Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The New Agronomists: Language Models are Experts in Crop Management (2403.19839v1)

Published 28 Mar 2024 in cs.LG, cs.AI, and cs.CL

Abstract: Crop management plays a crucial role in determining crop yield, economic profitability, and environmental sustainability. Despite the availability of management guidelines, optimizing these practices remains a complex and multifaceted challenge. In response, previous studies have explored using reinforcement learning with crop simulators, typically employing simple neural-network-based reinforcement learning (RL) agents. Building on this foundation, this paper introduces a more advanced intelligent crop management system. This system uniquely combines RL, a LLM (LM), and crop simulations facilitated by the Decision Support System for Agrotechnology Transfer (DSSAT). We utilize deep RL, specifically a deep Q-network, to train management policies that process numerous state variables from the simulator as observations. A novel aspect of our approach is the conversion of these state variables into more informative language, facilitating the LLM's capacity to understand states and explore optimal management practices. The empirical results reveal that the LM exhibits superior learning capabilities. Through simulation experiments with maize crops in Florida (US) and Zaragoza (Spain), the LM not only achieves state-of-the-art performance under various evaluation metrics but also demonstrates a remarkable improvement of over 49\% in economic profit, coupled with reduced environmental impact when compared to baseline methods. Our code is available at \url{https://github.com/jingwu6/LM_AG}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (84)
  1. Do as i can, not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691, 2022.
  2. Application, adoption and opportunities for improving decision support systems in irrigated agriculture: A review. Agricultural Water Management, 257:107161, 2021.
  3. Machine learning aided crop yield optimization. arXiv preprint arXiv:2111.00963, 2021.
  4. Uncertainty in simulating wheat yields under climate change. Nature climate change, 3(9):827–832, 2013.
  5. Using extended machine learning and simulation technics to design crop management strategies. In EFITA First European Conference for Information Technology in Agriculture, Copenhagen (Denmark), 1997.
  6. How do various maize crop models vary in their responses to climate change factors? Global change biology, 20(7):2301–2320, 2014.
  7. Openai gym. arXiv preprint arXiv:1606.01540, 2016.
  8. Open-vocabulary queryable scene representations for real world planning. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 11509–11522. IEEE, 2023a.
  9. Quantifying uncertainty in answers from any language model via intrinsic and extrinsic confidence assessment. arXiv preprint arXiv:2308.16175, 2023.
  10. When do you need chain-of-thought prompting for chatgpt? arXiv preprint arXiv:2304.03262, 2023b.
  11. Personalized fall risk assessment for long-term care services improvement. In 2017 Annual Reliability and Maintainability Symposium (RAMS), pages 1–7. IEEE, 2017a.
  12. Multi-state reliability demonstration tests. Quality Engineering, 29(3):431–445, 2017b.
  13. A data heterogeneity modeling and quantification approach for field pre-assessment of chloride-induced corrosion in aging infrastructures. Reliability Engineering & System Safety, 171:123–135, 2018.
  14. Claims data-driven modeling of hospital time-to-readmission risk with latent heterogeneity. Health care management science, 22:156–179, 2019.
  15. Optimal binomial reliability demonstration tests design under acceptance decision uncertainty. Quality Engineering, 32(3):492–508, 2020.
  16. Recontab: Regularized contrastive representation learning for tabular data. arXiv preprint arXiv:2310.18541, 2023c.
  17. Improving the robustness of reinforcement learning policies with ℒ1subscriptℒ1\mathcal{L}_{1}caligraphic_L start_POSTSUBSCRIPT 1 end_POSTSUBSCRIPT adaptive control. IEEE Robotics and Automation Letters, 7(3):6574–6581, 2022.
  18. Safe and efficient reinforcement learning using disturbance-observer-based control barrier functions. In Learning for Dynamics and Control Conference, pages 104–115. PMLR, 2023.
  19. Why does my soil moisture sensor read negative? Online]. Available: http://manuals. decagon. com/RetiredandDiscontinued/Slicksandcontent/ Presentations/SoilMoisture301.pdf, 2010.
  20. Nitrate leaching in temperate agroecosystems: sources, factors and mitigating strategies. Nutrient cycling in agroecosystems, 64:237–256, 2002.
  21. Confidence trigger detection: an approach to build real-time tracking-by-detection system. arXiv preprint arXiv:1902.00615, 2019.
  22. Eric Floehr. Weather forecast accuracy analysis. In Proc of the 9th Python in Science Conference, SciPy, pages 36–39, 2010.
  23. Frédérick Garcia. Use of reinforcement learning and simulation to optimize wheat crop technical management. In Proceedings of the International Congress on Modelling and Simulation, pages 801–806, 1999.
  24. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  25. Forecasting of solar radiation. Solar energy resource management for electricity generation from local level to global scale. Nova Science Publishers, New York, pages 83–94, 2006.
  26. How many validation labels do you need? exploring the design space of label-efficient model ranking. arXiv preprint arXiv:2312.01619, 2023.
  27. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International Conference on Machine Learning, pages 9118–9147. PMLR, 2022a.
  28. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608, 2022b.
  29. The DSSAT cropping system model. European Journal of Agronomy, 18(3-4):235–265, 2003.
  30. Brief history of agricultural systems modeling. Agricultural systems, 155:240–254, 2017.
  31. Nitrogen management with reinforcement learning and crop growth models. Environmental Data Science, 2:e34, 2023.
  32. Deep drone racing: Learning agile flight in dynamic environments. In Conference on Robot Learning, pages 133–145, 2018.
  33. Language models can solve computer tasks. Advances in Neural Information Processing Systems, 36, 2024.
  34. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  35. Adaptive ensembles of fine-tuned transformers for llm-generated text detection. arXiv preprint arXiv:2403.13335, 2024.
  36. A-tip: attribute-aware text infilling via pre-trained language model. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5857–5869, 2022.
  37. Joyful: Joint modality fusion and graph contrastive learning for multimodal emotion recognition. arXiv preprint arXiv:2311.11009, 2023a.
  38. Synthetic data generation with large language models for text classification: Potential and limitations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10443–10461, Singapore, 2023b. Association for Computational Linguistics.
  39. Code as policies: Language model programs for embodied control. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 9493–9500. IEEE, 2023.
  40. Distributed inverse constrained reinforcement learning for multi-agent systems. Advances in Neural Information Processing Systems, 35:33444–33456, 2022.
  41. Meta inverse constrained reinforcement learning: Convergence guarantee and generalization analysis. In The Twelfth International Conference on Learning Representations, 2023.
  42. Learning multi-agent behaviors from distributed and streaming demonstrations. Advances in Neural Information Processing Systems, 36, 2024.
  43. Temperature-scaling surprisal estimates improve fit to human reading times–but does it do so for the “right reasons”? In ICLR 2024 Workshop on Representational Alignment, 2024a.
  44. News recommendation with attention mechanism. Journal of Industrial Engineering and Applied Science, 2(1):21–26, 2024b.
  45. Particle filter slam for vehicle localization. Journal of Industrial Engineering and Applied Science, 2(1):27–31, 2024c.
  46. A swat-based reinforcement learning framework for crop management. arXiv preprint arXiv:2302.04988, 2023.
  47. Dssat-ceres-maize modelling to improve irrigation and nitrogen management practices under mediterranean conditions. Agricultural Water Management, 213:298–308, 2019.
  48. Exploring trade-offs between profit, yield, and the environmental footprint of potential nitrogen fertilizer regulations in the us midwest. Frontiers in plant science, 13, 2022.
  49. Grounding language with visual affordances over unstructured data. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 11576–11582. IEEE, 2023.
  50. Human-level control through deep reinforcement learning. Nature, 518(7540):529–533, 2015.
  51. Cropgym: a reinforcement learning environment for crop management. arXiv preprint arXiv:2104.04326, 2021.
  52. The influence of organic and conventional fertilisation and crop protection practices, preceding crop, harvest year and weather conditions on yield and quality of potato (Solanum tuberosum) in a long-term management trial. European Journal of Agronomy, 49:83–92, 2013.
  53. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22, 2023.
  54. Sim-to-real transfer of robotic control with dynamics randomization. In IEEE International Conference on Robotics and Automation (ICRA), pages 3803–3810, 2018.
  55. Planning with large language models via corrective re-prompting. In NeurIPS 2022 Foundation Models for Decision Making Workshop, 2022.
  56. Crop management factors influencing yield and quality of crop residues. Field Crops Research, 84(1-2):57–77, 2003.
  57. gym-dssat: a crop model turned into a reinforcement learning environment. arXiv preprint arXiv:2207.03270, 2022.
  58. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108, 2019.
  59. Creating a sustainable food future: A menu of solutions to feed nearly 10 billion people by 2050. final report. World Resources Institude, 2019.
  60. Combining incremental conductance and firefly algorithm for tracking the global mpp of pv arrays. Journal of Renewable and Sustainable Energy, 9(2), 2017.
  61. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36, 2024.
  62. Impact of sprinkler irrigation management on the del reguero river (spain). i: Water balance and irrigation performance. Agricultural Water Management, 103:120–129, 2012.
  63. Large language models for forecasting and anomaly detection: A systematic literature review. arXiv preprint arXiv:2402.10350, 2024.
  64. Reinforcement learning control for water-efficient agricultural irrigation. In 2017 IEEE International Symposium on Parallel and Distributed Processing with Applications and 2017 IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC), pages 1334–1341, 2017.
  65. Optimizing crop management with reinforcement learning and imitation learning. arXiv preprint arXiv:2209.09991, 2022.
  66. Domain randomization for transferring deep neural networks from simulation to the real world. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 23–30, 2017.
  67. Optimal test design for reliability demonstration under multi-stage acceptance uncertainties. Quality Engineering, 0(0):1–14, 2023a.
  68. Emp: emotion-guided multi-modal fusion and contrastive learning for personality traits recognition. In Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, pages 243–252, 2023b.
  69. Balanced training for sparse gans. In Thirty-seventh Conference on Neural Information Processing Systems, 2023c.
  70. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
  71. Field corn production guide: Ss-agr-85/ag202, rev. 8/2022. EDIS, 2022(4), 2022.
  72. Optimizing nitrogen management with deep reinforcement learning and crop simulations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 1712–1720, 2022.
  73. Hallucination improves the performance of unsupervised visual representation learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16132–16143, 2023a.
  74. Genco: An auxiliary generator from contrastive learning for enhanced few-shot learning in remote sensing. arXiv preprint arXiv:2307.14612, 2023b.
  75. Extended agriculture-vision: An extension of a large aerial image dataset for agricultural pattern analysis. arXiv preprint arXiv:2303.02460, 2023c.
  76. Switchtab: Switched autoencoders are effective tabular learners. arXiv preprint arXiv:2401.02013, 2024.
  77. Mmap: Multi-modal alignment prompt for cross-domain multi-task learning. arXiv preprint arXiv:2312.08636, 2023.
  78. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629, 2022.
  79. On the trade-off of intra-/inter-class diversity for supervised pre-training. Advances in Neural Information Processing Systems, 36, 2024.
  80. Short-term rainfall forecasting using multi-layer perceptron. IEEE Transactions on Big Data, 6(1):93–106, 2018.
  81. A simple crop model. European Journal of Agronomy, 104:97–106, 2019.
  82. Sim-to-real transfer in deep reinforcement learning for robotics: a survey. In 2020 IEEE symposium series on computational intelligence (SSCI), pages 737–744. IEEE, 2020.
  83. Thread of thought unraveling chaotic contexts. arXiv preprint arXiv:2311.08734, 2023.
  84. Visual in-context learning for large vision-language models. arXiv preprint arXiv:2402.11574, 2024.
Citations (16)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets