Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods
Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/19/4806 |
| _version_ | 1797575243543347200 |
|---|---|
| author | Alireza Hamedianfar Kati Laakso Maarit Middleton Tuomo Törmänen Juha Köykkä Johanna Torppa |
| author_facet | Alireza Hamedianfar Kati Laakso Maarit Middleton Tuomo Törmänen Juha Köykkä Johanna Torppa |
| author_sort | Alireza Hamedianfar |
| collection | DOAJ |
| description | Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted. |
| first_indexed | 2024-03-10T21:35:58Z |
| format | Article |
| id | doaj.art-98da22ca113a466daefb8cc26a7d0347 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T21:35:58Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-98da22ca113a466daefb8cc26a7d03472023-11-19T15:00:13ZengMDPI AGRemote Sensing2072-42922023-10-011519480610.3390/rs15194806Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning MethodsAlireza Hamedianfar0Kati Laakso1Maarit Middleton2Tuomo Törmänen3Juha Köykkä4Johanna Torppa5Geological Survey of Finland, Information Solutions Unit, P.O. Box 96, FI-02151 Espoo, FinlandGeological Survey of Finland, Information Solutions Unit, P.O. Box 96, FI-02151 Espoo, FinlandGeological Survey of Finland, Information Solutions Unit, P.O. Box 77, FI-96101 Rovaniemi, FinlandGeological Survey of Finland, Mineral Economy Solutions Unit, P.O. Box 77, FI-96101 Rovaniemi, FinlandGeological Survey of Finland, Information Solutions Unit, P.O. Box 77, FI-96101 Rovaniemi, FinlandGeological Survey of Finland, Information Solutions Unit, P.O. Box 1237, FI-70211 Kuopio, FinlandLaboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted.https://www.mdpi.com/2072-4292/15/19/4806drill corehyperspectral imagingdeep learningensemble machine learning |
| spellingShingle | Alireza Hamedianfar Kati Laakso Maarit Middleton Tuomo Törmänen Juha Köykkä Johanna Torppa Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods Remote Sensing drill core hyperspectral imaging deep learning ensemble machine learning |
| title | Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods |
| title_full | Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods |
| title_fullStr | Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods |
| title_full_unstemmed | Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods |
| title_short | Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods |
| title_sort | leveraging high resolution long wave infrared hyperspectral laboratory imaging data for mineral identification using machine learning methods |
| topic | drill core hyperspectral imaging deep learning ensemble machine learning |
| url | https://www.mdpi.com/2072-4292/15/19/4806 |
| work_keys_str_mv | AT alirezahamedianfar leveraginghighresolutionlongwaveinfraredhyperspectrallaboratoryimagingdataformineralidentificationusingmachinelearningmethods AT katilaakso leveraginghighresolutionlongwaveinfraredhyperspectrallaboratoryimagingdataformineralidentificationusingmachinelearningmethods AT maaritmiddleton leveraginghighresolutionlongwaveinfraredhyperspectrallaboratoryimagingdataformineralidentificationusingmachinelearningmethods AT tuomotormanen leveraginghighresolutionlongwaveinfraredhyperspectrallaboratoryimagingdataformineralidentificationusingmachinelearningmethods AT juhakoykka leveraginghighresolutionlongwaveinfraredhyperspectrallaboratoryimagingdataformineralidentificationusingmachinelearningmethods AT johannatorppa leveraginghighresolutionlongwaveinfraredhyperspectrallaboratoryimagingdataformineralidentificationusingmachinelearningmethods |