows the inverse logic of regression kriging. To evaluate this approach, we assessed both the point and probabilistic prediction performance of KpR, using the TabPFN model across six fieldscale datasets from LimeSoDa. These datasets included soil organic carbon, clay content, and pH, along with features derived from remote sensing and in-situ proximal soil sensing. KpR with TabPFN demonstrated reliable uncertainty estimates and more accurate predictions in comparison to several other spatial techniques (e.g., regression/residual kriging with TabPFN), as well as to established non-spatial machine learning algorithms (e.g., random forest). Most notably, it significantly improved the average R2 by around 30% compared to machine learning algorithms without spatial context. This improvement was due to the strong prediction performance of the TabPFN algorithm itself and the complementary spatial information provided by KpR features. TabPFN is particularly effective for prediction tasks with small sample sizes, common in precision agriculture, whereas KpR can compensate for weak relationships between sensing features and soil properties when proximal soil sensing data are limited. Hence, we conclude that KpR with TabPFN is a very robust and versatile modelling framework for digital soil mapping in precision agriculture.

Förderung

  • Volkswagen Foundation
  • Niedersächsische Ministerium für Wissenschaft und Kultur
  • Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg

Zitieren

APA

Schmidinger, J., Barkov, V., Vogel, S., Atzmueller, M., & Heuvelink, G. B. (2026). Kriging prior regression: A case for kriging-based spatial features with TabPFN in soil mapping. Computers and Electronics in Agriculture, 243, 111352. https://doi.org/10.1016/j.compag.2025.111352

Vancouver

Schmidinger J, Barkov V, Vogel S, Atzmueller M, Heuvelink GB. Kriging prior regression: A case for kriging-based spatial features with TabPFN in soil mapping. Computers and Electronics in Agriculture. 2026;243:111352. doi:10.1016/j.compag.2025.111352

BibTeX
@article{Schmidinger2026,
  author = {Schmidinger, Jonas and Barkov, Viacheslav and Vogel, Sebastian and Atzmueller, Martin and Heuvelink, Gerard B.M.},
  title = {Kriging prior regression: A case for kriging-based spatial features with TabPFN in soil mapping},
  journal = {Computers and Electronics in Agriculture},
  year = {2026},
  volume = {243},
  pages = {111352},
  doi = {10.1016/j.compag.2025.111352}
}
Kostenlos starten →