Lane Boyd

PhD Geological Engineering Student

I am keenly interested in the quantification and characterization of subsurface spatial uncertainty specifically due to aleatory (random) geologic variability, which is an intrinsic property of the processes that created the geology. The primary application of my research is tunneling and underground construction. Through the use of geostatistical algorithms that have been developed for a wide variety of applications including geothermal, oil and gas, and mining, a modification of these algorithms for tunneling and underground construction enhances an understanding of potential uncertainty and risk assessment at all stages of the design and construction process. My work aims to increase the knowledge and understanding of risk and hazard in these industries, which in turn aids engineers and designers who decide to engage in these expensive, challenging, and risky projects.

Hayden Powers

MSc Geohysics Student, Department of Geophysics

My research revolves around the application of machine learning on stochastic earth models, specifically those from producing oil fields.  The stochastic models used are MCMC and derived from AVA data.  The goal of my work is to take the multiple output attributes and many earth models to train and predict production.  Currently cross validation is being used to check accuracy and sensitivity. The end goal is to predict production across the field to determine economic areas within the reservoir.

Xiaodan Yu

MSc Student, Department of Geophysics

My current research interest is implementing data science, statistical learning, and spatial statistics to interpret various Geophysical and Petroleum data for decision making. My current project focuses on performing wavelet analysis for feature extraction in hydraulic pressure data and implementing anomaly detection for screenout issues with machine learning model.

Bane Sullivan

MSc Student, Hydrologic Science & Engineering

I am interested in the intersection of geoscientific visualization, machine learning, and large-scale geophysics for tackling common-pool resource issues and communicating geophysical findings.

I previously graduated from the Colorado School of Mines with a B.S. in Geophysical Engineering, and currently, I am continuing my education in the Hydrological Science and Engineering graduate program at CSM. My current research focusses on developing open-source tools to make 3/4D visualization more accessible to the geoscientific community – helping researchers rapidly gain insights from their data and communicate their findings.

Bane’s links:

  • Bane’s Website
  • Bane’s GitHub
  • Open-Source Projects:
    • vtki: A Streamlined Python Interface for the Visualization Toolkit (VTK)
    • PVGeo: Python package of VTK-based algorithms to analyze geoscientific data and models
    • omfvtk: 3D visualization for the Open Mining Format (OMF)

Arnab Dhara

PhD Geophysics Student, Department of Geophysics

I am interested the application of data analytics and machine learning techniques to a wide variety of problems in geophysics. I am working on the integrating of geostatistics and machine learning to produce stochastic models of the reservoir. In addition, I am working on the application of dictionary learning to attenuate surface wave noise from land seismic data.

My 2018 SEG abstract: Machine-learning-based methods for estimation and stochastic simulation,  SEG Technical Program Expanded Abstracts 2018: pp. 2261-2265, (

Post Doctoral Scholar

Bin Luo

My research interests lie in the field of computational geophysics. I have been working on a variety of seismological projects to understand subsurface structure and earthquake dynamics with advanced computational techniques, such as FEM-based modeling of fault sliding and earthquake rupture, seismic inversion of DAS data, and application of deep learning methods in geophysical data analysis

Past Students

Samir Jreij

Geophysicist, Cimarex