Authors: Bryan Runck*, University of Minnesota
Topics: Geographic Information Science and Systems, Land Use and Land Cover Change, Quantitative Methods
Keywords: agent-based model, multifunctional agriculture, natural language processing
Session Type: Poster
Start / End Time: 9:55 AM / 11:35 AM
Room: Lincoln 2, Marriott, Exhibition Level
Presentation File: No File Uploaded
Multifunctional agriculture (MFA) is a critical approach to sustainable development because it produces standard commodity goods such as food or fiber along with a broader range of human and ecological services. However, empirical evidence from Europe and the United States suggests that MFA does not always emerge organically at the landscape-scale even under favorable market conditions. Landscape approaches engage farmers, environmental and commodity groups, and other place-based stakeholders in discussion and deliberation about potential future pathways for sustainable development. While empirical results suggest collaborative processes can have positive impacts on the adoption of MFA, little is known about how communication within collaborative interventions causes cascading effects from changes in individual-level attributes to subsequent land use decision-making. Using natural language processing tools to model key aspects of human learning and cognition, we develop a spatial agent-based model of Seven Mile Creek Watershed in southern Minnesota, USA. Using this model, we tested how the communication approach, duration of landscape initiative, and frequency of collaboration result in agent learning related to agricultural production, and how learning corresponded with MFA preferences. While substantial variation exists, we find strong correlation between the frequency of meetings and the time to impact for landscape initiatives regardless of other structural factors. Overall, this project addresses critical gaps in our understanding of multifunctionality and advances the broader research agenda in land change and sustainability, as well as advances the methodological reach of regional science and policy.