Detecting nematodes in potato plants an explainable machine learning approach for detection of potato cyst nematode infections using hyperspectral imaging.

Abstract

Potato cyst nematodes pose a major threat to potato cultivation, with infestations often going undetected for years. Early and accurate detection is crucial for effective management, necessitating reliable, large-scale monitoring methods. Hyperspectral imaging shows great promise for non-invasive nematode detection, yet distinguishing between biotic (e.g., nematodes) and abiotic (e.g., drought) stressors remains a challenge. This study investigated the stress responses of potato plants to potato cyst nematodes Globodera rostochiensis and G. pallida , and water deficiency. We generated datasets to isolate and evaluate single and combined stressor effects on plant physiology and morphology. Various machine learning models and spectral processing techniques were applied to assess classification performance. Exploratory methods identified key spectral wavelengths, while statistical analyses evaluated the significance of physiological and morphological traits. Results showed that water deficiency was the dominant classification factor (F1 ​= ​0.95). The distinction between infected and non-infected plants reached F1 ​= ​0.70 in well-watered conditions and 0.80 in water-deficient plants. Distinguishing nematode species and inoculation levels yielded moderate accuracy (F1 ​= ​0.65-0.80), improving to 0.80 when combining biotic and abiotic stress. However, classifying multiple stress categories simultaneously reduced performance (F1 ​= ​0.58). These findings highlight the challenges of stressor separation and the potential of hyperspectral imaging for nematode detection. Further research is needed to refine classification models and validate findings under field conditions, facilitating the integration of hyperspectral imaging into precision agriculture.

Code and data availability

The authors explicitly state that processed hyperspectral data plus morphology and physiology measurements are publicly available on Zenodo, and their analysis code is on GitHub. Both are paper-specific, public, and actionable. The SiaPy library is a generic third-party tool and is excluded.