Journal of Bio-Environment Control (생물환경조절학회지)

The Korean Society for Bio-Environment Control (한국생물환경조절학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Air Temperature and Relative Humidity in Greenhouse via a Multilayer Perceptron Using Environmental Factors

환경요인을 이용한 다층 퍼셉트론 기반 온실 내 기온 및 상대습도 예측

  • Choi, Hayoung (Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University) ;
  • Moon, Taewon (Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University) ;
  • Jung, Dae Ho (Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University) ;
  • Son, Jung Eek (Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University)
  • 최하영 (서울대학교 식물생산과학부) ;
  • 문태원 (서울대학교 식물생산과학부) ;
  • 정대호 (서울대학교 식물생산과학부) ;
  • 손정익 (서울대학교 식물생산과학부)
  • Received : 2019.01.11
  • Accepted : 2019.02.25
  • Published : 2019.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Temperature and relative humidity are important factors in crop cultivation and should be properly controlled for improving crop yield and quality. In order to control the environment accurately, we need to predict how the environment will change in the future. The objective of this study was to predict air temperature and relative humidity at a future time by using a multilayer perceptron (MLP). The data required to train MLP was collected every 10 min from Oct. 1, 2016 to Feb. 28, 2018 in an eight-span greenhouse ($1,032m^2$) cultivating mango (Mangifera indica cv. Irwin). The inputs for the MLP were greenhouse inside and outside environment data, and set-up and operating values of environment control devices. By using these data, the MLP was trained to predict the air temperature and relative humidity at a future time of 10 to 120 min. Considering typical four seasons in Korea, three-day data of the each season were compared as test data. The MLP was optimized with four hidden layers and 128 nodes for air temperature ($R^2=0.988$) and with four hidden layers and 64 nodes for relative humidity ($R^2=0.990$). Due to the characteristics of MLP, the accuracy decreased as the prediction time became longer. However, air temperature and relative humidity were properly predicted regardless of the environmental changes varied from season to season. For specific data such as spray irrigation, however, the numbers of trained data were too small, resulting in poor predictive accuracy. In this study, air temperature and relative humidity were appropriately predicted through optimization of MLP, but were limited to the experimental greenhouse. Therefore, it is necessary to collect more data from greenhouses at various places and modify the structure of neural network for generalization.

온도와 상대습도는 작물 재배에 있어서 중요한 요소로써, 수량과 품질의 증대를 위해서는 적절히 제어 되어야 한다. 그리고 정확한 환경 제어를 위해서는 환경이 어떻게 변화할지 예측할 필요가 있다. 본 연구의 목적은 현시점의 환경 데이터를 이용한 다층 퍼셉트론(multilayer perceptrons, MLP)을 기반으로 미래 시점의 기온 및 상대습도를 예측하는 것이다. MLP 학습에 필요한 데이터는 어윈 망고(Mangifera indica cv. Irwin)을 재배하는 8연동 온실($1,032m^2$)에서 2016년 10월 1일부터 2018년 2월 28일까지 10분 간격으로 수집되었다. MLP는 온실내부 환경 데이터, 온실 외 기상 데이터, 온실 내 장치의 설정 및 작동 값을 사용하여 10~120분 후 기온 및 상대습도를 예측하기 위한 학습을 진행하였다. 사계절이 뚜렷한 우리나라의 계절에 따른 예측 정확도를 분석하기 위해서 테스트 데이터로 계절별로 3일간의 데이터를 사용했다. MLP는 기온의 경우 은닉층이 4개, 노드 수가 128개일 때($R^2=0.988$), 상대습도는 은닉층 4개, 노드 수 64개에서 가장 높은 정확도를 보였다($R^2=0.990$). MLP 특성상 예측 시점이 멀어질수록 정확도는 감소하였지만, 계절에 따른 환경 변화에 무관하게 기온과 상대습도를 적절히 예측하였다. 그러나 온실 내 환경 제어 요소 중 분무 관수처럼 특이적인 데이터의 경우, 학습 데이터 수가 적기 때문에 예측 정확도가 낮았다. 본 연구에서는 MLP의 최적화를 통해서 기온 및 상대습도를 적절히 예측하였지만 실험에 사용된 온실에만 국한되었다. 따라서 보다 일반화를 위해서 다양한 장소의 온실 데이터 이용과 이에 따른 신경망 구조의 변형이 필요하다.

Keywords

References

  1. Abadi, M., P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al. 2016. TensorFlow: A system for large-scale machine learning. In: Proceedings of 12th USENIX OSDI, November, Savanah, GA, USA, 265-283.
  2. Al Shalabi, L. and Z. Shaaban. 2006. Normalization as a preprocessing engine for data mining and the approach of preference matrix. In: Proceedings of 2006 International Conference on Dependability of Computer Systems, May, Szklarska Poreba, Poland, IEEE, 207-214.
  3. Arauz, L. F. and T. B. Sutton. 1990. Effect of interrupted wetness periods on spore germination and apple infection by Botryosphaeria obtusa. Phytopathol. 80:1218-1220. https://doi.org/10.1094/Phyto-80-1218
  4. Benediktsson, J.A., P.H. Swain, and O.K. Ersoy. 1990. Neural network approaches versus statistical methods in classification of multisource remote sensing data. In: Proceedings of Transactions on Geoscience and Remote Sensing, July, Vancouver, Canada, IEEE, 540-552.
  5. Chandra, P., L.D. Albright, and N.R. Scott. 1981. A time dependent analysis of greenhouse thermal environment. Trans. ASAE 24:442-449. https://doi.org/10.13031/2013.34271
  6. Ferreira, P.M., E.A. Faria, and A.E. Ruano. 2002. Neural network models in greenhouse air temperature prediction. Neurocomputing 43:51-75. https://doi.org/10.1016/S0925-2312(01)00620-8
  7. Froehlich, D.P., L.D. Albright, N.R. Scott, and P. Chandra. 1979. Steady-periodic analysis of glasshouse thermal environment. Trans. ASAE 22:387-399. https://doi.org/10.13031/2013.35027
  8. Glorot, X., A. Bordes, and Y. Bengio. 2011. Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, April, Ft. Lauderdale, FL, USA, 315-323.
  9. Grange, R.I. and D.W. Hand. 1987. A review of the effects of atmospheric humidity on the growth of horticultural crops. J. Hortic. Sci. 62:125-134. https://doi.org/10.1080/14620316.1987.11515760
  10. Haykin, S. 2009. Neural networks: a comprehensive foundation. 3st ed. Prentice Hall PTR, Upper Saddle River, NJ, USA. p. 122-129.
  11. He, F. and C. Ma. 2010. Modeling greenhouse air humidity by means of artificial neural network and principal component analysis. Comput. Electron. Agric. 71:S19-S23. https://doi.org/10.1016/j.compag.2009.07.011
  12. He, K., X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June, Las Vegas, NV, USA, IEEE, 770-778.
  13. Hinton, G., L. Deng, D. Yu, G.E. Dahl, A.R. Mohamed, N. Jaitly, A. Senior, V. Vanhouckeet, P. Nguyen, T.N. Sainath, et al. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Proc. Mag. 29:82-97.
  14. Hochreiter, S. and J. Schmidhuber. 1997. Long short-term memory. Neural Comput. 9:1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  15. Hong, S.W. and I.B. Lee. 2014. Predictive model of microenvironment in a naturally ventilated greenhouse for a model-based control approach. Protected Hort. Plant Fac. 23:181-191. https://doi.org/10.12791/KSBEC.2014.23.3.181
  16. Hornik, K., M. Stinchcombe, and H. White. 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2:359-366. https://doi.org/10.1016/0893-6080(89)90020-8
  17. Hornik, K. 1991. Approximation capabilities of multilayer feedforward networks. Neural Networks 4:251-257. https://doi.org/10.1016/0893-6080(91)90009-T
  18. Ioffe, S. and C. Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
  19. Jolliet, O. 1994. HORTITRANS, a model for predicting and optimizing humidity and transpiration in greenhouses. J. Agr. Eng. Res. 57:23-37. https://doi.org/10.1006/jaer.1994.1003
  20. Kingma, D. and J. Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980v9.
  21. Krizhevsky, A., I. Sutskever, and G.E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, December, Lake Tahoe, NV, USA, 1097-1105.
  22. LeCun, Y., Y. Bengio, and G. Hinton. 2015. Deep learning. Nature 521:436. https://doi.org/10.1038/nature14539
  23. Lee, J.W., J.H. Shin., J.H. Kim., H.W. Park, I.H. Yu., and J.E. Son. 2014. Analysis of light environments in reclaimed land and estimation of spatial light distributions in greenhouse by 3-D model. Protected Hort. Plant Fac. 23:303-308. https://doi.org/10.12791/KSBEC.2014.23.4.303
  24. Mnih, V., K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602.
  25. Moon, T.W., D.H. Jung, S.H. Chang, and J.E. Son. 2018. Estimation of greenhouse $CO_{2}$ concentration via an artificial neural network that uses environmental factors. Hortic. Environ. Biotechnol. 59:45-50. https://doi.org/10.1007/s13580-018-0015-1
  26. Pedregosa, F., G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al. 2011. Scikit-learn: Machine learning in python. JMLR. 12:2825-2830
  27. Pieters, J. G., J. M. Deltour, and M. J. Debruyckere. 1997. Light transmission through condensation on glass and polyethylene. Agric. Forest Meteorol. 85:51-62. https://doi.org/10.1016/S0168-1923(96)02393-3
  28. Seginer, I. 1997. Some artificial neural network applications to greenhouse environmental control. Comput. Electron. Agric. 18:167-186. https://doi.org/10.1016/S0168-1699(97)00028-8
  29. Sheela, K.G. and S.N. Deepa. 2013. Review on methods to fix number of hidden neurons in neural networks. Math. Probl. Eng. 2013:11.
  30. Silver, D., A. Huang, C.J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529:484-489. https://doi.org/10.1038/nature16961
  31. Tweedie, R. L., K.L. Mengersen, and J.A. Eccleston. 1994. Garbage in, garbage out: can statisticians quantify the effects of poor data?. Chance 7:20-27. https://doi.org/10.1080/09332480.1994.11882492
  32. Walker, J.N. 1965. Predicting temperatures in ventilated greenhouses. Trans. ASAE 8:445-448. https://doi.org/10.13031/2013.40545
  33. Went, F.W. 1953. The effect of temperature on plant growth. Annu. Rev. Plant Physiol. 4:347-362. https://doi.org/10.1146/annurev.pp.04.060153.002023