A Comparative Analysis of Machine Learning and Pedotransfer Functions Under Varying Data Availability in Two Greek Regions
Open Access
- 24 May 2025
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 15 (11) , 1134
Abstract
The current study evaluates the performance of pedotransfer functions (PTFs) and machine learning (ML) algorithms in predicting the soil bulk density (BD) across two distinct regions in Greece—Kozani and Veroia—using both limited and extended sets of soil parameters. The results reveal significant regional differences in prediction accuracy. In the full dataset scenario, Veroia consistently exhibits superior predictive performance across all models (PDF RMSE: 0.104, ML RMSE: 0.095) compared to Kozani (PDF RMSE: 0.133, ML RMSE: 0.122). Generally, ML models outperform PTFs in terms of the RMSE and MAE in both regions with the full dataset. However, PTFs occasionally demonstrate higher R2 values (Veroia PTF R2: 0.35 vs. ML R2: 0.28), suggesting a better explanation of the overall variance despite larger errors. Notably, the effectiveness of ML appears to be affected by the availability of data. In Kozani, when restricted to basic soil properties, ML’s performance (RMSE: 0.129, R2: 0.16) becomes similar to that of PTFs (RMSE: 0.133, R2: 0.16). However, incorporating the full dataset substantially enhances ML’s predictive power (RMSE: 0.122, R2: 0.26). Conversely, in Veroia, the inclusion of more variables paradoxically results in a slight decline in ML performance (ML_min RMSE: 0.093, R2: 0.31 vs. ML RMSE: 0.095, R2: 0.28). These contrasting results emphasize the need for context-specific modeling strategies, careful feature selection, and caution against the assumption that more data or complexity inherently improves the predictive performance.Keywords
Funding Information
- Rural Development Program (RDP) 2014–2020 (Μ16SΥΝ2-00195)
This publication has 29 references indexed in Scilit:
- Soil bulk density assessment in EuropeAgriculture, Ecosystems & Environment, 2024
- Pedotransfer functions and machine learning: Advancements and challenges in tropical soilsGeoderma Regional, 2023
- How does uncertainty of soil organic carbon stock affect the calculation of carbon budgets and soil carbon credits for croplands in the U.S. Midwest?Geoderma, 2022
- Improving pedotransfer functions for predicting soil mineral associated organic carbon by ensemble machine learningGeoderma, 2022
- Evaluation of pedotransfer functions for predicting soil bulk density for U.S. soilsAin Shams Engineering Journal, 2018
- Predicting bulk density using pedotransfer functions for soils in the Upper Anthemountas basin, GreeceGeoderma Regional, 2018
- Differences in pedotransfer functions of bulk density lead to high uncertainty in soil organic carbon estimation at regional scales: Evidence from Chinese terrestrial ecosystemsJournal of Geophysical Research: Biogeosciences, 2015
- Functional evaluation of PTF prediction uncertainty: An application at hillslope scaleGeoderma, 2010
- Pedotransfer functions for estimating soil bulk density from existing soil survey reports in BrazilGeoderma, 2007
- Support-vector networksMachine Learning, 1995