Martin Ange Mbalkam

Software engineer and AI researcher

I build machine learning systems for problems that matter in Central Africa: agricultural forecasting, patient monitoring, and decision support designed for data-scarce environments. My published research applies deep learning to crop monitoring and yield prediction. My current work extends to AI for health, collaborative multi-agent systems, robotics and AI safety.

Affiliated with the School of Mathematics and Computer Sciences, University of Ngaoundéré.

---

What I have actually done

• A peer-reviewed systematic review of deep learning for crop monitoring — 87 studies screened under PRISMA methodology, across 10 architecture families.
• A controlled multi-modal experiment on crop yield prediction in Cameroon, comparing six deep learning architectures over satellite, climate and socio-economic data.
• A Google Earth Engine pipeline producing analysis-ready satellite time series — NDVI, EVI, NDWI, NDRE and Sentinel-1 radar indices — for Cameroonian crop regions.
• An IoT health platform with embedded AI, designed for patient follow-up in sub-Saharan Africa.
• Competition work across acoustic species identification, subsurface geology, geolocation from imagery, and knowledge tracing in tutoring transcripts.

---