Hyperspectral remote sensing provides the opportunity to monitor nutrient status of vegetable crops. Previous studies have generally been limited in scope, either to a small wavelength range (e.g., 400-1300 nm), a small number of cultivars, a single growth stage or a single growing season. Methods that are not time- or site-specific are needed to use hyperspectral imaging for routine monitoring of plant nutrient status and sustainable nitrogen management. Using data from four cultivars of potatoes (Solanum tuberosum L.), three growth stages and two growing seasons (2018-2019), we studied the capacity of full-range (400-2350 nm) imaging spectroscopy to quantify potato nutrient status (petiole nitrate, whole leaf total nitrogen and whole vine total nitrogen) and predict tuber yield across cultivars, growth stages and growing seasons. We specifically tested the capabilities of: (1) ordinary least-squares regression (OLSR) using traditional hyperspectral vegetation indices (VIs); (2) partial least-squares regression (PLSR) using full spectrum (400-2350 nm), VNIR- (visible to near infrared: 400-1300 nm) or SWIR-only (shortwave infrared: 1400-2350 nm) wavelengths; (3) predictive models developed for one potato type or growing season from a different type or season. Our results show that OLSR models produced poor predictions with data from all dates pooled together (validation R2<0.01). Single-date OLSR models performed better (R2=0.20-0.60). PLSR models did well and were comparable using different spectral regions (full-spectrum, VNIR-only and SWIR-only), with validation R2=0.68-0.82. Testing across potato types, models produced reliable predictions (R2=0.45-0.75), but with some bias. Cross-season models had validation R2=0.46-0.75, with a more significant bias than the cross-potato type models. For future studies that aim at developing reliable and robust models for potatoes, we recommend: (1) obtaining ground measurements that capture different growing conditions and growth stages, and (2) ensuring that image processing minimizes spectral discrepancies among dates.