Title: Three generations of Multi-Agent system for environmental simulation (MASE)

Abstract

This talk presents a multi-agent model system to characterize land-use change dynamics. The evolution of MASE followed three generations. The first generation (Ralha et al., 2013), where the methodological two-fold approach intends to form a solid backbone based on: (i) the systematic and structured empirical characterization of the model; and (ii) the conceptual structure definition according to the agent-based model documentation protocol – Overview, Design concepts and Details (ODD). MASE was illustrated with a case study of the Brazilian Cerrado using LANDSAT ETM images. The simulation results prove the model importance with a figure of merit greater than 50%, what means the amount of correctly predicted change is larger than the sum of any type of error. MASE-BDI is the second generation (Coelho et al., 2016) introducing rationality to agents using a mentalistic approach with Belief-Desire-Intention (BDI) model. An auto-tuning approach aligned to parallelization techniques are employed to speed up the simulation execution times. Compared to MASE using the Brazilian Cerrado biome case reduces execution time by at least 82 X. MASE-EGTI is the third generation (Coelho & Ralha, 2022} with agents' decision model based on evolutionary game theory including three-dimensions: individual, peer-to-peer, and societal. The modeling structure includes Space, Time, Agents, Interactions and Public policy (STAIP). Experiments use real data form MapBiomas Brazilian public geographic database.