Predicting Rock Hardness and Abrasivity Using Hyperspectral Imaging Data and Random Forest Regressor Model

被引:1
|
作者
Ghadernejad, Saleh [1 ]
Esmaeili, Kamran [1 ]
机构
[1] Univ Toronto, Dept Civil & Mineral Engn, Toronto, ON M5S 1A4, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
hyperspectral imaging; Leeb rebound hardness (LRH); Cerchar abrasivity index (CAI); random forest regressor (RFR); visible and near-infrared (VNIR); short-wave infrared (SWIR); INDEX; WEAR;
D O I
10.3390/rs16203778
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This study aimed to develop predictive models for rock hardness and abrasivity based on hyperspectral imaging data, providing valuable information without interrupting the mining processes. The data collection stage first involved scanning 159 rock samples collected from 6 different blasted rock piles using visible and near-infrared (VNIR) and short-wave infrared (SWIR) sensors. The hardness and abrasivity of the samples were then determined through Leeb rebound hardness (LRH) and Cerchar abrasivity index (CAI) tests, respectively. The data preprocessing involved radiometric correction, background removal, and staking VNIR and SWIR images. An integrated approach based on K-means clustering and the band ratio concept was employed for feature extraction, resulting in 28 band-ratio-based features. Afterward, the random forest regressor (RFR) algorithm was employed to develop predictive models for rock hardness and abrasivity separately. The performance assessment showed that the developed models can estimate rock hardness and abrasivity of unseen data with R2 scores of 0.74 and 0.79, respectively, with the most influential features located mainly within the SWIR region. The results indicate that integrated hyperspectral data and RFR technique have strong potential for practical and efficient rock hardness and abrasivity characterization during mining processes.
引用
收藏
页数:25
相关论文
共 50 条
  • [31] Passenger Counter Based on Random Forest Regressor Using Drive Recorder and Sensors in Buses
    Nakashima, Hayato
    Arai, Ismail
    Fujikawa, Kazutoshi
    2019 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS WORKSHOPS (PERCOM WORKSHOPS), 2019, : 561 - 566
  • [32] Distributed Random Forest for Predicting Forest Wildfires Based on Weather Data
    Damasevisius, Robertas
    Maskeliunas, Rytis
    ADVANCED NETWORK TECHNOLOGIES AND INTELLIGENT COMPUTING, ANTIC 2023, PT II, 2024, 2091 : 305 - 320
  • [33] Predicting student dropouts using random forest
    Devi, Kapila
    Ratnoo, Saroj
    JOURNAL OF STATISTICS AND MANAGEMENT SYSTEMS, 2022, 25 (07) : 1579 - 1590
  • [34] Identifying and Mapping Alteration Minerals Using HySpex Airborne Hyperspectral Data and Random Forest Algorithm
    Wang, Shanshan
    Zhou, Kefa
    Wang, Jinlin
    Zhao, Jie
    FRONTIERS IN EARTH SCIENCE, 2022, 10
  • [35] A random forest model for predicting exosomal proteins using evolutionary information and motifs
    Arora, Akanksha
    Patiyal, Sumeet
    Sharma, Neelam
    Devi, Naorem Leimarembi
    Kaur, Dashleen
    Raghava, Gajendra P. S.
    PROTEOMICS, 2024, 24 (06)
  • [36] Predicting curve progression for adolescent idiopathic scoliosis using random forest model
    Alfraihat, Ausilah
    Samdani, Amer F.
    Balasubramanian, Sriram
    PLOS ONE, 2022, 17 (08):
  • [37] A spectral-spatial hyperspectral data classification approach using random forest with label constraints
    Ren, Yuemei
    Zhang, Yanning
    Wei, Wei
    Ren, Yuemei
    Li, Lei
    2014 IEEE WORKSHOP ON ELECTRONICS, COMPUTER AND APPLICATIONS, 2014, : 344 - 347
  • [38] Using hyperspectral data to assess forest structure
    Ustin, SL
    Trabucco, A
    JOURNAL OF FORESTRY, 2000, 98 (06) : 47 - +
  • [40] Predicting rock hardness using Gaussian weighted moving average filter on borehole data and machine learning
    Houshmand, Negin
    Esmaeili, Kamran
    Goodfellow, Sebastian
    Ordonez-Calderon, Juan Carlos
    MINERALS ENGINEERING, 2023, 204