Search Results (127)

This study presents a robust and extensible hybrid classification framework for accurately detecting diseases in citrus leaves by integrating transfer learning-based deep learning models with classical machine learning techniques. Features were extracted using advanced pretrained architectures—DenseNet201, ResNet50, MobileNetV2, and EfficientNet-B0—and refined via the minimum redundancy maximum relevance (mRMR) method to reduce redundancy while maximizing discriminative power. These features were classified using support vector machines (SVMs), ensemble bagged trees, k-nearest neighbors (kNNs), and neural networks under stratified 10-fold cross-validation. On the lemon dataset, the best configuration (DenseNet201 + SVM) achieved 94.1 ± 4.9% accuracy, 93.2 ± 5.7% F1 score, and a balanced accuracy of 93.4 ± 6.0%, demonstrating strong and stable performance. To assess external generalization, the same pipeline was applied to mango and pomegranate leaves, achieving 100.0 ± 0.0% and 98.7 ± 1.5% accuracy, respectively—confirming the model’s robustness across citrus and non-citrus domains. Beyond accuracy, lightweight models such as EfficientNet-B0 and MobileNetV2 provided significantly higher throughput and lower latency, underscoring their suitability for real-time agricultural applications. These findings highlight the importance of combining deep representations with efficient classical classifiers for precision agriculture, offering both high diagnostic accuracy and practical deployability in field conditions. Full article

The quality of mangoes is a crucial factor in both domestic and commercial markets that directly influences consumer satisfaction and economic value. Traditional methods of checking mango quality often involve destructive techniques, which lead to the loss of the fruit in the testing process. This study presents an advanced approach that could predict the quality of mangoes using advance non-destructive methods leveraging machine learning algorithms to predict quality parameters such as ripeness, sweetness and overall freshness without damaging the fruit. In this research, a dataset consisting of various mango samples was collected, with attributes including color, texture, size, weight and acidity levels. Sensors, such as pH sensors (for acidity) and e-nose sensors (for aroma and sweetness detection), were used to gather data, while a combination of machine learning models such as Decision Tree, K-Nearest Neighbors (KNN), and Automated Machine Learning (AutoMLP), Naive Bayes were applied to predict the mangoes’ quality. The accuracy of each model was measured based on its ability to classify mangoes as fresh, ripe, or rotten. The results determine that the AutoMLP model performs the best out of the traditional models, achieving an accuracy of 98.46%, making it the most suitable model for mango quality prediction. The research explains the significance of feature extraction methods, model optimization, and sensor data pretreatment in reaching a high prediction accuracy. Full article

This research investigates the adsorption potential of mango and pitanga tree pruning waste biochar produced at 300 °C and 500 °C for the uptake of Methylene Blue (MB) dye. The particle size of biochar, initial MB concentration, adsorbent mass and pH of the solution were varied. Equilibrium data were modeled using Langmuir, Freundlich and Temkin equations. Increasing the temperature of the treatment resulted in a slight increase in the efficiency and adsorption capacity of the material. Finer particles (<0.25 mm) and pH (>6) were more efficient in adsorbing MB. Both materials presented similar modeled parameters for Langmuir, Freundlich and Temkin isotherm equations. The adsorption at equilibrium of MB is best described by Langmuir and Freundlich models, and the modeled maximum adsorption capacity values are 20.53 ± 5.47 mg g⁻¹ for BTP-300 and 23.40 ± 6.41 mg g⁻¹ for BTP-500, proving the biochar’s efficiency in the adsorption of MB and that the temperature of the thermochemical process did not affect q_m. Full article

Mango (Mangifera indica L.) is cultivated in tropical and subtropical regions, with all parts of the tree—including leaves—used traditionally to treat diabetes, infections, pain, and other conditions. Mango leaves contain proteins, minerals, vitamins, and phenolic compounds, including mangiferin, quercetin, and kaempferol, whose content varies by cultivar. This study evaluated the functional and bioactive properties of dried mango leaves from five cultivars (Julie, DLO, Nam Dok Mai, Irwin, and Keïtt) to determine their potential for food and nutraceutical applications. Analyses included water- and oil-related parameters, swelling and solubility indices, foaming and emulsifying properties, and antioxidant activity (DPPH, ABTS, and FRAP in hydroalcoholic and water extracts), complemented by FT-IR/ATR spectroscopy. Significant differences between the five analyzed cultivars were observed. Irwin exhibited the highest antioxidant activity (2.65 ± 0.55 mg TE/g DM in DPPH assay), while Nam Dok Mai demonstrated superior foaming capacity (82.69 ± 7.79 mL). Strong correlations (r > 0.9) between reducing sugars and antioxidant capacity suggest cultivar selection based on sugar content could predict antioxidant potential. FT-IR confirmed the presence of polar phenolic and protein compounds. The results demonstrate that mango leaves offer cultivar-dependent functional and antioxidant attributes relevant to food systems. Their targeted valorization may support sustainable industrial applications and circular bioeconomy strategies, particularly in tropical regions where mango cultivation is widespread. Full article

The accurate estimation of evapotranspiration ($ET$) and its components are vital for water resource management and irrigation planning. This study models tree transpiration ($T$) and $ET$ for grapefruit, litchi, and mango orchards using light gradient-boosting machine (LightGBM) optimized using the Bayesian hyperparameter optimization. Grounds $T$ and $ET$ for these crops were measured using the heat ratio method of monitoring sap flow and the eddy covariance technique for quantifying $ET$. The Sentinel 2 satellite was used to compute field leaf area index ($LAI$). The modelled data were used to partition the orchard $ET$ into beneficial ($T$) and non-beneficial water uses (orchard floor evaporation—$E_s$). We adopted the 10-fold cross-validation to test the model robustness and an independent validation to test performance on unseen data. The 10-fold cross-validation and independent validation on $ET$ and $T$ models produced high accuracy with coefficient of determination ($R^2$) $\ge$ 0.88, Kling–Gupta efficiency ($KGE$) $\ge$ 0.91, root mean square error ($RMSE$) $\le$ 0.04 mm/h, and mean absolute error ($MAE$) $\le$ 0.03 mm/h for all the crops. The study demonstrates that LightGBM can accurately model the transpiration and evapotranspiration for subtropical tree crops using Sentinel 2 data. The study found that $E_s$ which combined soil evaporation and understorey vegetation transpiration contributed 35, 32, and 31% to the grapefruit, litchi and mango orchard evapotranspiration, respectively. We conclude that improvements on orchard floor management practices can be utilized to minimize non-beneficial water losses while promoting the productive water use ($T$). Full article

A method based on Vis-NIR spectroscopy and machine learning-based modeling for non-destructive detection of the internal disorders of black flesh, spongy tissue, jelly seed, and soft nose in mango fruit was developed using the vis-NIR spectra of intact mango fruit of three cultivars sourced from three orchards in each of the two seasons, with spectra collected both at harvest and after storage. After spectra were acquired of the stored fruit, the fruit cheeks were cut longitudinally to allow visual assessment of the incidence of the internal disorders. Five models were evaluated: two tree-based algorithms (J48 and random forest), one neural network (multilayer perceptron, MLP), and two SVM training algorithms (sequential minimal optimization, SMO, and LibSVM). The models were evaluated using a tenfold cross-validation approach. Non-destructive discrimination of health from all disordered and healthy fruit from fruit with specific disorders was achieved with an accuracy ranging from 72.3 to 97.0% when using spectra collected at harvest and 63.7 to 96.2% when using spectra collected after ripening. No one machine learning algorithm out-performed other methods—for spectra collected at harvest, the highest discrimination accuracy was achieved with RF and MLP for black flesh, J48 for spongy tissue, and LibSVM for soft nose and jelly seed. For spectra collected of stored fruit, the highest discrimination accuracy was achieved with SMO for jelly seed and RF for soft nose. A recommendation is made for the consideration of ensemble models in future. The ability to predict the development of the disorder using spectra of at-harvest fruit offers the potential to guide postharvest practices and reduce incidence of internal disorders in mangoes. Full article

The SWEET gene family is a group of genes with important functions in plants that is mainly involved in the transport and metabolism of carbohydrate substances. In this study, 32 mango (Mangifera indica L.) SWEET genes were screened and identified at the whole-genome level through bioinformatics methods. A systematic predictive analysis was conducted on their physicochemical properties, homology relationships, phylogenetic relationships, chromosomal locations, genomic structures, promoter cis-acting elements, and transcription factor regulatory networks. Meanwhile, the transcription levels of mango SWEET genes in different varieties and at different fruit development stages were also analyzed to obtain information about their functions. These results showed that 32 mango SWEET genes were unevenly distributed on 12 chromosomes. Phylogenetic analysis divided the SWEET proteins of mango, Arabidopsis thaliana (L.) Heynh., and Oryza sativa L. into four clades; in each clade, the mango SWEET proteins were more closely related to those of Arabidopsis. Four types of cis-acting elements were also found in the promoter regions of mango SWEET genes, including light-responsive elements, development-related elements, plant hormone-responsive elements, and stress-responsive elements. Interestingly, we found that the Misweet3 and Misweet10 genes showed strong expression in different mango varieties and at different fruit development stages, and they both belonged to the fourth Clade IV (G4) in the phylogenetic tree, indicating that they play a key role in the sugar accumulation process of mango. In this study, the upstream transcription factors of Misweet3, Misweet8, Misweet9, Misweet10, Misweet17, Misweet18, Misweet19, Misweet21, Misweet23, Misweet25, Misweet27, and Misweet31, those that had high expression levels in the transcriptome data, were predicted, and transcription factors such as ERF, NAC, WRKY, MYB, and C₂H₂ were screened. The results of this study provide a new way to further study the regulation of mango SWEET family genes on sugar accumulation, highlight their potential role in fruit quality improvement, and lay an important foundation for further study of mango SWEET function and enhance mango competitiveness in fruit market. Full article

Thermal stress due to high temperatures has different negative effects on citizens as it generates a decrease in physical capacity and causes cardiovascular and respiratory alterations, which is especially true for pedestrians. In this paper, using a drone, routes for pedestrians with the best thermal comfort were traced between the different headquarters of the Simón Bolívar University (Barranquilla, Colombia). Maps were created for three time intervals, from 10 a.m. to 1 p.m., from 1 to 2 p.m. and from 2 to 3 p.m., and variations in temperature and relative humidity of both natural and artificial shadow areas were identified. The routes with the best thermal comfort were those with natural shade that presented ca. 3 °C less than the unshaded areas. The predominant trees’ genera in most of the traced pedestrian routes were Arecaceae (palm), Tabebuia (purple oak), Mangifera (mango), and Delonix (red acacia). Some of them lose their leaves between March and June, which gives rise to an increase in the temperature along those routes. The developed cell phone application allows for the selection of walking environments with the best thermal comfort, favoring the mobility of the pedestrians along the considered area. Full article

During the flowering period of mango trees, pests often hide in the inflorescences to suck sap, affecting fruit formation. By accurately detecting the number and location of mango inflorescences in the early stages, it can help target-specific spraying equipment to perform precise pesticide application. This study focuses on mango panicles and addresses challenges such as high crop planting density, poor image quality, and complex backgrounds. A series of improvements were made to the YOLOv8 model to enhance performance for this type of detection task. Firstly, a mango panicle dataset was constructed by selecting, augmenting, and correcting samples based on actual agricultural conditions. Second, the backbone network of YOLOv8 was replaced with FasterNet. Although this led to a slight decrease in accuracy, it significantly improved inference speed and reduced model parameters, demonstrating that FasterNet effectively reduced computational complexity while optimizing accuracy. Further, the GAM (Global Attention Module) attention mechanism was introduced as an attention module in the backbone network to enhance feature extraction capabilities. Experimental results indicated that the addition of GAM improved the average precision by 2.2 percentage points, outperforming other attention mechanisms such as SE, CA, and CBAM. Finally, the model’s bounding box localization ability was enhanced by replacing the loss function with WIoU, which also accelerated model convergence and improved the mAP@.5 metric by 1.1 percentage points. Our approach demonstrates a discrepancy of less than 10% compared to manual counted results. Full article

Mango (Mangifera Indica L.), a key horticultural crop, particularly in Pakistan, has been primarily studied locally using low- to medium-resolution satellite imagery, usually focusing on a particular phenological stage. The large canopy size, complex tree structure, and unique phenology of mango trees further accentuate intrinsic challenges posed by low-spatiotemporal-resolution data. The absence of mango-specific vegetation indices compounds the problem of accurate health classification and yield estimation at the tree level. To overcome these issues, this study utilizes high-resolution multi-spectral UAV imagery collected from two mango orchards in Multan, Pakistan, throughout the annual phenological cycle. It introduces MangiSpectra, an integrated two-staged framework based on Long Short-Term Memory (LSTM) networks. In the first stage, nine conventional and three mango-specific vegetation indices derived from UAV imagery were processed through fine-tuned LSTM networks to classify the health of individual mango trees. In the second stage, associated data such as the trees’ age, variety, canopy volume, height, and weather data were combined with predicted health classes for yield estimation through a decision tree algorithm. Three mango-specific indices, namely the Mango Tree Yellowness Index (MTYI), Weighted Yellowness Index (WYI), and Normalized Automatic Flowering Detection Index (NAFDI), were developed to measure the degree of canopy covered by flowers to enhance the robustness of the framework. In addition, a Cumulative Health Index (CHI) derived from imagery analysis after every flight is also proposed for proactive orchard management. MangiSpectra outperformed the comparative benchmarks of AdaBoost and Random Forest in health classification by achieving 93% accuracy and AUC scores of 0.85, 0.96, and 0.92 for the healthy, moderate and weak classes, respectively. Yield estimation accuracy was reasonable with $R^2=0.21$, and $\mathrm{RMSE}=50.18$. Results underscore MangiSpectra’s potential as a scalable precision agriculture tool for sustainable mango orchard management, which can be improved further by fine-tuning algorithms using ground-based spectrometry, IoT-based orchard monitoring systems, computer vision-based counting of fruit on control trees, and smartphone-based data collection and insight dissemination applications. Full article

The development of unmanned aerial spraying systems (UASSs) has significantly transformed pest and disease control methods of crop plants. Precisely adjusting pesticide application rates based on the target conditions is an effective method to improve pesticide use efficiency. In orchard spraying, the structural characteristics of the canopy are crucial for guiding the pesticide application system to adjust spraying parameters. This study selected mango trees as the research sample and evaluated the differences between UAV aerial photography with a Structure from Motion (SfM) algorithm and airborne LiDAR in the results of extracting canopy parameters. The maximum canopy height, canopy projection area, and canopy volume parameters were extracted from the canopy height model of SfM (${CHM}_{SfM}$) and the canopy height model of LiDAR (${CHM}_{LiDAR}$) by grids with the same width as the planting rows (5.0 m) and 14 different heights (0.2 m, 0.3 m, 0.4 m, 0.5 m, 0.6 m, 0.8 m, 1.0 m, 2.0 m, 3.0 m, 4.0 m, 5.0 m, 6.0 m, 8.0 m, and 10.0 m), respectively. Linear regression equations were used to fit the canopy parameters obtained from different sensors. The correlation was evaluated using $R^2$ and $rRMSE$, and a t-test (α = 0.05) was employed to assess the significance of the differences. The results show that as the grid height increases, the $R^2$ values for the maximum canopy height, projection area, and canopy volume extracted from ${CHM}_{SfM}$ and ${CHM}_{LiDAR}$ increase, while the $rRMSE$ values decrease. When the grid height is 10.0 m, the $R^2$ for the maximum canopy height extracted from the two models is $92.85\%$, with an $rRMSE$ of $0.0563$. For the canopy projection area, the $R^2$ is 97.83%, with an $rRMSE$ of 0.01, and for the canopy volume, the $R^2$ is 98.35%, with an $rRMSE$ of 0.0337. When the grid height exceeds 1.0 m, the t-test results for the three parameters are all greater than 0.05, accepting the hypothesis that there is no significant difference in the canopy parameters obtained by the two sensors. Additionally, using the coordinates $x_0$ of the intersection of the linear regression equation and $y=x$ as a reference, ${CHM}_{SfM}$ tends to overestimate lower canopy maximum height and projection area, and underestimate higher canopy maximum height and projection area compared to ${CHM}_{LiDAR}$. This to some extent reflects that the surface of ${CHM}_{SfM}$ is smoother. This study demonstrates the effectiveness of extracting canopy parameters to guide UASS systems for variable-rate spraying based on UAV oblique photography combined with the SfM algorithm. Full article

The use of resistant plants is recognized as an environmentally friendly measure for mite control. Oligonychus mangiferus, known as the mango red spider mite (MRSM), is a dangerous pest for mango production. To date, the resistance levels of the mango germplasms against the MRSM remain largely unknown. Furthermore, the environmental factors potentially influencing resistance performance have been seldom discussed. To fill those knowledge gaps, this study aimed to identify the resistance level of twelve mango cultivars against the MRSM. Based on three rounds of greenhouse and five seasons of field tests, cultivars with distinct resistant levels were identified. When exploring the climate impact, we found that for the susceptible cultivars, precipitation is the primary external environment factor altering the resistance performance, while temperature presents a secondary effect, and air humidity did not show a significant impact on MRSM resistance. By contrast, MRSM-resistant cultivars were not prone to be affected by changing climate conditions. Furthermore, yield tests indicated that the resistant cultivars can better reduce the yield losses compared with the susceptible ones. This study illustrated the climate element-driven effect on mango tree resistance performance against the MRSM, which can provide insight into insect pest management under changing climate conditions. Full article

Nitrogen (N) is vital for mango yield and fruit quality, but finding the optimal amount is crucial to avoid the ‘stay green’ problem, which diminishes both fruit quality and profitability. This study aimed to assess the impact of N levels on the fruit quality and yield of ‘Kensington Pride’ (‘KP’) mangoes and determine the amount of N that triggers the ‘stay green’ effect in fruit. A field trial was conducted in a commercial orchard with N treatments (0, 12.5, 25, and 50 kg ha⁻¹) and four replications during the 2018 and 2019 cropping seasons. Fruit yield was quantified, and post-harvest quality (skin color during ripening, sugar content [°Brix], and texture) as well as ethylene effects were assessed. Fruit yields did not vary among N levels over the two cropping seasons but were significantly lower in 2018 (20.0 t ha⁻¹) compared to 2019 (38.5 t ha⁻¹), illustrating the alternate year-bearing habit of ‘KP’ mangoes. In the 2018 harvest, fruit from trees receiving 25 kg N ha⁻¹ appeared yellow–green compared to those with less N, while fruit from trees with 50 kg N ha⁻¹ exhibited ‘stay green’ skin, indicating that applications of 25 and 50 kg N ha⁻¹ were excessive. There was no ‘stay green’ skin observed in the 2019 harvest, indicating that the environment may also be a contributing factor. The texture of ripe fruit from untreated control trees had the highest flesh resistance. Moreover, ethylene-treated fruit ripened in nine days post-harvest and had significantly lower sugar content than untreated fruit, which ripened in 14 days. This study provides valuable insights into the complex interactions among N application, fruit quality, and yield of ‘KP’ mangoes, highlighting the importance of appropriate N management for a sustainable and environmentally friendly commercial mango production system. Full article

Mango (Mangifera indica L.) (2n = 40) is an important perennial fruit tree in tropical and subtropical regions. The lack of information on genetic diversity at the molecular level hinders efforts in mango genetic improvement and molecular marker-assisted breeding. In this study, a genome-wide screening was conducted to develop simple sequence repeat (SSR) markers using the Alphonso reference genome. A total of 187 SSR primer pairs were designed based on SSR loci with consisting of tri- to hexa-nucleotide motifs, and 34 highly polymorphic primer pairs were selected to analyze the diversity of 231 germplasm resources. These primers amplified 219 alleles (Na) across 231 accessions, averaging of 6.441 alleles for per marker. The polymorphic information content (PIC) values ranged from 0.509 to 0.757 with a mean of 0.620. Genetic diversity varied among populations, with Southeast Asia showing the highest diversity, and Australia the lowest. Population structure analysis, divided the accessions into two groups, Group I (India) and Group II (Southeast Asia), containing 104 and 127 accessions, respectively, consistent with results from phylogenetic analysis and principal component analysis (PCA). Sixteen SSR primer pairs capable of distinguishing all tested accessions, were selected as core primers for constructing fingerprints of 229 mango accessions. These findings offer valuable resources for enhancing the utilization of mango germplasm in breeding programs. Full article

Commercial mango growers commonly spray potassium nitrate (KNO₃) solution to enhance flowering and fruit quality, yet there is limited information on the uptake efficiency of nitrogen (N) by mango cultivars through leaf cuticles. The study aimed to assess N uptake efficiency (NUpE) from foliar application of KNO₃ solution and compare NUpE among mango varieties. Mango cultivars were ‘Kensington Pride’ (‘KP’), ‘B74’ (‘Calypso^®’), and ‘NMBP 1201’ (‘AhHa!^®’), ‘NMBP 1243’ (‘Yess!^®’), and ‘NMBP 4069’ (‘Now^®’) grafted onto ‘KP’ seedlings. Leaves of six-month-old seedlings were dipped in ¹⁵N-enriched KNO₃ solution and analyzed for total N and ¹⁵N contents. A significant correlation was observed between the leaf area and the amount of solution retained after dipping the leaves in the KNO₃ solution. Moreover, leaves treated with the KNO₃ solution had higher ¹⁵N levels than the natural ¹⁵N abundance, indicating successful N uptake from the KNO₃ solution. The NUpE ranged from 27% to 44% and varied with variety. Cultivar ‘NMBP 4069’ had the highest NUE (44%) which was comparable with that of ‘B74’ (40%). ‘NMBP 1201’ showed the lowest (27%) NUpE which was comparable with that of ‘NMBP 1243’ (30%) and ‘KP’ (33%). These data on ¹⁵N uptake through the mango leaf cuticle demonstrates the effectiveness of foliar application as a method of supplying N to mango trees, highlighting important varietal differences in foliar ¹⁵N uptake efficiency. Considering these differences in NUpE among mango varieties will help in making informed decisions about cultivar selection and N management strategies for sustainable mango production. Full article