About

I am a data scientist with a Ph.D. in Computing, with a concentration in Data Science, from the School of Computing at Boise State University. My expertise spans artificial intelligence, machine learning, data engineering, high-performance computing, statistical modeling, and large-scale data analytics.

My research focuses on developing scalable machine learning and deep learning methods for complex scientific systems, including Earth system and hydrological modeling. This work involves building end-to-end data workflows, designing reproducible pipelines, training and evaluating predictive models, managing large multidimensional datasets, and developing machine learning surrogates that improve computational efficiency and decision support.

While my applied research is rooted in climate and environmental science, the technical foundation of my work is highly transferable. I am interested in data science, data engineering, and machine learning engineering roles where I can apply my experience in Python, machine learning, big data processing, cloud and HPC environments, model development, and scalable analytics to solve real-world problems across domains.

Research & Technical Interests

• Machine Learning and Predictive Modeling
  I develop machine learning and deep learning models for complex, data-intensive systems, with experience in supervised learning, neural networks, uncertainty-aware modeling, and model evaluation. My work includes building scalable predictive models that support scientific discovery, operational decision-making, and real-world analytics.

• Machine Learning Emulators for Scientific and Physical Systems
  I design machine learning surrogates to emulate computationally expensive simulations, including Earth system and land surface models such as CLM5. These approaches reduce computational cost, accelerate experimentation, and enable faster scenario analysis, calibration, and sensitivity testing.

• Uncertainty Quantification and Interpretable AI
  I apply uncertainty-aware learning methods, including evidential deep learning, to improve the reliability and trustworthiness of model predictions. I also use interpretability and sensitivity analysis techniques, such as SHAP and feature attribution methods, to better understand model behavior and support transparent decision-making.

• Data Engineering and Scalable Analytics Workflows
  I design reproducible data pipelines and large-scale analytics workflows for high-dimensional scientific and operational datasets. My work emphasizes automation, data quality, scalability, efficient memory use, and integration of tools such as Python, Xarray, Dask, Spark, Slurm, Docker, Singularity, and cloud/HPC environments.

• Geospatial and Spatiotemporal Data Science
  I analyze spatial and temporal patterns in large environmental datasets using statistical learning, clustering, self-organizing maps, empirical orthogonal functions, and scalable Python workflows. These methods support anomaly detection, pattern discovery, model validation, and decision-support applications.

• Hybrid AI-Physics Modeling and Decision Support
  I am interested in approaches that combine physics-based models, machine learning, and data-driven analytics to improve prediction reliability and computational efficiency. My broader goal is to build models and systems that translate complex data into actionable insights for climate resilience, water resources, risk assessment, and other applied domains.

Technical Skills

• Programming and Scientific Computing
  Python, R, MATLAB, Java, Scala, PySpark, Bash, SQL; NumPy, Pandas, SciPy, Xarray

• Machine Learning and Artificial Intelligence
  PyTorch, TensorFlow, Keras, scikit-learn; deep learning, convolutional neural networks, recurrent neural networks, uncertainty-aware learning, generative AI, and large language models

• High-Performance Computing and Big Data
  Dask, Apache Spark, Hadoop, GPU-accelerated computing, Slurm job scheduling, parallel processing, memory optimization, AWS, and Google Cloud

• Climate, Hydrology, and Geospatial Tools
  CLM5, WRF, NetCDF, Zarr, CDO, NCO, GIS tools, Cartopy, and scalable analysis of multidimensional climate datasets

• Data Engineering and Reproducible Research
  Docker, Singularity, Git/GitHub, Linux shell scripting, workflow automation, CI/CD practices, and reproducible computational environments

• Data Visualization
  Matplotlib, Cartopy, HoloViews, Plotly, Tableau; development of clear, publication-quality figures for scientific communication

Education

• Ph.D. in Computing, Data Science Concentration
  Boise State University, Boise, Idaho, USA — May 2026

• M.Sc. in Mathematical Sciences, Data Science Concentration
  African Institute for Mathematical Sciences, Kigali, Rwanda — 2020–2021

• B.Sc. in Physics, Computational Physics
  Copperbelt University, Kitwe, Zambia — 2015–2019

Selected Updates

• September 2025
  Joined the Computational and Information Systems Laboratory at the NSF National Center for Atmospheric Research as a CISL Visiting Scholar.

• June 2025
  Awarded the AWWA Pacific Northwest Section Scholarship in recognition of graduate research excellence in water and climate data science.

• Summer 2025
  Received a travel award to attend the NCAR CESM Tutorial in Boulder, Colorado, for advanced training in Earth system modeling and simulation.

• September 2024
  Selected as a William Averette Anderson Fund Fellow, a national fellowship focused on hazard mitigation, disaster resilience, and community-engaged research.

• July 2024
  Presented machine learning research on climate pattern analysis at the SIAM Annual Meeting and the SIAM Mathematics of Data Science Conference, supported by SIAM travel awards.

• June 2024
  Completed a graduate research fellowship through the NCAR Advanced Study Program, focusing on adaptive learning techniques for climate model calibration and evaluation.

Awards and Fellowships

• 2025
  • AWWA Pacific Northwest Section Scholarship Recipient
  • NCAR CESM Tutorial Travel Award for advanced training in Earth system modeling
• 2024
  • William Averette Anderson Fund Fellow in hazard and disaster mitigation
  • NCAR Advanced Study Program Graduate Research Fellow
  • SIAM Travel Award recipient for presentations at applied mathematics and data science conferences
• 2021
  • Boise State University GEM Scholarship recipient
  • Boise State University Graduate Assistantship
  • AIMS Master’s Scholarship for graduate study in mathematical sciences and data science
• 2015
  • Zambia National Merit Scholarship for undergraduate study at Copperbelt University