Register      Login
Australian Energy Producers Journal Australian Energy Producers Journal Society
Journal of Australian Energy Producers
RESEARCH ARTICLE

Improving operational confidence and decision-making in the absence of key reservoir data through utilisation of a machine learning-based coal identification model in coal seam gas wells

Gonzalo Vazquez A * , Mitch Allder A , Joel Zimmermann A , Jack Mclean-Hodgson A and Kim Owen A
+ Author Affiliations
- Author Affiliations

A Senex Energy Pty Ltd, Brisbane, Qld, Australia.




Gonzalo Vazquez is a seasoned drilling engineer with 26 years of experience in the oil and gas industry. Born in Venezuela, he started his career in 1999 at Intevep, a leading research and development institute, specialising in drilling fluids and cement. Gonzalo gained extensive field experience in offshore and onshore operations before earning a Master’s degree in Drilling and Well Engineering from Robert Gordon University in Aberdeen, UK, in 2010. Relocating to Australia, he worked with Arrow Energy and Santos before joining Senex Energy, where he has served as a Senior Drilling and Completions Engineer for 8 years. Gonzalo integrates sustainability with innovative solutions, while also mentoring young engineers. A lifelong learner, he applies his passion for machine learning and artificial intelligence to optimise processes. Outside of work, Gonzalo enjoys tennis, soccer and family time. Known for his positivity, he thrives in dynamic teams and champions efficiency in all endeavours.



Mitch Allder is a geologist with over 11 years’ experience in the oil and gas industry. Graduating with a First Class Honours degree in Geological Science from the University of Queensland, Mitch has worked across various Australian basins, focusing on the Cooper/Eromanga and Bowen/Surat basins. His experience spans from regional play-based exploration and work program planning to field development modelling and drilling. Recognising the potential power that digital workflows could bring to operations, he now serves as the Analytics Lead at Senex Energy, driving the application of initiative digital solutions to maximise value. Outside of work, Mitch enjoys spending time with his family, following sport and playing cricket.



Joel Zimmermann is a geologist with over 10 years’ experience in operations, exploration, appraisal and development of both conventional and unconventional plays across a range of Australian basins. Graduating with Honours from the University of Queensland in 2013, he has spent a large portion of his career with Senex, through its transition from an oil explorer and producer to the major coal seam gas (CSG) player it is today. His focus as the Senior Development Geologist with Senex Energy is on portfolio growth, geological modelling of existing development assets, compliance reporting and exploring for opportunities to maximise value within the companies new and existing CSG fields in the Surat and Bowen basins. In his free time, Joel enjoys catching up with friends, playing trivia, gardening and walking his golden retriever, Toby.



Jack Mclean-Hodgson is a geoscientist with over 14 years of experience within the oil and gas industry. After earning his degree from Queensland University of Technology in 2010, he began his career at Senex. Throughout his time there, he has taken on various roles within the subsurface team, including operations, development and exploration geology and geophysics. Jack initially worked with the Cooper Basin Exploration Team, focusing primarily on seismic interpretation for Western Flank oil exploration prospects. In 2020, he transferred to the Surat Basin team, where he has been actively involved in advancing exploration opportunities within the Surat and Bowen basins. He enjoys tackling the various and unique challenges that subsurface can pose, especially when it comes to mapping, volumetrics and risk analysis. Outside of work, Jack enjoys cycling, football and spending time with his family.



Kim Owen is an experienced operations geologist, specialising in CSG exploration, appraisal and production within Queensland. With a MSc degree with First Class Honours in Geology, and a BSc degree in Environmental Science from Victoria University of Wellington, she has contributed to numerous unconventional projects with leading companies across the Surat and Bowen basins. Kim’s expertise encompasses drilling and geological operations, with a proven track record in supervising and supporting complex drilling programs. As a committee member of PESA Queensland, she is dedicated to advancing geological research and operational excellence. She is also a strong advocate for women in science, technology, engineering and mathematics, encouraging and supporting their participation and advancement in the field. Outside of work, Kim enjoys staying active through CrossFit, skiing and exploring new travel destinations.


Australian Energy Producers Journal 65, EP24204 https://doi.org/10.1071/EP24204
Submitted: 13 December 2024  Accepted: 1 April 2025  Published: 22 May 2025

© 2025 The Author(s) (or their employer(s)). Published by CSIRO Publishing on behalf of Australian Energy Producers.

Abstract

This study investigates the feasibility of using machine learning algorithms to identify the presence of coal (at a scale comparable to wireline logging), utilising drilling parameters from coal seam gas (CSG) wells located in the Surat Basin, Queensland, Australia. Generally, during the drilling operation and before wireline logging, the presence of coal lithologies is inferred from elevated gas levels liberated into the drilling mud. However, the reliability of gas sensors can be compromised, necessitating operations geologists to rely on fluctuating drilling parameters to make decisions. To address this, a supervised classification model using the XGBoost algorithm has been developed to predict coal in the absence of reliable gas sensor data, improving data available to the operations geologists for decision-making purposes. Trained on data from over 150 wells, the classification model identifies coal lithologies by analysing typically available, high-resolution drilling parameters. While these parameters vary due to physical changes in the drilled lithology, they are also significantly overprinted by operational factors. Underpinned by iterative exploratory data analysis, the machine learning workflow involved processing a large amount of raw data, defining the predictive target, feature engineering and model development. Traditional machine learning performance metrics, such as F1 score, recall and precision, have been used in conjunction with business-based metrics to compare model iterations. Even though the model faces challenges related to class imbalances, overfitting and variable operational environments, results demonstrate the utility in predicting the location of coal and assisting operational geology workflows in wells where gas readings are unreliable or unavailable.

Keywords: AI, artificial intelligence, coal prediction, coal seam gas, CSG, drilling technology, machine learning, Surat Basin, unconventional, XGBoost.

Biographies

EP24204_B1.png

Gonzalo Vazquez is a seasoned drilling engineer with 26 years of experience in the oil and gas industry. Born in Venezuela, he started his career in 1999 at Intevep, a leading research and development institute, specialising in drilling fluids and cement. Gonzalo gained extensive field experience in offshore and onshore operations before earning a Master’s degree in Drilling and Well Engineering from Robert Gordon University in Aberdeen, UK, in 2010. Relocating to Australia, he worked with Arrow Energy and Santos before joining Senex Energy, where he has served as a Senior Drilling and Completions Engineer for 8 years. Gonzalo integrates sustainability with innovative solutions, while also mentoring young engineers. A lifelong learner, he applies his passion for machine learning and artificial intelligence to optimise processes. Outside of work, Gonzalo enjoys tennis, soccer and family time. Known for his positivity, he thrives in dynamic teams and champions efficiency in all endeavours.

EP24204_B2.png

Mitch Allder is a geologist with over 11 years’ experience in the oil and gas industry. Graduating with a First Class Honours degree in Geological Science from the University of Queensland, Mitch has worked across various Australian basins, focusing on the Cooper/Eromanga and Bowen/Surat basins. His experience spans from regional play-based exploration and work program planning to field development modelling and drilling. Recognising the potential power that digital workflows could bring to operations, he now serves as the Analytics Lead at Senex Energy, driving the application of initiative digital solutions to maximise value. Outside of work, Mitch enjoys spending time with his family, following sport and playing cricket.

EP24204_B3.png

Joel Zimmermann is a geologist with over 10 years’ experience in operations, exploration, appraisal and development of both conventional and unconventional plays across a range of Australian basins. Graduating with Honours from the University of Queensland in 2013, he has spent a large portion of his career with Senex, through its transition from an oil explorer and producer to the major coal seam gas (CSG) player it is today. His focus as the Senior Development Geologist with Senex Energy is on portfolio growth, geological modelling of existing development assets, compliance reporting and exploring for opportunities to maximise value within the companies new and existing CSG fields in the Surat and Bowen basins. In his free time, Joel enjoys catching up with friends, playing trivia, gardening and walking his golden retriever, Toby.

EP24204_B4.png

Jack Mclean-Hodgson is a geoscientist with over 14 years of experience within the oil and gas industry. After earning his degree from Queensland University of Technology in 2010, he began his career at Senex. Throughout his time there, he has taken on various roles within the subsurface team, including operations, development and exploration geology and geophysics. Jack initially worked with the Cooper Basin Exploration Team, focusing primarily on seismic interpretation for Western Flank oil exploration prospects. In 2020, he transferred to the Surat Basin team, where he has been actively involved in advancing exploration opportunities within the Surat and Bowen basins. He enjoys tackling the various and unique challenges that subsurface can pose, especially when it comes to mapping, volumetrics and risk analysis. Outside of work, Jack enjoys cycling, football and spending time with his family.

EP24204_B5.png

Kim Owen is an experienced operations geologist, specialising in CSG exploration, appraisal and production within Queensland. With a MSc degree with First Class Honours in Geology, and a BSc degree in Environmental Science from Victoria University of Wellington, she has contributed to numerous unconventional projects with leading companies across the Surat and Bowen basins. Kim’s expertise encompasses drilling and geological operations, with a proven track record in supervising and supporting complex drilling programs. As a committee member of PESA Queensland, she is dedicated to advancing geological research and operational excellence. She is also a strong advocate for women in science, technology, engineering and mathematics, encouraging and supporting their participation and advancement in the field. Outside of work, Kim enjoys staying active through CrossFit, skiing and exploring new travel destinations.

References

Amagada PU (2023) ‘An inferable machine learning approach for reservoir lithology characterization using drilling data.’ (Kazan National Research Technological University: Russia)

An Q, Li Y, Hai L, Feng Z, Qi Y, Hao L, Ningbo L, Cheng Z, Hui L, Zhou F, Li H (2024) ‘Lithology identification of deep coal seam based on machine learning.’ (China University of Petroleum: Beijing)

Chen T, Guestrin C (2016) ‘XGBoost: A scalable tree boosting system.’ (University of Washington)

Chen G, Yang H, Yang D, Guo K, Feng M, Wang Y, Fu L, Jiang H (2022) A new rate of penetration prediction model based on the XGBoost and explanation method. Paper presented at the 56th U.S. Rock Mechanics/Geomechanics Symposium, Santa Fe, New Mexico, USA.

Department of Natural Resources, Mines and Energy (2019a) ‘Underground Water Impact Report for the Surat Cumulative Management Area.’ (Queensland Government)

Department of Natural Resources, Mines and Energy (2019b) ‘Code of practice for the construction and abandonment of petroleum wells and associated bores in Queensland (Version 2).’ (Queensland Government)

Gamal H, Elkatatny S, Abdulaziz AM (2024) ‘Intelligent solution for auto-detecting lithology scheme while drilling by machine learning.’ (Weatherford: Saudi Arabia)

Keylabs (2024) Understanding the F1 score and AUC-ROC curve. Available at https://keylabs.ai/blog/understanding-the-f1-score-and-auc-roc-curve/

Leung R, Scheding S (2015) ‘Automated coal seam detection using a modulated specific energy measure in a monitor-while-drilling context.’ (University of Sydney)

Peña-Gutiérrez J, Sabirov A (2024) ‘Automated estimation of mechanical specific energy as a tool for stratigraphic interpretation during real-time drilling operations.’ (Saudi Aramco)

Petrosys Pty Ltd (2025) GPinfo (Version 6.1.4). Available at https://www.petrosys.com.au/products/gpinfo/​​​​

Zhang P, Gao T, Li R, Fu J (2024) ‘Advanced machine learning framework for enhanced lithology classification and identification.’ (University of Central Oklahoma)

Zhong R, Johnson Jr RL, Chen Z (2021) ‘Using machine learning for geosteering during in-seam drilling.’ (University of Queensland)

Ziadat, W, Gamal H (2023) ‘Real-time machine learning application for formation tops and lithology prediction.’ (Weatherford)