A Samuel Pottinger | Searcharxiv

arXiv2025

Using Game Design to Inform a Plastics Treaty: Fostering Collaboration between Science, Machine Learning, and Policymaking

Introduction: This multi-disciplinary case study details how an interactive decision support tool leverages game design to inform an international plastic pollution treaty. Design: Seeking to make our scientific findings more usable within the policy process, our interactive software supports manipulation of a mathematical model using techniques borrowed from games. These "ludic" approaches aim to enable user agency to find custom policy solutions, invite deep engagement with scientific results, serve audiences of diverse expertise, and accelerate scientific process to keep pace with intergovernmental negotiations. Implementation: Built in JavaScript and D3 with user-modifiable logic via an ANTLR domain specific language, this browser-based application offers adaptability and explorability for our machine learning results with privacy preserving architecture and offline capability. Demonstration: Policymakers and the supporting community engaged with this public simulation tool across multiple treaty-related events, investigating plastic waste outcomes under diverse and sometimes unexpected policy scenarios. Conclusion: Contextualizing our open source software within a broader lineage of digital media research, we reflect on this interactive modeling platform, considering how game design approaches may help facilitate collaboration at the science / policy nexus. Materials: Available on the public Internet, we host this browser-based decision support tool at global-plastics-tool.org, work also archived at zenodo.org/records/12615011 in a Docker container.

cs.HC↗

arXiv2024

Climate-Driven Doubling of U.S. Maize Loss Probability: Interactive Simulation with Neural Network Monte Carlo

Climate change not only threatens agricultural producers but also strains related public agencies and financial institutions. These important food system actors include government entities tasked with insuring grower livelihoods and supporting response to continued global warming. We examine future risk within the U.S. Corn Belt geographic region for one such crucial institution: the U.S. Federal Crop Insurance Program. Specifically, we predict the impacts of climate-driven crop loss at a policy-salient "risk unit" scale. Built through our presented neural network Monte Carlo method, simulations anticipate both more frequent and more severe losses that would result in a costly doubling of the annual probability of maize Yield Protection insurance claims at mid-century. We also provide an open source pipeline and interactive visualization tools to explore these results with configurable statistical treatments. Altogether, we fill an important gap in current understanding for climate adaptation by bridging existing historic yield estimation and climate projection to predict crop loss metrics at policy-relevant granularity.

cs.LG↗