Kris Darnell

Kris is a data scientist and computational geoscientist who has extensive experience developing software and algorithms for a variety of spatiotemporal problems. He has used computer vision and deep learning to develop geospatial intelligence models using satellite imagery and lidar for natural disaster assessments, insurance applications, and earth monitoring. Most recently, he has contributed substantially to the development of in-house Python libraries for a cloud-based forecasting software platform that leveraged geospatial data, human choices, and historical production data to make predictions about the expected volumetric output of oil and gas wells. His specific contributions to that platform focused on uncertainty quantification of forecasts, feature engineering of noisy time series data, and a modular, extensible machine learning pipeline framework.

Kris received his Ph.D. in Geological Sciences from The University of Texas at Austin where he studied clathrate hydrates with a particular focus on Carbon Dioxide storage as clathrate hydrate deposits in sub-marine and sub-permafrost sedimentary basins. He also holds a M.S. in Geophysical Sciences from University of Chicago and a B.S. in Civil Engineering from The University of Texas at Austin.