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.
To solve the problem that the parameters of the multiple-input multiple-output (MIMO) irrigation system are difficult to control accurately, an on-demand irrigation control experimental device was developed. The main input parameters of the device are the opening degree of the main pipe valve, the opening frequency of and the pump station, the opening degree of the branch pipeline valve with the different combinations of different opening degrees. Based on these input parameters, four types of experimental methods were designed, and a total of 1695 groups of experiments were designed. The results show that the different opening degree combinations of the branch electric valve cannot significantly affect the flow of the branch pipeline but also significantly affect the pressure of the main pipeline. The prediction error of the operating frequency of the pump station and the opening degree of the branch valve were regarded as the objective function. Six intelligent prediction models were constructed, which are Back Propagation (BP), support vector regression (SVR) Linear, SVR-RBF, SVR-Poly, random forest (RF) and eXtreme Gradient Boosting (XGBoost), respectively. The results show that the XGBoost is the best model among the six models. For the opening degree of three branch valves, the mean absolute error (MAE) between the predicted value and actual value is less than 3.3%, the mean square deviation (RMSE) between the predicted values and actual values is less than 4.5%, and the R2 of between the predicted values and actual values is greater than 0.990. The control models and system can meet the needs of an on-demand irrigation system.
Due to population growth and human activities, water shortages have become an increasingly serious concern in the North China Plain, which has become the world’s largest underground water funnel. Because the yield per unit area, planting area of crops, and effective precipitation in the region are uncertain, it is not easy to plan the amount of irrigation water for crops. In order to improve the applicability of the uncertainty programming model, a hybrid LSTM-CPP-FPP-IPP model (long short-term memory, chance-constrained programming, fuzzy possibility programming, interval parameter programming) was developed to plan the irrigation water allocation of irrigation system under uncertainty. The LSTM (long short-term memory) model was used to predict crop yield per unit area, and CPP-FPP-IPP programming (chance-constrained programming, fuzzy possibility programming, interval parameter programming) was used to plan the crop area and the effective precipitation under uncertainty. The hybrid model was used for the crop production profit of winter wheat and summer corn in five cities in the North China Plain. The average absolute error between the model prediction value and the actual value of the yield per unit area of winter wheat and summer maize in four cities in 2020 was controlled within the range of 14.02 to 696.66 kg/hectare. It shows that the model can more accurately predict the yield per unit area of crops. The planning model for the benefit of irrigation water allocation generated three scenarios of rainfall level and four planting intentions, and compared the planned scenarios with the actual production benefits of the two crops in 2020. In a dry year, the possibility of planting areas for winter wheat and summer corn is optimized. Compared with the traditional deterministic planning method, the model takes into account the uncertain parameters, which helps decision makers seek better solutions under uncertain conditions.
Rapid and non-destructive detection of nitrogen content in greenhouse cucumber leaves is essential for precision fertilization, yet traditional chemical methods are destructive and time-consuming, and existing spectral technologies suffer from high cost and poor field adaptability. This study aims to propose a high-precision detection scheme for cucumber leaf nitrogen content based on a lightweight model, suitable for complex scenarios. A total of 698 cucumber leaf images covering three growth stages were collected to build a segmentation dataset. Four categories and eight types of deep learning segmentation models were optimized and compared, and the optimal one was selected to extract leaf regions. Nine color features were extracted and combined with Kjeldahl-measured nitrogen content to construct and optimize three machine learning models, forming a deep learning segmentation–color feature extraction–machine learning prediction process. The results showed that YOLOv11n achieved the best segmentation accuracy, with an IoU of 0.9212 and AP of 0.9998 for high-resolution images. The optimized XGBoost had the highest prediction accuracy, with an MAE of 0.469, MSE of 0.461, and RMSE of 0.679, which are 10.15%, 8.71%, and 4.36% lower than Support Vector Regression with Radial Basis Function kernel (SVR_RBF) respectively, and its predicted nitrogen content aligned well with true values. The proposed scheme integrating YOLOv11n and XGBoost offers a lightweight technical solution for nitrogen nutrition diagnosis and precise fertilization of greenhouse cucumbers.