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

Introduction

Traditional rice varieties represent a vital reservoir of genetic diversity and cultural heritage in rice-producing regions like Tamil Nadu, India. Over centuries, local farming communities have preserved indigenous landraces including Karunkuruvai, Mappillai Samba, Karuppu Kavuni, Kattuyanam and Kullakar, each uniquely adapted to specific agroecological niches and cultivated through traditional practices. These landraces embody the resilience and ingenuity of smallholder farmers while conserving valuable traits such as drought tolerance, pest resistance and distinctive nutritional qualities. In recent years, their agronomic and socioeconomic importance has grown considerably due to rising health awareness and shifting consumer preferences. Traditional varieties are increasingly valued for their low glycemic index, making them suitable for diabetic and health-conscious populations. Additionally, they command premium prices in niche markets and contribute to the enhancement of rural livelihoods through value-added marketing and heritage branding initiatives [1,2] . In Fig. 1, the dominance of rice cultivation in India's top rice-growing states based on area coverage during the 2024-25 season is depicted. Uttar Pradesh leads with an impressive 154.74 lakh acres, followed by West Bengal at 102.50 lakh acres and Chhattisgarh with 96.40 lakh acres. This geographic distribution reflects both the climatic suitability and agricultural focus of these regions, highlighting their critical role in sustaining India's overall rice economy [3] . Despite these advantages, many farmers remain hesitant to adopt Indigenous Rice cultivation due to uncertainties regarding yield performance, market demand, input costs, and seasonal adaptability. This underscores the need for robust, data-driven decision-support tools that can assist growers in selecting the most suitable varieties under complex, often conflicting, criteria. In response to this challenge, the present study introduces a novel Multi-Criteria Decision-Making (MCDM) framework by extending the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) into a Pentapartitioned Neutrosophic environment. This approach enables a more nuanced representation of uncertainty, ignorance, contradiction, and expert disagreement in agricultural planning. By aggregating diverse expert opinions through the Pentapartitioned Neutrosophic Weighted Averaging (PNWA) operator, the proposed PN-TOPSIS model provides actionable insights for variety selection, validated through real-world data on key criteria such as yield, crop duration, seed cost, market demand, and seasonal stability. The findings offer practical guidance for farmers and policymakers aiming to revitalize traditional rice cultivation while navigating the complexities of modern agricultural systems.

Literature Review

Researchers have studied the theory of Neutrosophic sets in enormous detail to tackle uncertainty in our everyday lives. Smarandache F introduced the Neutrosophic Set [5] involving indeterminancy and inconsistent data as a mathematical tool for handling problems. Karabaevi et al. (2020) [4] introduced a novel MCDM method based on TOPSIS on SVNS. In 2023, Porchudar et al [11] developed an MCDM model for entrepreneurs and farmers using Neutrosophic Fuzzy SAW method. Rama Mallick and Surapati Pramanik [6] introduced the set called Pentapartitioned Neutrosophic Set and its properties in 2020. The Indeterminacy membership function is subdivided into three parts as contradiction, ignorance and unknown membership function. In 2021, R. Radha and A. Stanis Arul Mary [7] have proposed the concept of Pentapartitioned Neutrosophic Pythagorean Set. In 2022, Shio Gai Quek et al. [8] have introduced the concepts of pentapartitioned neutrosophic graphs (PPNGs) & have emphasized the effectiveness at extremely heterogeneous data in our daily life. In 2023, Yi-ming Li et al. [9] introduced pentapartitioned neutrosophic cubic set and also its operational laws. They have used these operators to check its applicability in some of the models, to detect the air pollution of cities in Pakistan. In 2024, Porchudar and Ajay [10] Makers have utilized the linguistic variables to weight the performance of each criterion over the selected Indigenous Rice varieties taken for evaluation. The following Table 1 explains the transformation of linguistic variables to corresponding Pentapartitioned Neutrosophic Numbers. The Pentapartitioned Neutrosophic Weight of each criterion is in Table 2 and the weight vector for the decision makers in Table 3 are presented respectively. Step:1 Based on the experts' opinion we constructed an Aggregated Pentapartitioned Neutrosophic Decision Matrix.

Step:2 Using the Criteia weights in table 2, we have aggregated the weighted Pentapartitioned Neutrosophic decision matrix and have tabulated it in table 4 and 5. Step:3 Pentapartitioned Neutrosophic Positive Ideal Solution (PNPIS) and Pentapartitioned Neutrosophic Negative Ideal Solution(PNNIS) were evaluated using Eq.8 and Eq.9, PNPIS and PNNIS were calculated.

Step:4 The separation measures is calculated and tabulated in table 6 for each alternative using the positive and negative ideal solution using Eq.(10 and 11).

Step:5 And finally the Closeness Coefficient for all the alternative are been calculated and displayed (table 9) using Eq. ( 10).

Conclusion

This study introduced the Pentapartitioned Neutrosophic Weighted Averaging (PNWA) operator and advanced a novel Pentapartitioned Neutrosophic TOPSIS (PN-TOPSIS) framework to address multi-criteria decision-making challenges in Indigenous Rice Cultivation. By integrating expert opinions under conditions of uncertainty, ignorance, and contradiction, the model evaluated five traditional varieties-Karunkuruvai, Mappillai Samba, Karuppu Kavuni, Kattuyanam, and Kullakar-against critical agronomic and economic criteria: yield, crop duration, seed cost, market demand, and seasonal stability. The PN-TOPSIS analysis revealed Kullakar as the optimal variety (closeness coefficient: 0.5685), followed by Karunkuruvai (0.5591), Kattuyanam (0.5407), Karuppu Kavuni (0.5317), and Mappillai Samba (0.4631). This ranking provides actionable guidance for farmers prioritizing resilience, profitability, and market alignment in traditional rice cultivation. The PN-TOPSIS method demonstrates robust decision-support capabilities, bridging empirical data with practical agricultural planning. Future research should expand this framework to other crops, regional contexts, and sustainability metrics, reinforcing the role of computational tools in preserving agrobiodiversity while enhancing farmer livelihoods.

References

1. Anuratha A, Krishnan V, Arulselvi S, Chitra M, Shibi S, Sangeetha M. Exploring traditional paddy varieties: Preserving a legacy of health, culture, and biodiversity -A review. Applied Ecology and Environmental Research. 2025;23(1).
2. Department of Agriculture & Farmers Welfare, Ministry of Agriculture and Farmers Welfare, Government of India. Paddy Area and Production Statistics. New Delhi; 2024.
3. Karabasevic D, Popovic G, Zavadskas EK. A Novel extension of the TOPSIS method adapted for the use of single valued neutrosophic sets and hamming distance for E-Commerce development strategies selection. MDPI. 2020.
4. Li Y, Khan M, Khurshid A, et al. Designing pentapartitioned neutrosophic cubic set aggregation operator-based air pollution decision-making model. Complex Intell Syst. 2023;9:4765-4782.
5. Malick R, Pramanik S. Pentapartitioned neutrosophic set and its properties. Neutrosophic sets and systems. 2020;36.
6. Porchudar T, et al. An MCDM Based on Neutrosophic Fuzzy SAW Method for New Entrepreneurs in Organic Farming. In: Recent Developments in Algebra and Analysis(ICRDM2022). Cham: Springer International Publishing; 2023. p 67-75.
7. Porchudar T, Ajay D. An MCDM on Complex Pentapartitioned Neutrosophic Einstein Aggregation Operators in Oil-Centric Agriculture. In: Intelligent and Fuzzy Systems. INFUS 2024. Lecture Notes in Networks and Systems, vol 1090. Cham: Springer; 2024.
8. Quek SG, Ajay D, Chellamani P, Taniar D, Fujita H, Duong P, et al. New concepts of pentapartitioned neutrosophic graphs and applications for determining safest paths and towns in response to COVID-19. Computational and Applied Mathematics. 2023.
9. Radha R, Arul Mary AS. Pentapartitioned Neutrosophic pythagorean Soft Set. International Research Journal of Modernization in Engineering Technology and Science. 2021;3(2).
10. Smarandache F. A Unifying field in logics: Neutrosophic logic: Neutrosophy, Neutrosophic set, Neutrosophic Probability. 4th ed. American Research Press; 1999.
11. Valarmathi R, Raveendran M, Robin S, Senthil N. Unraveling the nutritional and therapeutic properties of 'Kavuni' a traditional rice variety of Tamil Nadu. Journal of Plant Biochemistry and Biotechnology. 2015;24(3):305315.