Model for tomato photosynthetic rate based on neural network with genetic algorithm

Jin Hu, Pingping Xin, Siwei Zhang, HaiHui Zhang, DongJian He

Abstract


A photosynthetic rate model provides a theoretical basis for fine-grained control of light, and has become the key component to determine the effectiveness of light-controlled environments. Therefore, it is critical to identify an intelligent algorithm that can be used to build an efficient and precise photosynthetic rate model. Depending on the initial weights of a BP (Back Propagation) neural network algorithm for arbitrary random numbers, the establishment of a regressive prediction model can be easily trapped in a partially-flat area. Existing photosynthetic rate models based on neural networks are facing problems such as a slow convergence speed and a long training time, and this study presents a photosynthetic rate model of a heuristic neural network for tomatoes based on a genetic algorithm to address the above problems. The performance of the model can be effectively improved using a genetic algorithm to optimize the initial weights. A multi-factor nesting experiment was firstly conducted to obtain 825 groups of tomato seedling photosynthesis rate test data in the foundation, and the photosynthetic rate model of the heuristic neural network for the tomato is established through BP network structure construction and data preprocessing. The genetic algorithm was used to optimize the network weights and threshold, and the LM (Levenberg-Marquardt) training method for network training. On this basis, the training performance and precision of the photosynthetic rate prediction models can be further compared with the genetic neural network model and the neural network model. The test results have shown that the training effects and accuracy of the genetic neural network prediction model of the photosynthetic rate were better than those of the neural network prediction model. The correlation coefficient between the model predicted data and the measured data is 0.987, and the absolute error of the photosynthetic rate is less than ±0.5 μmol/(m2•s).
Keywords: genetic algorithm, neural network, photosynthetic ratemodel, prediction model, tomato plant
DOI: 10.25165/j.ijabe.20191201.3127

Citation: Hu J, Xin P P, Zhang S W, Zhang H H, He D J. A model for tomato photosynthetic rate based on neural network with genetic algorithm. Int J Agric & Biol Eng, 2019; 12(1): 179–185.

Keywords


genetic algorithm, neural network, photosynthetic ratemodel, prediction model, tomato plant

Full Text:

PDF

References


Zhu J X. Influence of artificial supplement of light on plant growth and development. Crop Research, 2012; 26(1): 74–78.

Liu J G, Mahoney K J, Sikkema P H, Swanton C J. The importance of light quality in crop–weed competition. Weed Research, 2009; 49(2): 217–224.

Xu Z H, Song Z M, Wang D F, Meng X X, Long Q X, Ding Z L, et al. Determination of light transmittance in different tilt angle of different transparent material Southwest China Journal of Agricultural Sciences, 2012; 25(3): 1090–1096.

Onuf C P. Seagrass responses to long-term light reduction by brown tide in upper Laguna Madre. Texas: distribution and biomass patterns. Marine Ecology Progress, 1996; 138: 219–231

Charvet S, Vincent W F, Lovejoy C. Effects of light and prey availability on Arctic freshwater protist communities examined by high-throughput DNA and RNA sequencing. FEMS Microbiology Ecology, 2014; 88(3): 550–564. (in Chinese)

Du C F, Li C H, Liu T X, Zhao Y L. Response of anatomical structure and photosynthetic characteristics to low light stress in leaves of different maize genotypes. Acta Ecologica Sinica, 2011; 31(21): 6633–6640

Novickovas A, Brazaityte A, Duchovskis P, Jankauskiene J, Samuoliene G, Virsile A, et al. Solid-state lamps (LEDs) for the short-wavelength supplementary lighting in greenhouses: experimental results with cucumber. Acta Horticulturae, 2012; 927(1): 723–730.

Murakami K, Matsuda R, Fujiwara K. Effects of supplemental lighting to a lower leaf using light-emitting diodes with different spectra on the leaf photosynthetic rate in sweet pepper. Journal of Agricultural Meteorology, 2013; 69(2): 55–63.

Ye Z P, Kang H J, Tao Y L, Wang L X. Comparative analysis on the fitting effect of different models of Koelreuteria bipinnata var integrifoliola rapid light curves. Chinese Journal of Ecology, 2011; 30(8): 1662–1667.

Yan X H, Yin J H, Duan S H, Zhou B, Hu W H, Liu S. Photosynthesis light response curves of four rice varieties and model fitting. Chinese Journal of Ecology, 2013; 32(3): 604－610. (in Chinese)

Ye Z P, Hu W H, Xiao Y, Fan D Y, Yin J H, Duan S H, et al. A mechanistic model of light-response of photosynthetic electron flow and its application. Chinese Journal of Plant Ecology, 2014; 38(11): 1241–1249.

Caemmerer S V. Steady-state models of photosynthesis. Plant Cell & Environment, 2013; 36(9): 1617–1630.

Xu J Z, Yu Y M, Peng S Z, Yang S H, Liao L X. A modified nonrectangular hyperbola equation for photosynthetic light-response curves of leaves with different nitrogen status. Photosynthetica, 2014; 52(1): 117–123.

Kai W, Jing Z, Hao C. Simulation of the canopy photosynthesis model of greenhouse tomato. Journal of Shanxi Agricultural University, 2011; 16(1): 632–639. (in Chinese)

Li P P, Wang J Z, Chen X, Liu W H. Studies on photosynthesis model of mini-cucumber leaf in greenhouse. Crop Modeling and Decision Support, Springer Berlin Heidelberg, 2009; pp.24–29.

Hou J L Wang Y M, Xu Y, Jun Y. Simulation model of tomato growth. Transactions of the CSAM, 2006; 37(3): 80–83. (in Chinese)

Liu X B, Yu X L, Guo Y R, Xiang Z F, Zhao K, Ren F. Influence of allele frequency on predicting animal phenotype using back-propagation artificial neural networks. Wuhan University Journal of Natural Sciences, 2011; 16(2): 101–105. (in Chinese)

Rakhtala S M, Ghaderi R, Noei A R. Proton exchange membrane fuel cell voltage-tracking using artificial neural networks. Journal of Zhejiang University Science C (Computers and Electronics), 2011; 12(4): 338–344.

Kmet T, Kmetova M. Adaptive critic design and Hopfield neural network based simulation of time delayed photosynthetic production and prey–predator model. Information Sciences, 2015; 294:586–599.

Wang W Z, Zhang M, Jiang Y, S S, Li M Z. Photosynthetic rate prediction of tomato plants based on wireless sensor network in greenhouse. Transactions of the CSAM, 2013; 44(Supp2): 192–197. (in Chinese)

Wang Z B, Kong Y N, Liu Y C, Zhang Q. Prediction of junction temperature for high power LED by optimizing BP neural network based on genetic algorithm. Journal of Optoelectronics Laser, 2014; 25(7): 1303–1309. (in Chinese)

Zhang X L, Jun H U, Zhao T Y. Geometric parameters optimization of dump slope based on BP neural network-genetic algorithm. Mining & Metallurgical Engineering, 2017; 37(2): 16–19. (in Chinese)

Yu F, Xu X. A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network. Applied Energy, 2014; 134(134): 102–113.

Mohamed S J, Jellings A J, Fuller M P. Positive effects of elevated CO2 and its interaction with nitrogen on safflower physiology and growth. Agronomy for Sustainable Development, 2013; 33(3): 497–505.

Xue W, Xiang Y L, Lin L S, Wang Y J, Lei A L. Effects of short time heat stress on photosystem Ⅱ, Rubisco activities and oxidative radicals in Alhagi sparsifolia. Chinese Journal of Plant Ecology, 2011; 35(4): 441–451. (in Chinese)

Zhang J, Jiang X D, Li T L, Cao X J. Photosynthesis and ultrastructure of photosynthetic apparatus in tomato leaves under elevated temperature. Photosynthetica, 2014; 52(3): 430–436.

Zhang X C, Yu X F, Ma Y F, Shangguan Z P. The responses of photosynthetic energy use in wheat flag leaves to nitrogen application rates and light density under elevated atmospheric CO2 concentration. Acta Ecologica Sinica, 2011; 31(4): 1046–1057.

Peri P L, Arena M, Pastur G M, Lencinas M V. Photosynthetic response to different light intensities, water status and leaf age of two Berberis, species (Berberidaceae) of Patagonian steppe, Argentina. Journal of Arid Environments, 2011; 75(11): 1218–1222.

Zhao H, Si L. Effects of topdressing with nitrogen fertilizer on wheat yield, and nitrogen uptake and utilization efficiency on the Loess Plateau. Acta Agriculturæ Scandinavica, 2015; 65(8): 1–7.

Li J M, Pan T H, Wang L H, Du Q J, Chang Y B, Zhang D L. Effects of water-fertilizer coupling on tomato photosynthesis, yield and water use efficiency. Transactions of the CSAE, 2014; 30(10): 82–90. (in Chinese)

Jeonghwan H, Changsun S, Hyun Y. A wireless sensor network-based ubiquitous paprika growth management system. Sensors, 2010; 10(12): 11566–115689.




Copyright (c) 2019 International Journal of Agricultural and Biological Engineering



2023-2026 Copyright IJABE Editing and Publishing Office