Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models
In an effort to improve the efficiency of soil classification, traditional methods are being combined with analytical and computational techniques. This integration has strengthened the connection between conventional classification and the application of machine-learning (ML) models to interpret so...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/19/4859 |
| _version_ | 1797575254166470656 |
|---|---|
| author | Karym Mayara de Oliveira Renan Falcioni João Vitor Ferreira Gonçalves Caio Almeida de Oliveira Weslei Augusto Mendonça Luís Guilherme Teixeira Crusiol Roney Berti de Oliveira Renato Herrig Furlanetto Amanda Silveira Reis Marcos Rafael Nanni |
| author_facet | Karym Mayara de Oliveira Renan Falcioni João Vitor Ferreira Gonçalves Caio Almeida de Oliveira Weslei Augusto Mendonça Luís Guilherme Teixeira Crusiol Roney Berti de Oliveira Renato Herrig Furlanetto Amanda Silveira Reis Marcos Rafael Nanni |
| author_sort | Karym Mayara de Oliveira |
| collection | DOAJ |
| description | In an effort to improve the efficiency of soil classification, traditional methods are being combined with analytical and computational techniques. This integration has strengthened the connection between conventional classification and the application of machine-learning (ML) models to interpret soil spectral reflectance data. Due to the time and computational cost, several studies are limited to testing the classification performance of a few algorithms and do not always explore the best parameters for model optimization. The study aims to assess the efficiency of combining soil spectral reflectance with prevalent ML models for classifying pedogenetic horizons and soil suborders, enhancing traditional classification methods. We collected seven soil monoliths, previously classified according to the Brazilian Soil Classification System (SiBCS) and soil taxonomy. Using the ASD Fieldspec spectroradiometer, we obtained spectral reflectance samples along each monolith (<i>n</i> = 800 per monolith) to classify horizons and <i>n</i> = 5600 for suborder classification. Spectral fingerprints were obtained and explored by Principal Component Analysis (PCA). The spectral data were subdivided into training (70%) and test (30%) sets and submitted to the Logistic Regression (LR), Artificial Neural Network (NN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB) models for the classification of horizons and suborders, considering the model’s adjustment parameters. Accuracy and F-Score were used to verify the performance of the models. There was a significant influence of particle size and soil organic carbon on the spectral fingerprint of the soils. The PCA indicated that topsoil horizons clustered in most of the monoliths analyzed, while most of the subsoil horizons showed data overlap. The NN model showed the highest accuracy in the classification of horizons (97%), while the SVM showed the lowest performance (52% accuracy). The classification of soil suborders presented accuracies between 95% and 98%. Therefore, our study concludes that spectral data combined with ML models can enhance the discrimination and classification of soil horizons and suborders, improving upon traditional methods. |
| first_indexed | 2024-03-10T21:36:07Z |
| format | Article |
| id | doaj.art-bf3b2d86b0de4379a769f26dd1e50cec |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T21:36:07Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-bf3b2d86b0de4379a769f26dd1e50cec2023-11-19T15:00:56ZengMDPI AGRemote Sensing2072-42922023-10-011519485910.3390/rs15194859Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning ModelsKarym Mayara de Oliveira0Renan Falcioni1João Vitor Ferreira Gonçalves2Caio Almeida de Oliveira3Weslei Augusto Mendonça4Luís Guilherme Teixeira Crusiol5Roney Berti de Oliveira6Renato Herrig Furlanetto7Amanda Silveira Reis8Marcos Rafael Nanni9Graduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilEmbrapa Soja (Empresa Brasileira de Pesquisa Agropecuária), Londrina 86001-970, BrazilGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilGulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USAGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilGraduate Program in Agronomy, Department of Agronomy, State University of Maringá, Av. Colombo, 5790, Maringa 87020-900, BrazilIn an effort to improve the efficiency of soil classification, traditional methods are being combined with analytical and computational techniques. This integration has strengthened the connection between conventional classification and the application of machine-learning (ML) models to interpret soil spectral reflectance data. Due to the time and computational cost, several studies are limited to testing the classification performance of a few algorithms and do not always explore the best parameters for model optimization. The study aims to assess the efficiency of combining soil spectral reflectance with prevalent ML models for classifying pedogenetic horizons and soil suborders, enhancing traditional classification methods. We collected seven soil monoliths, previously classified according to the Brazilian Soil Classification System (SiBCS) and soil taxonomy. Using the ASD Fieldspec spectroradiometer, we obtained spectral reflectance samples along each monolith (<i>n</i> = 800 per monolith) to classify horizons and <i>n</i> = 5600 for suborder classification. Spectral fingerprints were obtained and explored by Principal Component Analysis (PCA). The spectral data were subdivided into training (70%) and test (30%) sets and submitted to the Logistic Regression (LR), Artificial Neural Network (NN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB) models for the classification of horizons and suborders, considering the model’s adjustment parameters. Accuracy and F-Score were used to verify the performance of the models. There was a significant influence of particle size and soil organic carbon on the spectral fingerprint of the soils. The PCA indicated that topsoil horizons clustered in most of the monoliths analyzed, while most of the subsoil horizons showed data overlap. The NN model showed the highest accuracy in the classification of horizons (97%), while the SVM showed the lowest performance (52% accuracy). The classification of soil suborders presented accuracies between 95% and 98%. Therefore, our study concludes that spectral data combined with ML models can enhance the discrimination and classification of soil horizons and suborders, improving upon traditional methods.https://www.mdpi.com/2072-4292/15/19/4859data modelingpredictive modelreflectanceremote sensingsoil spectral behaviorsoil classification |
| spellingShingle | Karym Mayara de Oliveira Renan Falcioni João Vitor Ferreira Gonçalves Caio Almeida de Oliveira Weslei Augusto Mendonça Luís Guilherme Teixeira Crusiol Roney Berti de Oliveira Renato Herrig Furlanetto Amanda Silveira Reis Marcos Rafael Nanni Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models Remote Sensing data modeling predictive model reflectance remote sensing soil spectral behavior soil classification |
| title | Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models |
| title_full | Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models |
| title_fullStr | Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models |
| title_full_unstemmed | Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models |
| title_short | Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models |
| title_sort | rapid determination of soil horizons and suborders based on vis nir swir spectroscopy and machine learning models |
| topic | data modeling predictive model reflectance remote sensing soil spectral behavior soil classification |
| url | https://www.mdpi.com/2072-4292/15/19/4859 |
| work_keys_str_mv | AT karymmayaradeoliveira rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT renanfalcioni rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT joaovitorferreiragoncalves rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT caioalmeidadeoliveira rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT wesleiaugustomendonca rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT luisguilhermeteixeiracrusiol rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT roneybertideoliveira rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT renatoherrigfurlanetto rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT amandasilveirareis rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels AT marcosrafaelnanni rapiddeterminationofsoilhorizonsandsubordersbasedonvisnirswirspectroscopyandmachinelearningmodels |