Potato is the third major crop in the world and more than 375 million metric tonnes of potatoes are produced globally on an annual basis. Potato Virus Y (PVY) poses a significant threat to the production of seed potatoes thus resulting in a substantial economic loss and a threat to food security. The traditional approach uses serological assays to detect PVY in potato leaves and PCR is used to detect PVY in tubers, however, the processes are sophisticated, labor-intensive, and time-consuming. We propose to use Unmanned Aerial Vehicles (UAVs) integrated with hyperspectral cameras included with a downwelling irradiance spectrometer, to detect the PVY virus in commercial growers’ fields. We have used a 400-1000 nm visible and near-infrared (Vis-NIR) hyperspectral camera. We have trained several machine learning and deep learning models with optimized hyperparameters on the curated dataset. The performance of the models are very promising, and we found the convolutional neural network (CNN) is reliable in identifying the healthy plants (precision 0.980), and the feedforward neural neural network (FNN) is reliable in identifying the PVY-infected plants (recall 0.988). The hyperspectral camera provides a wide spectrum and most of them are redundant in identifying PVY. According to our analysis, five spectra regions are impactful in identifying the PVY. Two of them are in the visible spectrum, two in the near-infrared spectrum, and one in the red-edge spectrum. This research shows that PVY detection is possible in the early growing season minimizing the economic and yield losses, and identifies the most relevant spectra carrying the signatures of PVY.