Presentation: 2025 ND EPSCoR Annual conference 

October 21, 2025, NDSU Memorial Union, Fargo, North Dakota

Use of Artificial Intelligence in Soybean Diseases

Artificial intelligence (AI) enables computer systems to perform tasks typically associated with human cognition, including learning, reasoning, prediction, and decision-making. AI is transforming the field of plant pathology by enhancing the accuracy, speed, and scope of disease detection and management. Recent research highlights the deployment of machine learning (ML) and deep learning (DL) models for detecting plant diseases using imagery. In this review, we are considering two case studies on the use of AI for diagnosing soybean (Glycine max L.) diseases. One case study involves convolutional neural networks applied to assess Rhizoctonia root rot severity in soybean. We screened 228 USDA-ARS soybean accessions for resistance to the causal agent of Rhizoctonia root rot, Rhizoctonia solani under greenhouse conditions. A convolutional neural network (ResNet50) trained on root images classified root rot severity with high accuracy, particularly in detecting severe infections. A second case study involves the use of hyperspectral imaging for the diagnosis of sudden death syndrome (SDS) in soybeans. Two soybean genotypes with different levels of disease susceptibility will be grown under greenhouse conditions and inoculated with the SDS fungus, Fusarium virguliforme. Hyperspectral imaging from V1 (unifoliate leaf) to V5 (fourth trifoliate) growth stages is expected to reveal differences in spectral signature associated with the disease, enabling early disease diagnosis. Collectively, these approaches show that AI can enable fast, scalable, and reliable soybean disease diagnostics, serving as a valuable complement to expert assessments as well as traditional and molecular diagnostic tools.