Kel Markert
Cloud Geographer at Google
Huntsville, Alabama, United States
Summary
🤩
Rockstar🎓
Top SchoolKel Markert is a Cloud Geographer at Google with 11 years of experience blending hydrology research and cloud-native geospatial engineering. He holds a PhD in Civil Engineering (hydrology) from BYU and an MBA, bringing both rigorous research skills and business-savvy to production problems. Based in Huntsville, Alabama, Kel has contributed machine learning functionality to the popular geemap project, enabling local scikit-learn Random Forest models to integrate with Google Earth Engine and produce probability outputs. His work sits at the intersection of environmental science, ML, and cloud platforms, translating complex hydrologic models into reproducible, scalable geospatial tools. Colleagues value him for making research-grade methods practical for large-scale Earth observation workflows.
11 years of coding experience
Master in Business Administration (MBA), Master in Business Administration (MBA) at The University of Alabama in HuntsvilleBachelor’s Degree, Bachelor’s Degree at University of Alabama in HuntsvilleDoctor of Philosophy (PhD), Doctor of Philosophy (PhD) at Brigham Young University
German, English
Stackoverflow
817reputation
45kreached
25answers
0questions
Github Skills (18)
python10
image-processing10
scikit10
machine-learning10
geospatial10
scikit-learn10
jupyter-notebook10
random-forest10
earth-engine10
data-science9
mappings7
optimization6
mean6
google-earth-engine6
landsat6
Programming languages (8)
Github contributions (5)
gee-community/geemap
Oct 2020 - Jun 2021
A Python package for interactive geospatial analysis and visualization with Google Earth Engine.
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:18 commits, 4 PRs, 5 pushes in 8 months
Contributions summary:Kel significantly contributed to the development of a machine learning module within the geemap package. Their work involved implementing functionality to train Random Forest models locally using scikit-learn, which could then be used with Google Earth Engine. The user's contributions include converting scikit-learn estimators into string representations suitable for Earth Engine, and creating an example notebook demonstrating the model training, classification, and saving process. They also added support for probability outputs from the models.
pythonjupyter-notebookgoogle-earthdeck-glcolab
Servir-Mekong/hydra-floods
Jun 2018 - Apr 2022
HYDrologic Remote sensing Analysis for Floods Python package
Contributions:9 releases, 449 commits, 19 PRs in 3 years 10 months
pythonsarsensinggoogle-earth-engineearth-engine
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.