Johannes Schielein
I earned degrees in Geography and Economics at the University of Bonn and completed a PhD in Agricultural Economics, where I harnessed geospatial technologies and econometrics to analyze and model land-use and land-cover change in the Amazon. My career spans roles in nature conservation with the German Technical Cooperation (GIZ) and project impact assessment in the evaluation department at KfW Development Bank. For the past three years, I have served as IT Manager at KfW Development Bank, where I spearhead the development of a robust data infrastructure—with a particular focus on implementing geospatial solutions exclusively through open-source technologies. I am also the co-founder of the MAPME initiative, an open-source community committed to scaling up the use of geoinformation in development cooperation.
Sessions
Maps have long been essential tools in both public and private sectors. However, until recently, Geographic Information Systems (GIS) and map creation were largely confined to a small community of highly trained experts. Mainstream adoption has been stifled by several entry barriers: (1) the need for specialized domain knowledge in GIS concepts, data, and methodologies; (2) the technological complexity inherent in data management, integration, and processing; (3) unintuitive, cluttered user interfaces in many widely used GIS applications and data portals; and (4) prohibitive software licensing costs—especially for public institutions in developing countries. These challenges have often necessitated hiring specialized staff, thereby limiting the proliferation of geospatial technologies among small to medium enterprises and public agencies, despite the critical role geoinformation plays in addressing key 21st-century challenges such as climate change adaptation.
Recent advancements in Generative Artificial Intelligence—especially the emergence of large language models and agent-based systems—promise to lower these barriers significantly. In response, we have initiated the open-source project aGEOi (Artificial Geospatial Intelligence). aGEOi is designed to democratize access to geospatial information by automating significant portions of the map creation process, including data research, geospatial processing, and web-based data and map integration. The framework is built on widely adopted open-source technologies such as Python, ReactJS, LangChain, Graphagent, and OpenLayers. Its core components include a user-friendly chatbot, an interactive map interface, and an extensive data library based on web-crawling of open-data portals. The chatbot automatically geocodes user requests and intelligently searches for tools, datasets, and unstructured information—enabling users to generate maps with written text commands and evaluate data suitability for specific research questions without requiring deep GIS expertise.
By seamlessly integrating with existing geospatial infrastructures, aGEOi not only builds upon current workflows but also scales the reach of geodata products from established teams and projects. In doing so, it has the potential to empower decision-makers across multiple sectors—from urban planning and environmental monitoring to crisis response. With our talk we would like to invite the FOSS4G community to join us in pioneering a more accessible, efficient, and inclusive future for geospatial intelligence.