Mapping several soil types using hyperspectral datasets and advanced machine learning methods
Specifying surface soil types is vital for healthy agricultural management to enhance food production. Recent advancements in machine learning are essential in soil science, quantitatively predicting and classifying soil types. The current study concentrates on generating and testing the spectral li...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Results in Optics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666950123001554 |
| _version_ | 1797733840789176320 |
|---|---|
| author | Amol D. Vibhute Karbhari V. Kale |
| author_facet | Amol D. Vibhute Karbhari V. Kale |
| author_sort | Amol D. Vibhute |
| collection | DOAJ |
| description | Specifying surface soil types is vital for healthy agricultural management to enhance food production. Recent advancements in machine learning are essential in soil science, quantitatively predicting and classifying soil types. The current study concentrates on generating and testing the spectral library to classify surface soil types. It deals with advanced machine learning methods in evaluating soil physicochemical properties and soil type classification using Spectroradiometer and satellite imagery. The proposed methodology tests Phulambri Tehsil's agricultural regions in Aurangabad district, Maharashtra, India. The soil properties determination has been accomplished using partial least square regression (PLSR) models, enabling the relationship between soil profiles and reflectance spectra. The soil type classification has been done on identified values of specific properties in sampled profiles. Machine learning methods such as PLSR, support vector machine (SVM), and spectral angle mapper (SAM), along with principal component analysis (PCA) and minimum-noise-fraction (MNF), were used. The study showed that the three major soil classes have accurately identified and mapped from satellite images using machine learning methods with more than 95% classification accuracy. The results proved to be useful for soil study in heterogeneous areas. Therefore, this study is used in precision farming to enhance food production and management. |
| first_indexed | 2024-03-12T12:35:24Z |
| format | Article |
| id | doaj.art-8d091914d94447a5ad3442ebd81b0708 |
| institution | Directory Open Access Journal |
| issn | 2666-9501 |
| language | English |
| last_indexed | 2024-03-12T12:35:24Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Optics |
| spelling | doaj.art-8d091914d94447a5ad3442ebd81b07082023-08-29T04:18:20ZengElsevierResults in Optics2666-95012023-07-0112100503Mapping several soil types using hyperspectral datasets and advanced machine learning methodsAmol D. Vibhute0Karbhari V. Kale1Symbiosis Institute of Computer Studies and Research (SICSR), Symbiosis International (Deemed University), Pune 411016, MH, India; Corresponding author.Senior Professor of Computer Science & IT, Vice-Chancellor of Dr. Babasaheb Ambedkar Technological University, Lonere 402103, MH, IndiaSpecifying surface soil types is vital for healthy agricultural management to enhance food production. Recent advancements in machine learning are essential in soil science, quantitatively predicting and classifying soil types. The current study concentrates on generating and testing the spectral library to classify surface soil types. It deals with advanced machine learning methods in evaluating soil physicochemical properties and soil type classification using Spectroradiometer and satellite imagery. The proposed methodology tests Phulambri Tehsil's agricultural regions in Aurangabad district, Maharashtra, India. The soil properties determination has been accomplished using partial least square regression (PLSR) models, enabling the relationship between soil profiles and reflectance spectra. The soil type classification has been done on identified values of specific properties in sampled profiles. Machine learning methods such as PLSR, support vector machine (SVM), and spectral angle mapper (SAM), along with principal component analysis (PCA) and minimum-noise-fraction (MNF), were used. The study showed that the three major soil classes have accurately identified and mapped from satellite images using machine learning methods with more than 95% classification accuracy. The results proved to be useful for soil study in heterogeneous areas. Therefore, this study is used in precision farming to enhance food production and management.http://www.sciencedirect.com/science/article/pii/S2666950123001554Machine learningSoil mappingSVMPartial least square regressionUSDA soil taxonomy |
| spellingShingle | Amol D. Vibhute Karbhari V. Kale Mapping several soil types using hyperspectral datasets and advanced machine learning methods Results in Optics Machine learning Soil mapping SVM Partial least square regression USDA soil taxonomy |
| title | Mapping several soil types using hyperspectral datasets and advanced machine learning methods |
| title_full | Mapping several soil types using hyperspectral datasets and advanced machine learning methods |
| title_fullStr | Mapping several soil types using hyperspectral datasets and advanced machine learning methods |
| title_full_unstemmed | Mapping several soil types using hyperspectral datasets and advanced machine learning methods |
| title_short | Mapping several soil types using hyperspectral datasets and advanced machine learning methods |
| title_sort | mapping several soil types using hyperspectral datasets and advanced machine learning methods |
| topic | Machine learning Soil mapping SVM Partial least square regression USDA soil taxonomy |
| url | http://www.sciencedirect.com/science/article/pii/S2666950123001554 |
| work_keys_str_mv | AT amoldvibhute mappingseveralsoiltypesusinghyperspectraldatasetsandadvancedmachinelearningmethods AT karbharivkale mappingseveralsoiltypesusinghyperspectraldatasetsandadvancedmachinelearningmethods |