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...

Descripción completa

Detalles Bibliográficos
Autores principales: Carbajal, Mariella, Ramirez, David A., Turin Canchaya, Cecilia Claudia, Schaeffer, Sean M., Konkel, Julie, Ninanya, Johan, Rinza, Javier, De Mendiburu, Felipe, Zorogastua, Percy, Villaorduña, Liliana, Quiroz, Roberto
Formato: info:eu-repo/semantics/article
Lenguaje:Inglés
Publicado: Springer 2024
Materias:
Acceso en línea:https://hdl.handle.net/20.500.12955/2576
https://doi.org/10.1007/s10021-024-00928-7
_version_ 1855028388960403456
author Carbajal, Mariella
Ramirez, David A.
Turin Canchaya, Cecilia Claudia
Schaeffer, Sean M.
Konkel, Julie
Ninanya, Johan
Rinza, Javier
De Mendiburu, Felipe
Zorogastua, Percy
Villaorduña, Liliana
Quiroz, Roberto
author_browse Carbajal, Mariella
De Mendiburu, Felipe
Konkel, Julie
Ninanya, Johan
Quiroz, Roberto
Ramirez, David A.
Rinza, Javier
Schaeffer, Sean M.
Turin Canchaya, Cecilia Claudia
Villaorduña, Liliana
Zorogastua, Percy
author_facet Carbajal, Mariella
Ramirez, David A.
Turin Canchaya, Cecilia Claudia
Schaeffer, Sean M.
Konkel, Julie
Ninanya, Johan
Rinza, Javier
De Mendiburu, Felipe
Zorogastua, Percy
Villaorduña, Liliana
Quiroz, Roberto
author_sort Carbajal, Mariella
collection Repositorio INIA
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 (d13CSOC)—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 variablesusing remote sensing data, land-use and landcover (LULC, nine categories), climate topography, and sampled physical–chemical soil variables. RF was the best algorithm for SOC and d13CSOC 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 d13CSOC (- 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 d13CSOC. 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 info:eu-repo/semantics/article
id INIA2576
institution Institucional Nacional de Innovación Agraria
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Springer
publisherStr Springer
record_format dspace
spelling INIA25762024-09-30T18:24:11Z 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, Mariella Ramirez, David A. Turin Canchaya, Cecilia Claudia Schaeffer, Sean M. Konkel, Julie Ninanya, Johan Rinza, Javier De Mendiburu, Felipe Zorogastua, Percy Villaorduña, Liliana Quiroz, Roberto Artificial neural networks Bofedales 13C isotope composition Extreme gradient boosting Grasslands Random forest Refractory C fraction Support vector machine https://purl.org/pe-repo/ocde/ford#4.01.04 Redes de neuronas Fishing nets Tierra húmeda Wetlands Isótopo Isotopes Gradiente de temperatura Temperature gradients Grasslands Pradera Machine learning Aprendizaje automático 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 (d13CSOC)—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 variablesusing remote sensing data, land-use and landcover (LULC, nine categories), climate topography, and sampled physical–chemical soil variables. RF was the best algorithm for SOC and d13CSOC 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 d13CSOC (- 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 d13CSOC. 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. 2024-09-30T18:24:09Z 2024-09-30T18:24:09Z 2024-09-09 info:eu-repo/semantics/article Carbajal, M.; Ramirez, D.A.; Turin-Canchaya, C.C.; Schaeffer, S.M.; Konkel, J.; Ninanya, J.; Rinza, J.; De Mendiburu, F.; Zorogastua, P.; Villaordun, 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 (2024). doi: 10.1007/s10021-024-00928-7 1435-0629 https://hdl.handle.net/20.500.12955/2576 https://doi.org/10.1007/s10021-024-00928-7 eng urn:issn:1435-0629 Ecosystems info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf application/pdf Springer US Instituto Nacional de Innovación Agraria Repositorio Institucional - INIA
spellingShingle Artificial neural networks
Bofedales
13C isotope composition
Extreme gradient boosting
Grasslands
Random forest
Refractory C fraction
Support vector machine
https://purl.org/pe-repo/ocde/ford#4.01.04
Redes de neuronas
Fishing nets
Tierra húmeda
Wetlands
Isótopo
Isotopes
Gradiente de temperatura
Temperature gradients
Grasslands
Pradera
Machine learning
Aprendizaje automático
Carbajal, Mariella
Ramirez, David A.
Turin Canchaya, Cecilia Claudia
Schaeffer, Sean M.
Konkel, Julie
Ninanya, Johan
Rinza, Javier
De Mendiburu, Felipe
Zorogastua, Percy
Villaorduña, Liliana
Quiroz, Roberto
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 Artificial neural networks
Bofedales
13C isotope composition
Extreme gradient boosting
Grasslands
Random forest
Refractory C fraction
Support vector machine
https://purl.org/pe-repo/ocde/ford#4.01.04
Redes de neuronas
Fishing nets
Tierra húmeda
Wetlands
Isótopo
Isotopes
Gradiente de temperatura
Temperature gradients
Grasslands
Pradera
Machine learning
Aprendizaje automático
url https://hdl.handle.net/20.500.12955/2576
https://doi.org/10.1007/s10021-024-00928-7
work_keys_str_mv AT carbajalmariella fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT ramirezdavida fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT turincanchayaceciliaclaudia fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT schaefferseanm fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT konkeljulie fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT ninanyajohan fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT rinzajavier fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT demendiburufelipe fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT zorogastuapercy fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT villaordunaliliana fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach
AT quirozroberto fromrangelandstocroplandlandusechangeanditsimpactonsoilorganiccarbonvariablesinaperuvianandeanhighlandsamachinelearningmodelingapproach