Breeders have made important efforts to develop genotypes able to resist virus attacks in sweetpotato, a major crop providing food security and poverty alleviation to smallholder farmers in many regions of Sub-Saharan Africa, Asia and Latin America. However, a lack of accurate objective quantitative methods for this selection target in sweetpotato prevents a consistent and extensive assessment of large breeding populations. In this study, an approach to characterize and classify resistance in sweetpotato was established by assessing total yield loss and virus load after the infection of the three most common viruses (SPFMV, SPCSV, SPLCV). Twelve sweetpotato genotypes with contrasting reactions to virus infection were grown in the field under three different treatments: pre-infected by the three viruses, un-infected and protected from re-infection, and un-infected but exposed to natural infection. Virus loads were assessed using ELISA, (RT-)qPCR, and loop-mediated isothermal amplification (LAMP) methods, and also through multispectral reflectance and canopy temperature collected using an unmanned aerial vehicle. Total yield reduction compared to control and the arithmetic sum of (RT-)qPCR relative expression ratios were used to classify genotypes into four categories: resistant, tolerant, susceptible, and sensitives. Using 14 remote sensing predictors, machine learning algorithms were trained to classify all plots under the said categories. The study found that remotely sensed predictors were effective in discriminating the different virus response categories. The results suggest that using machine learning and remotely sensed data, further complemented by fast and sensitive LAMP assays to confirm results of predicted classifications could be used as a high throughput approach to support virus resistance phenotyping in sweetpotato breeding.