An Intelligent Decision Support Framework for Agricultural Applications Based on Bipolar Spherical Fuzzy Hypersoft Sets

Abstract

Agriculture plays a vital role in economic development and food security, where effective planning, evaluation, and resource management are essential for achieving sustainable outcomes. Agricultural decision-making often involves complex, uncertain, and sometimes contradictory information arising from multiple criteria and sub-criteria such as soil conditions, climatic factors, crop characteristics, irrigation methods, and environmental constraints. Therefore, reliable decision support tools are required to analyze such information and assist policymakers, researchers, and practitioners in making well-informed choices. To address these challenges, this study proposes a novel Bipolar Spherical Fuzzy Hypersoft Set (BSFHSS) framework, which extends the capability of existing fuzzy models by simultaneously handling positive and negative information under a spherical fuzzy environment. The proposed structure consists of two interconnected spherical fuzzy hypersoft sets, representing favorable and unfavorable information for each degree of membership, non-membership, and hesitancy. Fundamental properties of the proposed model are established, including set-theoretic operations and an in-depth investigation of De Morgans laws within the BSFHSS context. Furthermore, a Bipolar Spherical Fuzzy Hypersoft Weighted Geometric (BSFHSWG) aggregation operator is developed to effectively combine bipolar spherical fuzzy hypersoft numbers under multiple sub-attributes. Based on the proposed operators, a systematic multi-attribute decision-making algorithm is constructed to support performance evaluation and comparative analysis in agricultural applications. The presented framework demonstrates the significance of incorporating bipolarity, uncertainty, and hierarchical attribute structures when addressing complex agricultural decision-making problems, thereby offering a robust and flexible tool for intelligent agricultural planning and assessment.