Summary
Chase Dwelle is a geospatial data engineer and computational scientist with a decade of experience applying machine learning, probabilistic programming, and Bayesian methods to complex modeling and big data problems. Trained as an environmental engineer with a PhD and postdoctoral work at the University of Michigan, he has translated domain expertise in hydrology and water-quality forecasting into production-ready forecasting and computer vision systems. He runs a consulting practice and founded Fix6, delivering probabilistic forecasting and sensor/imagery-based insights using PyTorch and custom pipelines, and currently contributes geospatial engineering at Salient. Comfortable in legacy codebases and multi-language stacks (C++, Python, Julia, R), he bridges research-grade uncertainty quantification with practical deployment. Notably, his work has supported real-time disaster-management modeling for urban flooding and operational plant-health monitoring in indoor agriculture. Based in Philadelphia, he combines academic rigor with entrepreneurial delivery to turn noisy sensor data into actionable decisions.
10 years of coding experience
12 years of employment as a software developer
Bachelor of Science in Engineering Civil and Environmental Engineering, Bachelor of Science in Engineering Civil and Environmental Engineering at University of Michigan