Schmidinger, Jonas, Vogel, Sebastian, Barkov, Viacheslav, Pham, Anh-Duy, Gebbers, Robin, Tavakoli, Hamed, Correa, Jose, Tavares, Tiago R., Filippi, Patrick, Jones, Edward J., Lukas, Vojtech, Boenecke, Eric, Ruehlmann, Joerg, Schroeter, Ingmar, Kramer, Eckart, Paetzold, Stefan, Kodaira, Masakazu, Wadoux, Alexandre M.J.-C., Bragazza, Luca, Metzger, Konrad, Huang, Jingyi, Valente, Domingos S.M., Safanelli, Jose L., Bottega, Eduardo L., Dalmolin, Ricardo S.D., Farkas, Csilla, Steiger, Alexander, Horst, Taciara Z., Ramirez-Lopez, Leonardo, Scholten, Thomas, Stumpf, Felix, Rosso, Pablo, Costa, Marcelo M., Zandonadi, Rodrigo S., Wetterlind, Johanna, and Atzmueller, Martin (2025) LimeSoDa: A dataset collection for benchmarking of machine learning regressors in digital soil mapping. Geoderma, 459. 117337.

Preview

PDF (Published Version) - Published Version Available under License Creative Commons Attribution. Download (7MB) | Preview

Abstract

Digital soil mapping (DSM) relies on a broad pool of statistical methods, yet determining the optimal method for a given context remains challenging and contentious. Benchmarking studies on multiple datasets are needed to reveal strengths and limitations of commonly used methods. Existing DSM studies usually rely on a single dataset with restricted access, leading to incomplete and potentially misleading conclusions. To address these issues, we introduce an open-access dataset collection called Precision Liming Soil Datasets (LimeSoDa). LimeSoDa consists of 31 field- and farm-scale datasets from various countries. Each dataset has three target soil properties: (1) soil organic matter or soil organic carbon, (2) clay content and (3) pH, alongside a set of features. Features are dataset-specific and were obtained by optical spectroscopy, proximal- and remote soil sensing. All datasets were aligned to a tabular format and are ready-to-use for modeling. We demonstrated the use of LimeSoDa for benchmarking by comparing the predictive performance of four learning algorithms across all datasets. This comparison included multiple linear regression (MLR), support vector regression (SVR), categorical boosting (CatBoost) and random forest (RF). The results showed that although no single algorithm was universally superior, certain algorithms performed better in specific contexts. MLR and SVR performed better on high-dimensional spectral datasets, likely due to better compatibility with principal components. In contrast, CatBoost and RF exhibited considerably better performances when applied to datasets with a moderate number (<20) of features. These benchmarking results illustrate that the performance of statistical methods can be highly context-dependent. LimeSoDa therefore provides an important resource for improving the development and evaluation of statistical methods in DSM.

Item ID:	94087
Item Type:	Article (Research - C1)
ISSN:	1872-6259
Copyright Information:	© 2025 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Date Deposited:	07 Oct 2026 03:56
FoR Codes:	41 ENVIRONMENTAL SCIENCES > 4106 Soil sciences > 410602 Pedology and pedometrics @ 100%
SEO Codes:	18 ENVIRONMENTAL MANAGEMENT > 1806 Terrestrial systems and management > 180601 Assessment and management of terrestrial ecosystems @ 100%
	More Statistics