Soybean cyst nematode (SCN) is a major threat to soybean crop, causing significant yield losses. In North Dakota (ND), since its first detection in 2003 in Richland County, SCN has been spreading rapidly. SCN can become ND soybean growers’ biggest disease problem if it is not detected early and managed proactively. Early and accurate detection of SCN is crucial for its effective and timely management. Traditional methods of detection include visual inspection, soil sampling, microscopic identification of morphological features, and manual counting of cysts and eggs, which is very labor intensive, time consuming, and requires specialized training. The NDSU nematology lab and other nematode diagnostic labs have invested tremendous time and money for SCN cysts and eggs identification and counting from numerous samples collected from soybean fields and from greenhouse and field experiments using the traditional methods. In recent years, research on utilization of artificial intelligence (AI) in different sectors has gained a momentum with rapid advancement and widespread adoption across various sectors including agriculture science. However, AI detection and quantification of SCN haven’t been evaluated in North Dakota.

• Develop a nematode image database for SCN eggs
• Develop a nematode image database for SCN cysts.
• Develop and evaluate deep learning-based algorithms to detect, identify and count SCN eggs and cysts by comparing with traditional methods

• Image databases for SCN cysts and eggs will be generated and shared with farmers.
• An AI model trained and tested on the annotated datasets will be disclosed and shared with farmers and stakeholders

SCN is an important disease in soybean. Our research will focus on utilization of AI for automated identification and counting of SCN cysts and eggs. This presented research proposal aims to develop user friendly AI approach for quick and easy SCN assessment, which otherwise is very time consuming and tedious. With the innovative technology advancement, utilizing AI for automated detection and quantification of the SCN cysts and eggs offers a promising solution for enhanced efficiency and accuracy in monitoring SCN infestations for farmers. This will further facilitate the timely intervention and ultimately effective management of SCN to reduce the losses from SCN to improve soybean yield and production.