NSF 2024-2026: POSE: Phase II: An Open Source Ecosystem for Spatial Data Science

This project is funded by Pathways to Enable Open-Source Ecosystems (POSE) Program which seeks to harness the power of open-source development for the creation of new technology solutions to problems of national and societal importance. In today’s rapidly evolving world, it is important to understand location data as related to complex societal issues. From urban planning and environmental management to public health and economic development, spatial data science stands at the forefront of decision-making processes, enabling the visualization and analyzis of data in ways that reveal relationships, patterns, and trends across various geographies. This project, spearheaded by an interdisciplinary team at the San Diego State University in collaboration with the University of Chicago, the University of Maryland, and the University of California Riverside, aims to improve the field of spatial data science through the development and enhancement of the Python Spatial Analysis Library (PySAL) open-source ecosystem. With a focus on expanding accessibility, functionality, and collaborative potential, the initiative is poised to democratize spatial data analysis, making powerful tools available to researchers, policymakers, and the public. The project’s dedication to open-source principles fosters innovation and ensures that advancements in spatial data science are shared freely, promoting transparency and inclusivity in research and application.

The technical core of this project revolves around the strategic expansion of PySAL and the cultivation of a supportive ecosystem that bridges the gap between scientific inquiry and practical application. By integrating advancements in spatial analysis with the latest computational techniques, the project aims to refine and extend PySAL?s capabilities to meet the growing demands of diverse data-intensive environments. The initiative seeks to build a robust network of users, developers, and educators through participatory learning and targeted outreach. This multi-faceted approach includes enhancing educational resources to train the next generation of spatial data scientists, fostering cross-domain collaborations, and developing user-friendly tools that cater to the specific needs of industry and government sectors. Through these efforts, the project aspires to advance the science of spatial analysis and equip stakeholders with the means to address real-world challenges more effectively and equitably.