The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Analysis of Deep Reinforcement Learning for Crop Yield Prediction

작물 생산량 예측을 위한 심층강화학습 성능 분석

  • 옴마킨 (순천대학교 인공지능공학부) ;
  • 이성근 (순천대학교 인공지능공학부)
  • Received : 2022.12.27
  • Accepted : 2023.02.17
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, many studies on crop yield prediction using deep learning technology have been conducted. These algorithms have difficulty constructing a linear map between input data sets and crop prediction results. Furthermore, implementation of these algorithms positively depends on the rate of acquired attributes. Deep reinforcement learning can overcome these limitations. This paper analyzes the performance of DQN, Double DQN and Dueling DQN to improve crop yield prediction. The DQN algorithm retains the overestimation problem. Whereas, Double DQN declines the over-estimations and leads to getting better results. The proposed models achieves these by reducing the falsehood and increasing the prediction exactness.

최근 딥러닝 기술을 활용하여 작물 생산량 예측 연구가 많이 진행되고 있다. 딥러닝 알고리즘은 입력 데이터 세트와 작물 예측 결과에 대한 선형 맵을 구성하는데 어려움이 있다. 또한, 알고리즘 구현은 획득한 속성의 비율에 긍정적으로 의존한다. 심층강화학습을 작물 생산량 예측 응용에 적용한다면 이러한 한계점을 보완할 수 있다. 본 논문은 작물 생산량 예측을 개선하기 위해 DQN, Double DQN 및 Dueling DQN 의 성능을 분석한다. DQN 알고리즘은 과대 평가 문제가 제기되지만, Double DQN은 과대 평가를 줄이고 더 나은 결과를 얻을 수 있다. 본 논문에서 제안된 모델은 거짓 판정을 줄이고 예측 정확도를 높이는 것으로 나타났다.

Keywords

Acknowledgement

"본 연구는 과학기술정보통신부 및 정보통신기획평가원의 지역지능화혁신인재양성(Grand ICT연구센터) 사업의 연구결과로 수행되었음"(IITP-2023-2020-0-01489)

References

  1. S. Li, S. Peng, W. Chen, and X. Lu, "INCOME: Practical land monitoring precision agriculture with sensor networks," Computer Communications, vol. 36, no. 4, 2013, pp. 459-467. https://doi.org/10.1016/j.comcom.2012.10.011
  2. A. D. Jones, F. M. Ngure, G. Pelto, and S. L. Young, "What are we assessing when we measure food security? A compendium and review of current metrics," Advances in Nutrition, vol. 4, no. 5, 2013, pp. 481-505. https://doi.org/10.3945/an.113.004119
  3. Y. Cai, K. Guan, J. Peng, S. Wang, C. Seifert, and Z. Li, "A high-performance and in-season classification system of field-level croptypes using time-series Landsat data and a machine learning approach," Remote Sensing of Environment, vol. 210, 2018, pp. 35-47. https://doi.org/10.1016/j.rse.2018.02.045
  4. A. Kaya, A. S. Keceli, C. Catal, H. Y. Yalic, H. Temucin, and B. Tekinerdogan, "Analysis of transfer learning for deep neural network based plant classification models," Computers and Electronics in Agriculture, vol. 158, 2019, pp. 20-29. https://doi.org/10.1016/j.compag.2019.01.041
  5. A. Kamilaris and F. X. Prenafeta-Boldu, "Deep learning in agriculture: A survey," Computers and Electronics in Agriculture, vol. 147, 2018, pp. 70-90. https://doi.org/10.1016/j.compag.2018.02.016
  6. H. Huang, M. Lin, and Q. Zhang, "Double-Q learning based DVFS for multi-core real-time systems," in Proc. IEEE Int. Conf. Internet Things(iThings), Exeter, United Kingdom, 2017.
  7. K. Peng, R. Jiao, J. Dong, and Y. Pi, "A deep belief network based healthindicator construction and remaining useful life prediction using improvedparticle filter," Neurocomputing, vol. 361, 2019, pp. 19-28. https://doi.org/10.1016/j.neucom.2019.07.075
  8. F. Du, J. Zhang, J. Hu, and R. Fei, "Discriminative multi-modal deep generative models," Knowledge Base System, vol. 173, 2019, pp. 74-82. https://doi.org/10.1016/j.knosys.2019.02.023
  9. S. Jung and S. Lee, "A Queue Management Mechanism for Service groups based on Deep Reinforcement Learning," J. of the Korea Institute of Electronic Communication Sciences, vol. 15, no. 6, 2020, pp. 1099-1104.
  10. S. Lee, "A Routing Algorithm based on Deep Reinforcement Learning in SDN," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 6, 2021, pp. 1153-1160.
  11. M. D. Johnson, W. W. Hsieh, A. J. Cannon, A. Davidson, and F. Bedard, "Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods," Agricultural and Forest Meteorology, vol. 218-219, 2016, pp. 74-84. https://doi.org/10.1016/j.agrformet.2015.11.003
  12. A. Tolba, O. Said, and Z. Al-Makhadmeh, "MDS: Multi level decision sys tem for patient behavior analysis based on wearable device information," Computer Communications, vol. 147, 2019, pp. 180-187. https://doi.org/10.1016/j.comcom.2019.08.022