Abstract. Soil organic carbon (SOC) plays a major role concerning chemical, physical, and biological soil properties and functions. To get a better understanding of how soil management affects the SOC content, the precise monitoring of SOC on long-term field experiments (LTFEs) is needed. Visible and near-infrared (Vis–NIR) reflectance spectrometry provides an inexpensive and fast opportunity to complement conventional SOC analysis and has often been used to predict SOC. For this study, 100 soil samples were collected at an LTFE in central Germany by two different sampling designs. SOC values ranged between 1.5 % and 2.9 %. Regression models were built using partial least square regression (PLSR). In order to build robust models, a nested repeated 5-fold group cross-validation (CV) approach was used, which comprised model tuning and evaluation. Various aspects that influence the obtained error measure were analysed and discussed. Four pre-processing methods were compared in order to extract information regarding SOC from the spectra. Finally, the best model performance which did not consider error propagation corresponded to a mean RMSEMV of 0.12 % SOC (R2=0.86). This model performance was impaired by ΔRMSEMV=0.04 % SOC while considering input data uncertainties (ΔR2=0.09), and by ΔRMSEMV=0.12 % SOC (ΔR2=0.17) considering an inappropriate pre-processing. The effect of the sampling design amounted to a ΔRMSEMV of 0.02 % SOC (ΔR2=0.05). Overall, we emphasize the necessity of transparent and precise documentation of the measurement protocol, the model building, and validation procedure in order to assess model performance in a comprehensive way and allow for a comparison between publications. The consideration of uncertainty propagation is essential when applying Vis–NIR spectrometry for soil monitoring.
Abstract. Machine-learning algorithms are good at computing non-linear problems and fitting complex composite functions, which makes them an adequate tool for addressing multiple environmental research questions. One important application is the development of pedotransfer functions (PTFs). This study aims to develop water retention PTFs for two remote tropical mountain regions with rather different soil landscapes: (1) those dominated by peat soils and soils under volcanic influence with high organic matter contents and (2) those dominated by tropical mineral soils. Two tuning procedures were compared to fit boosted regression tree models: (1) tuning with grid search, which is the standard approach in pedometrics; and (2) tuning with differential evolution optimization. A nested cross-validation approach was applied to generate robust models. The area-specific PTFs developed outperform other more general PTFs. Furthermore, the first PTF for typical soils of Páramo landscapes (Ecuador), i.e., organic soils under volcanic influence, is presented. Overall, the results confirmed the differential evolution algorithm's high potential for tuning machine-learning models. While models based on tuning with grid search roughly predicted the response variables' mean for both areas, models applying the differential evolution algorithm for parameter tuning explained up to 25 times more of the response variables' variance.
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.
Soil organic carbon (SOC) plays a major role concerning the chemical, physical and biological soil properties and functions. To get a better understanding how soil management affects the SOC content, the exact monitoring of SOC on long-term field experiments (LTFE) is needed. Visible and near infrared (Vis-NIR) reflectance spectrometry is an inexpensive and fast possibility to enhance conventional SOC analysis and has often been 15 used to predict SOC. For this study, 100 soil samples were collected at a LTFE in central Germany by two different sampling designs. Regression models were built using partial least square regression (PLSR). In order to build robust models, 10-fold cross-validation was used for model tuning and validation procedure. We analysed and discussed various aspects that influence the obtained error measure. A transparent and precise documentation of the model building and validation process, including the calculation of the error measure, is 20 necessary in order to assess the model accuracy in a comprehensive way. This would be the first step to gain a standardized method for model building and validation procedure. 25
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.