Conventional crop fertilization classification and fertilization decision-making methods are difficult to operate efficiently and accurately. In order to improve the efficiency of greenhouse tomato fertilization and fertilization decision-making, this study is based on more than 1,800 greenhouse tomato leaf pictures, using data enhancement, migration learning, gradient descent, the regularization method optimizes the Convolutional Neural Network (CNN), and builds a deep learning model for tomato leaf fertility classification. The full convolutional neural network (FCN) is optimized using data enhancement and hyperparameter optimization methods, and a deep learning model for tomato leaf region segmentation and region information extraction is constructed. In this paper, the leaf image information collected by the on-site camera is converted into improved color space information, combined with the tomato leaf nitrogen deficiency-color model, to realize the amount of decision of the tomato nitrogen fertilizer at the irrigation site. Research shows that the accuracy of the CNN leaf fertility recognition model training set is close to 100%, the accuracy of the validation set can reach 95%, and the accuracy of the test set is 91%; the average intersection ratio from the test set data of the FCN leaf segmentation model is 0.91 and the average pixel accuracy is 0.94.
The shortage of available water resources and climate change are major factors affecting agricultural irrigation. In order to improve the irrigation water use efficiency, it is necessary to predict the water requirements for crops in advance. Reference evapotranspiration (ETo) is a hypothetical standard reference crop evapotranspiration, many types of artificial intelligence models have been applied to predict ETo; However, there are still few in the literature regarding the application of hybrid models for deep learning model parameters optimization. This paper proposes two hybrid models based on particle swarm optimization (PSO) and long-short-term memory (LSTM) neural network, used to predict ETo at the four climate stations, Shaanxi province, China. These two hybrid models were trained using 40 years of historical data, and the PSO was used to optimize the hyperparameters in the LSTM network. We applied the optimized model to predict the daily ETo in 2019 under different datasets, the result showed that the optimized model has good prediction accuracy. The optimized hybrid models can help farmers and irrigation planners to make plan earlier and precisely, and can provide valuable information to improve tasks such as irrigation planning.
The type of single-slope solar greenhouse is mainly used for vegetable production in China. The coupling of heat storage and release courses and the dynamic change in the outdoor weather parameters momentarily affect the indoor environment. Due to the high cost of small weather stations, the environmental parameters monitored by the nearest meteorological stations are usually used as outdoor environmental parameters in China. In order to accurately predict the solar greenhouse and crop water demand, this paper proposes three deep learning models, including neural network regression (DNNR), long short-term memory (LSTM), and convolutional neural network-long- short-term memory (CNN-LSTM), and the hyperparameters of three models were determined by orthogonal experimental design (OD). The temperature and relative humidity monitored by the indoor sensors and outdoor weather station were taken as the inputs of models, the temperature and relative humidity 3, 6, 12 and 24 h in advance were taken as the output, 16 combinations of input and output data of two typical solar greenhouses were trained separately by three deep learning models, those models were trained 144, 144 and 288 times, respectively. The best model of three type models at four prediction time points were selected, respectively. For the forecast time point of 12 h in advance, the errors of the best LSTM and CNN-LSTM models in two greenhouses were all smaller than the DNNR models. For the three other time points, the results show that the DNNR models have excellent prediction accuracy among the three models. The maximum and minimum temperature, relative humidity, and ETo were also accurately predicted using the corresponding optimized models. In sum, this study provided an optimized deep learning prediction model for environmental parameters of greenhouse and provides technical support for irrigation decision-making and water allocation.
a 929631470@qq.com, b yangqilianglovena@163.com. Abstract.Two irrigation treatments (W1,total irrigation amount was12L.W2,total irrigation amount was 6L) and three vermiculite laying methods (Z0, no vermiculite. Z2, vermiculite was laid on the surface of the pot.Z2, vermiculite was laid in the bottom of the pot) were designed in the trial. The results showed that, the number and percentage of red leaves significantly decreased by 27.03%,16.00% in Z2 treatment than Z0 when irrigation amount was W1, respectively. The number and percentage of red leaves respectively increased by 6.49%,0.60% in Z2 treatment as compared to Z1 when irrigation amount was W2.Diurnal variation of evapotranspiration and transpiration of poinsettia showed a single peak curve, and the maximum were all occurred at the period of 14:00-16:00.The mass of dry matter (roots, stems) and the number of red leaves had a slight fall (no obvious difference) on the premise of saving 50% irrigation amount in W2Z2 treatment than W1Z0,the total dry mass and evapotranspiration were all evidently decreased,while irrigation water use efficiency was significantly uplifted by 72.36%.Therefore,W2Z2 treatment was the optimal combination mode which was not affected appreciation of the plants and meanwhile conducive to uplift for irrigation water use efficiency of potted poinsettia under the condition of the trial.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.