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

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 isotop...

Full description

Bibliographic Details
Main Authors: Carbajal, M., Ramírez, D., Turin, C., Schaeffer, S.M., Konkel, J., Ninanya, J., Rinza, J., De Mendiburu, F., Zorogastua, P., Villaorduña, L., Quiroz, R.
Format: Journal Article
Language:Inglés
Published: Springer 2024
Subjects:
Online Access:https://hdl.handle.net/10568/152095
_version_ 1855517027543810048
author Carbajal, M.
Ramírez, D.
Turin, C.
Schaeffer, S.M.
Konkel, J.
Ninanya, J.
Rinza, J.
De Mendiburu, F.
Zorogastua, P.
Villaorduña, L.
Quiroz, R.
author_browse Carbajal, M.
De Mendiburu, F.
Konkel, J.
Ninanya, J.
Quiroz, R.
Ramírez, D.
Rinza, J.
Schaeffer, S.M.
Turin, C.
Villaorduña, L.
Zorogastua, P.
author_facet Carbajal, M.
Ramírez, D.
Turin, C.
Schaeffer, S.M.
Konkel, J.
Ninanya, J.
Rinza, J.
De Mendiburu, F.
Zorogastua, P.
Villaorduña, L.
Quiroz, R.
author_sort Carbajal, M.
collection Repository of Agricultural Research Outputs (CGSpace)
description 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.
format Journal Article
id CGSpace152095
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Springer
publisherStr Springer
record_format dspace
spelling CGSpace1520952025-12-08T09:54:28Z 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 Carbajal, M. Ramírez, D. Turin, C. Schaeffer, S.M. Konkel, J. Ninanya, J. Rinza, J. De Mendiburu, F. Zorogastua, P. Villaorduña, L. Quiroz, R. crops neural networks grasslands soil organic carbon machine learning 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. 2024-11 2024-09-10T20:53:32Z 2024-09-10T20:53:32Z Journal Article https://hdl.handle.net/10568/152095 en Open Access Springer Carbajal, M.; Ramírez, D.A.; Turin, C.; Schaeffer, S.M.; Konkel, J.; Ninanya, J.; Rinza, J.; De Mendiburu, F.; Zorogastua, P.; Villaorduña, L.; Quiroz, R. 2024. 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. Ecosystems. ISSN 1435-0629. https://doi.org/10.1007/s10021-024-00928-7
spellingShingle crops
neural networks
grasslands
soil organic carbon
machine learning
Carbajal, M.
Ramírez, D.
Turin, C.
Schaeffer, S.M.
Konkel, J.
Ninanya, J.
Rinza, J.
De Mendiburu, F.
Zorogastua, P.
Villaorduña, L.
Quiroz, R.
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
title 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
title_full 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
title_fullStr 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
title_full_unstemmed 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
title_short 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
title_sort 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
topic crops
neural networks
grasslands
soil organic carbon
machine learning
url https://hdl.handle.net/10568/152095
work_keys_str_mv AT carbajalm fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT ramirezd fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT turinc fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT schaeffersm fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT konkelj fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT ninanyaj fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT rinzaj fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT demendiburuf fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT zorogastuap fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT villaordunal fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT quirozr fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach