A dataset of knowledge graph construction for facility-grown tomato and cucumber pests and diseases

<p indent="0mm">Facility-grown tomatoes and cucumbers are among the most widely grown, cultivated and processed vegetable crops in the world. With the challenges of global warming and frequent international trade, pests and diseases affecting tomatoes and cucumbers have been rapidly spreading all over the world, and have become one of the major constraints on their production worldwide. The construction of a knowledge graph for pests and diseases in facility-grown tomatoes and cucumbers is a fundamental work to precise pest and disease prevention and control, and plays an important role in the development of precision facility agriculture in protected cultivation systems. The dataset was constructed based on information sourced from agricultural websites, professional books, and academic literature (e.g., CNKI), using Python crawler and OCR technologies. The data were cleaned, sorted and merged to form a dataset that contains 70 tomato diseases with 8 defined fields and 34 common pest types affecting facility-grown cucumbers. In order to ensure the quality and accuracy of this dataset, the data come from authoritative sources and subjected to rigorous pre-processing, collation, manual validation, and expert review. This dataset can provide foundational data support for constructing knowledge graphs of tomato and cucumber pests and diseases, and serves as a valuable resource for advancing integrated pest and disease prevention and control of tomatoes and cucumbers in China’s protected agriculture sector.