A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines
The necessity for applying a potent analytical regolith geochemical grade estimator is driven by the reality of mineral exploration. This is because many exploration geologists rely upon the classical geostatistical method of Kriging which oftentimes do not produce accurate predictions due to the co...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | Geosystems and Geoenvironment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772883822000176 |
| _version_ | 1818356944971235328 |
|---|---|
| author | Fareed Majeed Yao Yevenyo Ziggah Charles Kusi-Manu Bemah Ibrahim Isaac Ahenkorah |
| author_facet | Fareed Majeed Yao Yevenyo Ziggah Charles Kusi-Manu Bemah Ibrahim Isaac Ahenkorah |
| author_sort | Fareed Majeed |
| collection | DOAJ |
| description | The necessity for applying a potent analytical regolith geochemical grade estimator is driven by the reality of mineral exploration. This is because many exploration geologists rely upon the classical geostatistical method of Kriging which oftentimes do not produce accurate predictions due to the complexity of interactions between geological features and spatial variables. In this study, a novel non-linear data-driven approach known as Multivariate Adaptive Regression Spline (MARS) is proposed as an effective predictive tool to unravel regolith geochemical complexities. The proposed MARS approach was used to predict regolith geochemical grade from a thick regolith cover in the Tarkwaian paleo-placer of the South-Western Ashanti belt in Ghana. Out of the 891 samples, the data was partitioned into 70% training (model development) and 30% testing (model validation). The proposed MARS result was compared with three other artificial intelligence techniques (i.e., radial basis function neural network, backpropagation neural network and generalised regression neural network) and kriging geostatistical technique. Based on the test results, MARS had the highest correlation coefficient (R = 0.9675) and the least statistical error metrics (RMSE = 0.7791, MAE = 0.6014, and ρ = 0.0472). The implementation of the MARS approach in regolith geochemical grade estimation domain has yielded outstanding and promising results. The MARS superiority was evident in its calibration strength, prediction accuracy, robust interaction of variables and overcoming the black box system of ANN. Thus, the proposed MARS approach could be an excellent tool in regolith geochemical grade estimation workflow when fully integrated with exploration tasks. |
| first_indexed | 2024-12-13T20:05:16Z |
| format | Article |
| id | doaj.art-5fe9706a81f04f0f8cefa0a2d8f80499 |
| institution | Directory Open Access Journal |
| issn | 2772-8838 |
| language | English |
| last_indexed | 2024-12-13T20:05:16Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Geosystems and Geoenvironment |
| spelling | doaj.art-5fe9706a81f04f0f8cefa0a2d8f804992022-12-21T23:33:02ZengElsevierGeosystems and Geoenvironment2772-88382022-05-0112100038A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splinesFareed Majeed0Yao Yevenyo Ziggah1Charles Kusi-Manu2Bemah Ibrahim3Isaac Ahenkorah4Adamus Resource Limited Box 31, Esiama, W/R, GhanaDepartment of Geomatic Engineering, University of Mines and Technology, GhanaDepartment of Geology, Anglogold Iduapriem Limited, GhanaGeoxpert Limited, GhanaUniversity of South Australia, UniSA STEM, SA, 5000, Australia; Corresponding author.The necessity for applying a potent analytical regolith geochemical grade estimator is driven by the reality of mineral exploration. This is because many exploration geologists rely upon the classical geostatistical method of Kriging which oftentimes do not produce accurate predictions due to the complexity of interactions between geological features and spatial variables. In this study, a novel non-linear data-driven approach known as Multivariate Adaptive Regression Spline (MARS) is proposed as an effective predictive tool to unravel regolith geochemical complexities. The proposed MARS approach was used to predict regolith geochemical grade from a thick regolith cover in the Tarkwaian paleo-placer of the South-Western Ashanti belt in Ghana. Out of the 891 samples, the data was partitioned into 70% training (model development) and 30% testing (model validation). The proposed MARS result was compared with three other artificial intelligence techniques (i.e., radial basis function neural network, backpropagation neural network and generalised regression neural network) and kriging geostatistical technique. Based on the test results, MARS had the highest correlation coefficient (R = 0.9675) and the least statistical error metrics (RMSE = 0.7791, MAE = 0.6014, and ρ = 0.0472). The implementation of the MARS approach in regolith geochemical grade estimation domain has yielded outstanding and promising results. The MARS superiority was evident in its calibration strength, prediction accuracy, robust interaction of variables and overcoming the black box system of ANN. Thus, the proposed MARS approach could be an excellent tool in regolith geochemical grade estimation workflow when fully integrated with exploration tasks.http://www.sciencedirect.com/science/article/pii/S2772883822000176Multivariate adaptive regression splineArtificial intelligence techniquesKriging geostatistical techniqueAshanti beltGeochemical grade prediction |
| spellingShingle | Fareed Majeed Yao Yevenyo Ziggah Charles Kusi-Manu Bemah Ibrahim Isaac Ahenkorah A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines Geosystems and Geoenvironment Multivariate adaptive regression spline Artificial intelligence techniques Kriging geostatistical technique Ashanti belt Geochemical grade prediction |
| title | A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines |
| title_full | A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines |
| title_fullStr | A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines |
| title_full_unstemmed | A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines |
| title_short | A novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines |
| title_sort | novel artificial intelligence approach for regolith geochemical grade prediction using multivariate adaptive regression splines |
| topic | Multivariate adaptive regression spline Artificial intelligence techniques Kriging geostatistical technique Ashanti belt Geochemical grade prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2772883822000176 |
| work_keys_str_mv | AT fareedmajeed anovelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT yaoyevenyoziggah anovelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT charleskusimanu anovelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT bemahibrahim anovelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT isaacahenkorah anovelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT fareedmajeed novelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT yaoyevenyoziggah novelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT charleskusimanu novelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT bemahibrahim novelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines AT isaacahenkorah novelartificialintelligenceapproachforregolithgeochemicalgradepredictionusingmultivariateadaptiveregressionsplines |