Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir
The knowledge about the spatial distribution of soil organic carbon stock (SOCS) helps in sustainable land-use management and ecosystem functioning. No such study has been attempted in the complex topography and land use of Himalayas, which is associated with great spatial heterogeneity and uncertai...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/11/12/2180 |
| _version_ | 1797456804994613248 |
|---|---|
| author | Iqra Farooq Shabir Ahmed Bangroo Owais Bashir Tajamul Islam Shah Ajaz A. Malik Asif M. Iqbal Syed Sheraz Mahdi Owais Ali Wani Nageena Nazir Asim Biswas |
| author_facet | Iqra Farooq Shabir Ahmed Bangroo Owais Bashir Tajamul Islam Shah Ajaz A. Malik Asif M. Iqbal Syed Sheraz Mahdi Owais Ali Wani Nageena Nazir Asim Biswas |
| author_sort | Iqra Farooq |
| collection | DOAJ |
| description | The knowledge about the spatial distribution of soil organic carbon stock (SOCS) helps in sustainable land-use management and ecosystem functioning. No such study has been attempted in the complex topography and land use of Himalayas, which is associated with great spatial heterogeneity and uncertainties. Therefore, in this study digital soil mapping (DSM) was used to predict and evaluate the spatial distribution of SOCS using advanced geostatistical methods and a machine learning algorithm in the Himalayan region of Jammu and Kashmir, India. Eighty-three soil samples were collected across different land uses. Auxiliary variables (spectral indices and topographic parameters) derived from satellite data were used as predictors. Geostatistical methods—ordinary kriging (OK) and regression kriging (RK)—and a machine learning method—random forest (RF)—were used for assessing the spatial distribution and variability of SOCS with inter-comparison of models for their prediction performance. The best fit model validation criteria used were coefficient of determination (R2) and root mean square error (RMSE) with resulting maps validated by cross-validation. The SOCS concentration varied from 1.12 Mg/ha to 70.60 Mg/ha. The semivariogram analysis of OK and RK indicated moderate spatial dependence. RF (RMSE = 8.21) performed better than OK (RMSE = 15.60) and RK (RMSE = 17.73) while OK performed better than RK. Therefore, it may be concluded that RF provides better estimation and spatial variability of SOCS; however, further selection and choice of auxiliary variables and higher soil sampling density could improve the accuracy of RK prediction. |
| first_indexed | 2024-03-09T16:12:14Z |
| format | Article |
| id | doaj.art-a6e97d7b44944ccfa11e6475356e071a |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-09T16:12:14Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-a6e97d7b44944ccfa11e6475356e071a2023-11-24T16:06:44ZengMDPI AGLand2073-445X2022-12-011112218010.3390/land11122180Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of KashmirIqra Farooq0Shabir Ahmed Bangroo1Owais Bashir2Tajamul Islam Shah3Ajaz A. Malik4Asif M. Iqbal5Syed Sheraz Mahdi6Owais Ali Wani7Nageena Nazir8Asim Biswas9Division of Soil Science, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaDivision of Soil Science, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaDivision of Soil Science, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaDivision of Soil Science, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaFaculty of Horticulture, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaFaculty of Agriculture, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaFaculty of Agriculture, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaFaculty of Agriculture, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaDivision of Agricultural Statistics, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir, Shalimar 190025, Jammu and Kashmir, IndiaSchool of Environmental Sciences, University of Guelph, 50 Stone Road East, Guelph, ON N1G 2W1, CanadaThe knowledge about the spatial distribution of soil organic carbon stock (SOCS) helps in sustainable land-use management and ecosystem functioning. No such study has been attempted in the complex topography and land use of Himalayas, which is associated with great spatial heterogeneity and uncertainties. Therefore, in this study digital soil mapping (DSM) was used to predict and evaluate the spatial distribution of SOCS using advanced geostatistical methods and a machine learning algorithm in the Himalayan region of Jammu and Kashmir, India. Eighty-three soil samples were collected across different land uses. Auxiliary variables (spectral indices and topographic parameters) derived from satellite data were used as predictors. Geostatistical methods—ordinary kriging (OK) and regression kriging (RK)—and a machine learning method—random forest (RF)—were used for assessing the spatial distribution and variability of SOCS with inter-comparison of models for their prediction performance. The best fit model validation criteria used were coefficient of determination (R2) and root mean square error (RMSE) with resulting maps validated by cross-validation. The SOCS concentration varied from 1.12 Mg/ha to 70.60 Mg/ha. The semivariogram analysis of OK and RK indicated moderate spatial dependence. RF (RMSE = 8.21) performed better than OK (RMSE = 15.60) and RK (RMSE = 17.73) while OK performed better than RK. Therefore, it may be concluded that RF provides better estimation and spatial variability of SOCS; however, further selection and choice of auxiliary variables and higher soil sampling density could improve the accuracy of RK prediction.https://www.mdpi.com/2073-445X/11/12/2180predictive soil mappingordinary krigingregression krigingrandom forestTaylor diagramsemivariogram |
| spellingShingle | Iqra Farooq Shabir Ahmed Bangroo Owais Bashir Tajamul Islam Shah Ajaz A. Malik Asif M. Iqbal Syed Sheraz Mahdi Owais Ali Wani Nageena Nazir Asim Biswas Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir Land predictive soil mapping ordinary kriging regression kriging random forest Taylor diagram semivariogram |
| title | Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir |
| title_full | Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir |
| title_fullStr | Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir |
| title_full_unstemmed | Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir |
| title_short | Comparison of Random Forest and Kriging Models for Soil Organic Carbon Mapping in the Himalayan Region of Kashmir |
| title_sort | comparison of random forest and kriging models for soil organic carbon mapping in the himalayan region of kashmir |
| topic | predictive soil mapping ordinary kriging regression kriging random forest Taylor diagram semivariogram |
| url | https://www.mdpi.com/2073-445X/11/12/2180 |
| work_keys_str_mv | AT iqrafarooq comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT shabirahmedbangroo comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT owaisbashir comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT tajamulislamshah comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT ajazamalik comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT asifmiqbal comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT syedsherazmahdi comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT owaisaliwani comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT nageenanazir comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir AT asimbiswas comparisonofrandomforestandkrigingmodelsforsoilorganiccarbonmappinginthehimalayanregionofkashmir |