A Comparative Study of Machine Learning Models with Hyperparameter Optimization Algorithm for Mapping Mineral Prospectivity

Selecting internal hyperparameters, which can be set by the automatic search algorithm, is important to improve the generalization performance of machine learning models. In this study, the geological, remote sensing and geochemical data of the Lalingzaohuo area in Qinghai province were researched. A multi-source metallogenic information spatial data set was constructed by calculating the Youden index for selecting potential evidence layers. The model for mapping mineral prospectivity of the study area was established by combining two swarm intelligence optimization algorithms, namely the bat algorithm (BA) and the firefly algorithm (FA), with different machine learning models. The receiver operating characteristic (ROC) and prediction-area (P-A) curves were used for performance evaluation and showed that the two algorithms had an obvious optimization effect. The BA and FA differentiated in improving multilayer perceptron (MLP), AdaBoost and one-class support vector machine (OCSVM) models; thus, there was no optimization algorithm that was consistently superior to the other. However, the accuracy of the machine learning models was significantly enhanced after optimizing the hyperparameters. The area under curve (AUC) values of the ROC curve of the optimized machine learning models were all higher than 0.8, indicating that the hyperparameter optimization calculation was effective. In terms of individual model improvement, the accuracy of the FA-AdaBoost model was improved the most significantly, with the AUC value increasing from 0.8173 to 0.9597 and the prediction/area (P/A) value increasing from 3.156 to 10.765, where the mineral targets predicted by the model occupied 8.63% of the study area and contained 92.86% of the known mineral deposits. The targets predicted by the improved machine learning models are consistent with the metallogenic geological characteristics, indicating that the swarm intelligence optimization algorithm combined with the machine learning model is an efficient method for mineral prospectivity mapping.

[1]  Yu-Rong Zeng,et al.  Effective sparse adaboost method with ESN and FOA for industrial electricity consumption forecasting in China , 2018, Energy.

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Mohamed Elhoseny,et al.  Automated toxicity test model based on a bio-inspired technique and AdaBoost classifier , 2018, Comput. Electr. Eng..

[4]  Si Wu,et al.  Improving support vector machine classifiers by modifying kernel functions , 1999, Neural Networks.

[5]  Renguang Zuo,et al.  GIS-based rare events logistic regression for mineral prospectivity mapping , 2018, Comput. Geosci..

[6]  C. Larbes,et al.  Bat algorithm based maximum power point tracking for photovoltaic system under partial shading conditions , 2017 .

[7]  Mahyar Yousefi,et al.  Prediction-area (P-A) plot and C-A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling , 2015, Comput. Geosci..

[8]  Mohammed Essaid Riffi,et al.  Incorporating a modified uniform crossover and 2-exchange neighborhood mechanism in a discrete bat algorithm to solve the quadratic assignment problem , 2017 .

[9]  Latifa Dekhici,et al.  A Firefly Algorithm for the Mono-Processors Hybrid Flow Shop Problem , 2017 .

[10]  Guo-Xing Wen,et al.  Fuzzy Neural Network-Based Adaptive Control for a Class of Uncertain Nonlinear Stochastic Systems , 2014, IEEE Transactions on Cybernetics.

[11]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[12]  David A. Landgrebe,et al.  A survey of decision tree classifier methodology , 1991, IEEE Trans. Syst. Man Cybern..

[13]  Natarajan Sriraam,et al.  Optimal configuration of multilayer perceptron neural network classifier for recognition of intracranial epileptic seizures , 2017, Expert Syst. Appl..

[14]  Lin Li,et al.  Featured temporal segmentation method and AdaBoost-BP detector for internal leakage evaluation of a hydraulic cylinder , 2018, Measurement.

[15]  Carlos A. Coello Coello,et al.  Handling multiple objectives with particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[16]  Yongliang Chen,et al.  Mapping mineral prospectivity using an extreme learning machine regression , 2017 .

[17]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[18]  Mohamed A. Tawhid,et al.  Multi-directional bat algorithm for solving unconstrained optimization problems , 2017 .

[19]  Silvio Romero de Lemos Meira,et al.  A class of hybrid multilayer perceptrons for software development effort estimation problems , 2017, Expert Syst. Appl..

[20]  Hao Wu,et al.  Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification , 2018, IEEE Transactions on Image Processing.

[21]  Padmavathi Kora,et al.  ECG based Myocardial Infarction detection using Hybrid Firefly Algorithm , 2017, Comput. Methods Programs Biomed..

[22]  P. Lakshminarayana,et al.  Automatic Generation and Optimization of Test case using Hybrid Cuckoo Search and Bee Colony Algorithm , 2020, J. Intell. Syst..

[23]  Emmanuel John M. Carranza,et al.  Data-Driven Index Overlay and Boolean Logic Mineral Prospectivity Modeling in Greenfields Exploration , 2016, Natural Resources Research.

[24]  Yongliang Chen,et al.  A Bat-Optimized One-Class Support Vector Machine for Mineral Prospectivity Mapping , 2019, Minerals.

[25]  Alessandro De Gloria,et al.  Clustered Boltzmann Machines: Massively Parallel Architectures for Constrained Optimization Problems , 1993, Parallel Comput..

[26]  Paul F. Pinsky,et al.  Scaling of True and Apparent ROC AUC with Number of Observations and Number of Variables , 2005 .

[27]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[28]  Yi Liu,et al.  SemiBoost: Boosting for Semi-Supervised Learning , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Haydemar Núñez,et al.  Handling binary classification problems with a priority class by using Support Vector Machines , 2017, Appl. Soft Comput..

[30]  Y. Chen,et al.  Mapping mineral prospectivity by using one-class support vector machine to identify multivariate geological anomalies from digital geological survey data , 2017 .

[31]  Yan Zhang,et al.  Recognition of diseased Pinus trees in UAV images using deep learning and AdaBoost classifier , 2020 .

[32]  Yongliang Chen,et al.  A prospecting cost-benefit strategy for mineral potential mapping based on ROC curve analysis , 2016 .

[33]  Héctor Quintián-Pardo,et al.  Comparative Study of One-Class Based Anomaly Detection Techniques for a Bicomponent Mixing Machine Monitoring , 2020, Cybern. Syst..

[34]  R. Bergmann,et al.  Different Outcomes of the Wilcoxon—Mann—Whitney Test from Different Statistics Packages , 2000 .

[35]  M. R. Seddighian,et al.  Simultaneously multi-material layout, and connectivity optimization of truss structures via an Enriched Firefly Algorithm , 2020 .

[36]  Debasish Ghose,et al.  Formations of minimalist mobile robots using local-templates and spatially distributed interactions , 2005, Robotics Auton. Syst..

[37]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[38]  Xin-She Yang,et al.  Bat algorithm: a novel approach for global engineering optimization , 2012, 1211.6663.

[39]  Fabricio A. Chiappini,et al.  Sensitivity for Multivariate Calibration based on Multilayer Perceptron Artificial Neural Networks. , 2020, Analytical chemistry.

[40]  Yongliang Chen,et al.  Mineral Potential Mapping Using a Conjugate Gradient Logistic Regression Model , 2019, Natural Resources Research.

[41]  Yongliang Chen,et al.  A Bat Algorithm-Based Data-Driven Model for Mineral Prospectivity Mapping , 2019, Natural Resources Research.

[42]  Nancy A Obuchowski,et al.  Receiver operating characteristic (ROC) curves: review of methods with applications in diagnostic medicine , 2018, Physics in medicine and biology.

[43]  Mahyar Yousefi,et al.  Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping , 2015, Comput. Geosci..

[44]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[45]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[46]  R. Raja,et al.  Parameter optimization of 5.5 GHz low noise amplifier using multi-objective Firefly Algorithm , 2018, Microsystem Technologies.

[47]  Jian Wang,et al.  Mapping Mineral Prospectivity via Semi-supervised Random Forest , 2019, Natural Resources Research.

[48]  Hossam Faris,et al.  Unsupervised intelligent system based on one class support vector machine and Grey Wolf optimization for IoT botnet detection , 2019, Journal of Ambient Intelligence and Humanized Computing.

[49]  Q. Cheng,et al.  Application of singularity analysis for mineral potential identification using geochemical data — A case study: Nanling W–Sn–Mo polymetallic metallogenic belt, South China , 2013 .

[50]  Aidin Delgoshaei,et al.  A multi-layer perceptron for scheduling cellular manufacturing systems in the presence of unreliable machines and uncertain cost , 2016, Appl. Soft Comput..

[51]  Gerhard-Wilhelm Weber,et al.  A classification problem of credit risk rating investigated and solved by optimisation of the ROC curve , 2012, Central Eur. J. Oper. Res..

[52]  Seung Jun Lee,et al.  Comparison of Multilayer Perceptron and Long Short-Term Memory for Plant Parameter Trend Prediction , 2020 .

[53]  Yi Gu,et al.  Energy-aware workflow scheduling and optimization in clouds using bat algorithm , 2020, Future Gener. Comput. Syst..

[54]  Xin-She Yang,et al.  A New Metaheuristic Bat-Inspired Algorithm , 2010, NICSO.

[55]  C. Dragos,et al.  ROC curve for discrete choice models an application to the Romanian car market , 2010 .

[56]  Fang Yu,et al.  Intelligent Islanding Detection Method for Photovoltaic Power System Considering the Inter-Connection Relationship of the Electrical Parameters , 2020 .

[57]  Sheng-De Wang,et al.  Fuzzy support vector machines , 2002, IEEE Trans. Neural Networks.

[58]  Yuan-chin Ivan Chang,et al.  A modified area under the ROC curve and its application to marker selection and classification , 2014 .

[59]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[60]  Fei Chen,et al.  Data-Driven Predictive Modelling of Mineral Prospectivity Using Machine Learning and Deep Learning Methods: A Case Study from Southern Jiangxi Province, China , 2020, Minerals.

[61]  Oliver Kuss,et al.  A modified Wald interval for the area under the ROC curve (AUC) in diagnostic case-control studies , 2014, BMC Medical Research Methodology.

[62]  Anil K. Jain,et al.  Unsupervised Learning of Finite Mixture Models , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[63]  Yue Liu,et al.  A MaxEnt Model for Mineral Prospectivity Mapping , 2018, Natural Resources Research.

[64]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[65]  Yu-Lin He,et al.  Fuzziness based semi-supervised learning approach for intrusion detection system , 2017, Inf. Sci..

[66]  Qing Xu,et al.  System reliability analysis of slopes using multilayer perceptron and radial basis function networks , 2017 .

[67]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[68]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[69]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.