Data-driven selection of indigenous rice varieties using a Pentapartitioned Neutrosophic decision model

In this study, five prominent indigenous rice varieties Karunkuruvai, Mappillai Samba, Karuppu Kavuni, Kattuyanam, and Kullakar were critically analyzed to assist the farming community in selecting the most suitable variety under multiple conflicting criteria. A novel Multi-Criteria Decision-Making (MCDM) framework is proposed by extending the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) into a Pentapartitioned Neutrosophic environment, allowing for a more realistic representation of uncertainty, ignorance, contradiction, and expert disagreement. To aggregate the opinions of diverse experts, we introduce a new operator termed the Pentapartitioned Neutrosophic Weighted Averaging (PNWA) operator. This enhanced decision model, referred to as PN-TOPSIS, is applied to real-world agricultural data involving key criteria such as yield, crop duration, seed cost, market demand, and seasonal stability. Based on the closeness coefficients derived from the model, Kullakar emerged as the most recommended rice variety, offering valuable insight to farmers interested in traditional rice cultivation. The results demonstrate the practical relevance and decision-support capabilities of the PN-TOPSIS method in agricultural planning.