Data scientist | Machine learning for climate and Earth-observation data MSc Computer Science candidate (Copperbelt University, expected 2027) · Zimbabwean, currently in Zambia Python · SQL · scikit-learn · geospatial analysis · PostgreSQL
I build machine learning and data analysis projects on satellite and climate data, and I explain the results in plain language, a skill from two years of teaching Computer Science and Mathematics.
Open to: data science and ML roles, research (PhD) positions, remote work or relocation.
Urban Age Classification: cross-city transfer learning Classifies urban development age from multi-temporal Landsat features. Trains on Madrid and tests on Amsterdam, comparing zero-shot prediction with few-shot adaptation at 5–200 labelled pixels per class. Python, scikit-learn.
Zimbabwe Drought Analysis, 1981–2024 A 44-year assessment of meteorological drought using SPEI and SPI at four timescales, with Bulawayo as a local case study. Shows how accounting for evaporative demand changes drought assessments compared with rainfall alone. Google Earth Engine, pandas, SciPy.
Smart-Campus Distributed Monitoring and Load Balancing Simulated edge and fog services with threshold alerts and workload redistribution, plus a browser dashboard. Python, Flask, Docker Compose.
Netflix Titles ETL Pipeline Cleans and normalises a raw dataset into a relational schema and loads it into PostgreSQL. Python, SQL.
Machine learning and analysis: scikit-learn, pandas, NumPy, SciPy, time-series analysis, model evaluation, domain adaptation Geospatial and climate data: Landsat, ERA5-Land, TerraClimate, Google Earth Engine Data and software: SQL, PostgreSQL, Python, Flask, Docker Compose, Git/GitHub Learning now: PyTorch, PySpark, cloud (AWS) fundamentals
