Optimizing UAV Hyperspectral Imaging for Predictive Analysis of Nutrient Concentrations, Biomass Growth, and Yield Prediction of Potatoes

Abstract

Accurate real-time estimation of nutrient concentrations in potato (Solanum tuberosum L.) canopies is crucial for advanced decision support systems in site-specific nutrient management. This study investigated the effectiveness of unmanned aerial vehicle (UAV) based hyperspectral imaging in predicting nitrogen (N), phosphorus (P), potassium (K), and sulfur (S) concentrations in potato plants comparing two sampling types such as petiole/leaves and above-ground biomass (AGB) sampling. Furthermore, this study also investigates the prediction of AGB, total, and marketable yield of two potato cultivars, 'Atlantic' (chipping) and 'Red La Soda' (tablestock). Four UAV flights over experimental sites were made, and hyperspectral imaging sensors (393–995 nm, 273 bands) were conducted, which coincided with the in-field sample collection as ground truth. Data were analyzed using the partial least square regression model after preprocessing and extracting spectra from images. The model showed high accuracy in estimating plant N concentration from petiole/leaf samples (external validation R² = 0.58; [external validation RMSE = 0.31 × 10⁴ mg kg⁻¹]), as well as for P (0.75 [0.05 × 10⁴ mg kg⁻¹]) and S (0.58 [0.03 × 10⁴ mg kg⁻¹]). Potassium estimation accuracy improved with biomass sampling (0.47 [1.19 × 10⁴ mg kg⁻¹]). Above-ground biomass estimation had higher accuracy for 'Atlantic' (0.75 [1.29 Mg ha⁻¹]) than for 'Red La Soda' (0.57 [1.38 Mg ha⁻¹]). The model accurately estimated total and marketable tuber yields for both cultivars, with variations noted based on flight timing related to the crop stage. Cultivar ‘Red La Soda’ achieved the highest total yield accuracy on the first (0.76 [3.31 Mg ha⁻¹]) and fourth flights (0.76 [3.31]), while the ‘Atlantic’ had the highest accuracy on the third flight (0.50 [4.11]). Model outputs, including standardized coefficients and variable importance in prediction, visualizing band contributions to measured parameter predictions are presented. This study concludes that hyperspectral imaging successfully estimates the potato nutrient concentration and predicts the in-season potato yield, which can contribute significantly to the potato management decision support system. However, it underscores the importance of multiyear high temporal data acquisition with variable potato varieties to establish a reliable AGB and yield estimation model to improve performance.