In this study, the authors conduct a review of their own prior research, practical experience from farming enterprises, and both domestic and international scientific literature in order to refine the existing model for an industrial raspberry cultivar adapted to open-field cultivation in Central Russia. The proposed model comprises five blocks and more than 50 criteria, encompassing plant morphological and biological characteristics, adaptability indicators, productivity, fruit quality, and technological suitability. According to the model, the target cultivar should tolerate early-winter frosts down to -25 °C without damage, withstand midwinter temperatures as low as -40 °C, endure -25 °C immediately following a thaw, and survive repeated hardening at temperatures down to -30 °C. For everbearing raspberry cultivars, early crop maturation represents a key adaptive trait for Central Russia, implying the ability to complete fruiting and fully finish the growing season within a frost-free period of less than 150 days and a minimum sum of active temperatures of 20002200 °C. An essential requirement for new cultivars consists in their immunity or high resistance (not less than 4.0 points) to viral and fungal diseases under epiphytotic conditions. The primary objective of yield-oriented breeding is to develop cultivars with a productivity of at least 4.0 kg per bush and an average berry mass exceeding 5.5 g under manual harvesting and 3.5 g under mechanized harvesting. The target cultivar should also accumulate fruits with more than 10 % sugars, over 15 % soluble solids, 1.0-1.9 % organic acids, more than 50 mg/100 g of ascorbic acid, over 100 mg/100 g of anthocyanins, and more than 500 mg/100 g of polyphenols. The key requirements for raspberry fruit include a harmonious flavor profile with a rich aroma, increased firmness (>7 N), good detachment from the receptacle (0.3–0.7 N), and the ability to maintain quality during post-harvest storage for 10–15 days without significant deterioration. The proposed model serves as a framework for more targeted development of initial parental forms for hybridization, the creation of new commercial cultivars, and the overall improvement of breeding efficiency.

Unstable weather conditions characteristic of the moderately continental climate of the Northwestern Ciscaucasia contribute to somatic mutations in grapevines and the emergence of biotypes exhibiting both positive and negative traits within long-cultivated varieties. Clonal selection has made it possible to identify, within a wide diversity, the most adaptive protoclones of Aligoté, Chardonnay, and Riesling varieties, which retain their favorable agronomic and productivity traits in vegetative progeny. This study was aimed at selecting the most promising biotypes possessing heritable traits of high adaptability and productivity for their subsequent inclusion in the Russian State Register of Plant Varieties and Hybrids Approved for Use. The research objects were protoclones of the first and second vegetative generations of the white wine grape varieties Aligoté, Riesling, and Chardonnay. For the Aligoté variety, in the first vegetative generation at the clonal testing site in Anapa (2014–2016), protoclones ZA 11-75-15 and ZA 11-79-37 were identified based on superior agronomic traits and productivity. These protoclones exceeded the reference samples in the proportion of fruitful shoots, total number of clusters, fruiting coefficient (K1), and overall productivity. The yield of ZA 11-79-37 was 20 % higher than that of the control, while ZA 11-91-15 exceeded it by 12 %. In the second vegetative generation at the clonal testing site in Taman Peninsula, the ZA 11-79-37 protoclone, unlike other biotypes, maintained high agronomic performance and productivity. In 2015–2016, its yield corresponded to the average values of the studied analogues, while in 2025 it exceeded the control by 35 %. For the Chardonnay variety, the ZSh 137-44 protoclone demonstrated the greatest stability and productivity at all stages of evaluation. It outperformed the other varieties in the number of fruitful shoots, number of clusters, shoot productivity, and yield, exceeding the control by 9–22 %. For the Riesling variety, protoclones RYUCH 38-67 and RYUCH 39-39 were identified. The yield of RYUCH 38-67 exceeded the control by 10–31%, while RYUCH 39-39 exceeded it by 7–32 %.

The study of heat and drought resistance in grapevines has become particularly relevant due to climatic changes in the Anapa-Taman zone of the Krasnodar krai, where water deficit and high temperatures during active berry growth impair both fruit quality and plantation productivity. The aim of this work was to assess the adaptation of grapevine cultivars of diverse ecological and geographical origins to water deficit and high temperatures using parameters of leaf water relations and photosynthetic pigment content. The findings are intended to support the selection of cultivars suitable for cultivation in the Anapa-Taman zone of the Krasnodar krai and to select genotypes that could be used in breeding programs as donors and sources of economically valuable traits. The plant material comprised crossings and interspecific hybrids of various ecological and geographical origins: Kristall (Hungary), Dostoinyi, Krasnostop AZOS, Vostorg (Russia), Aligote (France), and Zarif (Tajikistan). This research investigated the water regime and the content of photosynthetic pigments in leaves during the summer growing seasons of 2023-2025. It was found that the adaptive characteristics of the leaves enable all grapevine cultivars to maintain full physiological activity throughout the vegetative period. Leaf water content decreased in summer by 1.77-5.04% depending on the cultivar and the phenological phase. In the artificial turgor loss experiment, the Krasnostop AZOS and Aligote cultivars showed the lowest water loss – 10.34 % and 9.87 %, respectively. In the other studied cultivars, water loss ranged from 17.03 % to 19.62 %. Chlorophyll content increased by the end of summer by 11.30-25.06 %, depending on the cultivar. Furthermore, the proportion of carotenoids in the leaf pigment composition, which perform a stress-protective function, also increased. The Krasnostop AZOS and Aligote cultivars exhibited the minimum chlorophyll/carotenoid ratios – 2.23 and 2.28, respectively, in contrast to other cultivars where these ratios ranged from 3.03 to 3.47. Based on the physiological and biochemical data obtained, the Krasnostop AZOS and Aligote cultivars demonstrated the highest potential for heat and drought resistance. These cultivars are recommended as donor parents in breeding programs for the development of new cultivars.

Climate warming increases abiotic stress, which necessitates the identification of adaptive genotypes for high-yielding grapevine production. The research objects were wine grape varieties Kurchansky, Vladimir, and Dmitry, characterized by high adaptability to water deficit and elevated temperature conditions. Field experiments were conducted under extreme weather conditions during 2023–2024 across the main agroecological viticulture zones of Krasnodar Krai: Central Zone, Black Sea Zone, and Foothill Zone. During the study period, maximum air temperatures reached 40 °C. The sum of active temperatures exceeded long-term averages by 10–13%, while precipitation during the active growing season was 36–56% below normal. Grapevine adaptability was evaluated using leaf physiological parameters, including water content (WC), relative water content (RWC), and electrolyte leakage (EL). Yield performance was assessed by berry weight. Sugar concentration was determined by the areometric method, and titratable acidity was measured by direct titration with 0.1 N NaOH. Statistical analysis was conducted using STATISTICA 12.0. Based on the set of physiological indicators, the Kurchansky variety demonstrated the highest adaptability to the environmental conditions of the Central Zone. The Vladimir variety showed adaptability to the Central Zone primarily in terms of WC and EL, whereas the Dmitry variety exhibited adaptability in the Central Zone based on WC and RWC, and in the Foothill Zone based on RWC and EL. Despite its superior yield in the Central Zone, the Kurchansky variety exhibited lower fruit quality compared to other terroirs. This finding supports the hypothesis of an inverse relationship between leaf physiological parameters and crop quality in this variety. The genetic trait of the Vladimir variety, characterized by high sugar concentration, is more pronounced in the Central Zone terroir. Yields are higher in the Black Sea Zone terroir due to larger cluster size. The Dmitry variety has higher yields and lower quality indicators in the Central Zone, which is associated with the optimal physiological condition of the plants. In the Foothill Zone, the variety exhibits low yields but a high concentration of sugars and titratable acids suitable for the production of red dry wines, which is due to the agroecological characteristics of the terroir.

As a preliminary step in breeding, a comprehensive evaluation of columnar apple cultivars from the bioresource collection was conducted to identify superior genotypes as sources of economically valuable traits. The bioresource collection of Russian Research Institute of Fruit Crop Breeding includes 12 introduced columnar cultivars: Tuscan (England); Akademicheskaya, Victoria, Korall, Mikhailovskaya, Natalyushka (Rossosh); Prezident, KV-5, KV-43, Moskovskoe Ozherelie (Moscow); Geyser, Gotika (Michurinsk). In addition, the collection contains 8 cultivars bred at the Institute: Zvezda Efira, Girlyanda, Vostorg, Poetziya, Priokskoye, Orlovskaya Yeseniya, Sozvezdie, Pamyati Blynskogo. Over four years of cultivating domestic and foreign columnar cultivars on rootstock 54-118, the highest yield was recorded for Mikhailovskaya — 5.4 kg/tree (Rossoshansk Zonal Experimental Horticulture Station JSC), Prezident — 5.1 kg/tree, and form KV-43 — 4.5 kg/tree (Federal Scientific Center of Horticulture). Over the eight-year study period, the use of form 3-4-98 as a skeleton former ensured high yields for Mikhailovskaya (19.9 kg/tree), Victoria (13.0 kg/tree), and Natalyushka (14.6 kg/tree), which were bred at Rossoshanskaya Zonal Experimental Horticulture Station JSC. These cultivars surpassed Tuscan (9.8 kg/ tree), Gotika (7.5 kg/tree), and Geyser (8.0 kg/tree) in terms of yield. Regarding scab resistance, no symptoms of scab infection were observed throughout the entire study period under the conditions of the Oryol region in the following cultivars: Priokskoye, Zvezda Efira, Girlyanda, Vostorg, Poeziya (Russian Research Institute of Fruit Crop Breeding); Korall (Rossoshanskaya Zonal Experimental Horticulture Station JSC); and the forms KV-5 and KV-43 (Federal Scientific Center of Horticulture). The cultivation of Priokskoye and Girlyanda columnar apple trees on dwarf rootstocks P-60, M-9, and Malysh during the first six years of fruiting resulted in the highest yields on rootstock P-60 and the lowest yields on rootstock Malysh. The studied rootstocks exhibited no significant effect on average fruit weight. The findings of the cultivar evaluation suggest the following cultivars as sources of valuable traits: for high fruit taste quality — Victoria and Priokskoye; for high scab resistance — Zvezda Efira, Girlyanda, Vostorg, Poeziya, Priokskoye, Korall, and the forms KV-5 and KV-43; for high productivity — Victoria, Mikhailovskaya, and Prezident.

This article presents a smart system for automated sorting of apple fruits based on YOLO convolutional neural network architectures. A software package that integrates detection, instance segmentation, object tracking, and real-time fruit quality analysis has been developed. The system, implemented in Python using OpenCV, PyQt5, NumPy, and other libraries, supports video stream processing from industrial conveyor lines. A comparative study of the YOLO12s (for detection) and YOLO11m-seg (for segmentation) models was conducted using such key metrics as Precision, Recall, mAP, F1-score, MOTA, IDF1, and FPS. The analysis of experimental data established the following optimal operating modes: for YOLO12s, conveyor speed up to 0.18 m/s at MOTA > 0.75 and FPS ≈ 38 frames/s; for YOLO11m-seg, conveyor speed up to 0.15 m/s at MOTA > 0.65 and FPS ≈ 25 frames/s. The software package recognizes eight classes of objects, including rot, scab, and mechanical damage. The system allows the degree of ripeness to be assessed using HSV histograms and fruit sizes to be measured. Tracking is performed using the ByteTrack algorithm, which ensures preservation of object identifiers during movement, thus minimizing erroneous ID reassignment in conditions of partial overlap and high conveyor speeds. The system software is a ready-made solution for the digitalization of the sorting process. By ensuring real-time operation, automatic defect recognition, and statistical data collection, the software increases production efficiency and labor productivity compared to conventional visual inspection methods.