Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis
Soil organic carbon (SOC) is a crucial factor influencing soil quality and fertility. In this particular investigation, we aimed to explore the possibility of using diffuse reflectance infrared fourier transform spectroscopy (DRIFT-FTIR) in conjunction with machine-learning models, such as partial l...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Soil Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-8789/8/1/22 |
| _version_ | 1827304995783966720 |
|---|---|
| author | Fatma N. Thabit Osama I. A. Negim Mohamed A. E. AbdelRahman Antonio Scopa Ali R. A. Moursy |
| author_facet | Fatma N. Thabit Osama I. A. Negim Mohamed A. E. AbdelRahman Antonio Scopa Ali R. A. Moursy |
| author_sort | Fatma N. Thabit |
| collection | DOAJ |
| description | Soil organic carbon (SOC) is a crucial factor influencing soil quality and fertility. In this particular investigation, we aimed to explore the possibility of using diffuse reflectance infrared fourier transform spectroscopy (DRIFT-FTIR) in conjunction with machine-learning models, such as partial least squares regression (PLSR), artificial neural networks (ANN), support vector regression (SVR) and random forest (RF), to estimate SOC in Sohag, Egypt. To achieve this, we collected a total of ninety surface soil samples from various locations in Sohag and estimated the total organic carbon content using both the Walkley-Black method and DRIFT-FTIR spectroscopy. Subsequently, we used the spectral data to develop regression models using PLSR, ANN, SVR, and RF. To evaluate the performance of these models, we used several evaluation parameters, including root mean square error (RMSE), coefficient of determination (R<sup>2</sup>), and ratio of performance deviation (RPD). Our survey results revealed that the PLSR model had the most favorable performance, yielding an R<sup>2</sup> value of 0.82 and an RMSE of 0.006%. In contrast, the ANN, SVR, and RF models demonstrated moderate to poor performance, with R<sup>2</sup> values of 0.53, 0.27, and 0.18, respectively. Overall, our study highlights the potential of combining DRIFT-FTIR spectroscopy with multivariate analysis techniques to predict SOC in Sohag, Egypt. However, additional studies and research are needed to improve the accuracy or predictability of machine-learning models incorporated into DRIFT-FTIR analysis and to compare DRIFT-FTIR analysis techniques with conventional soil chemical measurements. |
| first_indexed | 2024-04-24T17:49:42Z |
| format | Article |
| id | doaj.art-a79c1e5d14b54d058eaf7d61844c0076 |
| institution | Directory Open Access Journal |
| issn | 2571-8789 |
| language | English |
| last_indexed | 2024-04-24T17:49:42Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Soil Systems |
| spelling | doaj.art-a79c1e5d14b54d058eaf7d61844c00762024-03-27T14:04:51ZengMDPI AGSoil Systems2571-87892024-02-01812210.3390/soilsystems8010022Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical AnalysisFatma N. Thabit0Osama I. A. Negim1Mohamed A. E. AbdelRahman2Antonio Scopa3Ali R. A. Moursy4Soil and Water Department, Faculty of Agriculture, Sohag University, Sohag 82524, EgyptSoil and Water Department, Faculty of Agriculture, Sohag University, Sohag 82524, EgyptDivision of Environmental Studies and Land Use, National Authority for Remote Sensing and Space Sciences (NARSS), Cairo 11769, EgyptScuola di Scienze Agrarie, Forestali, Alimentari ed Ambientali (SAFE), Università degli Studi della Basilicata, Via dell’Ateneo Lucano 10, 85100 Potenza, ItalySoil and Water Department, Faculty of Agriculture, Sohag University, Sohag 82524, EgyptSoil organic carbon (SOC) is a crucial factor influencing soil quality and fertility. In this particular investigation, we aimed to explore the possibility of using diffuse reflectance infrared fourier transform spectroscopy (DRIFT-FTIR) in conjunction with machine-learning models, such as partial least squares regression (PLSR), artificial neural networks (ANN), support vector regression (SVR) and random forest (RF), to estimate SOC in Sohag, Egypt. To achieve this, we collected a total of ninety surface soil samples from various locations in Sohag and estimated the total organic carbon content using both the Walkley-Black method and DRIFT-FTIR spectroscopy. Subsequently, we used the spectral data to develop regression models using PLSR, ANN, SVR, and RF. To evaluate the performance of these models, we used several evaluation parameters, including root mean square error (RMSE), coefficient of determination (R<sup>2</sup>), and ratio of performance deviation (RPD). Our survey results revealed that the PLSR model had the most favorable performance, yielding an R<sup>2</sup> value of 0.82 and an RMSE of 0.006%. In contrast, the ANN, SVR, and RF models demonstrated moderate to poor performance, with R<sup>2</sup> values of 0.53, 0.27, and 0.18, respectively. Overall, our study highlights the potential of combining DRIFT-FTIR spectroscopy with multivariate analysis techniques to predict SOC in Sohag, Egypt. However, additional studies and research are needed to improve the accuracy or predictability of machine-learning models incorporated into DRIFT-FTIR analysis and to compare DRIFT-FTIR analysis techniques with conventional soil chemical measurements.https://www.mdpi.com/2571-8789/8/1/22DRIFT-FTIR spectroscopysoil organic carbonPLSRANNSVRRF |
| spellingShingle | Fatma N. Thabit Osama I. A. Negim Mohamed A. E. AbdelRahman Antonio Scopa Ali R. A. Moursy Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis Soil Systems DRIFT-FTIR spectroscopy soil organic carbon PLSR ANN SVR RF |
| title | Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis |
| title_full | Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis |
| title_fullStr | Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis |
| title_full_unstemmed | Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis |
| title_short | Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis |
| title_sort | using various models for predicting soil organic carbon based on drift ftir and chemical analysis |
| topic | DRIFT-FTIR spectroscopy soil organic carbon PLSR ANN SVR RF |
| url | https://www.mdpi.com/2571-8789/8/1/22 |
| work_keys_str_mv | AT fatmanthabit usingvariousmodelsforpredictingsoilorganiccarbonbasedondriftftirandchemicalanalysis AT osamaianegim usingvariousmodelsforpredictingsoilorganiccarbonbasedondriftftirandchemicalanalysis AT mohamedaeabdelrahman usingvariousmodelsforpredictingsoilorganiccarbonbasedondriftftirandchemicalanalysis AT antonioscopa usingvariousmodelsforpredictingsoilorganiccarbonbasedondriftftirandchemicalanalysis AT aliramoursy usingvariousmodelsforpredictingsoilorganiccarbonbasedondriftftirandchemicalanalysis |