The occurrence of maize diseases is frequent but challenging to manage. Traditional identification methods have low accuracy and complex model structures with numerous parameters, making them difficult to implement on mobile devices. To address these challenges, this paper proposes a corn leaf disease recognition model SNMPF based on convolutional neural network ShuffleNetV2. In the down-sampling module of the ShuffleNet model, the max pooling layer replaces the deep convolutional layer to perform down-sampling. This improvement helps to extract key features from images, reduce the overfitting of the model, and improve the model’s generalization ability. In addition, to enhance the model’s ability to express features in complex backgrounds, the Sim AM attention mechanism was introduced. This mechanism enables the model to adaptively adjust focus and pay more attention to local discriminative features. The results on a maize disease image dataset demonstrate that the SNMPF model achieves a recognition accuracy of 98.40%, representing a 4.1 percentage point improvement over the original model, while its size is only 1.56 MB. Compared with existing convolutional neural network models such as EfficientNet, MobileViT, EfficientNetV2, RegNet, and DenseNet, this model offers higher accuracy and a more compact size. As a result, it can automatically detect and classify maize leaf diseases under natural field conditions, boasting high-precision recognition capabilities. Its accurate identification results provide scientific guidance for preventing corn leaf disease and promote the development of precision agriculture.

Rapid and accurate identification and timely protection of crop disease is of great importance for ensuring crop yields. Aiming at the problems of large model parameters of existing crop disease recognition methods and low recognition accuracy in the complex background of the field, we propose a lightweight crop leaf disease recognition model based on improved ShuffleNetV2. First, the repetition number and the number of output channels of the basic module of the ShuffleNetV2 model are redesigned to reduce the model parameters to make the model more lightweight while ensuring the accuracy of the model. Second, the residual structure is introduced in the basic feature extraction module to solve the gradient vanishing problem and enable the model to learn more complex feature representations. Then, parallel paths were added to the mechanism of the efficient channel attention (ECA) module, and the weights of different paths were adaptively updated by learnable parameters, and then the efficient dual channel attention (EDCA) module was proposed, which was embedded into the ShuffleNetV2 to improve the cross-channel interaction capability of the model. Finally, a multi-scale shallow feature extraction module and a multi-scale deep feature extraction module were introduced to improve the model’s ability to extract lesions at different scales. Based on the above improvements, a lightweight crop leaf disease recognition model REM-ShuffleNetV2 was proposed. Experiments results show that the accuracy and F1 score of the REM-ShuffleNetV2 model on the self-constructed field crop leaf disease dataset are 96.72% and 96.62%, which are 3.88% and 4.37% higher than that of the ShuffleNetV2 model; and the number of model parameters is 4.40M, which is 9.65% less than that of the original model. Compared with classic networks such as DenseNet121, EfficientNet, and MobileNetV3, the REM-ShuffleNetV2 model not only has higher recognition accuracy but also has fewer model parameters. The REM-ShuffleNetV2 model proposed in this study can achieve accurate identification of crop leaf disease in complex field backgrounds, and the model is small, which is convenient to deploy to the mobile end, and provides a reference for intelligent diagnosis of crop leaf disease.

China has the largest apple-growing area and fresh fruit production in the world; however, water shortages and low fertilizer utilization rates have restricted agricultural development. It is a major challenge to obtain scientific and reasonable irrigation and fertilization systems for young apple trees in semi-arid regions of northern China. A 2-year field bucket experiment with four irrigation levels of W1 (75–90% Fs, where Fs is the field water holding capacity), W2 (65–80% Fs), W3 (55–70% Fs), and W4 (45–60% Fs), and three fertilizer levels of F1 (27-9-9 g N-P₂O₅-K₂O), F2 (18-9-9 g N-P₂O₅-K₂O), and F3 (9-9-9 g N-P₂O₅-K₂O) was conducted in 2019 and 2020, so as to explore the effects of different water and fertilizer treatments on the growth and physiological characteristics of young apple trees. The results showed that the plant growth, leaf area, and dry matter of young apple trees at each growing period reached maximum values under F1W2, and they showed a positive linear relationship with relative chlorophyll content (SPAD), net photosynthetic rate (Pn), transpiration rate (Tr), stomatal conductance (Gs), water consumption, and water use efficiency (WUE). With the growth of young apple trees, water-fertilizer coupling could significantly increase the leaf SPAD of young apple trees. Pn, Tr, and Gs reached the maximum value under F1W1, and although they decreased under F1W2, the water use efficiency increased by 2.3–25.7% and 4.0–23.8% under F1W2 compared with other treatments in two years, respectively. The water consumption of young apple trees increased with the increase of irrigation and fertilizer, and both dry matter and water productivity reached the maximum value under F1W2, which increased by 0.8%, 14.6% in 2019, and 0.6%, 11.1% in 2020 compared with F1W1, while water consumption decreased by 12.2% and 9.4% in both years. In conclusion, F1W2 treatment (soil moisture was controlled at 65–80% of field water holding capacity, and N-P₂O₅-K₂O was controlled at 27-9-9 g) was the best coupling mode of water and fertilizer for young apple trees in semi-arid areas of northern China.