A Full-Circle Moment
A full-circle moment—from applying GIS in public health and disease surveillance to exploring GeoAI and enterprise systems.
Recognition from Esri for contributions to public health GIS in Liberia—accompanied by a copy of Mapping the Nation from Esri’s headquarters in California.
When I first started working with GIS in public health, my focus was simple:
What is happening—and where?
Over time, I realized that answering those questions was only the beginning. The real challenge—and opportunity—was learning how to move from understanding patterns to predicting outcomes and supporting decisions at scale.
That realization marked the beginning of my transition from traditional GIS to GeoAI and enterprise spatial systems. It didn’t just change my technical skillset—it reshaped how I think about GIS as a discipline:
- From producing maps
- To designing systems that support decisions
GIS Is Evolving Beyond Maps
GIS is no longer just about maps.
It is increasingly becoming a core component of enterprise data systems—integrating machine learning, cloud infrastructure, and real-time analytics to support decision-making at scale.
For me, this realization was both exciting and uncomfortable.
It meant that the skills that once defined GIS expertise were no longer enough on their own. To grow, I had to start thinking beyond visualization and understand how spatial data fits into broader data ecosystems.
From Public Health GIS to GeoAI
From descriptive public health GIS to predictive GeoAI systems—illustrating the shift from understanding spatial patterns to building scalable, data-driven decision-support systems.
My journey into GIS began through public health and environmental applications, where spatial data plays a critical role in understanding disease patterns, guiding resource allocation, and supporting decision-making.
Before securing my first professional role, I volunteered on public health and geospatial initiatives—collaborating with multidisciplinary teams and supporting data collection and analysis efforts. This early experience exposed me to real-world challenges: working with limited resources, imperfect data, and high-stakes decision environments.
It also provided opportunities to engage with government institutions, international partners, and multilateral organizations, shaping my understanding of how geospatial systems operate within broader development and policy contexts.
Early Foundations in Predictive Thinking
Early in my career, I was already working at the intersection of spatial analysis and modeling.
During my MSc research in Geoinformation Science and Remote Sensing, I developed models to analyze the relationship between malaria vector distribution and climate change, applying machine learning techniques such as Maximum Entropy (MaxEnt) to predict future risk patterns under different climate scenarios.
This work was later featured in the President’s & Plenary Sessions at the 2020 Esri User Conference.
That experience introduced me to predictive spatial modeling—long before GeoAI became a common term—and shaped how I approached spatial problems beyond visualization.
Building GIS Under Real-World Constraints
I later applied similar analytical thinking during the COVID-19 pandemic, contributing to research on reinfection patterns in Liberia. Using national surveillance data and geospatial analysis in ArcGIS Pro, we identified clustering patterns and transmission dynamics, reinforcing how critical spatial intelligence is in public health decision-making.
One of my most impactful operational experiences involved developing spatiotemporal GIS analysis for COVID-19 surveillance in Liberia.
This work was carried out under real-world constraints:
- Missing coordinates for most cases that should have been spatial
- Limited field data collection tools
- Fragmented and inconsistent reporting systems
To overcome this, I:
- Digitized case locations manually
- Reconstructed spatial datasets from non-standard inputs
- Applied density-based hotspot and clustering analysis for operational surveillance, alongside spatial statistical methods (e.g., Moran’s I) in research contexts to support national response efforts
This became a defining turning point in my journey.
It taught me that real-world GIS is rarely clean—it is built from imperfect data, constraints, and constant problem-solving. It also highlighted the importance of data reconstruction, spatial validation, and adaptive analytical approaches when working with incomplete or imperfect data.
View project: COVID-19 Temporal Hotspot Analysis — Montserrado County, Liberia
This work was later featured in the 2021 Esri User Conference Virtual Map Gallery as a model for hyperlocal outbreak monitoring and resource planning, and again in 2023—where it supported daily national incident management decisions.
At the time, my work was primarily descriptive and spatiotemporal—but it established the analytical foundation for my transition into predictive modeling, GeoAI, and scalable decision-support systems.
Lessons from the Transition
Transitioning from traditional GIS workflows to GeoAI and enterprise systems was not straightforward.
One of the biggest challenges I encountered was moving beyond map-centric thinking.
Early in my career, success was measured by how well I could visualize and communicate spatial patterns. But as I explored GeoAI, I realized that visualization was only one part of a much larger system.
I needed to think in terms of:
- Data pipelines
- Machine learning workflows
- Cloud-based architectures
At first, these concepts felt far outside the traditional GIS skillset.
Another challenge was bridging the gap between domain expertise and technical implementation. Understanding public health data was one thing—but building systems that could process, analyze, and operationalize that data at scale was another.
My MSc in Big Data Technologies played a critical role in helping me bridge that gap. It exposed me to distributed data processing, machine learning pipelines, and cloud-based systems—connecting spatial analysis to enterprise-scale architectures.
I navigated this transition by:
- Working on small, practical projects
- Expanding into Python and data engineering tools
- Learning continuously through communities like Esri YPN
Over time, this shifted my perspective from creating outputs to building systems that support decisions.
The Shift to System-Level Thinking
Today, GIS is no longer just about visualization.
It is about building end-to-end data pipelines, integrating multi-source datasets, and delivering actionable insights through scalable, production-oriented architectures.
This shift reflects a broader transformation in the field:
GIS is evolving into a data engineering–driven, decision-support platform.
Building GeoAI Systems in Practice
A high-level GeoAI system architecture integrating spatial data, machine learning, APIs, and cloud infrastructure to support scalable, secure, and explainable decision-making systems.
Recently, I have been working on a GeoAI-based health surveillance system that integrates spatial modeling, machine learning, and governance-aware data processing.
This experience reinforced an important lesson:
Real-world systems require the integration of:
- Spatial analytics and machine learning
- Data engineering and cloud infrastructure
- Governance, privacy, and explainability
In domains like public health and infrastructure, these elements must work together to support trusted and scalable decision-making.
Insights from the YPN Charlotte Meetup
Esri YPN Charlotte Spring Meetup, 2026 — Connecting GIS professionals and exploring emerging technologies
Inside the Esri YPN Charlotte Spring Meetup—exploring enterprise GIS, Digital Twins, and real-world applications of spatial data across infrastructure and urban systems.
Attending the Esri YPN Charlotte Spring Meetup reinforced many of these ideas.
It was especially insightful to see how concepts like Digital Twins and enterprise GIS are already being applied in real-world environments—from infrastructure and utilities to urban planning.
What stood out most to me, however, was the power of community.
Engaging with professionals across different domains provided real insight into how GIS is being operationalized at scale—and reminded me that growth in this field is not just technical, but also collaborative.
Advice for Emerging GIS Professionals
If you are starting your journey—or thinking about transitioning into GeoAI—here is my biggest takeaway:
GIS is no longer just about mapping—it’s about integrating spatial thinking into larger data and decision systems.
You don’t need to master everything at once. Start by:
- Strengthening your foundation in spatial analysis
- Learning basic scripting (Python, SQL)
- Exploring how GIS connects with cloud and data platforms
Most importantly:
- Stay curious
- Stay adaptable
The field is evolving rapidly, and your ability to learn continuously will matter just as much as your current skillset.
Community also plays a key role. Platforms like the Esri Young Professionals Network provide exposure, ideas, and connections that can significantly accelerate your growth.
Looking Ahead
If you’re working on enterprise GIS or GeoAI, I’d be interested in hearing about the challenges and tools you’re seeing in practice.
I look forward to connecting with others in the YPN community who are exploring similar paths and contributing to the future of GIS.
This journey is still evolving—but it is clear that the future of GIS lies not just in mapping the world, but in building intelligent systems that help shape it.
What tools or skills have you found most critical for bridging GIS with data engineering and AI in real-world systems? Let’s discuss in the comments.
I’m always interested in connecting with fellow GIS professionals and exploring how spatial technologies continue to evolve.
Feel free to connect with me on LinkedIn to continue the conversation.
— Godwin E. Akpan
