Identification of plant-parasitic nematode genera in turfgrass using deep learning algorithms

TL;DR

This study explores using deep learning models to accurately identify plant-parasitic nematodes in turfgrass, which could help improve nematode management without requiring expert knowledge.

Contribution

The study introduces and evaluates deep learning models for automated identification of nematode genera in turfgrass.

Findings

EfficientNet V2-S and Swin Transformer V2-B achieved the highest balanced classification accuracy (94.63% and 94.34%) in identifying nematode taxa.

EfficientNet V2-S outperformed other models in a user-end platform test with 82.47% accuracy.

Abstract

Plant-parasitic nematodes are an important threat to turfgrass. Left unmanaged, they can cause serious reductions in the quality and playability of golf courses and sports fields. Effective nematode management depends on accurate identification of the nematode genera extracted from soil samples. However, this process requires specialized expertise in nematology, which is often limited in plant diagnostic laboratories. Recent advancements in deep learning models offer promising solutions for the future of nematode identification. In this study, we evaluated the performance of EfficientNet V2-S, MobileNetV3-L, ResNet101, and Swin Transformer V2-B convolutional neural network model architectures in the classification of seven nematode taxa associated with turfgrass. Models were trained using a dataset of 5406 plant-parasitic nematode images where the dataset was split into 70, 15, and 15% for training, testing, and validation, respectively. Data augmentation and hyperparameter optimization using a combined Bayesian optimization and Hyperband algorithm (BOHB) approach were used to improve the model performance. Balanced classification accuracy on the test set was highest for EfficientNet V2-S and Swin Transformer V2-B at 94.63% and 94.34%, respectively. MobileNetV3-L and ResNet101 had lower balanced accuracies of 90.83% and 86.33%, respectively. Testing the models on an additional dataset using a user-end platform indicated the superiority of EfficientNet V2-S to other models with 82.47% accuracy. The findings of this study indicate the potential application of deep learning tools for accurate nematode identification to aid in diagnostics.

The online version contains supplementary material available at 10.1038/s41598-025-29467-4.

Figures