Development of pedotransfer functions for tropical mountain soilscapes: Spotlight on parameter tuning in machine learning

Abstract

Abstract. Machine learning algorithms are good in computing non-linear problems and fitting complex composite functions, which makes them an adequate tool to address multiple environmental research questions. One important application is the development of pedotransfer functions (PTF). This study aims to develop water retention PTFs for two remote tropical mountain regions of rather different soil-landscapes, dominated by (1) organic soils under volcanic influence, and (2) tropical mineral soils. Two tuning procedures were compared to fit boosted regression tree models: (1) tuning by grid search, which is the standard approach in pedometrics and (2) tuning by differential evolution optimization. A nested cross-validation approach was applied to generate robust models. The developed area-specific PTFs outrival other more general PTFs. Furthermore, the first PTF for typical soils of Páramo landscapes, i.e. organic soils under volcanic influence, is presented. Overall, results confirmed the differential evolution algorithm’s high potential for tuning machine learning models. While models based on tuning by grid search roughly predicted the response variables' mean for both areas, models applying the differential evolution algorithm for parameter tuning explained up to 22 times more of the response variables' variance.

Hydro-pedotransfer functions: A roadmap for future development

“…This has been corroborated by Gupta et al (2021a) whose prediction of 𝐾 𝑠𝑎𝑡 improved for tropical regions when explicitly considering data from tropical soils. Ottoni et al (2018) introduced the Hydrophysical Database for Brazilian Soils (HYBRAS), Gunarathna et al, 2019) developed PTFs for tropical Sri Lankan soils, while Gebauer et al (2020) developed PTFs for two remote tropical mountain regions dominated by organic soils under volcanic influence, and tropical mineral soils. Thus, data is becoming increasingly available and opportunities have never been greater for collaborative research to develop a bridge between temperate and tropical PTFs.…”