Robust multi criteria decision making framework for sustainable management of equatorial forests in Central Africa

Long-term forest management planning is inherently complex due to the involvement of multiple stakeholders with diverse and often conflicting objectives. This study develops an AI-enhanced decision-support framework that integrates fuzzy multi-criteria decision-making (MCDA) with adaptive learning mechanisms for sustainable forest management. Multi-criteria decision analysis (MCDA) are applied to enhance decision making by integrating the fuzzy analytical hierarchy process (FAHP), the fuzzy technique for order preference by similarity to the ideal solution (FTOPSIS), and the fuzzy preference ranking organization method for enrichment evaluation (FPROMETHEE). Traditional MCDA methods often struggle to evaluate numerous management plans, potentially overlooking optimal solutions. FAHP determines criteria weights based on stakeholder preferences, while FTOPSIS and FPROMETHEE rank alternatives to identify the most suitable plan. The methodology is applied to a forest management case study in Central Africa, demonstrating that this integrated approach improves participatory planning by efficiently evaluating multiple options. By incorporating these methods into decision support systems, the framework expands the range of feasible solutions, increasing the likelihood of selecting a plan that aligns with stakeholder interests and promotes sustainable forest management. This study provides a robust, structured decision-making approach that facilitates transparency and inclusivity in forest management planning, offering valuable insights for policymakers and practitioners.