Journal of Bio-Environment Control (생물환경조절학회지)

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

DOI QR Code

Transpiration Prediction of Sweet Peppers Hydroponically-grown in Soilless Culture via Artificial Neural Network Using Environmental Factors in Greenhouse

온실의 환경요인을 이용한 인공신경망 기반 수경 재배 파프리카의 증산량 추정

  • Nam, Du Sung (Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University) ;
  • Lee, Joon Woo (Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University) ;
  • Moon, Tae Won (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)
  • 남두성 (서울대학교 식물생산과학부) ;
  • 이준우 (서울대학교 식물생산과학부) ;
  • 문태원 (서울대학교 식물생산과학부) ;
  • 손정익 (서울대학교 식물생산과학부)
  • Received : 2017.09.08
  • Accepted : 2017.10.23
  • Published : 2017.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Environmental and growth factors such as light intensity, vapor pressure deficit, and leaf area index are important variables that can change the transpiration rate of plants. The objective of this study was to compare the transpiration rates estimated by modified Penman-Monteith model and artificial neural network. The transpiration rate of paprika (Capsicum annuum L. cv. Fiesta) was obtained by using the change in substrate weight measured by load cells. Radiation, temperature, relative humidity, and substrate weight were collected every min for 2 months. Since the transpiration rate cannot be accurately estimated with linear equations, a modified Penman-Monteith equation using compensated radiation (Shin et al., 2014) was used. On the other hand, ANN was applied to estimating the transpiration rate. For this purpose, an ANN composed of an input layer using radiation, temperature, relative humidity, leaf area index, and time as input factors and five hidden layers was constructed. The number of perceptons in each hidden layer was 512, which showed the highest accuracy. As a result of validation, $R^2$ values of the modified model and ANN were 0.82 and 0.94, respectively. Therefore, it is concluded that the ANN can estimate the transpiration rate more accurately than the modified model and can be applied to the efficient irrigation strategy in soilless cultures.

광도, 포차와 같은 환경요인과 엽면적 지수와 같은 생육요인은 증산 속도를 변화시키는 중요한 변수이다. 본 연구에서는 Penman-Monteith의 증산 모델과 인공신경망(ANN)에 학습에 의한 증산속도 추정값을 비교하는 것을 목표로 하였다. 파프리카(Capsicum annuum L. cv. Fiesta)의 증산속도 추정은 로드셀을 이용한 배지의 중량변화를 통해 계산하였다. 온도, 상대습도, 배지 중량 데이터는 1분 단위로 2개월간 수집하였다. 증산량은 일차식으로는 정확한 추정이 어렵기 때문에, 기존의 Penman-Monteith식에 보정 광도를 사용한 수정식 Shin 등(2014)을 사용하였다. 이와는 별개로 ANN을 사용하여 증산량을 추정 비교하였다. 이를 위하여 광도, 온도, 습도, 엽면적지수, 시간을 사용한 입력층과 5개의 은닉층으로 구성된 ANN을 구축하였다. 각 은닉층의 퍼셉트론 개수는 가장 정확성이 높은 512개로 하였다. 검증 결과, 보정된 Penman-Monteith 모델식의 $R^2=0.82$이었고, ANN의 $R^2=0.94$로 나타났다. 따라서 ANN은 일반적인 모델식에 비해 정확한 증산량 추정이 가능한 것으로 나타났고, 추후 수경재배의 효율적인 관수전략 수립에 있어 적용 가능할 것으로 판단되었다.

Keywords

References

  1. Antony, E. and R.B. Singandhupe. 2004. Impact of drip and surface irrigation on growth, yield and WUE of capsicum (Capsicum annum L.). Agric. Water Manage. 65:121-132. https://doi.org/10.1016/j.agwat.2003.07.003
  2. Aubinet, M., J. Deltour, D. De Halleux, and J. Nijskens. 1989. Stomatal regulation in greenhouse crops: analysis and simulation. Agric. Forest. Meteorol. 48:21-44. https://doi.org/10.1016/0168-1923(89)90005-1
  3. Bange, G.G.J. 1953. On the quantitative explanation of stomatal transpiration. Acta Bot. Neer. 2:255-297. https://doi.org/10.1111/j.1438-8677.1953.tb00275.x
  4. Boulard, T. and R. Jemaa. 1992. Greenhouse tomato crop transpiration model application to irrigation control. In International Symposium on Irrigation of Horticultural Crops 335:381-388.
  5. Bryla, D.R., T.J. Trout, and J.E. Ayars. 2010. Weighing lysimeters for developing crop coefficients and efficient irrigation practices for vegetable crops. HortScience 45:1597-1604.
  6. de Boodt, M.A.V.O. and O. Verdonck. 1971. The physical properties of the substrates in horticulture. In III Symposium on Peat in Horticulture 26:37-44.
  7. Gadissa, T. and D. Chemeda. 2009. Effects of drip irrigation levels and planting methods on yield and yield components of green pepper (Capsicum annuum, L.) in Bako, Ethiopia. Agric. Water Manage. 96:1673-1678. https://doi.org/10.1016/j.agwat.2009.07.004
  8. Gercek, S., N. Comlekcioglu, and M. Dikilitas. 2009. Effectiveness of water pillow irrigation method on yield and water use efficiency on hot pepper (Capsicum annuum L.). Sci. Hortic. 120:325-329. https://doi.org/10.1016/j.scienta.2008.11.028
  9. Hamer, P.J. 1993. Validation of a model used for irrigation control of a greenhouse crop. In International Symposium on Water Quality & Quantity-Greenhouse 458:75-82.
  10. Jolliet, O. and B.J. Bailey. 1992. The effect of climate on tomato transpiration in greenhouses: measurements and models comparison. Agric. Forest. Meteorol. 58:43-62. https://doi.org/10.1016/0168-1923(92)90110-P
  11. Montieth, J.L. and M.H. Unsworth. 1990. Principles of environmental physics. Edward Arnold, London, 291.
  12. Moreno, M.M., F. Ribas, A. Moreno, and M.J. Cabello. 2003. Physiological response of a pepper (Capsicum annuum L.) crop to different trickle irrigation rates. Span. J. Agric. Res. 1:65-74.
  13. Motulsky, H. and A. Christopoulos. 2004. Fitting models to biological data using linear and nonlinear regression: a practical guide to curve fitting. GraphPad Sofware Inc. San Diego. CA., USA.
  14. Medrano, E., P. Lorenzo., M.C. Sanchez-Guerrero, and J.I. Montero. 2005. Evaluation and modelling of greenhouse cucumber-crop transpiration under high and low radiation conditions. Sci. Hortic. 105:163-175. https://doi.org/10.1016/j.scienta.2005.01.024
  15. Nguyen, H.T., J. Park, T.I. Ann, J.H. Lee, D.J. Myoung, Y.Y. Cho, and J.E. Son. 2010. Analysis of relationship among growth, environmental factors and transpiration in soilless culture of paprika plants. Korean J. Hortic. Sci. 28:59-64.
  16. Sezen, S.M., A. Yazar, and S. Eker. 2006. Effect of drip irrigation regimes on yield and quality of field grown bell pepper. Agric. Water Manage. 81:115-131. https://doi.org/10.1016/j.agwat.2005.04.002
  17. Shin, J.H., E.H. Noh, and J.E. Son. 2012. Transpiration, growth, and water use efficiency of paprika plants (Capsicum annuum L.) as affected by irrigation frequency. Hortic. Environ. Biotechnol. 53:129-134. https://doi.org/10.1007/s13580-012-0095-2
  18. Shin, J.H., J.S. Park, and J.E. Son. 2014. Estimating the actual transpiration rate with compensated levels of accumulated radiation for the efficient irrigation of soilless cultures of paprika plants. Agric. Water Manage. 135:9-18. https://doi.org/10.1016/j.agwat.2013.12.009
  19. Shin, J.H., T.I. Ahn, and J.E. Son. 2011. Modeling of transpiration of paprika (Capsicum annuum L.) plants based on radiation and leaf area index in soilless culture. Hortic. Environ. Biotechnol. 52:265 https://doi.org/10.1007/s13580-011-0216-3
  20. Silber, A., M. Bruner, E. Kenig, G. Reshef, H. Zohar, I. Posalski et al. 2005. High fertigation frequency and phosphorus level: Effects on summer-grown bell pepper growth and blossom-end rot incidence. Plant Soil 270:135-146. https://doi.org/10.1007/s11104-004-1311-3
  21. Smittle, D.A., W.L. Dickens, and J.R. Stansell. 1994. Irrigation regimes affect yield and water use by bell pepper. J. Amer. Soc. Hortic. Sci. 119:936-939.
  22. Salisbury, F.B. and C.W. Ross. 1992. Plant physiology. Fourth edition. Wadsworth Publishing Company, Belmont, California.
  23. Seginer, I. 1994. Transpirational cooling of a greenhouse crop with partial ground cover. Agric. Forest. Meteorol. 71:265-281. https://doi.org/10.1016/0168-1923(94)90015-9
  24. Stanghellini, C. 1987. Transpiration of greenhouse crops. An aid to climate management. Ph.D. Diss. Wageningen Agricultural Univ., Wageningen, 150pp.
  25. Tetko, I.V., D.J. Livingstone, and A.I. Luik. 1995. Neural network studies. 1. Comparison of overfitting and overtraining. J. Chem. Inf. Comput. Sci. 35:826-833. https://doi.org/10.1021/ci00027a006
  26. Taormina, R. and K.W. Chau. 2015. Neural network river forecasting with multi-objective fully informed particle swarm optimization. J. Hydroniform. 17:99-113. https://doi.org/10.2166/hydro.2014.116
  27. Vaidyanathan, S. 2015. 3-cells cellular neural network (CNN) attractor and its adaptive biological control. Int. J. Pharmtech. Res. 8:632-640.
  28. Wang, T., H. Gao, and J. Qiu. 2016. A combined adaptive neural network and nonlinear model predictive control for multirate networked industrial process control. IEEE Trans. Neural Netw. Learn. Syst. 27:416-425. https://doi.org/10.1109/TNNLS.2015.2411671