Strategies for the Development of Spectral Models for Soil Organic Matter Estimation
Visible (V), Near Infrared (NIR) and Short Waves Infrared (SWIR) spectroscopy has been indicated as a promising tool in soil studies, especially in the last decade. However, in order to apply this method, it is necessary to develop prediction models with the capacity to capture the intrinsic differe...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/7/1376 |
id |
doaj-77855cd7b7714d53a69a471a414b12d8 |
---|---|
record_format |
Article |
spelling |
doaj-77855cd7b7714d53a69a471a414b12d82021-04-02T23:06:29ZengMDPI AGRemote Sensing2072-42922021-04-01131376137610.3390/rs13071376Strategies for the Development of Spectral Models for Soil Organic Matter EstimationEverson Cezar0Marcos Rafael Nanni1Luís Guilherme Teixeira Crusiol2Liang Sun3Mônica Sacioto Chicati4Renato Herrig Furlanetto5Marlon Rodrigues6Rubson Natal Ribeiro Sibaldelli7Guilherme Fernando Capristo Silva8Karym Mayara de Oliveira9José A. M. Demattê10Department of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilKey Laboratory of Agricultural Remote Sensing, Ministry of Agriculture/CAAS-CIAT Joint Laboratory in Advanced Technologies for Sustainable Agriculture—Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilMathematician, Statistical Specialist, Londrina, PR 86001-970, BrazilDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilDepartment of Agronomy, State University of Maringá, Maringá, PR 87020-900, BrazilDepartment of Soil Science, University of São Paulo, Piracicaba, SP 13418-900, BrazilVisible (V), Near Infrared (NIR) and Short Waves Infrared (SWIR) spectroscopy has been indicated as a promising tool in soil studies, especially in the last decade. However, in order to apply this method, it is necessary to develop prediction models with the capacity to capture the intrinsic differences between agricultural areas and incorporate them in the modeling process. High quality estimates are generally obtained when these models are applied to soil samples displaying characteristics similar to the samples used in their construction. However, low quality predictions are noted when applied to samples from new areas presenting different characteristics. One way to solve this problem is by recalibrating the models using selected samples from the area of interest. Based on this premise, the aim of this study was to use the spiking technique and spiking associated with hybridization to expand prediction models and estimate organic matter content in a target area undergoing different uses and management. A total of 425 soil samples were used for the generation of the state model, as well as 200 samples from a target area to select the subsets (10 samples) used for model recalibration. The spectral readings of the samples were obtained in the laboratory using the ASD FieldSpec 3 Jr. Sensor from 350 to 2500 nm. The spectral curves of the samples were then associated to the soil attributes by means of a partial least squares regression (PLSR). The state model obtained better results when recalibrated with samples selected through a cluster analysis. The use of hybrid spectral curves did not generate significant improvements, presenting estimates, in most cases, lower than the state model applied without recalibration. The use of the isolated spiking technique was more effective in comparison with the spiked and hybridized state models, reaching r<sup>2</sup>, square root of mean prediction error (RMSEP) and ratio of performance to deviation (RPD) values of 0.43, 4.4 g dm<sup>−3</sup>, and 1.36, respectively.https://www.mdpi.com/2072-4292/13/7/1376PLSRhybrid curvesreflectancerecalibrationspiking |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Everson Cezar Marcos Rafael Nanni Luís Guilherme Teixeira Crusiol Liang Sun Mônica Sacioto Chicati Renato Herrig Furlanetto Marlon Rodrigues Rubson Natal Ribeiro Sibaldelli Guilherme Fernando Capristo Silva Karym Mayara de Oliveira José A. M. Demattê |
spellingShingle |
Everson Cezar Marcos Rafael Nanni Luís Guilherme Teixeira Crusiol Liang Sun Mônica Sacioto Chicati Renato Herrig Furlanetto Marlon Rodrigues Rubson Natal Ribeiro Sibaldelli Guilherme Fernando Capristo Silva Karym Mayara de Oliveira José A. M. Demattê Strategies for the Development of Spectral Models for Soil Organic Matter Estimation Remote Sensing PLSR hybrid curves reflectance recalibration spiking |
author_facet |
Everson Cezar Marcos Rafael Nanni Luís Guilherme Teixeira Crusiol Liang Sun Mônica Sacioto Chicati Renato Herrig Furlanetto Marlon Rodrigues Rubson Natal Ribeiro Sibaldelli Guilherme Fernando Capristo Silva Karym Mayara de Oliveira José A. M. Demattê |
author_sort |
Everson Cezar |
title |
Strategies for the Development of Spectral Models for Soil Organic Matter Estimation |
title_short |
Strategies for the Development of Spectral Models for Soil Organic Matter Estimation |
title_full |
Strategies for the Development of Spectral Models for Soil Organic Matter Estimation |
title_fullStr |
Strategies for the Development of Spectral Models for Soil Organic Matter Estimation |
title_full_unstemmed |
Strategies for the Development of Spectral Models for Soil Organic Matter Estimation |
title_sort |
strategies for the development of spectral models for soil organic matter estimation |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-04-01 |
description |
Visible (V), Near Infrared (NIR) and Short Waves Infrared (SWIR) spectroscopy has been indicated as a promising tool in soil studies, especially in the last decade. However, in order to apply this method, it is necessary to develop prediction models with the capacity to capture the intrinsic differences between agricultural areas and incorporate them in the modeling process. High quality estimates are generally obtained when these models are applied to soil samples displaying characteristics similar to the samples used in their construction. However, low quality predictions are noted when applied to samples from new areas presenting different characteristics. One way to solve this problem is by recalibrating the models using selected samples from the area of interest. Based on this premise, the aim of this study was to use the spiking technique and spiking associated with hybridization to expand prediction models and estimate organic matter content in a target area undergoing different uses and management. A total of 425 soil samples were used for the generation of the state model, as well as 200 samples from a target area to select the subsets (10 samples) used for model recalibration. The spectral readings of the samples were obtained in the laboratory using the ASD FieldSpec 3 Jr. Sensor from 350 to 2500 nm. The spectral curves of the samples were then associated to the soil attributes by means of a partial least squares regression (PLSR). The state model obtained better results when recalibrated with samples selected through a cluster analysis. The use of hybrid spectral curves did not generate significant improvements, presenting estimates, in most cases, lower than the state model applied without recalibration. The use of the isolated spiking technique was more effective in comparison with the spiked and hybridized state models, reaching r<sup>2</sup>, square root of mean prediction error (RMSEP) and ratio of performance to deviation (RPD) values of 0.43, 4.4 g dm<sup>−3</sup>, and 1.36, respectively. |
topic |
PLSR hybrid curves reflectance recalibration spiking |
url |
https://www.mdpi.com/2072-4292/13/7/1376 |
work_keys_str_mv |
AT eversoncezar strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT marcosrafaelnanni strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT luisguilhermeteixeiracrusiol strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT liangsun strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT monicasaciotochicati strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT renatoherrigfurlanetto strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT marlonrodrigues strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT rubsonnatalribeirosibaldelli strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT guilhermefernandocapristosilva strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT karymmayaradeoliveira strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation AT joseamdematte strategiesforthedevelopmentofspectralmodelsforsoilorganicmatterestimation |
_version_ |
1721544510014488576 |