Agriculture diseases are unavoidable problems in agricultural production. With the extensive adoption of deep learning in agricultural diseases, the impact of diseases on crops has been effectively reduced. Many existing disease recognition models use multi-level small kernel convolutional structures, but small kernel convolution is not conducive to extracting global information and cannot capture the relationship between distant pixels. To solve this problem, this paper adopts the large kernel convolutional network RepLKNet to identify the Plant Diseases Training Dataset, and the large kernel convolutional network can effectively increase the receptive field and extract long-term dependencies. Improving model accuracy and training speed using transfer learning techniques. In this paper, experiments were conducted at Plant Diseases Training Dataset and the overall accuracy of the model was 93.6%, with an average accuracy of 91.9% and a Kappa coefficient of 93.3%, which proves its validity and reliability in the identification of agricultural diseases.
Accurate estimation of chlorophyll and nitrogen content in tea leaves is essential for effective nutrient management. This study introduces a proof-of-concept dual-view RGB regression framework developed under controlled scanner conditions. Paired adaxial and abaxial images of Yun Kang 10 tea leaves were collected from four villages in Lincang, Yunnan, alongside corresponding soil and plant analyzer development (SPAD) and nitrogen measurements. A lightweight dual-input CoAtNet backbone with streamlined Bneck modules was designed, and three fusion strategies, Pre-fusion, Mid-fusion, and Late-fusion, were systematically compared. Ten-fold cross-validation revealed that Mid-fusion delivered the best performance ( = 94.19% ± 1.75%, root mean square error () = 3.84 ± 0.65, = 3.00 ± 0.45) with only 1.92 M parameters, outperforming both the single-view baseline and other compact models. Transferability was further validated on a combined smartphone–scanner dataset, where the framework maintained robust accuracy. Overall, these findings demonstrate a compact and effective system for non-destructive biochemical trait estimation, providing a strong foundation for future adaptation to field conditions and broader crop applications.
24 September 2025 in Smart Agricultural Technology