Data Analytics | Data Engineering | Enterprise GIS | GeoAI | Machine Learning

I design secure, explainable, and governance-aware data systems that transform complex spatial, public-health, and enterprise data into trusted intelligence. My work combines data analytics, data engineering, enterprise GIS, spatial analysis, machine learning, cloud computing, and secure software engineering to support practical decision-making.

MSc Big Data Technologies Candidate · M.Tech. Geoinformation Science and Remote Sensing · 10+ years of professional experience · 10+ peer-reviewed publications

Portfolio · LinkedIn · Email

A working research prototype that transforms aggregated district-level data into outbreak-risk classifications, spatial intelligence, explainable model outputs, and dashboard-based public-health decision support.

• XGBoost outbreak-risk classification
• Getis-Ord Gi* hotspot analysis
• Local Moran's I cluster and outlier analysis
• SHAP-based model explanations
• Interactive Streamlit and Folium dashboard
• Secure FastAPI gateway
• JWT authentication and role-based access control
• Audit logging and governance monitoring
• Docker-based application packaging
• AWS prototype API deployment and Streamlit Cloud dashboard deployment

Technology stack: Python GeoPandas PySAL Scikit-learn XGBoost SHAP FastAPI Streamlit Folium Docker AWS JWT RBAC

Data architecture: The public demonstration uses CSV and GeoJSON data. The production-oriented architecture incorporates PostgreSQL/PostGIS as the scalable spatial database layer.

Explore the project:

• Live Dashboard: Open dashboard
• Source Repository: View on GitHub
• Secure API Documentation: Request authorised academic access by email

This system is an academic research prototype. It is not intended for clinical diagnosis or operational public-health deployment without further validation, security hardening, governance review, and institutional approval.

• Data analytics and dashboard-driven decision-support systems
• Data engineering and ETL/ELT workflows
• Enterprise GIS, spatial data management, and geospatial infrastructure
• GeoAI, spatial machine learning, and explainable AI applications
• Secure APIs and cloud-enabled intelligence platforms
• Research software and reproducible technical artefacts

Explore additional work in data engineering, machine learning, enterprise GIS, public-health GeoAI, cloud security, automation, and reliability engineering:

• Portfolio Repository: View source projects

Data Analytics and Engineering: Python SQL Pandas NumPy PostgreSQL PostGIS ETL/ELT Data Validation Feature Engineering Spark PySpark Hive

GeoAI and Enterprise GIS: ArcGIS Pro ArcGIS Online QGIS GeoPandas PySAL Spatial Statistics Moran's I LISA Getis-Ord Gi* Hotspot Analysis Cartography Remote Sensing

Machine Learning and Explainable AI: Scikit-learn XGBoost Random Forest Logistic Regression SHAP Model Evaluation Spatial Machine Learning Responsible AI

Cloud, APIs, and Secure Systems: FastAPI REST APIs Docker AWS Streamlit Git/GitHub JWT RBAC Audit Logging API Security Privacy-Preserving Analytics

Over the past decade, I have supported enterprise GIS, spatial data management, public-health surveillance, emergency response, and analytics across research and operational environments.

My professional work includes:

• Enterprise GIS implementation and spatial data infrastructure
• Public-health surveillance and outbreak response
• COVID-19, malaria, measles, cholera, mpox, and Lassa fever intelligence
• Dashboard development and operational reporting
• GIS training and capacity building
• Geospatial data quality assurance and automation
• Applied research in spatial epidemiology and public-health analytics

Design and Evaluation of a Privacy-Preserving GeoAI Health Surveillance System Using a Hybrid Cloud Architecture

Submitted for assessment as part of the MSc Big Data Technologies programme.

Using Design Science Research, I designed, implemented, and evaluated a governance-aware GeoAI public-health surveillance artefact across six dimensions:

• Predictive performance
• Spatial intelligence
• Explainability
• Security and governance
• Usability
• Decision-support value

The research demonstrates how aggregated and de-identified surveillance data can be transformed into actionable outbreak-risk intelligence while supporting transparency, controlled access, and governance traceability.

University of East London / UNICAF
Final award pending

Coursework and research covering big data engineering, machine learning, cloud computing, cybersecurity, and intelligent data systems.

Federal University of Technology, Akure (FUTA), Nigeria / UN-ARCSSTEE

Specialised training in geographic information systems, remote sensing, spatial analysis, geospatial data management, cartography, and environmental modelling.

I have authored and co-authored 10+ peer-reviewed publications covering infectious-disease surveillance, spatial epidemiology, GIS, GeoAI, and public-health intelligence.

Google Scholar · ORCID · ResearchGate

My research complements my engineering work by translating analytical methods into practical, reproducible GeoAI and decision-support solutions.

• IBM Data Engineering Professional Certificate
• Microsoft Fabric and modern analytics engineering
• Cloud-native data engineering and lakehouse architectures
• GeoAI, spatial machine learning, and GeoFoundation Models
• Spatio-temporal AI and AI agents for spatial intelligence
• Cloud security and security monitoring

I am open to professional opportunities and collaborations involving data analytics, data engineering, enterprise GIS, GeoAI, machine learning, explainable AI, privacy-aware analytics, and public-health intelligence.

• LinkedIn: Godwin Etim Akpan
• GitHub: Jedidiah82
• Email: godwinea.ai@gmail.com

Committed to building secure, explainable, and practical data solutions that create measurable impact.