EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Navigating challenges in spatial machine learning: Validation, uncertainty, algorithms, and reproducibility

Jakub Nowosad, Carmelo Bonannella, Darius Görgen, Marta Jemeljanova, Teja Kattenborn, Jan Linnenbrink, Hanna Meyer, Madlene Nussbaum, Luca Patelli, Rolf Simoes, Evelyn Uuemaa

ERDKUNDE · 08.06.2026

DOI: 10.3112/erdkunde.2026.04.01 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ERDKUNDE, online erschienen am 08.06.2026. Verfasst von Jakub Nowosad und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial machine learning has matured considerably in recent years, providing powerful approaches for mapping and prediction. However, many challenges remain in achieving methodological robustness, transparency, and comparability. This paper examines six key methodological themes – validation, assessment, uncertainty quantification, algorithm design, software implementation, and reporting – and highlights the need for greater rigor to ensure reliable spatial predictions. We emphasize the importance of domain knowledge, appropriate sampling design, and prediction-domain adaptive cross-validation for realistic model evaluation. When training data fail to represent the prediction domain, areas beyond the model’s area of applicability should be masked, and performance should be reported only within unmasked regions. Uncertainty remains a prominent challenge, requiring methodological innovation to account for spatial dependencies and improved strategies for quantifying and communicating it to diverse audiences. Furthermore, while numerous methods now incorporate spatial information into machine learning, the lack of theoretical grounding and systematic benchmarking continues to constrain comparability and progress. Finally, we highlight the critical role of open, reproducible software tools and call for standardized reporting protocols tailored to spatial prediction workflows. Addressing these methodological and practical gaps will enhance reliability, transparency, and reproducibility in spatial machine learning applications.

Zitieren

APA

Nowosad, J., Bonannella, C., Görgen, D., Jemeljanova, M., Kattenborn, T., Linnenbrink, J., Meyer, H., Nussbaum, M., Patelli, L., Simoes, R., & Uuemaa, E. (2026). Navigating challenges in spatial machine learning: Validation, uncertainty, algorithms, and reproducibility. ERDKUNDE. https://doi.org/10.3112/erdkunde.2026.04.01

Vancouver

Nowosad J, Bonannella C, Görgen D, Jemeljanova M, Kattenborn T, Linnenbrink J, et al. Navigating challenges in spatial machine learning: Validation, uncertainty, algorithms, and reproducibility. ERDKUNDE. 2026. doi:10.3112/erdkunde.2026.04.01

BibTeX
@article{Nowosad2026,
  author = {Nowosad, Jakub and Bonannella, Carmelo and Görgen, Darius and Jemeljanova, Marta and Kattenborn, Teja and Linnenbrink, Jan and Meyer, Hanna and Nussbaum, Madlene and Patelli, Luca and Simoes, Rolf and Uuemaa, Evelyn},
  title = {Navigating challenges in spatial machine learning: Validation, uncertainty, algorithms, and reproducibility},
  journal = {ERDKUNDE},
  year = {2026},
  doi = {10.3112/erdkunde.2026.04.01}
}
Kostenlos starten →