The Multi Agent-Based Environmental Landscape model (MABEL) introduces a Distributed Artificial Intelligence (DAI) systemic methodology, to simulate land use and transformation changes over time and space. Computational agents represent abstract relations among geographic, environmental, human and socio-economic variables, with respect to land transformation pattern changes. A multi-agent environment is developed providing task-nonspecific problem-solving abilities, flexibility on achieving goals and representing existing relations observed in real-world scenarios, and goal-based efficiency. Intelligent MABEL agents acquire spatial expressions and perform specific tasks demonstrating autonomy, environmental interactions, communication and cooperation, reactivity and proactivity, reasoning and learning capabilities. Their decisions maximize both task-specific marginal utility for their actions and joint, weighted marginal utility for their time-stepping. Agent behavior is achieved by personalizing a dynamic utility-based knowledge base through sequential GIS filtering, probability-distributed weighting, joint probability Bayesian correlational weighting, and goal-based distributional properties, applied to socio-economic and behavioral criteria. First-order logics, heuristics and appropriation of time-step sequences employed, provide a simulation-able environment, capable of re-generating space-time evolution of the agents.