PROJECTS
Projects
I have organized my projects primarily by scale and topic: Portfolio Projects represent a significant investment of time and are well aligned with my field and my research interests. My other projects are less related to my primary field or represent a less significant time investment.
My open source contributions are listed seperately in Open Source Contributions.
Portfolio Projects
- SEG Facies Classification Challenge: This project is based on a dataset released as part of a contest to predict facies from geophysical well log data. Repository available at the following link. A summary of my work can be found at the following link.
- Stratigraphic Surface Picking in Well Logs: This project is based on a database of 2193 vertical wells (with geospatial data/collar locations and geophysical well logs) released by the Alberta Geological Survey. I applied an ensemble geostatistics/ML approach to predict the depth and extent of the McMurray Formation throughout the survey area. The repository is available at the following link. A summary of my work can be found at the following link.
- TGS Salt Identification Challenge: I worked with the seismic image data released by TGS as part of their TGS Salt Identification Challenge Kaggle competition. I evaluate different approaches to detecting and segmenting salt in seismic sections, from textural methods using conventional computer vision algorithms to deep learning, including the UNet architecture.
Babbitt Cu-Ni Deposit Drill Results: I worked with a drill log database compiled by the University of Minnesota’s Natural Resources Research Institute from the Keweenawan Duluth Complex (disseminated copper-nickel-PGE sulfide mineralization) of northeastern Itasca County, Minnesota. My work included digitizing the drilling results from low-quality scans of the assay reports, performing a geostatistical analysis of the mineral resource, and experimenting with an ML method to predict PGE grades.
Lead Free Buffalo: I used open municipal data on lead testing results and
Open Source Contributions
I contribute to:
- dtreeplt: Drawing interactive Decision Trees using matplotlib
- harmonica: Forward modeling, inversion, and processing gravity and magnetic data
Other Projects
- In Codd we Trust
- Splenitis: Bayes
- ASHRAE: Kaggle
- Various weekend projects