International Journal of Engineering and Manufacturing (IJEM)
IJEM Vol. 16, No. 4, 8 Aug. 2026
Cover page and Table of Contents: PDF (size: 862KB)
A Novel Explainable LLM-based Why-QA Framework for Climate Resilient and Sustainable Smart Agriculture
PDF (862KB), PP.302-323
Views: 0 Downloads: 0
Author(s)
Index Terms
Explainable AI, Question Answering System, Sustainability, Knowledge Graph, Smart Agriculture, Causality, LLM
Abstract
Sustainable smart agriculture and climate resilience are significant factors for maintaining food security with environmental management. Existing agricultural systems target predicting and generating reports but lack detailed explanations as to why the phenomenon occurs. The examples of such why are like “Why there is a significant decline in the yield?”, “Why the soil is degrading?”, “Why the level of water is declining?” and so on. To address this challenge, the paper presents a prototype for Explainable LLM based Why-QA framework for sustainable smart agriculture. The implemented prototype integrates domain-enriched LLM with knowledge graph, causal inference engine with explainability layer to provide detailed explanations to complex “why-questions”. Domain-specific LLMs are used to support the domain knowledge with knowledge graph analyzing the sustainable relationships in the answer, causal reasoning to produce the causes of events and explainability module to provide the detailed reasoning supported with benchmark sustainable metrics incorporating the soil, climate and crop data. The prototype implementation of framework is evaluated on a dataset of 500 annotated agricultural why-type questions constructed from FAOSTAT, USDA, and NOAA sources. Results clearly demonstrate promising improvements over five baseline systems developed across causal reasoning and explanation quality metrics, which help validating the architectural feasibility of the proposed framework.
Cite This Paper
Manvi Breja, "A Novel Explainable LLM-based Why-QA Framework for Climate Resilient and Sustainable Smart Agriculture", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.4, pp.302-323, 2026. DOI:10.5815/ijem.2026.04.21
Reference
[1]Breja, M., & Jain, S. K. (2022). Analyzing linguistic features for answer re-ranking of why-questions. Journal of Cases on Information Technology (JCIT), 24(3), 1-16. https://doi.org/10.4018/JCIT.20220701.oa10
[2]Surdeanu, M., Ciaramita, M., & Zaragoza, H. (2011). Learning to rank answers to non-factoid questions from web collections. Computational linguistics, 37(2), 351-383. https://doi.org/10.1162/COLI_a_00051
[3]Mishra, A., & Jain, S. K. (2016). A survey on question answering systems with classification. Journal of King Saud University-Computer and Information Sciences, 28(3), 345-361. https://doi.org/10.1016/j.jksuci.2014.10.007
[4]Sharp, R., Surdeanu, M., Jansen, P., Clark, P., & Hammond, M. (2016). Creating causal embeddings for question answering with minimal supervision. In EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 138-148). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d16-1014
[5]Breja, M., & Jain, S. K. (2022). A survey on non-factoid question answering systems. International Journal of Computers and Applications, 44(9), 830-837. https://doi.org/10.1080/1206212X.2021.1949117
[6]Breja, M., & Jain, S. K. (2020). Causality for Question Answering. In COLINS (pp. 884-893). https://ceur-ws.org/Vol-2604/
[7]Bondarenko, A., Wolska, M., Heindorf, S., Blübaum, L., Ngomo, A. C. N., Stein, B., ... & Potthast, M. (2022, October). CausalQA: A benchmark for causal question answering. In Proceedings of the 29th International Conference on Computational Linguistics (pp. 3296-3308). https://aclanthology.org/2022.coling-1.291/
[8]Pechsiri, C., & Piriyakul, R. (2016). Developing a Why–How Question Answering system on community web boards with a causality graph including procedural knowledge. Information Processing in Agriculture, 3(1), 36-53. https://doi.org/10.1016/j.inpa.2016.01.002
[9]Lamm, M., Palomaki, J., Alberti, C., Andor, D., Choi, E., Soares, L. B., & Collins, M. (2021). QED: A framework and dataset for explanations in question answering. Transactions of the Association for computational Linguistics, 9, 790-806. https://doi.org/10.1162/tacl_a_00398
[10]Fan, Y., Wang, Y., Wang, G., Jie, Z., Liu, J., Ye, Q., & Ruan, T. (2025, July). MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 10517-10548). https://doi.org/10.48550/arXiv.2506.15215
[11]Linders, J., Tomczak, J.M. Knowledge graph-extended retrieval augmented generation for question answering. Appl Intell 55, 1102 (2025). https://doi.org/10.1007/s10489-025-06885-5
[12]Knollmeyer, S., Caymazer, O., & Grossmann, D. (2025). Document graphrag: knowledge graph enhanced retrieval augmented generation for document question answering within the manufacturing domain. Electronics, 14(11), 2102. https://doi.org/10.3390/electronics14112102
[13]Rajbongshi, A., Johora, F.T., Hossain, A. et al. Leveraging explainable AI for sustainable agriculture: a comprehensive review of recent advances. Artif Intell Rev 59, 105 (2026). https://doi.org/10.1007/s10462-025-11459-5
[14]Breja, M., & Jain, S. K. (2022). Why-Type Question to Query Reformulation for Efficient Document Retrieval. International Journal of Information Retrieval Research (IJIRR), 12(1), 1-18. https://doi.org/10.4018/IJIRR.289948
[15]Yasunaga, M., Ren, H., Bosselut, A., Liang, P., & Leskovec, J. (2021, June). QA-GNN: Reasoning with language models and knowledge graphs for question answering. In Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies (pp. 535-546). https://doi.org/ 10.18653/v1/2021.naacl-main.45
[16] Li, Z.W., Wang, G.Y., Khan, K. et al. Irrigation combines with nitrogen application to optimize soil carbon and nitrogen, increase maize yield, and nitrogen use efficiency. Plant Soil 499, 605–620 (2024). https://doi.org/10.1007/s11104-024-06480-6
[17]Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30. https://doi.org/10.48550/arXiv.1705.07874
[18]Food and Agriculture Organization of the United Nations (FAO). (2024). FAOSTAT Statistical Database. Rome, Italy: FAO. Available at: https://www.fao.org/faostat/
[19]United States Department of Agriculture (USDA). (2023). USDA National Agricultural Statistics Service (NASS) Quick Stats Database. Washington, DC: USDA. Available at: https://www.nass.usda.gov/datasets
[20]National Oceanic and Atmospheric Administration (NOAA). (2023). NOAA National Centers for Environmental Information (NCEI) Climate Data Online. Silver Spring, MD, USA. Available at: https://www.ncdc.noaa.gov/cdo-web/
[21]Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., ... & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33, pp. 9459-9474. https://dl.acm.org/doi/abs/10.5555/3495724.3496517
[22]Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024, May). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In International conference on learning representations (Vol. 2024, pp. 9112-9141).
[23]https://doi.org/10.48550/arXiv.2310.11511
[24]Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., ... & Larson, J. (2024). From local to global: A graph rag approach to query-focused summarization. https://doi.org/10.48550/arXiv.2404.16130
[25]Wang, X., Wei, J., Schuurmans, D., Le, Q. V., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2023). Self-Consistency Improves Chain of Thought Reasoning in Language Models. International Conference on Learning Representations (ICLR) https://doi.org/10.48550/arXiv.2203.11171
[26]Kuska, M. T., Wahabzada, M., & Paulus, S. (2024). AI for crop production–Where can large language models (LLMs) provide substantial value?. Computers and electronics in agriculture, 221, 108924. https://doi.org/ 10.1016/j.compag.2024.108924
[27] Christadoss, J., & Panda, M. R. (2025). Harnessing Agentic AI for Sustainable Innovation and Environmental Responsibility. Futurity Proceedings, (5), 269-280. https://doi.org/10.5281/zenodo.17662706