Considering that the occurrence and spread of diseases are closely related to the planting environment, a tomato disease diagnosis method based on Multi-ResNet34 multi-modal fusion learning based on residual learning is proposed for the problem of limited recognition rate of a single RGB image of a tomato disease. Based on the ResNet34 backbone network, this paper introduces transfer learning to speed up training, reduce data dependencies, and prevent overfitting due to a small amount of sample data; it also integrates multi-source data (tomato disease image data and environmental parameters). The feature-level multi-modal data fusion method is used to retain the key information of the data to identify the feature, so that the different modal data can complement, support and correct each other, and obtain a more accurate identification effect. Firstly, Mask R-CNN was used to extract partial images of leaves from complex background tomato disease images to reduce the influence of background regions on disease identification. Then, the formed image environment data set was input into the multi-modal fusion model to obtain the identification results of disease types. The proposed multi-modal fusion model Multi-ResNet34 has a classification accuracy of 98.9% for six tomato diseases: bacterial spot, late blight, leaf mold, yellow aspergillosis, gray mold, and early blight, which is higher than that of the single-modal model. With the increase by 1.1%, the effect is obvious. The method in this paper can provide an important basis for the analysis and diagnosis of tomato intelligent greenhouse diseases in the context of agricultural informatization.

Wireless sensor networks (WSN) can accurately and timely obtain the production information of crops, and provide data basis for intelligent agriculture. The dynamic crop state and unstable climate environment make it difficult to predict the connectivity probability of wireless links. Therefore, this paper studies an energy-saving opportunity routing transmission strategy under the influence of dynamic link interaction. The protocol establishes an importance model based on algebraic connectivity to reduce the energy consumption of network key nodes. At the same time, based on the improved Bellman–Ford algorithm, a method of constructing candidate sets is studied. It converts the opportunistic routing transmission cost of farm WSN into anycast link cost and the remaining opportunistic path cost affected by energy consumption. The priority queue is used to determine the nodes participating in the iteration, thereby reducing the computational overhead. The protocol also designs a backoff strategy considering the current residual energy to select the only forwarding node and reduce the unnecessary packet copies in the transmission process. Simulation results show that the studied method is superior to the existing opportunistic routing schemes in terms of packet overhead, network lifetime, energy consumption, and packet delivery rate.