Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area?
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
Texto Completo: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1155276 https://doi.org/10.3390/rs15153719 |
Resumo: | Airborne geophysical data (AGD) have great potential to represent soil-forming factors. Because of that, the objective of this study was to evaluate the importance of AGD in predicting soil attributes such as aluminum saturation (ASat), base saturation (BS), cation exchange capacity (CEC), clay, and organic carbon (OC). The AGD predictor variables include total count (uR/h), K (potassium), eU (uranium equivalent), and eTh (thorium equivalent), ratios between these elements (eTh/K, eU/K, and eU/eTh), factor F or F-parameter, anomalous potassium (Kd), anomalous uranium (Ud), anomalous magnetic field (AMF), vertical derivative (GZ), horizontal derivatives (GX and GY), and mafic index (MI). The approach was based on applying predictive modeling techniques using (1) digital elevation model (DEM) covariates and Sentinel-2 images with AGD; and (2) DEM covariates and Sentinel-2 images without the AGD. The study was conducted in Bom Jardim, a county in Rio de Janeiro-Brazil with an area of 382,430 km², with a database of 208 soil samples to a predefined depth (0-30 cm). Non-explanatory covariates for the selected soil attributes were excluded. Through the selected covariables, the random forest (RF) and support vector machine (SVM) models were applied with separate samples for training (75%) and validation (25%). The model's performance was evaluated through the R-squared (R2), root mean square error (RMSE), and mean absolute error (MAE), as well as null model values and coefficient of variation (CV%). The RF algorithm showed better performance with AGD (R2 values ranging from 0.15 to 0.23), as well as the SVM model (R2 values ranging from 0.08 to 0.23) when compared to RF (R2 values ranging from 0.10 to 0.20) and SVM (R2 values ranging from 0.04 to 0.10) models without AGD. Overall, the results suggest that AGD can be helpful for soil mapping. Nevertheless, it is crucial to acknowledge that the accuracy of AGD in predicting soil properties could vary depending on various common factors in DSM, such as the quality and resolution of the covariates and available soil data. Further research is needed to determine the optimal approach for using AGD in soil mapping. |
id |
EMBR_d17c46542f12b3bfbb9c530ec72366fd |
---|---|
oai_identifier_str |
oai:www.alice.cnptia.embrapa.br:doc/1155276 |
network_acronym_str |
EMBR |
network_name_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository_id_str |
2154 |
spelling |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area?Machine learningDigital soil mappingGamma-ray spectrometry dataMagnetic dataHillslope areasParent materialMapeamento digital do soloSensoriamento RemotoAirborne geophysical data (AGD) have great potential to represent soil-forming factors. Because of that, the objective of this study was to evaluate the importance of AGD in predicting soil attributes such as aluminum saturation (ASat), base saturation (BS), cation exchange capacity (CEC), clay, and organic carbon (OC). The AGD predictor variables include total count (uR/h), K (potassium), eU (uranium equivalent), and eTh (thorium equivalent), ratios between these elements (eTh/K, eU/K, and eU/eTh), factor F or F-parameter, anomalous potassium (Kd), anomalous uranium (Ud), anomalous magnetic field (AMF), vertical derivative (GZ), horizontal derivatives (GX and GY), and mafic index (MI). The approach was based on applying predictive modeling techniques using (1) digital elevation model (DEM) covariates and Sentinel-2 images with AGD; and (2) DEM covariates and Sentinel-2 images without the AGD. The study was conducted in Bom Jardim, a county in Rio de Janeiro-Brazil with an area of 382,430 km², with a database of 208 soil samples to a predefined depth (0-30 cm). Non-explanatory covariates for the selected soil attributes were excluded. Through the selected covariables, the random forest (RF) and support vector machine (SVM) models were applied with separate samples for training (75%) and validation (25%). The model's performance was evaluated through the R-squared (R2), root mean square error (RMSE), and mean absolute error (MAE), as well as null model values and coefficient of variation (CV%). The RF algorithm showed better performance with AGD (R2 values ranging from 0.15 to 0.23), as well as the SVM model (R2 values ranging from 0.08 to 0.23) when compared to RF (R2 values ranging from 0.10 to 0.20) and SVM (R2 values ranging from 0.04 to 0.10) models without AGD. Overall, the results suggest that AGD can be helpful for soil mapping. Nevertheless, it is crucial to acknowledge that the accuracy of AGD in predicting soil properties could vary depending on various common factors in DSM, such as the quality and resolution of the covariates and available soil data. Further research is needed to determine the optimal approach for using AGD in soil mapping.BLENDA PEREIRA BASTOS, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; HELENA SARAIVA KOENOW PINHEIRO, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; FRANCISCO JOSÉ FONSECA FERREIRA, UNIVERSIDADE FEDERAL DO PARANÁ; WALDIR DE CARVALHO JUNIOR, CNPS; LÚCIA HELENA CUNHA DOS ANJOS, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO.BASTOS, B. P.PINHEIRO, H. S. K.FERREIRA, F. J. F.CARVALHO JUNIOR, W. deANJOS, L. H. C. dos2023-07-26T11:23:35Z2023-07-26T11:23:35Z2023-07-262023info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleRemote Sensing, v. 15, n. 15, 3719, 2023.http://www.alice.cnptia.embrapa.br/alice/handle/doc/1155276https://doi.org/10.3390/rs15153719enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPA2023-07-26T11:23:35Zoai:www.alice.cnptia.embrapa.br:doc/1155276Repositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestopendoar:21542023-07-26T11:23:35falseRepositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestcg-riaa@embrapa.bropendoar:21542023-07-26T11:23:35Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
title |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
spellingShingle |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? BASTOS, B. P. Machine learning Digital soil mapping Gamma-ray spectrometry data Magnetic data Hillslope areas Parent material Mapeamento digital do solo Sensoriamento Remoto |
title_short |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
title_full |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
title_fullStr |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
title_full_unstemmed |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
title_sort |
Could airborne geophysical data be used to improve predictive modeling of agronomic soil properties in tropical hillslope area? |
author |
BASTOS, B. P. |
author_facet |
BASTOS, B. P. PINHEIRO, H. S. K. FERREIRA, F. J. F. CARVALHO JUNIOR, W. de ANJOS, L. H. C. dos |
author_role |
author |
author2 |
PINHEIRO, H. S. K. FERREIRA, F. J. F. CARVALHO JUNIOR, W. de ANJOS, L. H. C. dos |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
BLENDA PEREIRA BASTOS, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; HELENA SARAIVA KOENOW PINHEIRO, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO; FRANCISCO JOSÉ FONSECA FERREIRA, UNIVERSIDADE FEDERAL DO PARANÁ; WALDIR DE CARVALHO JUNIOR, CNPS; LÚCIA HELENA CUNHA DOS ANJOS, UNIVERSIDADE FEDERAL RURAL DO RIO DE JANEIRO. |
dc.contributor.author.fl_str_mv |
BASTOS, B. P. PINHEIRO, H. S. K. FERREIRA, F. J. F. CARVALHO JUNIOR, W. de ANJOS, L. H. C. dos |
dc.subject.por.fl_str_mv |
Machine learning Digital soil mapping Gamma-ray spectrometry data Magnetic data Hillslope areas Parent material Mapeamento digital do solo Sensoriamento Remoto |
topic |
Machine learning Digital soil mapping Gamma-ray spectrometry data Magnetic data Hillslope areas Parent material Mapeamento digital do solo Sensoriamento Remoto |
description |
Airborne geophysical data (AGD) have great potential to represent soil-forming factors. Because of that, the objective of this study was to evaluate the importance of AGD in predicting soil attributes such as aluminum saturation (ASat), base saturation (BS), cation exchange capacity (CEC), clay, and organic carbon (OC). The AGD predictor variables include total count (uR/h), K (potassium), eU (uranium equivalent), and eTh (thorium equivalent), ratios between these elements (eTh/K, eU/K, and eU/eTh), factor F or F-parameter, anomalous potassium (Kd), anomalous uranium (Ud), anomalous magnetic field (AMF), vertical derivative (GZ), horizontal derivatives (GX and GY), and mafic index (MI). The approach was based on applying predictive modeling techniques using (1) digital elevation model (DEM) covariates and Sentinel-2 images with AGD; and (2) DEM covariates and Sentinel-2 images without the AGD. The study was conducted in Bom Jardim, a county in Rio de Janeiro-Brazil with an area of 382,430 km², with a database of 208 soil samples to a predefined depth (0-30 cm). Non-explanatory covariates for the selected soil attributes were excluded. Through the selected covariables, the random forest (RF) and support vector machine (SVM) models were applied with separate samples for training (75%) and validation (25%). The model's performance was evaluated through the R-squared (R2), root mean square error (RMSE), and mean absolute error (MAE), as well as null model values and coefficient of variation (CV%). The RF algorithm showed better performance with AGD (R2 values ranging from 0.15 to 0.23), as well as the SVM model (R2 values ranging from 0.08 to 0.23) when compared to RF (R2 values ranging from 0.10 to 0.20) and SVM (R2 values ranging from 0.04 to 0.10) models without AGD. Overall, the results suggest that AGD can be helpful for soil mapping. Nevertheless, it is crucial to acknowledge that the accuracy of AGD in predicting soil properties could vary depending on various common factors in DSM, such as the quality and resolution of the covariates and available soil data. Further research is needed to determine the optimal approach for using AGD in soil mapping. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-26T11:23:35Z 2023-07-26T11:23:35Z 2023-07-26 2023 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
Remote Sensing, v. 15, n. 15, 3719, 2023. http://www.alice.cnptia.embrapa.br/alice/handle/doc/1155276 https://doi.org/10.3390/rs15153719 |
identifier_str_mv |
Remote Sensing, v. 15, n. 15, 3719, 2023. |
url |
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1155276 https://doi.org/10.3390/rs15153719 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
collection |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository.name.fl_str_mv |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
cg-riaa@embrapa.br |
_version_ |
1794503547793965056 |