Research Onprediction Model Of Cucumber Photosynthesis Based On BP Neural Network

All around the world, our facility vegetable cultivation area ismore than 90% of the total area and hasbecome a significance part of modern agriculture in our country.Cucumber is one of the main cultivation vegetables in our country. Crop demand model construction is the foundation of the facilities efficient management. The photosynthetic rate predictionmodel is the theoretical basis of appropriate crop photosynthesis in the small environment. The environmental factors such as photon flux density, CO2 concentration and temperature, were only considered in the existing photosynthetic rate models based on neural network.Slow convergence speed and low model fitting degree were still the existing problem. The influence factors of photosynthetic rate were analyzedin the paper, not only environmental factors,especially the chlorophyll content was considered in the paper, establishedthe fusion chlorophyll content of cucumber seedling photosynthetic rate prediction model.By analyzing the seedling period and blossom period photosynthetic rate differences,considering parameters and without considering phase parameters of the two modelswere established and contrasted. Eventually the fusion physiological factor prediction model of the full growth period cucumber photosynthesis rate was established.In this paper, the main work and conclusions were as follows:(1)Modeling method based on BP neural network research.Deeplyanalyzed the crop photosynthesis mechanism, selected cucumber as the test sample.Designed the entire multi-factor nested tests coveredthe entire stage from seedling stage to flowering stage.Temperature gradientswere set to 5 gradients, the carbon dioxide concentration gradientswere set to 5gradients, the light intensity were set to 11 gradients.The Li-6400 xt portable photosynthetic measured the crop net photosynthetic rate. The obtained 1650 groups of experimental dataprocessed bynormalized processing.The results showed that, when the input factors were five dimensions,the model used the gradient descent method, thecorrelation coefficient between actual measured and the calculated was 0.9131, the network training error was 0.00084; the model used the adaptive vector control method, the correlation coefficient between actual measured and the calculated was 0.9186, the network training error was0.00053; the model used the LM training method, the correlation coefficient between actual measured and the calculated was 0.9872, the network training error was less than0.0001.Thenetwork training error of the LM training model was small, the degree of fitting was good.Whenthe growthstage was considered as one-dimensional input factor, the LM training method was the best among the three methods,so the LM training method was adopted for model building.(2) Effect of chlorophyll on photosynthetic rate model, LM training method was used to establish the prediction model of photosynthetic rate of fusion and non fusion chlorophyll content. The fusion model of chlorophyll content, the correlation coefficient between actual measured and the calculated was 0.9872, the network training error was less than 0.0001.The non fusion model of chlorophyll content,the correlation coefficient between actual measured and the calculated was 0.9702, the network training error was 0.00025. The chlorophyll content of the model integration training effect was good, the model can effectively flat over the local areaand meet the requirement. The training error is less than 0.0001, the model predicted and measured values fit well.(3)The influence analysis of the growth stage of photosynthetic rate model.The photosynthetic capacity was different in different growth phase. LM training method was adopted to improve the cucumber blossom period model training,there was a large difference between the blossom period model and the seedling period model.The parameters were not considered, the neural network model was established contained 1650 groups in two stages.The correlation coefficient between actual measured and the calculated was 0.8796, the network training error was 0.00030. Setthe phase parameters as one-dimensional factor input to the neural network and the prediction model of the photosynthetic rate of the fusion stage parameters was established.The correlation coefficient between actual measured and the calculated was 0.9897, the network training error was less than 0.0001. This showed that the model training effect of the fusion stage parameters was good and the network training error was small.In this paper, the prediction model of photosynthetic rate of cucumber based onBP neural network was constructed. The effects of chlorophyll and stage parameters on photosynthetic rate were discussed. The research played an important role in improving facilities cucumber yield and quality, also provided the theoretical basis ofthe appropriate facilities small environment of the different crop periods.