Dr. Katende Ronald

Ronald Katende is a lecturer in the Department of Mathematics, Faculty of Science, Kabale University. He holds a PhD in Mathematics, specializing in Scientific Computing and Machine Learning. His expertise covers numerical analysis, stochastic modelling, scientific machine learning, uncertainty quantification, and reproducible computational research.

His work focuses on building reliable early-warning and decision-support methods for systems affected by limited data, noise, long-term dependence, and operational constraints. In AMMED, he developed multi-timescale memory methods for early detection of clinical deterioration. The work evaluates whether warnings arrive early enough for clinical action, controls false alarms explicitly, and tests whether performance transfers to independent hospital populations.

He also developed GridTwin Sentinel, a low-compute early-warning system for electricity infrastructure. It combines forecasting, sudden- and gradual-change detection, temporal memory, physical consistency checks, network localization, uncertainty, abstention, and controlled warning decisions. The system is designed to detect developing faults early, identify the likely affected asset, and maintain a manageable false-warning burden.

His climate-resilience research develops data-efficient methods for combining household, agricultural, socioeconomic, satellite, and geospatial data. This work includes cross-country resilience assessment, localized risk mapping, spatial interpolation, and decision models for translating uncertain regional evidence into locally relevant priorities.

Across these areas, his central strength is converting rigorous mathematics into practical systems that can work with limited data and computing resources. He has extensive experience in data harmonization, forecasting, model validation, uncertainty assessment, low-compute implementation, and reproducible software development. His research provides a strong technical foundation for developing and validating reliable early-warning systems across African health, climate, and infrastructure settings.