Prediction of End-Of-Season Tuber Yield and Tuber Set in Potatoes Using In-Season UAV-Based Hyperspectral Imagery and Machine Learning

Potato is the largest non-cereal food crop in the world. Timely estimation of end-of-season tuber production using in-season information can inform sustainable agricultural management decisions that increase productivity while reducing impacts on the environment. Recently, unmanned aerial vehicles (UAVs) have become increasingly popular in precision agriculture due to their flexibility in data acquisition and improved spatial and spectral resolutions. In addition, compared with natural color and multispectral imagery, hyperspectral data can provide higher spectral fidelity which is important for modelling crop traits. In this study, we conducted end-of-season potato tuber yield and tuber set predictions using in-season UAV-based hyperspectral images and machine learning. Specifically, six mainstream machine learning models, i.e., ordinary least square (OLS), ridge regression, partial least square regression (PLSR), support vector regression (SVR), random forest (RF), and adaptive boosting (AdaBoost), were developed and compared across potato research plots with different irrigation rates at the University of Wisconsin Hancock Agricultural Research Station. Our results showed that the tuber set could be better predicted than the tuber yield, and using the multi-temporal hyperspectral data improved the model performance. Ridge achieved the best performance for predicting tuber yield (R2 = 0.63) while Ridge and PLSR had similar performance for predicting tuber set (R2 = 0.69). Our study demonstrated that hyperspectral imagery and machine learning have good potential to help potato growers efficiently manage their irrigation practices.

Genomic composition of 4x–2x potato hybrids: influence of Solanum chacoense

Tetraploid potato hybrids representing three genomic compositions (TTTT, TTPP, and TTPC (T, Solanum tuberosum; P, Solanum phureja; C, Solanum chacoense)) were constructed by crossing S. tuberosum (2n = 4x = 48) cultivars or advanced breeding selections among themselves or with 2n pollen producing selections of either S. phureja (2n = 2x = 24) or F1 hybrids between S. phureja and S. chacoense (2n = 2x = 24). Seedling families were evaluated in the fall season and selections within each family were evaluated in spring trials at Ait-Melloul, Morocco. Genomic composition was the greatest source of variance for yield-attributing traits, with TTPC outperforming other hybrids in fall trials for vine vigor, tuber set, and tuber yield and TTPP outperforming other hybrids in spring trials for the same traits. The results imply that analytic breeding for potato by construction of complex interspecific hybrids may result in clones surpassing a previously proposed heterotic threshold if the target environment is conducive to expression of favorable traits from alien germ plasm.Key words: Solanum phureja, Solanum chacoense, Solanum tuberosum, 4x–2x hybrids, potato, analytic breeding.

Effects of irrigation regimes on powdery scab disease and yield of potatoes

The period of susceptibility of potato tubers to powdery scab (Spongospora subterranea) was studied by inoculating potato plants with spores, or by watering plants in infested soil, at different stages of plant development in greenhouse conditions. Maximum susceptibility began about 1 week before the stage when 50% of stolons had swollen to at least 5-mm diameter (tuber set), and ended 3-4 weeks later. With holding irrigation water during this period reduced the severity of powdery scab by 65-75% in field experiments in 1981-82 and 1982-83, but had no apparent effect on disease severity in 3 out of 6 large-scale field trials during 1984-85.