Quercus castaneifolia C.A. Mey. is an ecologically important oak species in the Hyrcanian forests of Iran, yet comprehensive studies integrating large-scale morphological datasets with multivariate analyses remain limited. The present study aimed to evaluate the phenotypic diversity of 51 Q. castaneifolia accessions collected from three natural populations in Golestan and Semnan provinces of Iran, and to identify the most informative traits for characterization and selection. A total of 52 morphological and pomological traits related to tree growth, leaf, nut, cupule, and kernel characteristics were assessed. One-way ANOVA, Pearson correlation analysis, hierarchical cluster analysis (HCA), and multiple regression analysis (MRA) were applied to elucidate trait variability and interrelationships. The results revealed substantial phenotypic diversity among the studied accessions, with 75% of the evaluated traits exhibiting coefficients of variation above 20%, indicating high discriminatory capacity. Reproductive traits, particularly nut and kernel dimensions and weights, were identified as the most informative and biologically meaningful descriptors. Strong and highly significant positive correlations were observed among nut size, nut weight, kernel size, and kernel weight, whereas the nut cover/kernel ratio exhibited negative associations with most size-related traits. Overall, the combined statistical analyses demonstrated clear patterns of phenotypic differentiation among accessions, and identified the key morphological traits contributing to the observed variability. HCA confirmed a structured yet heterogeneous phenotypic pattern among accessions. Overall, the integration of multivariate approaches demonstrated that fruit- and kernel-related traits are the most useful criteria for germplasm characterization, indirect selection, and future breeding programs in Q. castaneifolia. Based on a comprehensive assessment combining multivariate analyses and trait performance, ‘Olang-5’, ‘Olang-11’, ‘Tooskestan-1’, ‘Tooskestan-15’, and ‘Tooskestan-10’ emerged as the most promising accessions.

Pomegranate aril paleness (AP), a physiological disorder linked to climate change, causes pale, desiccated arils in otherwise healthy fruits, reducing marketability. To investigate the anatomical and physiological underpinnings of AP, this study examined four pomegranate cultivars exhibiting varying degrees of susceptibility: the resistant cultivar ‘Damavand’ (DN), the moderately affected cultivars ‘Kashmar’ (KN and KW), and the severely affected cultivar ‘Torud’ (TW). Seed viability and germinative capacity were assessed using tetrazolium staining and germination tests, while structural abnormalities in the seed coat were evaluated through histological analysis and scanning electron microscopy (SEM). The results revealed a strong association between AP severity and reduced germination rates, with germination rates ranging from 45% in the resistant cultivar ‘DN’ to just 4% in the severely affected cultivar ‘TW’. Interestingly, tetrazolium tests indicated that a large proportion of embryos remained viable despite severe AP symptoms, ranging from 67% in ‘TW’ to 98% in ‘DN’. Microscopic analyses further demonstrated substantial structural degradation in the seed coats of AP-affected cultivars, including blackened regions, tissue separation, and reduced cellular density in the inner seed coat layers. Taken together, the findings highlight that AP is associated with specific anatomical abnormalities in the seed coat and tegmen, which may underlie or exacerbate the physiological manifestations of the disorder.

This study assessed morphological and genetic diversity in twelve Berberis F-2 populations. Seeds were collected from selected F-1 hybrids resulting from crosses between Berberis integerrima, B. crataegina, and 'Zereshk Bidaneh'-a commercial seedless barberry cultivar. Initial evaluations compared seed germination and seedling survival on three substrates: perlite, cocopeat, and peat moss. Germination rates varied widely among F-2 populations, ranging from 17% to 95.48%. A 1:1 mixture of cocopeat and perlite significantly enhanced germination. Twelve morphological and vegetative traits were subsequently measured, revealing substantial phenotypic variability across F-2 populations. Correlation analyses identified strong positive associations among key traits such as leaf number, plant height, and leaf morphology characters. Factorial analysis indicated that the first two factors explained 35.5% of the total variance, primarily differentiating populations based on leaf pigmentation and leaf-spine architecture. Heatmap clustering grouped the F-2 genotypes into six distinct phenotypic clusters. Notably, traits such as leaf margin spine (CV = 33.89%) and leaf pigmentation (CV > 43%) exhibited high coefficients of variation, suggesting the potential for transgressive segregation and providing a wide basis for selection. These findings establish a robust framework for early-stage selection in barberry improvement programs.

Aril paleness (AP) is a new physiological disorder of pomegranate (Punica granatum L.) characterized by pale, dry and tasteless arils, while the peel remains healthy-looking. Its molecular basis is unknown. We used an integrated metabolomic and targeted gene expression approach on arils from four Iranian cultivars displaying no to severe AP symptoms. LC-MS profiling detected 617 reliable metabolites, with 266 metabolites consistently reduced in all symptomatic samples. Enrichment analysis revealed that arginine biosynthesis, glutathione metabolism and primary amino acid metabolism were the processes most strongly affected by AP. Protein interaction network analysis indicated that the arginine degradation pathway is the primary down-regulated module that interacts with the anthocyanin biosynthetic machinery, primarily through phenylalanine ammonia-lyase (PAL) hubs. Based on this network, seven genes representing both pathways were selected for targeted expression analysis. The qPCR analysis showed strong repression of arginase (PgADS, XM-031537872), aldehyde dehydrogenase (PgAL12A1, XM-031551051) and anthocyanin synthase (PgOXKF, KF841619.1) in the cultivar ‘Torud’ exhibiting severe AP symptoms compared with the symptom-free cultivar ‘Damavand’. In contrast, phenylalanine ammonia-lyase (PgPAL1, KY094504.2) was unexpectedly induced 33-fold in the cultivar ‘Torud’, while the downstream anthocyanin-related UDP-glucosyltransferase (PgUGT, MK058491.1) remained unchanged. These findings suggest that the collapse of arginine metabolism, combined with the downstream blockage of anthocyanin biosynthesis, underlies AP. These findings provide the first molecular insights into the mechanisms underlying AP, offering a basis for breeding and post-harvest strategies aimed at enhancing pomegranate’s AP tolerance.

This study investigated the effectiveness of various artificial pollination treatments, including pollen suspensions enriched with plant growth regulators (PGRs), on the yield and quality of ‘Sefied’ and ‘Shah-Pasand’ pistachio cultivars. A field experiment evaluated the effects of various treatments on fruit set, nut size (number and kernel dimensions), and kernel quality (kernel percentage, blank, and nonsplit nuts). The results demonstrated that PGR-enriched pollen applications significantly increased all parameters measured. Notably, the combined use of 0.01

In the South Khorasan province of Iran, the seedless barberry variety 'Zereshk Bidaneh' is cultivated extensively and is noted for its exceptional resilience to adverse climatic conditions. As part of a breeding program to develop new barberry cultivars, 90 F1 hybrid progenies were produced from crosses between 'Zereshk Bidaneh' and selected wild genotypes. This study investigates the biochemical and phenological diversity within this F1 population. Phenological assessments revealed a broad range in flowering time among genotypes, with statistically significant differences (p < 0.05). The earliest flowering was observed on April 15 in genotype '0506', while the latest occurred on May 5 in '0202', resulting in a 40-day interval. Biochemical evaluations indicated substantial and significant variability (p < 0.05) in total anthocyanin content (TAC), with values spanning from 133.37 mg/L ('0203') to 2063.55 mg/L ('0601'). The average TAC was 614.44 mg/L, and the high coefficient of variation (67%) emphasized the extent of diversity. Notably, four genotypes ('0601', '0606', '0607', and '0617') exhibited TAC levels above 1250 mg/L. Vitamin C concentrations also showed significant differences (p < 0.05), averaging 108.50 mg/100 mL, with several genotypes exceeding 130 mg/100 mL. Total antioxidant activity (TAA) ranged markedly from 7.89 to 90%, while total phenolic content (TPC) had a mean of 1770 mg GAE/100 mL (p < 0.05), underscoring the presence of bioactive compound-rich genotypes. Total soluble solids (TSS) varied between 14 and 38 °Brix, with a mean of 29.27 °Brix (p < 0.05). Measured pH values ranged from 2.66 to 3.76. The fruit flavor index (FI) also varied widely, ranging from 0.98 to 7.68 (p < 0.05). Principal component analysis (PCA) revealed that the first two principal components accounted for 50.04% of the total variance, with TAC, TAA, titratable acidity (TA), and FI identified as the most influential variables. Heat map analysis further classified the genotypes into seven distinct biochemical clusters, reinforcing the diversity patterns observed. The results reveal extensive phenotypic and biochemical diversity among the F1 barberry progenies, with several traits showing statistically significant variation (p < 0.05). These findings provide a valuable foundation for selecting superior genotypes and advancing breeding programs aimed at developing improved barberry cultivars with enhanced nutritional and horticultural qualities. Among the evaluated progenies, genotypes such as '0601' and '0203' stood out due to their exceptionally high total anthocyanin content (2063.55 mg/L) and antioxidant activity (90%), respectively, highlighting their potential value in future breeding strategies.

Identifying olive cultivars and maturity stages is crucial in the olive industry, as these traits significantly impact the nutritional and sensory properties of olive products and extracted oil. For this purpose, this study presents a novel automatic computer vision system that applies state-of-the-art deep learning technology to sort and classify two Iranian olive cultivars, Zard and Roghani, in five maturity stages, resulting in a total of ten distinct classes. The model was developed by evaluating multiple user-defined and standard structures. It was based on a dualpath lightweight convolutional neural network that uses both regular and dilated convolution operators. Dilated convolutions were used to extract more information and capture different properties by providing larger receptive fields. With a significantly lower number of trainable parameters than standard architectures, the lightweight nature of the model would enhance its potential for delivering fast responses in on-the-go applications. Four optimizers (RMSProp, SGD, Adam, and Nadam) were tested on the developed model to enhance its performance, and Nadam exhibited the greatest accuracy. The proposed model achieved a total classification accuracy of 95.79 % and a loss of 0.2214. The proposed model was completely accurate for some classes, and the classification metrics for all categories were high, ranging from 88 % to 100 % for precision, 83-100 % for recall, and 86-100 % for F1-score. The accuracy of classification within the Roghani cultivar classes stood at 98.28 %, while for the Zard cultivar classes, it achieved 97.76 %. The study found that the proposed model can be efficiently incorporated into an olive sorting system, facilitating the identification of olives with different cultivars and varying levels of maturity, thereby enhancing the production of post-harvest products and superior quality of oil.

Salicylic acid (SA) and melatonin (MT) are recognized as growth regulators and antioxidants in fruits and vegetables. This study examined the impact of foliar SA (0, 1.5, and 2.5 mM) and MT (0 μM as control, 100 μM foliar application, and 100 μM irrigation) on Botrytis cinerea in bell pepper (Capsicum annuum Cv. California Wonder). Treatments were administered pre-fungal infection (2-leaf stage), with one pre-flowering and two post fruit-set applications. Inoculation occurred at flowering, 3 days post-flowering, and 6 days post-flowering. Both SA and MT significantly affected plant growth, leaf and fruit drop, and enzymatic activities in Botrytis-infected plants. 100 μM MT foliar application increased chlorophyll b content, while 100 μM MT irrigation raised phenylalanine ammonia-lyase (PAL) enzyme activity compared to control. SA elevated H2O2 levels, PAL and polyphenol oxidase enzyme activities, total dry matter, plant weight, fruit firmness, and plant height in infected pepper plants compared to control. The 1.5 mM SA concentration notably enhanced plant height, fruit firmness, weight, PAL, and superoxide dismutase enzyme activities. This study underscores the potent synergy of SA and MT in bolstering bell pepper resilience against B. cinerea.

The Nishabur region in Iran is an ancient hub for plum production, home to numerous seedling orchards and indigenous plum varieties. In 2020, an evaluation was conducted in the primary plum-growing zones of Nishabur following a harsh spring frost. Forty-one plum genotypes and local varieties capable of bearing fruit after frost incidents were selected for further examination. These plum selections were evaluated based on 60 morphological, pomological, and phenological traits related to flowers, fruits, and trees, in accordance with the UPOV (2020) plum descriptor. Among the 41 genotypes evaluated, 35 exhibited high yields, demonstrating their potential as viable options for cultivation in frost-prone areas. The highest coefficient of variation (39.45

Climate changes over the past decade have caused significant problems for pistachio growers, particularly in the desert regions of Iran where water resources are becoming limited. In response, pistachio orchards are being established in marginal areas with lower temperatures, which can affect plant growth and nutrient uptake. This study aimed to evaluate the absorption of major nutrient elements in three Iranian pistachio rootstocks (‘Badami Zarand’, ‘Ghazvini’, and ‘Sarakhsi’) at different soil temperatures. The plants were grown in a growth chamber at temperatures of 10, 15, 20, and 25 °C for 15 days, and nutrient concentration and total nutrient content of nitrogen (N), phosphorus (P), potassium (K), magnesium (Mg), calcium (Ca), and sodium (Na) were measured in leaf, stem, and root tissues. The results showed that ‘Badami Zarand’ had a higher absorption of P at 10 and 15 °C compared to ‘Ghazvini’ and ‘Sarakhsi’, and leaf N in ‘Badami Zarand’ and ‘Ghazvini’ was also higher than ‘Sarakhsi’ ( P < 0.01). Leaf K showed a significant decrease in ‘Badami Zarand’ and ‘Sarakhsi’ with increasing temperature, and N decreased from 10 to 25 °C ( P < 0.01). Additionally, ‘Badami Zarand’ had higher nutrient uptake at lower temperatures and could be recommended as a more suitable rootstock for marginal areas with lower temperatures. These findings highlight the importance of considering soil temperature when selecting a suitable rootstock for pistachio cultivation.

Olive fruits at different ripening stages give rise to various table olive products and oil qualities. Therefore, developing an efficient method for recognizing and sorting olive fruits based on their ripening stages can greatly facilitate post-harvest processing. This study introduces an automatic computer vision system that utilizes deep learning technology to classify the ‘Roghani’ Iranian olive cultivar into five ripening stages using color images. The developed model employs convolutional neural networks (CNN) and transfer learning based on the Xception architecture and ImageNet weights as the base network. The model was modified by adding some well-known CNN layers to the last layer. To minimize overfitting and enhance model generality, data augmentation techniques were employed. By considering different optimizers and two image sizes, four final candidate models were generated. These models were then compared in terms of loss and accuracy on the test dataset, classification performance (classification report and confusion matrix), and generality. All four candidates exhibited high accuracies ranging from 86.93% to 93.46% and comparable classification performance. In all models, at least one class was recognized with 100% accuracy. However, by taking into account the risk of overfitting in addition to the network stability, two models were discarded. Finally, a model with an image size of 224 × 224 and an SGD optimizer, which had a loss of 1.23 and an accuracy of 86.93%, was selected as the preferred option. The results of this study offer robust tools for automatic olive sorting systems, simplifying the differentiation of olives at various ripening levels for different post-harvest products.

Interspecific hybrid rootstocks have the potential to improve the productivity and resilience of pistachio orchards in response to environmental stresses. This study aimed to produce inter-specific hybrids between P. vera and P. integerrima (In) and compare their early growth with their parents under chilling temperatures. Controlled pollination using In pollen was conducted on five pistachio cultivars including 'Kaleh-Ghuchi', 'Khanjari-Ghermze', 'Akbari', 'Khanjari-Sefid', 'Ohadi' and a local variety. The fruit set in female parents through controlled pollination of interspecific crossings was significantly lower than natural open pollination, resulting in a high percentage of blank seeds. Only 'Khenjari-Ghermze' and 'Kalleh-Ghoochi' produced a sufficient number of seeds for further experiment. The germination and survival rate of hybrid seeds were lower than that of pistachio cultivars (P<0.01). Growth parameters of hybrid seedlings and their parents were examined at 5°C and 25°C. All rootstocks showed a significant reduction in growth at low temperatures, with chlorophyll and chlorophyll fluorescence also decreasing significantly at 5°C. Overall, In seedlings showed more growth at 25°C than other rootstocks, and inter-specific hybrids showed better growth characteristics than seedlings obtained from pistachio cultivars. In seedlings growth almost stopped at 5°C, but pistachio seedlings continued growing despite the low temperature. In most traits, hybrid cultivars were intermediate between their parents, indicating the suitable inheritance of growth characteristics from In and cold resistance from P. vera. The hybrid between 'Khanjari-Ghermze' ×In showed good growth in the early growing stages under chilling temperature and could be a suitable rootstock for further research on interspecific hybrid.

Selecting winter-hardy cultivars is an effective way to avoid freezing damage in olive trees. In this study, we evaluated the cold hardiness of 10 olive cultivars in the field after a natural freezing event (-12 degrees C in December 2016, Sorkhe, Semnan, Iran) and treatment with controlled freezing temperatures ranging from 0 degrees C to -21 degrees C. The 50% lethal temperature (LT50) based on electrolyte leakage (LT50-EL) and tetrazolium tests (LT50-TZ) before, during, and after dormancy were determined in each cultivar's shoots. The proline and soluble carbohydrate content of leaves and shoots also were measured during dormancy. The LT50-EL had a mean of -9.5 degrees C and ranged from -16.5 degrees C to -4.8 degrees C. The LT50-TZ had a mean of -10.2 degrees C and ranged from -16.3 degrees C to -6.4 degrees C. We classified the olive cultivars into five groups based on their lab-freezing evaluations using cluster analysis. 'Manzanilla', 'Mission', and 'Rashid' were very sensitive to freezing, while 'Roughani' and 'Zrad' were the hardiest cultivars. In Field evaluation, the recovery ability and yield of each cultivar were evaluated six years after freezing damage. Visual scoring indicated that 'Roghani' and 'Zard' had the least amount of trunk damage. However, 'Zard' showed low regrowth power in the field after freezing damage despite its high freezing tolerance in lab and field experiments. 'Roughani' had the maximum fruit yield among the 10 olive cultivars six years after freezing damage (P < 0.01). Our finding indicates that laboratory techniques be combined with field assessments to more accurately evaluate the cold hardiness of olive trees.

Barberries are versatile shrubs with diverse applications, including ornamental, medicinal, and edible purposes. In this study, we employed molecular markers to assess the genetic diversity and genetic base of superior barberry genotypes selected from an F1 population obtained through Shahrood University Barberry Breeding Program (SUBBP), alongside their parents. We utilized nine ISSR markers and 10 RAPD markers to analyze the population's genetic diversity. From these markers, we obtained 98 polymorphic bands using ISSR markers and 112 polymorphic bands using RAPD markers. The average PIC value was 0.16 for ISSR markers and RAPD markers, while the average genetic resolution power was 3.93 for ISSR markers and 2.11 for RAPD markers. Furthermore, we calculated the genetic dissimilarity coefficient (GDC) based on ISSR and RAPD markers, which ranged from 0.23 to 0.86 (average 0.62) and 0.21 to 0.85 (average 0.60), respectively. The ISSR data analysis classified the genotypes into three main clusters, with genotypes 0515, R5N1, 'Bth', 'Seedless (BD)', and R2N1 being genetically distant from the others. Similarly, the analysis of 10 RAPD primers resulted in the classification of genotypes into three main groups. Notably, genotype 0609 exhibited greater genetic distance from other genotypes in this subgroup. The Principal Coordinates Analysis (PCoA) using both ISSR and RAPD marker data further supported the grouping of genotypes into three distinct clusters. These results provide valuable insights into the genetic composition of the F1 population and contribute to the advancement of barberry breeding strategies.

Wild pomegranate is a valuable edible species in the plant ecosystem of the Hyrcanian forests and the northern plains of the Caspian coast in Iran. The genetic diversity of these wild pomegranates can be effective in pomegranate breeding programs and germplasm conservation. In the present study, morphological diversity in 103 wild pomegranates (Punica granatum L. var. spinosa) in the northeastern area of Iran was studied using 46 traits related to trees, flowers, and fruits. The results showed that the fruit weight ranged from 17.93 to 99.9 g with an average of 48.92 g, the total aril weight ranged from 0.54 g to 64.78 g with an average of 24.25 g, and the weight of 100 arils was between 4.89 and 46.21 with an average of 13.79. The fruit cracking percent, crown shape, aril juiciness, calyx, and corolla colors show a high coefficient of variation (CV > 70%). Based on PCA results, fruit weight and total aril weight, peel weight, and fruit length and diameter were important on determining differences among accessions. In biplot analysis, genotype distribution was determined by two main factors. In cluster analysis, the studied accessions were divided into two different major clusters and two subclusters in each one. The results showed a high diversity of important pomological traits in wild pomegranates such as fruit weight, fruit cracking percent, crown shape, total aril weight, aril juiciness corolla, and calyx color that can be used in breeding programs to improve pomegranate juice quality and marketability.

The taxonomy of Iranian wild barberry and the unique seedless cultivar (CV) ‘Zereshk Bidaneh’ based on morphological characteristics is debated. The nuclear internal transcribed spacer (ITS) regions have high accuracy and efficiency for plant species identification and DNA barcoding. In this study, 17 wild barberry genotypes from northern and northeastern regions of Iran, along with CV ‘Zereshk Bidaneh’ and Japonica barberry, were classified by ITS 2 sequence analysis. Genetic distance and phylogenetic relationships among Berberis genotypes were assessed with MEGA X and the NCBI database. The results showed that the genetic distance between the studied barberry accessions varied from 0.012 to 0.154. Cluster analysis classified Iranian barberry genotypes into six groups, and the ‘JA’, ES4 and R9N3 genotypes were placed in a separate clade. In BLAST analysis, 93 DNA sequences from different barberry species in the NCBI database had over 90% identity with ITS sequences of the studied barberries. Seventeen of the studied Berberis genotypes were classified into two groups in an NCBI similarity dendrogram. The first group included 11 genotypes that were placed in the B. crataegina clade, and six genotypes of the second group along with the other NCBI Berberis genotypes belong to B. integerrima . The R9N3 genotype was separated from other studied barberry genotypes and inserted alongside the Berberis species, which are all unlisted species in Iran. ‘Zereshk Bidaneh’ was in the B. integerrima clade. ITS 2 sequence analysis can be used for true species identification based on DNA databases.

Winter frost injury is a major limiting factor for olive cultivation in temperate regions. The response of olive shoots to freezing stress can be used for selecting genotypes resistant to freezing. The electrolyte leakage (EL) and tetrazolium tests (TZ) are commonly used to evaluate dead tissues in cold stress studies. The temperature–response curve of dead tissues to lethal temperature (LT) is measured with models to calculate LT50 and LT90. In this study, we evaluated the accuracy and efficiency of eighteen nonlinear regression models (NLRs) in calculating LT50 and LT90 of freezing stress in different olive cultivars at various stages of dormancy. After evaluating the prediction performance of NLR models, it was found that only eight models were suitable for the purpose of this research out of the eighteen models examined. The 2p-logistic and Gompertz models were selected for modeling EL and TZ, respectively. Our research findings indicate that the Roughani, Kawi, and Zard varieties of olive trees exhibit the best performance under artificial temperature-controlled conditions. Our findings provide valuable insights into selecting frost-resistant cultivars and designing effective strategies for cold acclimation in olive cultivation.

Sweet Cayenne pepper is a nutrient-dense, sweet-tasting greenhouse vegetable that often faces water stress in dry areas, and optimizing growth with minimum water consumption is crucial. In this study, we investigated the impacts of amino acids (AAs) foliar application on reducing water stress losses in sweet Cayenne pepper cv. "Lombard" under greenhouse conditions. The pepper bushes were irrigated in 3-day and 6-day intervals and simultaneously sprayed with an AA fertilizer (0, 150, and 300 mg/L). Vegetative growth, reproductive traits, and yield parameters were measured. Results showed significant decreases in the plant height, the roots length, SPAD, leaf greenness index, and the pepper leaves turn yellow under brief drought stress. The number of flowers was reduced by up to 50%, and the 3-month yield decreased significantly from 7 to 5.05 kg/m(2). However, with AAs foliar application, vegetative growth, fruit number, and yield increased significantly. The highest yield, 2.93 kg/plant, was observed in 300 mg/L AAs, while the minimum yield, with an average of 1.83 kg/plant recorded under water stress treatment without AAs application. The spray of AAs fertilizer remarkably improves the yield and quality of pepper fruit and reverses the destructive effects of low irrigation. The future direction could focus on the mechanism of the positive impact of AA foliar application on growth, yield, and quality of the fruit, particularly in water stress conditions, to further optimize growth and minimize water consumption.

Fruit growth patterns are often exploited in predictions of final fruit size and to inform planting and harvesting decisions. Ten local apricot (Prunus armeniaca) varieties with superior genotypes (two early-ripening, five mid-ripening and three late-ripening varieties) were assessed using 20 nonlinear regression models (NRMs) and a radial basis function (RBF) neural network model. Fruit diameter and weight measurements for each genotype were collected at four-day intervals from fruit set to commercial harvest. Patterns based on diameter and weights were attributed to each genotype. Among the NRM tested, only four were able to flawlessly predict apricot diameter and weight during the growing season. In addition, comparison of nonlinear regression methods with the neural network indicated than the RBF model displayed fewer prediction errors than the NRMs. The RBF model predicted fruit size with a coefficient of determination (R2 value) greater than 0.95. Therefore, predictions of growth patterns in fruit trees can be accomplished with neural network modeling.