MSc Data Science & Environmental Intelligence | Petroleum Engineering background
Python · Machine Learning · GIS · Energy Demand Analytics
I combine energy domain knowledge with data science to investigate how energy is produced, distributed and used. My work applies Python, statistical modelling, machine learning and geospatial analysis to electricity systems, geothermal resources and energy demand.
I am currently completing an MSc in Data Science & Environmental Intelligence at the University of Plymouth, building on an academic background in Petroleum Engineering. I am interested in graduate and junior opportunities in energy data analytics, energy systems, electricity markets and geospatial analytics.
An end to end geospatial assessment of how closed loop ground source heat pump potential could contribute to residential energy demand across Plymouth.
Selected results
- Modelled 164 LSOAs using local geology, residential demand and candidate borehole locations.
- Estimated 398.5 GWh/year of representative geothermal potential, with 356.0 GWh/year locally matched to demand.
- Found representative city coverage of 44.8% of the modelled residential demand.
- A 10,000 run Monte Carlo analysis produced a median coverage of 44.3% and a central 90% interval of 42.5–45.9%.
- PRCC analysis identified boiler efficiency and slate thermal conductivity as the strongest model sensitivities.
Methods: GeoPandas · QGIS · spatial joins · G.POT modelling · Monte Carlo simulation · PRCC sensitivity analysis
- GB electricity demand and imbalance forecasting — probabilistic forecasting of demand, system imbalance and market signals using NESO and Elexon data.
- UK renewable imbalance risk analytics — analysis of renewable generation, weather, settlement and portfolio imbalance exposure.
- Energy system case studies — applied forecasting, modelling and energy-transition analytics.
These projects are being prepared as reproducible public case studies. The geothermal assessment above is the first full project available for review.
- Python for Oil and Gas — decline curve analysis, production forecasting and a one dimensional reservoir simulation exercise.
- ANN Enhanced Oil Recovery — neural network regression applied to enhanced oil recovery data.
| Area | Tools and methods |
|---|---|
| Data analysis | Python, pandas, NumPy, SciPy, exploratory analysis and visualisation |
| Machine learning | scikit learn, regression, classification, model evaluation and uncertainty analysis |
| Geospatial analysis | GeoPandas, QGIS, Shapely, Rasterio, spatial joins and thematic mapping |
| Energy analytics | Energy demand modelling, electricity forecasting, geothermal assessment and sensitivity analysis |
| Reproducible workflow | Jupyter, Conda environments, Git and documented analytical pipelines |
- Email: kwakyegeorge10@gmail.com
- LinkedIn: linkedin.com/in/gkwakye
- GitHub: github.com/kwakye02
- Location: Plymouth, United Kingdom