Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India
Soil Organic Carbon (SOC) is a crucial indicator of ecosystem health and soil quality. Machine learning (ML) models that predict soil quality based on environmental parameters are becoming more prevalent. However, studies have yet to examine how well each ML technique performs when predicting and ma...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/12/10/1841 |
| _version_ | 1827720689299226624 |
|---|---|
| author | Amit Kumar Pravash Chandra Moharana Roomesh Kumar Jena Sandeep Kumar Malyan Gulshan Kumar Sharma Ram Kishor Fagodiya Aftab Ahmad Shabnam Dharmendra Kumar Jigyasu Kasthala Mary Vijaya Kumari Subramanian Gandhi Doss |
| author_facet | Amit Kumar Pravash Chandra Moharana Roomesh Kumar Jena Sandeep Kumar Malyan Gulshan Kumar Sharma Ram Kishor Fagodiya Aftab Ahmad Shabnam Dharmendra Kumar Jigyasu Kasthala Mary Vijaya Kumari Subramanian Gandhi Doss |
| author_sort | Amit Kumar |
| collection | DOAJ |
| description | Soil Organic Carbon (SOC) is a crucial indicator of ecosystem health and soil quality. Machine learning (ML) models that predict soil quality based on environmental parameters are becoming more prevalent. However, studies have yet to examine how well each ML technique performs when predicting and mapping SOC, particularly at high spatial resolutions. Model predictors include topographic variables generated from SRTM DEM; vegetation and soil indices derived from Landsat satellite images predict SOC for the Lakhimpur district of the upper Brahmaputra Valley of Assam, India. Four ML models, Random Forest (RF), Cubist, Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM), were utilized to predict SOC for the top layer of soil (0–15 cm) at a 30 m resolution. The results showed that the descriptive statistics of the calibration and validation sets were close enough to the total set data and calibration dataset, representing the complete samples. The measured SOC content varied from 0.10 to 1.85%. The RF model’s performance was optimal in the calibration and validation sets (R<sup>2</sup>c = 0.966, RMSE<sub>c</sub> = 0.159%, R<sup>2</sup>v = 0.418, RMSE<sub>v</sub> = 0.377%). The SVM model, on the other hand, had the next-lowest accuracy, explaining 47% of the variation (R<sup>2</sup>c = 0.471, RMSEc = 0.293, R<sup>2</sup>v = 0.081, RMSEv = 0.452), while the Cubist model fared the poorest in both the calibration and validation sets. The most-critical variable in the RF model for predicting SOC was elevation, followed by MAT and MRVBF. The essential variables for the Cubist model were slope, TRI, MAT, and Band4. AP and LS were the most-essential factors in the XGBoost and SVM models. The predicted OC ranged from 0.44 to 1.35%, 0.031 to 1.61%, 0.035 to 1.71%, and 0.47 to 1.36% in the RF, Cubist, XGBoost, and SVM models, respectively. Compared with different ML models, RF was optimal (high accuracy and low uncertainty) for predicting SOC in the investigated region. According to the present modeling results, SOC may be determined simply and accurately. In general, the high-resolution maps might be helpful for decision-makers, stakeholders, and applicants in sericultural management practices towards precision sericulture. |
| first_indexed | 2024-03-10T21:08:00Z |
| format | Article |
| id | doaj.art-88ae7a9488ce42b09fad1313954260a2 |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-10T21:08:00Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-88ae7a9488ce42b09fad1313954260a22023-11-19T17:03:20ZengMDPI AGLand2073-445X2023-09-011210184110.3390/land12101841Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern IndiaAmit Kumar0Pravash Chandra Moharana1Roomesh Kumar Jena2Sandeep Kumar Malyan3Gulshan Kumar Sharma4Ram Kishor Fagodiya5Aftab Ahmad Shabnam6Dharmendra Kumar Jigyasu7Kasthala Mary Vijaya Kumari8Subramanian Gandhi Doss9Central Muga Eri Research and Training Institute, Lahdoigarh, Jorhat 785700, Assam, IndiaICAR-National Bureau of Soil Survey and Land Use Planning, Nagpur 440033, Maharashtra, IndiaICAR-Indian Institute of Water Management, Bhubaneswar 751023, Odisha, IndiaDepartment of Environmental Studies, Dyal Singh Evening College, University of Delhi, New Delhi 110003, IndiaICAR-Indian Institute of Soil and Water Conservation, Research Centre, Kota 324002, Rajasthan, IndiaICAR-Central Soil Salinity Research Institute, Karnal 132001, Haryana, IndiaCentral Muga Eri Research and Training Institute, Lahdoigarh, Jorhat 785700, Assam, IndiaCentral Muga Eri Research and Training Institute, Lahdoigarh, Jorhat 785700, Assam, IndiaCentral Muga Eri Research and Training Institute, Lahdoigarh, Jorhat 785700, Assam, IndiaCentral Sericultural Research and Training Institute, Mysuru 570008, Karnataka, IndiaSoil Organic Carbon (SOC) is a crucial indicator of ecosystem health and soil quality. Machine learning (ML) models that predict soil quality based on environmental parameters are becoming more prevalent. However, studies have yet to examine how well each ML technique performs when predicting and mapping SOC, particularly at high spatial resolutions. Model predictors include topographic variables generated from SRTM DEM; vegetation and soil indices derived from Landsat satellite images predict SOC for the Lakhimpur district of the upper Brahmaputra Valley of Assam, India. Four ML models, Random Forest (RF), Cubist, Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM), were utilized to predict SOC for the top layer of soil (0–15 cm) at a 30 m resolution. The results showed that the descriptive statistics of the calibration and validation sets were close enough to the total set data and calibration dataset, representing the complete samples. The measured SOC content varied from 0.10 to 1.85%. The RF model’s performance was optimal in the calibration and validation sets (R<sup>2</sup>c = 0.966, RMSE<sub>c</sub> = 0.159%, R<sup>2</sup>v = 0.418, RMSE<sub>v</sub> = 0.377%). The SVM model, on the other hand, had the next-lowest accuracy, explaining 47% of the variation (R<sup>2</sup>c = 0.471, RMSEc = 0.293, R<sup>2</sup>v = 0.081, RMSEv = 0.452), while the Cubist model fared the poorest in both the calibration and validation sets. The most-critical variable in the RF model for predicting SOC was elevation, followed by MAT and MRVBF. The essential variables for the Cubist model were slope, TRI, MAT, and Band4. AP and LS were the most-essential factors in the XGBoost and SVM models. The predicted OC ranged from 0.44 to 1.35%, 0.031 to 1.61%, 0.035 to 1.71%, and 0.47 to 1.36% in the RF, Cubist, XGBoost, and SVM models, respectively. Compared with different ML models, RF was optimal (high accuracy and low uncertainty) for predicting SOC in the investigated region. According to the present modeling results, SOC may be determined simply and accurately. In general, the high-resolution maps might be helpful for decision-makers, stakeholders, and applicants in sericultural management practices towards precision sericulture.https://www.mdpi.com/2073-445X/12/10/1841environmental covariatespredictive mappingrandom forestsericulture soildigital SOC map |
| spellingShingle | Amit Kumar Pravash Chandra Moharana Roomesh Kumar Jena Sandeep Kumar Malyan Gulshan Kumar Sharma Ram Kishor Fagodiya Aftab Ahmad Shabnam Dharmendra Kumar Jigyasu Kasthala Mary Vijaya Kumari Subramanian Gandhi Doss Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India Land environmental covariates predictive mapping random forest sericulture soil digital SOC map |
| title | Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India |
| title_full | Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India |
| title_fullStr | Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India |
| title_full_unstemmed | Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India |
| title_short | Digital Mapping of Soil Organic Carbon Using Machine Learning Algorithms in the Upper Brahmaputra Valley of Northeastern India |
| title_sort | digital mapping of soil organic carbon using machine learning algorithms in the upper brahmaputra valley of northeastern india |
| topic | environmental covariates predictive mapping random forest sericulture soil digital SOC map |
| url | https://www.mdpi.com/2073-445X/12/10/1841 |
| work_keys_str_mv | AT amitkumar digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT pravashchandramoharana digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT roomeshkumarjena digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT sandeepkumarmalyan digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT gulshankumarsharma digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT ramkishorfagodiya digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT aftabahmadshabnam digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT dharmendrakumarjigyasu digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT kasthalamaryvijayakumari digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia AT subramaniangandhidoss digitalmappingofsoilorganiccarbonusingmachinelearningalgorithmsintheupperbrahmaputravalleyofnortheasternindia |