Suzanne A. Pierce

Cities and urban areas present important opportunities for advancing toward sustainability and resilience goals. From a systems perspective, various targets and indicators of key outcomes reflect sustainability of urban areas, motivating consideration of local and regional context. We explore four key themes for creating sustainable urban areas: 1) urban areas are complex systems linked with diverse rural areas across the urban-rural gradient, 2) data and modeling of physical and non-physical systems can aid decision making for sustainability, 3) creating sustainable urban-rural systems requires collaboration with partner communities, and 4) change requires adaptive and transformative governance frameworks. These themes guide sustainability innovations through co-production of knowledge among communities, authorities, managers, and researchers. The sustainability of urban areas strongly depends on urban-rural connectivity regarding both physical systems and governance frameworks.

Science gateways represent pivotal computational infrastructure for deploying environmental decision support systems that address complex stakeholder requirements and wicked problems. This research demonstrates how these platforms democratize access to high-performance computing while enabling participatory decision-making that integrates community knowledge with scientific analysis. We developed the Decision Pathways Framework (DPF), a three-phase approach implemented through Computational Cookbooks that facilitate rapid prototyping and integration of flexible decision support capabilities at scale. Our methodology employs containerized workflows including natural language processing for extracting insights from community narratives and semantic linking algorithms connecting qualitative stakeholder descriptions to quantitative scientific variables through standardized naming conventions. The approach is validated through a case study analyzing interviews with members of an Alaskan village regarding Arctic infrastructure challenges, successfully processing themes across six categories and automatically linking community observations to measurable parameters such as permafrost thaw rates. The semantic linking enabled recommendation of relevant datasets and physics-based models from computational catalogs, significantly reducing technical barriers for non-expert users to build visualizations and reports. These findings demonstrate how science gateways can evolve beyond job submission platforms into collaborative sociotechnical environments that preserve community-centered decision-making while maintaining computational rigor, fostering collaborative intelligence in environmental management, and accelerating access to advanced analytical tools for communities facing urgent environmental challenges.

We use AI techniques to create a modeling environment that makes sophisticated models accessible to non-experts. Our AI framework for Model INTegration (MINT) assists users to explore scenarios, which MINT can run in a local environment or at scale in a supercomputing facility. We are using MINT with hydrology, agriculture, and drought models for food security.

Understanding the interactions between natural processes and human activities poses major challenges as it requires the integration of models and data across disparate disciplines. It typically takes many months and even years to create valid end-to-end simulations as different models need to be configured in consistent ways and generate data that is usable by other models. MINT is a novel framework for model integration that captures extensive knowledge about models and data and aims to automatically compose them together. MINT guides a user to pose a well-formed modeling question, select and configure appropriate models, find and prepare appropriate datasets, compose data and models into end-to-end workflows, run the simulations, and visualize the results. MINT currently includes hydrology, agriculture, and socioeconomic models.

A research agenda for intelligent systems that will result in fundamental new capabilities for understanding the Earth system.