Rethinking Spatial Composite Indicators with the Lens of Machine Learning
April 23, 2025 11:00 am (Central Time)
Abstract
Spatial composite indicators simplify complex, multi-dimensional data into concise performance metrics used in policy and decision-making. While useful for visualizing intricate systems, these indicators are inherently subjective, as their components are chosen by decision-makers. In this session, I will share how spatial composite indicators can be enhanced using machine learning, specifically self-organizing maps, to reduce dimensionality and improve interpretability. Using Arctic development as a case study, the research integrates socioeconomic, environmental, and infrastructural data to reveal hidden patterns and interconnections. By identifying key factors driving vulnerability and resilience, this approach aims to create more transparent indicators, reducing subjectivity and supporting policy, disaster preparedness, and resource allocation.
Speakers
Seda Şalap-Ayça
Brown University
I am a GIScientist passionate about solving spatial decision making problems and understanding the role of uncertainty in spatial models, particularly for human-environment interactions. I did my Ph.D. in Geography in a joint doctoral program between UC Santa Barbara and San Diego State University. As a Ph.D. Student, I focused on spatially explicit uncertainty and sensitivity analysis methods for land use models. At UMass, Amherst, as a researcher and educator, I have taught an array of GIS courses at various levels. At Brown, I am eager to engage with diverse minds and continue to work with my colleagues on the complexities of human-environment dynamics.