Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru

Remote sensing is essential in precision agriculture as this approach provides high-resolution information on the soil's physical and chemical parameters for detailed decision making. Globally, technologies such as remote sensing and machine learning are increasingly being used to infer these parame...

Descripción completa

Detalles Bibliográficos
Autores principales: Enriquez Pinedo, Lucia Carolina, Ortega Quispe, Kevin Abner, Ccopi Trucios, Dennis, Rios Chavarria, Claudia Sofía, Urquizo Barrera, Julio, Patricio Rosales, Solanch Rosy, Alejandro Mendez, Lidiana Rene, Oliva Cruz, Manuel, Barboza Castillo, Elgar, Pizarro Carcausto , Samuel Edwin
Formato: info:eu-repo/semantics/article
Lenguaje:Inglés
Publicado: MDPI 2025
Materias:
Acceso en línea:http://hdl.handle.net/20.500.12955/2681
https://doi.org/10.3390/agriengineering7030070
_version_ 1855028533537013760
author Enriquez Pinedo, Lucia Carolina
Ortega Quispe, Kevin Abner
Ccopi Trucios, Dennis
Rios Chavarria, Claudia Sofía
Urquizo Barrera, Julio
Patricio Rosales, Solanch Rosy
Alejandro Mendez, Lidiana Rene
Oliva Cruz, Manuel
Barboza Castillo, Elgar
Pizarro Carcausto , Samuel Edwin
author_browse Alejandro Mendez, Lidiana Rene
Barboza Castillo, Elgar
Ccopi Trucios, Dennis
Enriquez Pinedo, Lucia Carolina
Oliva Cruz, Manuel
Ortega Quispe, Kevin Abner
Patricio Rosales, Solanch Rosy
Pizarro Carcausto , Samuel Edwin
Rios Chavarria, Claudia Sofía
Urquizo Barrera, Julio
author_facet Enriquez Pinedo, Lucia Carolina
Ortega Quispe, Kevin Abner
Ccopi Trucios, Dennis
Rios Chavarria, Claudia Sofía
Urquizo Barrera, Julio
Patricio Rosales, Solanch Rosy
Alejandro Mendez, Lidiana Rene
Oliva Cruz, Manuel
Barboza Castillo, Elgar
Pizarro Carcausto , Samuel Edwin
author_sort Enriquez Pinedo, Lucia Carolina
collection Repositorio INIA
description Remote sensing is essential in precision agriculture as this approach provides high-resolution information on the soil's physical and chemical parameters for detailed decision making. Globally, technologies such as remote sensing and machine learning are increasingly being used to infer these parameters. This study evaluates soil fertility changes and compares them with previous fertilization inputs using high-resolution multispectral imagery and in situ measurements. A UAV-captured image was used to predict the spatial distribution of soil parameters, generating fourteen spectral indices and a digital surface model (DSM) from 103 soil plots across 49.83 hectares. Machine learning algorithms, including classification and regression trees (CART) and random forest (RF), modeled the soil parameters (N-ppm, P-ppm, K-ppm, OM%, and EC-mS/m). The RF model outperformed others, with R² values of 72% for N, 83% for P, 87% for K, 85% for OM, and 70% for EC in 2023. Significant spatiotemporal variations were observed between 2022 and 2023, including an increase in P (14.87 ppm) and a reduction in EC (-0.954 mS/m). High-resolution UAV imagery combined with machine learning proved highly effective for monitoring soil fertility. This approach, tailored to the Peruvian Andes, integrates spectral indices and field-collected data, offering innovative tools to optimize fertilization practices, address soil management challenges, and merge modern technology with traditional methods for sustainable agricultural practices.
format info:eu-repo/semantics/article
id INIA2681
institution Institucional Nacional de Innovación Agraria
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher MDPI
publisherStr MDPI
record_format dspace
spelling INIA26812025-03-24T05:08:33Z Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru Enriquez Pinedo, Lucia Carolina Ortega Quispe, Kevin Abner Ccopi Trucios, Dennis Rios Chavarria, Claudia Sofía Urquizo Barrera, Julio Patricio Rosales, Solanch Rosy Alejandro Mendez, Lidiana Rene Oliva Cruz, Manuel Barboza Castillo, Elgar Pizarro Carcausto , Samuel Edwin fertility soil mapping CART random forest precision agriculture https://purl.org/pe-repo/ocde/ford#4.01.04 Fertilidad del suelo; Cartografía; Teledetección; Agricultura de precisión Remote sensing is essential in precision agriculture as this approach provides high-resolution information on the soil's physical and chemical parameters for detailed decision making. Globally, technologies such as remote sensing and machine learning are increasingly being used to infer these parameters. This study evaluates soil fertility changes and compares them with previous fertilization inputs using high-resolution multispectral imagery and in situ measurements. A UAV-captured image was used to predict the spatial distribution of soil parameters, generating fourteen spectral indices and a digital surface model (DSM) from 103 soil plots across 49.83 hectares. Machine learning algorithms, including classification and regression trees (CART) and random forest (RF), modeled the soil parameters (N-ppm, P-ppm, K-ppm, OM%, and EC-mS/m). The RF model outperformed others, with R² values of 72% for N, 83% for P, 87% for K, 85% for OM, and 70% for EC in 2023. Significant spatiotemporal variations were observed between 2022 and 2023, including an increase in P (14.87 ppm) and a reduction in EC (-0.954 mS/m). High-resolution UAV imagery combined with machine learning proved highly effective for monitoring soil fertility. This approach, tailored to the Peruvian Andes, integrates spectral indices and field-collected data, offering innovative tools to optimize fertilization practices, address soil management challenges, and merge modern technology with traditional methods for sustainable agricultural practices. The Ministry of Agrarian Development and Irrigation (MIDAGRI) of the Peruvian Government provided funding for this study through the project “Creación del servicio de agricultura de precisión en los Departamentos de Lambayeque, Huancavelica, Ucayali y San Martín 4 Departamentos" (grant number CUI 2449640). It also received support from the Vice-Rectorate for Research of the Universidad Nacional del Amazonas Toribio Rodríguez de Mendoza—UNTRM. Special thanks are extended to the collaborators involved in field data collection and assistants of the Precision Agriculture Project (CUI 2449640) as well as other research programs of the “Estación Experimental Agraria Santa Ana”, INIA. 2025-03-24T05:08:33Z 2025-03-24T05:08:33Z 2025-03-06 info:eu-repo/semantics/article Enriquez, L.; Ortega, K.; Ccopi, D.; Rios, C.; Urquizo, J.; Patricio, S.; Alejandro, L.; Oliva-Cruz, M.; Barboza, E.; Pizarro, S. Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru. AgriEngineering 2025, 7, 70. https://doi.org/10.3390/agriengineering7030070 http://hdl.handle.net/20.500.12955/2681 https://doi.org/10.3390/agriengineering7030070 eng AgriEngineering info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/ application/pdf application/pdf MDPI CH Instituto Nacional de Innovación Agraria Repositorio Institucional - INIA
spellingShingle fertility soil mapping
CART
random forest
precision agriculture
https://purl.org/pe-repo/ocde/ford#4.01.04
Fertilidad del suelo; Cartografía; Teledetección; Agricultura de precisión
Enriquez Pinedo, Lucia Carolina
Ortega Quispe, Kevin Abner
Ccopi Trucios, Dennis
Rios Chavarria, Claudia Sofía
Urquizo Barrera, Julio
Patricio Rosales, Solanch Rosy
Alejandro Mendez, Lidiana Rene
Oliva Cruz, Manuel
Barboza Castillo, Elgar
Pizarro Carcausto , Samuel Edwin
Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru
title Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru
title_full Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru
title_fullStr Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru
title_full_unstemmed Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru
title_short Detecting Changes in Soil Fertility Properties Using Multispectral UAV Images and Machine Learning in Central Peru
title_sort detecting changes in soil fertility properties using multispectral uav images and machine learning in central peru
topic fertility soil mapping
CART
random forest
precision agriculture
https://purl.org/pe-repo/ocde/ford#4.01.04
Fertilidad del suelo; Cartografía; Teledetección; Agricultura de precisión
url http://hdl.handle.net/20.500.12955/2681
https://doi.org/10.3390/agriengineering7030070
work_keys_str_mv AT enriquezpinedoluciacarolina detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT ortegaquispekevinabner detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT ccopitruciosdennis detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT rioschavarriaclaudiasofia detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT urquizobarrerajulio detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT patriciorosalessolanchrosy detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT alejandromendezlidianarene detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT olivacruzmanuel detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT barbozacastilloelgar detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu
AT pizarrocarcaustosamueledwin detectingchangesinsoilfertilitypropertiesusingmultispectraluavimagesandmachinelearningincentralperu