Estimation of Mineral Resources with Machine Learning Techniques
In this study, the application of adaptive fuzzy inference systems (ANFISs) and artificial neural networks (NNs) for grade and reserve estimation of a copper deposit was studied. More specifically, a feedforward NN with backpropagation and two Sugeno- type ANFIS were developed for grade and reserve...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Materials Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4605/5/1/122 |
| _version_ | 1797610366675451904 |
|---|---|
| author | Michael Galetakis Anthoula Vasileiou Antonia Rogdaki Vasilios Deligiorgis Stella Raka |
| author_facet | Michael Galetakis Anthoula Vasileiou Antonia Rogdaki Vasilios Deligiorgis Stella Raka |
| author_sort | Michael Galetakis |
| collection | DOAJ |
| description | In this study, the application of adaptive fuzzy inference systems (ANFISs) and artificial neural networks (NNs) for grade and reserve estimation of a copper deposit was studied. More specifically, a feedforward NN with backpropagation and two Sugeno- type ANFIS were developed for grade and reserve estimation. Borehole assay data were used for training, validation, and testing of the NN and ANFIS. Grade estimates and tonnage–grade curves were produced and compared to those obtained using a geostatistical approach (Kriging). |
| first_indexed | 2024-03-11T06:14:13Z |
| format | Article |
| id | doaj.art-7b70c19edf044c22be3b9a47800a6a57 |
| institution | Directory Open Access Journal |
| issn | 2673-4605 |
| language | English |
| last_indexed | 2024-03-11T06:14:13Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials Proceedings |
| spelling | doaj.art-7b70c19edf044c22be3b9a47800a6a572023-11-17T12:25:26ZengMDPI AGMaterials Proceedings2673-46052022-03-015112210.3390/materproc2021005122Estimation of Mineral Resources with Machine Learning TechniquesMichael Galetakis0Anthoula Vasileiou1Antonia Rogdaki2Vasilios Deligiorgis3Stella Raka4School of Mineral Resources Engineering, Technical University of Crete, University Campus—Akrotiri, 73100 Chania, GreeceSchool of Mineral Resources Engineering, Technical University of Crete, University Campus—Akrotiri, 73100 Chania, GreeceSchool of Mineral Resources Engineering, Technical University of Crete, University Campus—Akrotiri, 73100 Chania, GreeceSchool of Mineral Resources Engineering, Technical University of Crete, University Campus—Akrotiri, 73100 Chania, GreeceSchool of Mineral Resources Engineering, Technical University of Crete, University Campus—Akrotiri, 73100 Chania, GreeceIn this study, the application of adaptive fuzzy inference systems (ANFISs) and artificial neural networks (NNs) for grade and reserve estimation of a copper deposit was studied. More specifically, a feedforward NN with backpropagation and two Sugeno- type ANFIS were developed for grade and reserve estimation. Borehole assay data were used for training, validation, and testing of the NN and ANFIS. Grade estimates and tonnage–grade curves were produced and compared to those obtained using a geostatistical approach (Kriging).https://www.mdpi.com/2673-4605/5/1/122mineral resourcesreserve estimationartificial neural networksadaptive neuro-fuzzy inference systems |
| spellingShingle | Michael Galetakis Anthoula Vasileiou Antonia Rogdaki Vasilios Deligiorgis Stella Raka Estimation of Mineral Resources with Machine Learning Techniques Materials Proceedings mineral resources reserve estimation artificial neural networks adaptive neuro-fuzzy inference systems |
| title | Estimation of Mineral Resources with Machine Learning Techniques |
| title_full | Estimation of Mineral Resources with Machine Learning Techniques |
| title_fullStr | Estimation of Mineral Resources with Machine Learning Techniques |
| title_full_unstemmed | Estimation of Mineral Resources with Machine Learning Techniques |
| title_short | Estimation of Mineral Resources with Machine Learning Techniques |
| title_sort | estimation of mineral resources with machine learning techniques |
| topic | mineral resources reserve estimation artificial neural networks adaptive neuro-fuzzy inference systems |
| url | https://www.mdpi.com/2673-4605/5/1/122 |
| work_keys_str_mv | AT michaelgaletakis estimationofmineralresourceswithmachinelearningtechniques AT anthoulavasileiou estimationofmineralresourceswithmachinelearningtechniques AT antoniarogdaki estimationofmineralresourceswithmachinelearningtechniques AT vasiliosdeligiorgis estimationofmineralresourceswithmachinelearningtechniques AT stellaraka estimationofmineralresourceswithmachinelearningtechniques |