Sugarcane breeding for drought tolerance is a sustainable strategy to cope with drought. In addition to biotechnology, high-throughput phenotyping has become an emerging tool for plant breeders. The objectives of the present study were to (1) identify drought-tolerant cultivars using vegetation indices (VIs), compared to the traditional method and (2) assess the accuracy of VIs-based prediction model estimating stomatal conductance (Gs) and chlorophyll content (Chl). A field trial was arranged in a randomized complete block design, consisting of seven cultivars of sugarcane. At the tillering and elongation stages, irrigation was withheld, and then furrow irrigation was applied to relieve sugarcane from stress. The physiological assessment measuring Gs and Chl using a handheld device and VIs were recorded under stress and recovery periods. The results showed that the same cultivars were identified as drought-tolerant cultivars when VIs and traditional methods were used for identification. Likewise, the results derived from genotype by trait biplot and heatmap were comparable, in which TCP93-4245 and CP72-1210 cultivars were classified as tolerant cultivars, while sensitive cultivars were CP06-2400 and CP89-2143 for both physiological parameters and VIs-based identification. In the prediction model, the random forest outperformed linear models in predicting the performance of cultivars in untested crops/environments for both Gs and Chl. In contrast, it underperformed linear models in the tested crops/environments. The identification of tolerant cultivars through prediction models revealed that at least two out of three cultivars had consistent rankings in both measured and predicted outcomes for both traits. This study shows the possibility of using UAS mounted with sensors to assist plant breeders in their decision-making.

Huanglongbing (HLB), also known as citrus greening disease, is a devastating disease of citrus. However, there is no known cure so far. Recently, under Section 24(c) of the Federal Insecticide, Fungicide, and Rodenticide Act (FIFRA), a special local need label was approved that allows the trunk injection of antimicrobials such as oxytetracycline (OTC) for HLB management in Florida. The objectives of this study were to use UAS-based remote sensing to assess the effectiveness of OTC on the HLB-affected citrus trees in Texas and to differentiate the levels of HLB severity and canopy health. We also leveraged UAS-based features, along with machine learning, for HLB severity classification. The results show that UAS-based vegetation indices (VIs) were not sufficiently able to differentiate the effects of OTC treatments of HLB-affected citrus in Texas. Yet, several UAS-based features were able to determine the severity levels of HLB and canopy parameters. Among several UAS-based features, the red-edge chlorophyll index (CI) was outstanding in distinguishing HLB severity levels and canopy color, while canopy cover (CC) was the best indicator in recognizing the different levels of canopy density. For HLB severity classification, a fusion of VIs and textural features (TFs) showed the highest accuracy for all models. Furthermore, random forest and eXtreme gradient boosting were promising algorithms in classifying the levels of HLB severity. Our results highlight the potential of using UAS-based features in assessing the severity of HLB-affected citrus.

Plant growth analysis provides insight regarding the variation behind yield differences in tested genotypes for plant breeders, but adopting this application solely for traditional plant phenotyping remains challenging. Here, we propose a procedure of using uncrewed aerial systems (UAS) to obtain successive phenotype data for growth analysis. The objectives of this study were to obtain high-temporal UAS-based phenotype data for growth analysis and investigate the correlation between the UAS-based phenotype and biomass yield. Seven different energy cane genotypes were grown in a random complete block design with four replications. Twenty-six UAS flight missions were flown throughout the growing season, and canopy cover (CC) and canopy height (CH) measurements were extracted. A five-parameter logistic (5PL) function was fitted through these temporal measurements of CC and CH. The first- and second-order derivatives of this function were calculated to obtain several growth parameters, which were then used to assess the growth of different genotypes with respect to weed competitiveness and biomass yield traits. The results show that CC and CH growth rates significantly differed among genotypes. TH16-16 was outstanding for its ground cover growth; therefore, it was identified as a weed-competitive genotype. Furthermore, TH16-22 had a higher CH maximum growth rate per day, yielding a higher biomass compared to other genotypes. The CH-based multi-temporal data as well as the growth parameters had a better relationship with biomass yield. This study highlights the application of UAS-based high-throughput phenotyping (HTP), along with growth analysis, for assisting plant breeders in decision-making.

Spinach ( Spinacia oleracea L.) yield prediction using unmanned aerial systems (UAS) has shown promise, but most existing models have been trained and validated within a single trial, leaving their generalizability across growing seasons largely untested; although UAS‐based growth analysis has been applied in other crops, it remains underexplored in spinach. The objectives of this study were to assess whether the fusion of vegetation indices (VIs) and textural features (TFs) could improve prediction ability, as evaluated through a cross‐year validation, in which the model was trained on data from 1 year and tested on unseen data from a different year. In addition, the UAS feature was further leveraged to perform spinach growth analysis. A 2‐year experiment (Exp. 1 and Exp. 2) was conducted using a randomized complete block design. One UAS flight mission was carried out before harvest, and yield was manually harvested at Exp. 1, while nine flight missions were implemented in addition to four biomass subsamples for Exp. 2. The UAS data and fresh yield of spinach from Exp. 2 were used to establish machine‐learning models and perform growth analysis, while the data from Exp. 1 was used to validate model accuracy. A fusion of VIs and TFs significantly improved the prediction ability of the models validated by the cross‐year scheme. Among the four models, Lasso regression showed the highest accuracy. In addition, a significant correlation between the maximum normalized difference red edge index (NDRE) growth rate and average yield was observed, suggesting that NDRE at the early growth stages reflects the final spinach yield. Our study highlights the potential of UAS, along with machine learning and growth function, to predict yield and describe growth of spinach.