Abstract
The rapid growth of machine and deep learning solutions has led to many advancements, including self-driving cars, multi-lingual audio assistants, diseases detection and other industrial robotic solutions. Recognizing importance of these state-of-the-art solutions based on artificial intelligence, applications have been developed that can benefit the domain of agriculture and natural resources management. In this chapter, we aim to study recent advances in artificial intelligence and present applications of these advances to agriculture domain. Towards this aim, we review recent literature and introduce two foundational concepts, a network concept of deep neural networks and a learning concept of reinforcement learning. We present important use case of crop yield maximization, and through the applications of Deep Reinforcement Learning (Deep RL), showcase approaches for solving two important problems using Deep RL. Further, we showcase how these solutions can be deployed on production-ready cloud infrastructure, thus making our solutions more practical and scalable.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
An alternate way to handle high volume of data or designing scalable solution is by selecting most important features in the data (Gandhi and Raval 2020).
- 2.
Similar stateless, scalable, micro-service-based cloud-deployed ML solution is presented in Mehta et al. (2019).
- 3.
It has been shown that RL agents are capable of finding better than human optimal strategy for solving given problems. See Deep RL agent for Atari Breakout game for more details (Mnih et al.2015).
References
AGC G (2021). Autonomous greenhouse control and monitoring using deep reinforcement learning. https://github.com/Kaushal1011/AutonomousGreenhouseControl
Binas J, Luginbuehl L, Bengio Y (2019) Reinforcement learning for sustainable agriculture. In: ICML workshop on climate change AI.
Burnetas AN, Katehakis MN (1997) Optimal adaptive policies for Markov decision processes. Math Oper Res 22(1):222–255
Elavarasan D, Vincent PM (2020) Crop yield prediction using deep reinforcement learning model for sustainable agrarian applications. IEEE Access 8:86886–86901
Gandhi R, Raval MS (2020) Algorithms for optimization and machine learning over cloud. In: Nature-inspired computation in data mining and machine learning. Springer, pp 23–46
Li Z, Xu L, Zhu S (2020) Pruning of network filters for small dataset. IEEE Access 8:4522–4533
Marshall-Colon A, Long SP, Allen DK, Allen G, Beard DA, Benes B, von Caemmerer S, Christensen AJ, Cox DJ, Hart JC, Hirst PM, Kannan K, Katz DS, Lynch JP, Millar AJ, Panneerselvam B, Price ND, Prusinkiewicz P, Raila D, Shekar RG, Shrivastava S, Shukla D, Srinivasan V, Stitt M, Turk MJ, Voit EO, Wang Y, Yin X, Zhu X-G (2017) Crops in silico: Generating virtual crops using an integrative and multi-scale modeling platform. Front Plant Sci 8:786
Mehta M, Derasari R, Patel S, Kakadiya A, Gandhi R, Chaudhary S, Goswami R (2019) A service-oriented human capital management recommendation platform. In: 2019 IEEE international systems conference (SysCon). IEEE, pp 1–8
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533
Ndikumana E, Dinh HTM, Baghdadi N, Courault D, Hossard L (2018) Deep recurrent neural network for agricultural classification using multitemporal SAR Sentinel-1 for Camargue, France. Remote Sens 10:1217
Pirinen A, Sminchisescu C (2018) Deep reinforcement learning of region proposal networks for object detection. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 6945–6954
Research WU (2020) Autonomous greenhouse challenge, 2nd ed. https://www.wur.nl/en/project/autonomous-greenhouses2nd-edition.htm
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
RPN G (2021). Region proposal network for tomatoes detection using deep reinforcement learning. https://github.com/Supan14/RPNDeep-RL
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Tomato (2020) Tomato dataset. https://www.kaggle.com/kangdali/tomato
Uzkent B, Yeh C, Ermon S (2020) Efficient object detection in large images using deep reinforcement learning. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 1824–1833
Zhou N (2020) Intelligent control of agricultural irrigation based on reinforcement learning. In: Journal of physics: conference series, vol 1601. IOP Publishing, p 052031
Acknowledgements
The author would like to thank Kaushal Patil, Supan Shah, Meet Akbari, Dhaval Deshkar, Vidish Joshi, Pathik Patel, Vyoma Patel, Shrishti Sharma and Arpitsinh Vaghela for their contributions to the case studies.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Gandhi, R. (2022). Deep Reinforcement Learning for Agriculture: Principles and Use Cases. In: Reddy, G.P.O., Raval, M.S., Adinarayana, J., Chaudhary, S. (eds) Data Science in Agriculture and Natural Resource Management. Studies in Big Data, vol 96. Springer, Singapore. https://doi.org/10.1007/978-981-16-5847-1_4
Download citation
DOI: https://doi.org/10.1007/978-981-16-5847-1_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5846-4
Online ISBN: 978-981-16-5847-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)