Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery

The spatial heterogeneity of soil properties has a significant impact on crop growth, making it difficult to adopt site-specific crop management practices. Traditional laboratory-based analyses are costly, and data extrapolation for mapping soil properties using high-resolution imagery becomes a com...

Descripción completa

Detalles Bibliográficos
Autores principales: Pizarro Carcausto, Samuel Edwin, Pricope, Narcisa G., Figueroa Venegas, Deyanira Antonella, Carbajal Llosa, Carlos Miguel, Quispe Huincho, Miriam Rocío, Vera Vilchez, Jesús Emilio, Alejandro Méndez, Lidiana Rene, Achallma Mendoza, Lino, González Tovar, Izamar Estrella, Salazar Coronel, Wilian, Loayza, Hildo, Cruz Luis, Juancarlos Alejandro, Arbizu Berrocal, Carlos Irvin
Formato: info:eu-repo/semantics/article
Lenguaje:Inglés
Publicado: MDPI 2023
Materias:
Acceso en línea:https://hdl.handle.net/20.500.12955/2290
https://doi.org/10.3390/rs15123203
_version_ 1855028750073200640
author Pizarro Carcausto, Samuel Edwin
Pricope, Narcisa G.
Figueroa Venegas, Deyanira Antonella
Carbajal Llosa, Carlos Miguel
Quispe Huincho, Miriam Rocío
Vera Vilchez, Jesús Emilio
Alejandro Méndez, Lidiana Rene
Achallma Mendoza, Lino
González Tovar, Izamar Estrella
Salazar Coronel, Wilian
Loayza, Hildo
Cruz Luis, Juancarlos Alejandro
Arbizu Berrocal, Carlos Irvin
author_browse Achallma Mendoza, Lino
Alejandro Méndez, Lidiana Rene
Arbizu Berrocal, Carlos Irvin
Carbajal Llosa, Carlos Miguel
Cruz Luis, Juancarlos Alejandro
Figueroa Venegas, Deyanira Antonella
González Tovar, Izamar Estrella
Loayza, Hildo
Pizarro Carcausto, Samuel Edwin
Pricope, Narcisa G.
Quispe Huincho, Miriam Rocío
Salazar Coronel, Wilian
Vera Vilchez, Jesús Emilio
author_facet Pizarro Carcausto, Samuel Edwin
Pricope, Narcisa G.
Figueroa Venegas, Deyanira Antonella
Carbajal Llosa, Carlos Miguel
Quispe Huincho, Miriam Rocío
Vera Vilchez, Jesús Emilio
Alejandro Méndez, Lidiana Rene
Achallma Mendoza, Lino
González Tovar, Izamar Estrella
Salazar Coronel, Wilian
Loayza, Hildo
Cruz Luis, Juancarlos Alejandro
Arbizu Berrocal, Carlos Irvin
author_sort Pizarro Carcausto, Samuel Edwin
collection Repositorio INIA
description The spatial heterogeneity of soil properties has a significant impact on crop growth, making it difficult to adopt site-specific crop management practices. Traditional laboratory-based analyses are costly, and data extrapolation for mapping soil properties using high-resolution imagery becomes a computationally expensive procedure, taking days or weeks to obtain accurate results using a desktop workstation. To overcome these challenges, cloud-based solutions such as Google Earth Engine (GEE) have been used to analyze complex data with machine learning algorithms. In this study, we explored the feasibility of designing and implementing a digital soil mapping approach in the GEE platform using high-resolution reflectance imagery derived from a thermal infrared and multispectral camera Altum (MicaSense, Seattle, WA, USA). We compared a suite of multispectral-derived soil and vegetation indices with in situ measurements of physical-chemical soil properties in agricultural lands in the Peruvian Mantaro Valley. The prediction ability of several machine learning algorithms (CART, XGBoost, and Random Forest) was evaluated using R2, to select the best predicted maps (R2 > 0.80), for ten soil properties, including Lime, Clay, Sand, N, P, K, OM, Al, EC, and pH, using multispectral imagery and derived products such as spectral indices and a digital surface model (DSM). Our results indicate that the predictions based on spectral indices, most notably, SRI, GNDWI, NDWI, and ExG, in combination with CART and RF algorithms are superior to those based on individual spectral bands. Additionally, the DSM improves the model prediction accuracy, especially for K and Al. We demonstrate that high-resolution multispectral imagery processed in the GEE platform has the potential to develop soil properties prediction models essential in establishing adaptive soil monitoring programs for agricultural regions.
format info:eu-repo/semantics/article
id INIA2290
institution Institucional Nacional de Innovación Agraria
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher MDPI
publisherStr MDPI
record_format dspace
spelling INIA22902023-08-31T17:37:25Z Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery Pizarro Carcausto, Samuel Edwin Pricope, Narcisa G. Figueroa Venegas, Deyanira Antonella Carbajal Llosa, Carlos Miguel Quispe Huincho, Miriam Rocío Vera Vilchez, Jesús Emilio Alejandro Méndez, Lidiana Rene Achallma Mendoza, Lino González Tovar, Izamar Estrella Salazar Coronel, Wilian Loayza, Hildo Cruz Luis, Juancarlos Alejandro Arbizu Berrocal, Carlos Irvin Soil mapping UAV Google Earth Engine Machine learning Cloud computing https://purl.org/pe-repo/ocde/ford#4.01.06 Soil surveys Reconocimiento de suelos Unmanned aerial vehicles Vehículos aéreos no tripulados Machine learning The spatial heterogeneity of soil properties has a significant impact on crop growth, making it difficult to adopt site-specific crop management practices. Traditional laboratory-based analyses are costly, and data extrapolation for mapping soil properties using high-resolution imagery becomes a computationally expensive procedure, taking days or weeks to obtain accurate results using a desktop workstation. To overcome these challenges, cloud-based solutions such as Google Earth Engine (GEE) have been used to analyze complex data with machine learning algorithms. In this study, we explored the feasibility of designing and implementing a digital soil mapping approach in the GEE platform using high-resolution reflectance imagery derived from a thermal infrared and multispectral camera Altum (MicaSense, Seattle, WA, USA). We compared a suite of multispectral-derived soil and vegetation indices with in situ measurements of physical-chemical soil properties in agricultural lands in the Peruvian Mantaro Valley. The prediction ability of several machine learning algorithms (CART, XGBoost, and Random Forest) was evaluated using R2, to select the best predicted maps (R2 > 0.80), for ten soil properties, including Lime, Clay, Sand, N, P, K, OM, Al, EC, and pH, using multispectral imagery and derived products such as spectral indices and a digital surface model (DSM). Our results indicate that the predictions based on spectral indices, most notably, SRI, GNDWI, NDWI, and ExG, in combination with CART and RF algorithms are superior to those based on individual spectral bands. Additionally, the DSM improves the model prediction accuracy, especially for K and Al. We demonstrate that high-resolution multispectral imagery processed in the GEE platform has the potential to develop soil properties prediction models essential in establishing adaptive soil monitoring programs for agricultural regions. 2023-08-31T17:37:23Z 2023-08-31T17:37:23Z 2023-06-20 info:eu-repo/semantics/article Pizarro, S.; Pricope, N. G.; Figueroa, D.; Carbajal, C.; Quispe, M.; Vera, J.; ... & Arbizu, C. I. (2023). Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery. Remote Sensing, 15(12), 3203. doi: 10.3390/rs15123203 2072-4292 https://hdl.handle.net/20.500.12955/2290 https://doi.org/10.3390/rs15123203 eng urn:issn:2072-4292 Remote sensing 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 Soil mapping
UAV
Google Earth Engine
Machine learning
Cloud computing
https://purl.org/pe-repo/ocde/ford#4.01.06
Soil surveys
Reconocimiento de suelos
Unmanned aerial vehicles
Vehículos aéreos no tripulados
Machine learning
Pizarro Carcausto, Samuel Edwin
Pricope, Narcisa G.
Figueroa Venegas, Deyanira Antonella
Carbajal Llosa, Carlos Miguel
Quispe Huincho, Miriam Rocío
Vera Vilchez, Jesús Emilio
Alejandro Méndez, Lidiana Rene
Achallma Mendoza, Lino
González Tovar, Izamar Estrella
Salazar Coronel, Wilian
Loayza, Hildo
Cruz Luis, Juancarlos Alejandro
Arbizu Berrocal, Carlos Irvin
Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
title Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
title_full Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
title_fullStr Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
title_full_unstemmed Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
title_short Implementing cloud computing for the digital mapping of agricultural soil properties from high resolution UAV multispectral imagery
title_sort implementing cloud computing for the digital mapping of agricultural soil properties from high resolution uav multispectral imagery
topic Soil mapping
UAV
Google Earth Engine
Machine learning
Cloud computing
https://purl.org/pe-repo/ocde/ford#4.01.06
Soil surveys
Reconocimiento de suelos
Unmanned aerial vehicles
Vehículos aéreos no tripulados
Machine learning
url https://hdl.handle.net/20.500.12955/2290
https://doi.org/10.3390/rs15123203
work_keys_str_mv AT pizarrocarcaustosamueledwin implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT pricopenarcisag implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT figueroavenegasdeyaniraantonella implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT carbajalllosacarlosmiguel implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT quispehuinchomiriamrocio implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT veravilchezjesusemilio implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT alejandromendezlidianarene implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT achallmamendozalino implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT gonzaleztovarizamarestrella implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT salazarcoronelwilian implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT loayzahildo implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT cruzluisjuancarlosalejandro implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery
AT arbizuberrocalcarlosirvin implementingcloudcomputingforthedigitalmappingofagriculturalsoilpropertiesfromhighresolutionuavmultispectralimagery