Logo PTI Logo FedCSIS

Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 43

Bridging Global Language Models and Local Spatial Data: The JackDaw Approach to Context-Aware Agriculture and Rural Planning

, , , , , , , , ,

DOI: http://dx.doi.org/10.15439/2025F8393

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 507–518 ()

Full text

Abstract. Large Language Models (LLMs) excel at synthesising globally documented knowledge but lack the fine-grained, real-time awareness required for field-level agricultural and rural-planning decisions. This paper introduces JackDaw, a spatially enabled chat-agent architecture that couples foundation-model reasoning with multi-modal geospatial data streams and a retrieval-augmented generation (RAG) pipeline. JackDaw implements a tool-prefiltering mechanism that selects only those data connectors whose topical, temporal and spatial metadata match the current query, thereby mitigating the diminishing returns observed when LLMs are exposed to large, flat toolsets. Through LangChain-based orchestration the platform dynamically assembles workflows that range from lightweight natural-language processing models to domain-specific analytic kernels, while a value-engineering strategy allocates computationally intensive models (e.g., GPT-4-class) only to tasks that require broad contextual reasoning. Benchmark experiments on forestry-asset discovery and vineyard-site assessment demonstrate that JackDaw delivers location-specific, traceable answers that outperform a standalone proprietary LLM, which provides only generic or spatially misattributed responses. The results confirm that bridging global language models with local spatial intelligence markedly reduces hallucination rates and enhances the operational readiness of AI for sustainable agriculture and rural development.

References

  1. Ryan, M., Isakhanyan, G., & Tekinerdogan, B. (2023). An interdisciplinary approach to artificial intelligence in agriculture. NJAS: Impact in Agricultural and Life Sciences, 95(1), 2168568, https://doi.org/10.1080/27685241.2023.2168568
  2. Ruiz-Real, J. L., Uribe-Toril, J., Torres Arriaza, J. A., & de Pablo Valenciano, J. (2020). A look at the past, present, and future research trends of artificial intelligence in agriculture. Agronomy, 10(11), 1839, https://doi.org/10.3390/agronomy10111839
  3. G. Cisotto, D. D. Tegegn, A. Zancanaro, I. Reguzzoni, E. Lotti, S. L. Manzoni, and I. F. Zoppis, “An AI-Empowered Energy-Efficient Portable NIRS Solution for Precision Agriculture: A Pilot Study on a Citrus Fruit,” Proc. 19th Conf. Computer Science and Intelligence Systems, ACSIS, vol. 39, pp. 313–318, 2024, DOI: 10.15439/2024F5111
  4. Bolfe, É. L., Parreiras, T. C., Sano, E. E., Bettiol, G. M., & Vicente, L. E. (2023). Mapping agricultural intensification in the Brazilian Savanna: A machine-learning approach using harmonised Landsat–Sentinel-2 data. ISPRS International Journal of Geo-Information, 12(7), 263, https://doi.org/10.3390/ijgi12070263
  5. Dakir, A., Barramou, F., & Bachir Alami, O. (2023). Towards a Machine Learning-based Model for Automated Crop Type Mapping. International Journal of Advanced Computer Science and Applications (IJACSA), 14(1). https://doi.org/10.14569/IJACSA.2023.0140185
  6. P. Bertellini, G. D’Addese, G. Franchini, S. Parisi, C. Scribano, D. Zanirato, and M. Bertogna, “Binary Classification of Agricultural Crops Using Sentinel Satellite Data and Machine Learning Techniques,” Proc. 18th Conf. Computer Science and Intelligence Systems, ACSIS, vol. 35, pp. 859–864, 2023, DOI: 10.15439/2023F1703
  7. Dhillon, M. S., Dahms, T. C., Kübert-Flock, C., Rummler, T., Arnault, J., Steffan-Dewenter, I., & Ullmann, T. (2023). Integrating random forest and crop modelling improves the yield prediction of winter wheat and oil-seed rape. Frontiers in Remote Sensing, 3, 1010978. https://doi.org/10.3389/frsen.2022.1010978
  8. Gumma, M. K., Nukala, R. M., Panjala, P., Bellam, P. K., Gajjala, S., Dubey, S. K., & Deevi, K. C. (2024). Optimizing Crop Yield Estimation through Geospatial Technology: A Comparative Analysis of a Semi-Physical Model, Crop Simulation, and Machine Learning Algorithms. AgriEngineering, 6(1), 786–802, https://doi.org/10.3390/agriengineering6010045
  9. Qi, H., Wang, L., Zhu, H., Gani, A., & Gong, C. (2023). The barren plateaus of quantum neural networks: review, taxonomy and trends. Quantum Information Processing, 22(12), 435. https://doi.org/10.1007/s11128-023-04188-7
  10. Farmonov, N., Esmaeili, M., Abbasi-Moghadam, D., Sharifi, A., Amankulova, K., & Mucsi, L. (2024). HypsLiDNet: 3D-2D CNN model and spatial-spectral morphological attention for crop classification with DESIS and LiDAR data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://ieeexplore.ieee.org/document/10571369, DOI: 10.1109/JSTARS.2024.3418854
  11. L. Parigi, G. Candiani, I. Gallo, P. Toscano, and M. Boschetti, “Towards Crop Traits Estimation from Hyperspectral Data: Evaluation of Neural Network Models Trained with Real Multi-Site Data or Synthetic RTM Simulations,” Proc. 19th Conf. Computer Science and Intelligence Systems, ACSIS, vol. 39, pp. 475–484, 2024, DOI: 10.15439/2024F4108
  12. Miranda, M., Pathak, D., Nuske, M., & Dengel, A. (2024, July). Multi-modal fusion methods with local neighborhood information for crop yield prediction at field and subfield levels. In IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium (pp. 4307–4311). IEEE. https://doi.org/10.1109/IGARSS53475.2024.10640993
  13. Pavlova M.A., Sidorchuk D.S., Bocharov D.A. Classification of crops by NDVI time series of reduced dimensionality // Sensornye sistemy. - 2023. - Vol. 37. - N. 2. - P. 306-312. DOI: 10.31857/S023500922302004X
  14. G. Castellano, P. De Marinis, and G. Vessio, “Applying Knowledge Distillation to Improve Weed Mapping With Drones,” Proc. 18th Conf. Computer Science and Intelligence Systems, ACSIS, vol. 35, pp. 393–400, 2023, DOI: 10.15439/2023F960.
  15. Toro, A. P., Bueno, I. T., Werner, J. P., Antunes, J. F., Lamparelli, R. A., Coutinho, A. C., ... & Figueiredo, G. K. (2023). SAR and optical data applied to the early-season mapping of integrated crop-livestock systems using deep and machine learning algorithms. Remote Sensing, 15(4), 1130. https://doi.org/10.3390/rs15041130
  16. R. Maskeliunas and R. Damaševičius, “d’Alembert Convolution for Enhanced Spatio-Temporal Analysis of Forest Ecosystems,” Proc. 19th Conf. Computer Science and Intelligence Systems, ACSIS, vol. 39, pp. 141–148, 2024, DOI: 10.15439/2024F4228.
  17. Pihrt, J., Šimánek, P., Kovalenko, A., Kvapil, J., & Charvát, K. (2024). AI-Based Spatiotemporal Crop Monitoring by Cloud Removal in Satellite Images. In Proceedings of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS), Annals of Computer Science and Information Systems, Volume 39, pp. 485–492, DOI: 10.15439/2024F5446
  18. F. Koutenský, J. Pihrt, M. Čepek, V. Rybář, P. Šimánek, M. Kepka, K. Jedlička, and K. Charvát, "Combining Local and Global Weather Data to Improve Forecast Accuracy for Agriculture," in Communication Papers of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS), 2024, pp. 77–82. DOI:10.15439/2024F5990
  19. Filippi, P., Jones, E., Bishop, T., Acharige, N., Dewage, S., Johnson, L., Ugbaje, S., Jephcott, T., Paterson, S., & Whelan, B. (2017, October). A Big Data Approach to Predicting Crop Yield. In Proceedings of the 7th Asian-Australasian Conference on Precision Agriculture (pp. 16–18). Hamilton, New Zealand. Zenodo. https://doi.org/10.5281/zenodo.893668
  20. M. Hosseini, I. Becker-Reshef, R. Sahajpal, L. Fontana, P. Lafluf, G. Leale, and C. Justice, "Crop Yield Prediction Using Integration of Polarimetric Synthetic Aperture Radar and Optical Data," in Proceedings of the 2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS), 2020, pp. 17–20. DOI: 10.1109/InGARSS48198.2020.9358978
  21. Wang, S., Hu, T., Huang, X., Li, Y., Zhang, C., Ning, H., Zhu, R., Li, Z., & Ye, X. (2024). GPT, large language models (LLMs) and generative artificial intelligence (GAI) models in geospatial science: a systematic review. International Journal of Digital Earth, 17(1), Article 2353122.LinkedIn+2University of Bristol+2University of Bristol+2, DOI: 10.1080/17538947.2024.2353122
  22. Sapkota, R., Qureshi, R., Hassan, S. Z., Shutske, J., Shoman, M., & Sajjad, M. (2024). Multi-Modal LLMs in Agriculture: A Comprehensive Review. TechRxiv Preprint. DOI: 10.36227/techrxiv.172651082.24507804/v1
  23. Mansourian, A., & Oucheikh, R. (2024). ChatGeoAI: Enabling Geospatial Analysis for Public through Natural Language, with Large Language Models. ISPRS International Journal of Geo-Information, 13(10), 348.Lund University, DOI: 10.3390/ijgi13100348
  24. L. Yuan, F. Mo, K. Huang, W. Wang, W. Zhai, X. Zhu, Y. Li, J. Xu, and J.-Y. Nie, "OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence," arXiv preprint https://arxiv.org/abs/2503.16326, Mar. 2025. https://arxiv.org/html/2503.16326v1
  25. L. Wang, J. Chou, A. Tien, X. Zhou, and D. M. Baumgartner, "AviationGPT: A Large Language Model for the Aviation Domain," in Proceedings of the AIAA AVIATION Forum and ASCEND 2024, 2024, p. 4250. DOI: 10.2514/6.2024-4250
  26. Ali. S. H, Shahid. M. F, Tanveer. M. H, Rauf. A, “Integrating LLM for Cotton SoilAnalysis in Smart Agriculture System”, IJIST, Special Issue pp 283-294, (2024) (PDF) Integrating LLM for Cotton Soil Analysis in Smart Agriculture System. Available from: https://www.researchgate.net/publication/389436000_Integrating_LLM_for_Cotton_Soil_Analysis_in_Smart_Agriculture_System [accessed May 23 2025]
  27. Peng, B., Li, C., He, P., Galley, M., & Gao, J. (2023). Instruction tuning with GPT-4. arXiv preprint https://arxiv.org/abs/2304.03277. https://doi.org/10.48550/arXiv.2304.03277
  28. Q. Huang, Y. Tao, S. Ding, Y. Liu, and F. Marinello, “Automatic Construction of Knowledge Graph of Tea Diseases and Pests,” Communication Papers of the 18th Conf. Computer Science and Intelligence Systems, ACSIS, vol. 37, pp. 141–146, 2023, DOI: 10.15439/2023F6100
  29. Auer, C., Lysak, M., Nassar, A., Dolfi, M., Livathinos, N., Vagenas, P., Berrospi Ramis, C., Omenetti, M., Lindlbauer, F., Dinkla, K., Mishra, L., Kim, Y., Gupta, S., Teixeira de Lima, R., Weber, V., Morin, L., Meijer, I., Kuropiatnyk, V., & Staar, P. W. J. (2024). Docling Technical Report (Version 1.0.0). arXiv preprint https://arxiv.org/abs/2408.09869. https://doi.org/10.48550/arXiv.2408.09869
  30. Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., & Zhang, M. (2023). Towards general text embeddings with multi-stage contrastive learning. arXiv preprint https://arxiv.org/abs/2308.03281. https://doi.org/10.48550/arXiv.2308.03281