Chengkai Fan, Ph.D., E.I.T.

Postdoctoral Fellow, Faculty of Engineering - Civil and Environmental Engineering Dept

Pronouns: he/him

Personal Website: https://sites.google.com/ualberta.ca/dr-chengkai-fan

Contact

Postdoctoral Fellow, Faculty of Engineering - Civil and Environmental Engineering Dept
Email
cfan1@ualberta.ca
Address
6-356 Donadeo Innovation Centre For Engineering
9211 116 St
Edmonton AB
T6G 2H5

Overview

Area of Study / Keywords

Mining Engineering Machine Learning CO2 Geological Storage Fiber Optic Sensing Rock Mechanics


About

Education

  • Ph.D. in Mining Engineering, University of Alberta, Edmonton, Alberta, Canada, 2019 - 2023
  • M.Sc. in Geotechnical Engineering, Chinese Academy of Sciences, Beijing, China, 2016 - 2019
  • B.E. in Geological Engineering, Anhui University of Science and Technology, Huainan, Anhui, China, 2012 - 2016

Professional Experience

  • Assistant Instructor Professor (Sessional Instructor), Department of Civil and Environmental Engineering, University of Alberta, 2024.01 - 2024.04
  • Postdoctoral Fellow, Department of Civil and Environmental Engineering, University of Alberta, 2023.12 - Present
  • Teaching Assistant, Department of Civil and Environmental Engineering, University of Alberta, 2020.09 - 2023.04
  • Research Assistant, Department of Civil and Environmental Engineering, University of Alberta, 2019.09 - 2023.08
  • Visiting Graduate Student, Department of Civil Engineering, Monash University, 2017.08 - 2017.11
  • Research Assistant, Wuhan Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, 2016.09 - 2019.08

Professional Affiliations

  • Association of Professional Engineers and Geoscientists of Alberta (E.I.T.), 2024 - Present
  • Society of Mining, Metallurgy & Exploration, 2022 - Present
  • Canadian Institute of Mining, Metallurgy and Petroleum, 2022 - Present

Awards and Honors

  • Jacob H Masliyah Graduate Award in Oil Sands Engineering, 2023
  • Alberta Innovates Graduate Student Scholarship, 2023
  • Graduate Students’ Association Academic Travel Grant, 2023
  • Mary Louise Imrie Graduate Student Award, 2023
  • Alberta Graduate Excellence Scholarship, 2022
  • University of Alberta Doctoral Recruitment Scholarship, 2019
  • China National Scholarship, 2018
  • Outstanding Graduate of Anhui Province, 2016
  • First-Class Scholarships for Undergraduates, 2015
  • China National Encouragement Scholarship, 2013, 2014

Research

Research Interests

I have cross-disciplinary study and research experience. My research interests are promoting Smart Mining Operations utilizing advanced machine learning techniques and sensing technologies to develop technically understandable, interpretable, and user-friendly machine learning toolkits, including

  • Applied machine learning in mine transport, cement mixture design, and geothermal areas.
  • Optimization and design of mine transport (e.g., truck fleet & production/productivity)
  • Fiber optic sensing (e.g., FBG & DAS) and its engineering applications (e.g., rock physics & percolation monitoring and CO2 leakage monitoring & risk assessment)
  • Remote sensing (e.g., small drone) and its engineering applications
  • CO2 geological storage
  • Graphic user interface design and development

a) Peer-Reviewed Published Journal Papers (* - corresponding author):

  1. Fan, C., Arachchilage, C.B., Zhang, N., Jiang, B.*, Liu, W.V.*, 2024. Machine learning with SHapley Additive exPlanations for evaluating mine truck productivity under real-site weather conditions at varying temporal resolutions. International Journal of Mining, Reclamation and Environment.
  2. https://doi.org/10.1080/17480930.2024.2348877

  3. Fan, C., Ugurlu, O.F. (Shared first author), Jiang, B.*, Liu, W.V.*, 2024. Deep neural network models for improving truck productivity prediction in open-pit mines. Mining, Metallurgy & Exploration 41, 619-636. https://doi.org/10.1007/s42461-024-00924-4
  4. Fan, C., Zhang, N., Jiang, B.*, Liu, W.V.*, 2023. Using deep neural networks coupled with principal component analysis for forecasting ore production at open-pit mines. Journal of Rock Mechanics and Geotechnical Engineering 16, 727-740. https://doi.org/10.1016/j.jrmge.2023.06.005
  5. Fan, C., Zhang, N., Jiang, B.*, Liu, W.V.*, 2023. Weighted ensembles of artificial neural networks based on Gaussian mixture modeling for truck productivity prediction at open-pit mines. Mining, Metallurgy & Exploration 40, 583-598. https://doi.org/10.1007/s42461-023-00747-9
  6. Fan, C., Zhang, N., Jiang, B.*, Liu, W.V.*, 2023. Prediction of truck productivity at mine sites using tree-based ensemble models combined with Gaussian mixture modeling. International Journal of Mining, Reclamation and Environment 37, 66-86. https://doi.org/10.1080/17480930.2022.2142425
  7. Fan, C., Zhang, N., Jiang, B.*, Liu, W.V.*, 2022. Preprocessing large datasets using Gaussian mixture modeling to improve prediction of truck productivity at mine sites. Archives of Mining Sciences 67, 661-680. https://doi.org/10.24425/ams.2022.143680
  8. Fan, C., Li, Q.*, Ma, J., Yang, D., 2019. Fiber Bragg grating-based experimental and numerical investigations of CO2 migration front in saturated sandstone under subcritical and supercritical conditions. Greenhouse Gases: Science and Technology 9, 106-124. https://doi.org/10.1002/ghg.1838
  9. Fan, C., Li, Q.*, Li, X., Niu, Z., Xu, L., 2019. Dynamic optical fiber monitoring of water-saturated sandstone during supercritical CO2 injection at different sequestration pressures. In: Zhan, L., Chen, Y., Bouazza, A. (eds) Environmental Science and Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-13-2227-3_2
  10. Fan, C., Sun Y., Li Q.*, Lu, H., Niu Z., Li X., 2017. Testing technology of fiber Bragg grating in the shale damage experiment under uniaxial compression conditions. Rock and Soil Mechanics 38, 2456-2464. https://doi.org/10.16285/j.rsm.2017.08.036
  11. Zhang, D., Fan, C.*, Kuang, D., 2019. Impact assessment of interlayers on geological storage of carbon dioxide in Songliao Basin. Oil & Gas Science and Technology - Rev. IFP Energies Nouvelles 74, 1-9. https://doi.org/10.2516/ogst/2019059
  12. Arachchilage, C.B., Huang, G., Fan, C., Liu, W.V.*, 2023. Forecasting unconfined compressive strength of calcium sulfoaluminate cement mixtures using ensemble machine learning techniques integrated with shapely-additive explanations. Construction and Building Materials 409, 134083. https://doi.org/10.1016/j.conbuildmat.2023.134083
  13. Ma, S., Fan, C., Liu, W.V.*, 2023. Effects of site operating conditions on real site TKPH (tonne-kilometer-per-hour) of ultra-large off-the-road tires. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. https://doi.org/10.1177/09544070231166166
  14. Arachchilage, C.B., Fan, C., Zhao, J., Huang, G., Liu, W.V.*, 2023. A machine learning model to predict unconfined compressive strength of alkali-activated slag-based cemented paste backfill. Journal of Rock Mechanics and Geotechnical Engineering 5, 2803-2815. https://doi.org/10.1016/j.jrmge.2022.12.009
  15. Xu, L., Li, Q.*, Mathias, S., Tan, Y., Yang, D., Fan, C., 2021. Strain characteristics and permeability evolution of faults under stress disturbance monitoring by fibre Bragg grating sensing and pressure pulses. Geomechanics and Geophysics for Geo-Energy and Geo-Resources 7, 93. https://doi.org/10.1007/s40948-021-00289-8
  16. Sun, Y., Liu, J., Xue, Z., Li, Q.*, Fan, C., Zhang, X., 2020. A critical review of distributed fiber optic sensing for real-time monitoring geologic CO2 sequestration. Journal of Natural Gas Science and Engineering 103751. https://doi.org/10.1016/j.jngse.2020.103751
  17. Sun, Y., Li, Q.*, Fan, C., 2017. Laboratory core flooding experiments in reservoir sandstone under different sequestration pressures using multichannel fiber Bragg grating sensor arrays. International Journal of Greenhouse Gas Control 60, 186-198. https://doi.org/10.1016/j.ijggc.2017.03.015
  18. Sun, Y., Li, Q.*, Fan, C., Yang, D., Li, X., Sun, A., 2017. Fiber-optic monitoring of evaporation-induced axial strain of sandstone under ambient laboratory conditions. Environmental Earth Sciences 76, 379. https://doi.org/10.1007/s12665-017-6706-6
  19. Sun, Y., Li, Q.*, Yang, D., Fan, C., Sun, A., 2016. Investigation of the dynamic strain responses of sandstone using multichannel fiber-optic sensor arrays. Engineering Geology 213, 1-10. https://doi.org/10.1016/j.enggeo.2016.08.008

b) Under-Review/Submitted Journal Papers (* - corresponding author):

  1. Fan, C., Zhang, N., Jiang, B.*, Liu, W.V.*, 2023. Improved extreme machine learning for rapid estimation of mining truck cycle time based on feature selection and unsupervised clustering techniques. International Journal of Coal Science & Technology. (Under review)
  2. Jian, Z., Fan, C., Huang, G., Guo, Y., Arachchilage, C.B., Liu, W.V.*, 2024. Machine Learning-Assisted Characterization of the Thermal Conductivity of Cement-Based Grouts for Borehole Heat Exchangers. Construction and Building Materials. (Submitted). 
  3. Onyekwena, C.C., Li, Y.*, Fan, C., Wu, W., 2024. Nature-inspired machine learning for optimal strength estimation of cement-geopolymer-stabilized soft soils and multi-objective optimization. Journal of Cleaner Production. (Under Review). 
  4. Tan, X., Chen, W.*, Fan, C., Mao, Y., Mao, K., Du, B., 2024. Missing data imputation in tunnel monitoring system with a spatio-temporal correlation fused machine learning model. Journal of Civil Structural Health Monitoring. (Under Review).

c) Referred Conference Presentation/Poster:

  1. Fan, C. Applying machine learning techniques to improving truck productivity prediction accuracy at mine sites. Wuhan Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan, China. (Invited oral presentation on Oct 11, 2023)
  2. Fan, C., Li, Q., Guo, Y., Liu, W.V., 2023. Fiber Bragg grating-based supercritical carbon dioxide core flooding experiment and numerical simulation. Faulty of Engineering Graduate Research Symposium 2023, University of Alberta, Edmonton, Canada. (Oral presentation on Aug 22, 2023)
  3. Fan, C., Singh, R., Liu, W.V., 2022. Predictive modeling of uniaxial compressive strength of cemented paste backfill using machine learning based on a divide-and-conquer strategy. SME 2023 Annual Conference, Denver, USA. (Oral presentation on Feb 28, 2023)
  4. Fan, C., Li, Q., Li, X., Niu, Z., Xu, L., 2019. Dynamic optical fiber monitoring of water-saturated sandstone during supercritical CO2 injection at different sequestration pressures. Proceedings of the 8th International Congress on Environmental Geotechnics, Hangzhou, China. (Oral presentation on Oct 28, 2018)
  5. Li, Q., Ma, J., Lu, X., Niu, Z., Fan, C., Li, X., 2018. Fluid sampling monitoring at Yanchang CO2-EOR demonstration site, Ordos Basin, China. The 14th Greenhouse Gas Control Technologies Conference, Melbourne, Australia. http://dx.doi.org/10.2139/ssrn.3365959
  6. Li, Q., Fan, C., Li, X., Xu, L., 2018. Can we monitor the breath of sandstone during CO2 flooding by optical fibers in laboratory experiments? American Geophysical Union, Fall Meeting 2018, Washington, D.C., USA. (Poster)

Teaching

[Upcoming] Short course at the 7th International Symposium on Mine Safety Science and Engineering


Instructors: Prof. Asli Sari, Dr. Chengkai Fan, Prof. Wei Victor Liu

Topic: Predictive Power: Machine Learning Techniques for Mining Engineering Challenges

Offered: Sunday, 18, August 2024 (1:00 pm - 5:00 pm)

In the mining discipline, massive training data (from real site operating conditions or lab conditions) are available across various applications; however, these data have been inadequately utilized for machine learning methods to predict future behaviors or phenomena. Substantial knowledge gaps persist in leveraging these data to train machine learning algorithms effectively and derive predictive rules relevant to the mining discipline. The goal of this short course is to get insights into how machine learning works and how to apply machine learning methods for predicting future behaviors or phenomena within the mining sector. Throughout this course, participants will explore both the foundational principles and real-world implementations of machine learning, aiming to foster inspiration for future research endeavors and collaborative efforts.