In apple cultivation, the total nitrogen content is an important indicator of plant growth, fruit quality, and yield. Timely monitoring of growth becomes imperative, since an imbalance, either in deficiency or excess nitrogen, can result in physiological disorders, adversely impacting both the quantity and quality of fruit. Leaf nitrogen content can be determined using simple chlorophyll meters or destructive testing; however, these methods are time-consuming. However, by employing spectral imaging technology, it is possible to swiftly predict leaf nitrogen content. This study estimated the total nitrogen content in apple trees via hyperspectral imaging and machine learning-based regression analysis (partial least-squares regression (PLSR), support vector regression (SVR), and eXtreme gradient boosting regression (XGBoost). Additionally, to reduce computational costs and improve reproducibility, spectral binning was divided into three stages (4, 8, and 16 bins), and models were compared with a 2-binning estimation model. The analysis focused on green, red, red edge, and near-infrared (NIR) spectra, with 5–10 selected wavelengths, and the SVR-based prediction model showed a similar or greater performance to that of the full spectrum. At 4- and 8-binning, the selected wavelengths were similar to those at 2-binning, maintaining similar prediction model performance. However, at 16 bp, the performance of the prediction model decreased owing to spectral data loss, leading to a significant reduction in wavelengths for nitrogen content estimation. These results can support informed nitrogen fertilization decisions, enabling precise, real-time monitoring of nitrogen content for enhanced plant growth, fruit quality, and yield in apple trees. Additionally, the selected wavelengths can be considered in the development of new types of multispectral sensors.

Peaches are one of the most popular fruits around the globe. Selecting the optimum harvesting maturity for peaches is crucial in assuring high-quality fruits. This study is a model for determining the ideal harvest time for a robot harvester. Our study was carried out over two years on ‘Mihong’ peaches during days after full bloom (DAFB) 71 to 90 in 2021 and DAFB 64 to 84 in 2022 to select the optimal maturity index through a quality survey. The fruit size, soluble solids content (SSC), titratable acidity (TA), firmness, peel color (L*, a*, b*, chroma, and hue), and ethylene production were investigated. Fruit size showed the regular double sigmoid curve, and SSC increased while firmness and TA decreased with time. The samples left in storage conditions in 2022 showed a massive change in SSC and firmness after DAFB 74, implying the optimum harvesting stage. Interestingly, color values manifest the same consequence with a*, b*, and hue by reaching a plateau with apex side color values after DAFB 74, indicating the desired maturity. Overall, the results show that color values are an outstanding non-destructive alternative to typical destructive measurements for determining the exact time to harvest ‘Mihong’ peaches.

This study investigated the effects of elevated temperature on the phenology and morphology of the early-maturing peach cultivar ‘Mihong’. The experiment was conducted from 2019 to 2024 in a temperature-gradient chamber at the National Institute of Horticultural and Herbal Science, Wanju, Korea, with four warming treatments (+2.2 °C to +5.0 °C above ambient). Higher temperatures delayed the onset of endodormancy and markedly shortened the period from endodormancy release to full bloom. Elevated temperatures also increased the LD ratio, with the proportion of fruits exceeding an LD ratio of 1.0 rising significantly with temperature. The LD ratio showed strong correlations with November mean temperature (MT11) and March maximum temperature (HT3) (r = 0.81) and was also associated with the average temperature (Temp3, r = 0.51) and duration (P3, r = −0.54) of the endodormancy release to full bloom phase. Stepwise and PLS regression identified temperatures in May, November, and March as key predictors of the LD ratio, while PCA revealed that temperature variables (Temp3, Temp5) and stage durations (P3, P4) were major contributors. These results confirm that climate warming alters the phenology and morphology of ‘Mihong’, reducing fruit quality and marketability, while providing a basis for predictive modeling and highlighting the importance of adaptive strategies such as shading or growth regulator application.

This study evaluates early detection of pepper wilt disease using vegetation indices obtained from unmanned aerial vehicle (UAV)-based multispectral time-series imagery and machine learning classification. Multispectral images were acquired from June–August 2023, and disease status was determined by field diagnosis and visual interpretation of the imagery using diagnosed plants as references. Nine vegetation indices were used to develop k-nearest neighbors (KNN), support vector machine, and logistic regression (LR) models. For the June and July datasets, the best model was LR, achieving validation accuracies of 0.860 and 0.925, recall of 0.850 and 1.000, and F1-scores of 0.850 and 0.930, respectively. The best combined-dataset model was KNN; however, it did not outperform the monthly dataset models. The difference vegetation index showed the highest variable importance in the two monthly dataset models, and the variable importance of the normalized difference vegetation index was markedly higher in the July model. Similar trends were observed in the histogram analysis of vegetation indices and spectral features. Thus, date-specific models reflecting crop growth and disease progression were more effective than pooled observations across dates. Overall, UAV-based multispectral time-series imagery provides a practical basis for the field-scale early detection and prompt management of pepper wilt disease.