From Rangelands to Cropland, Land-Use Change and Its Impact on Soil Organic Carbon Variables in a Peruvian Andean Highlands: A Machine Learning Modeling Approach
Open Access
- 9 September 2024
- journal article
- research article
- Published by Springer Nature in Ecosystems
- Vol. 27 (7) , 899-917
Abstract
Andean highland soils contain significant quantities of soil organic carbon (SOC); however, more efforts still need to be made to understand the processes behind the accumulation and persistence of SOC and its fractions. This study modeled SOC variables—SOC, refractory SOC (RSOC), and the 13C isotope composition of SOC (δ13CSOC)—using machine learning (ML) algorithms in the Central Andean Highlands of Peru, where grasslands and wetlands (“bofedales”) dominate the landscape surrounded by Junin National Reserve. A total of 198 soil samples (0.3 m depth) were collected to assess SOC variables. Four ML algorithms—random forest (RF), support vector machine (SVM), artificial neural networks (ANNs), and eXtreme gradient boosting (XGB)—were used to model SOC variables using remote sensing data, land-use and land-cover (LULC, nine categories), climate topography, and sampled physical–chemical soil variables. RF was the best algorithm for SOC and δ13CSOC prediction, whereas ANN was the best to model RSOC. “Bofedales” showed 2–3 times greater SOC (11.2 ± 1.60%) and RSOC (1.10 ± 0.23%) and more depleted δ13CSOC (− 27.0 ± 0.44 ‰) than other LULC, which reflects high C persistent, turnover rates, and plant productivity. This highlights the importance of “bofedales” as SOC reservoirs. LULC and vegetation indices close to the near-infrared bands were the most critical environmental predictors to model C variables SOC and δ13CSOC. In contrast, climatic indices were more important environmental predictors for RSOC. This study’s outcomes suggest the potential of ML methods, with a particular emphasis on RF, for mapping SOC and its fractions in the Andean highlands.Keywords
Funding Information
- Consortium of International Agricultural Research Centers (3rd Work Package of “AgriLAC Resiliente”, “Innovate” Work Package of “Excellence in Ag)
- Foreign Agricultural Service (Borlaug Fellowship Program (BF-CR-16-009))
- Bill and Melinda Gates Foundation (OPP1070785)
This publication has 91 references indexed in Scilit:
- Cross validation for model selection: A review with examples from ecologyEcological Monographs, 2023
- Soil organic carbon in Andean high-mountain ecosystems: importance, challenges, and opportunities for carbon sequestrationRegional Environmental Change, 2022
- Large-scale digital mapping of topsoil total nitrogen using machine learning models and associated uncertainty mapEnvironmental Monitoring and Assessment, 2021
- Patterns of SOC and soil 13C and their relations to climatic factors and soil characteristics on the Qinghai–Tibetan PlateauPlant and Soil, 2012
- Ecosystem Carbon Storage Across the Grassland–Forest Transition in the High Andes of Manu National Park, PeruEcosystems, 2010
- No Differences in Soil Carbon Stocks Across the Tree Line in the Peruvian AndesEcosystems, 2009
- Evaluation of structural chemistry and isotopic signatures of refractory soil organic carbon fraction isolated by wet oxidation methodsBiogeochemistry, 2009
- Soil Organic Carbon Dynamics and Land-Use Change2008
- Emerging technologies for in situ measurement of soil carbonClimatic Change, 2006
- The prediction of hillslope flow paths for distributed hydrological modelling using digital terrain modelsHydrological Processes, 1991