Chinese named entity recognition in agricultural diseases and pests domain(CNER-ADP) plays an important role in agricultural natural language processing such as relation extraction, agricultural knowledge graph construction, and agricultural knowledge question and answering, but it still presents some problems, i.e., the neglect of inherent semantic information and local contextual features and the insufficiency of capturing longdistance dependencies, which will lead to low accuracy and robustness. To solve the above problems and tackle the CNER-ADP task, a novel Chinese named entity recognition method for agricultural diseases and pests via jointly using radicalembedding and selfattention (RS-ADP) was proposed. Firstly, the model integrated radical embedding and character embedding as input to enrich semantic information. Among them, three different strategies, including CNN and BiLSTM were both designed to capture the radicallevel embedding. Secondly, a CNNs layer with different kernel sizes was considered capturing multiscale local contextual features. Thirdly, based on the BiLSTM layer, selfattention mechanism was used to further enhance the ability of the model to extract longerdistance dependencies. Finally, the conditional random field (CRF) was utilized to identify entity boundaries and category. The experiments were carried out on the corpus of agricultural diseases and pests, named AgCNER, which contained 11 categories and 24715 samples. At macrolevel, the RS-ADP model achieved optimal precision, recall, and F1 values of 94.16%, 94.47%, and 94.32%, respectively. In terms of specific categories, it achieved F1 values as high as 95.81%, 97.76%, and 97.23% on easily identifiable entities such as crop, disease, and pest. Meanwhile, this model still maintained over 86% of F1 value on some other difficultly recognized entities such as weed and pathogeny. The experimental results showed that the proposed model could effectively recognize the named entities of agricultural pests and diseases without feature engineering. Moreover, it had certain generalization and outperformed other models. 