Mango Maturity Research Articles

Mango crop maturity estimation using meta‐learning approach

AbstractMangos are a significant fruit crop that is widely cultivated in tropical and subtropical regions. However, manual detection of mango crop maturity is time‐consuming and labor‐intensive. It is a vital agricultural commodity, and accurate assessment of the mango maturity stage is critical for harvesting and post‐harvest handling. Accurately detecting mango crop maturity is essential for ensuring optimal harvesting and quality. This study introduced a specialized Meta‐learning method for classifying mango crop images with limited data. The conventional approach to maturity classification, often hindered by limited labeled data, is significantly enhanced by meta‐learning's ability to adapt quickly to new tasks with minimal examples. The proposed approach works as initial image segmentation to isolate mango crop regions, comprehensive feature extraction to capture meaningful data representations, and a critical meta‐training. This phase involves refining a classifier within a metric space by utilizing cosine distance and an adaptable scale parameter, this is followed by a meta‐testing stage. where the adapted classifier is utilized for maturity prediction with minimal support samples. This research holds substantial promise for the agricultural sector, offering practical solutions to optimize harvest management practices and improve mango crop yield predictions.Practical applicationsOptimized Harvest Scheduling: Scenario: Farmers can use crop maturity estimation to schedule harvest times more precisely. Application: Knowing crop maturity optimizes harvest, minimizing losses. Resource Management: Scenario: Efficient use of resources such as water, fertilizers, and pesticides is essential for sustainable agriculture. Application: Crop maturity guides resource use, for example, reducing late‐stage water/nutrients prevents overuse, saves resources. Quality Assurance: Scenario: Crop quality is often linked to its maturity level. Application: Maturity estimation assesses crop quality, guiding post‐harvest planning and determining market value. Data‐Driven Decision Making: Scenario: Modern agriculture relies on data for decision‐making. Application: Maturity estimation promotes data‐driven farming, aiding trend analysis, optimizing planting, and enhancing farm management.

IMPACT OF THE ‘KENT’ MANGO (Mangifera indica L.) JAM FORMULATION WITH DIFFERENT GELLING AGENTS ON THE PHYSICOCHEMICAL AND SENSORY PROPERTIES

Pectin content decreases as mango (Mangifera indica L.) maturity progresses. When making jam, a hydrocolloid will be required, which can impact the physicochemical and sensory properties of the processed product. The objective of this work was to evaluate the effect of two mango maturity stages (60 and 100 %) and four different gelling agents (pectin, xanthan gum, guar gum, and corn starch) on the physicochemical and sensory properties of jams, using a commercial jam as a control. Eight treatments were obtained, and a completely randomized experimental design was applied. The experimental unit was a glass jar (250 g) of jam with three replicates for physicochemical and sensory analysis. Analysis of variance and comparisons of means with Tukey’s test were carried out with SAS® software. The physicochemical properties of the jam were affected according to its formulation. Those with 100 % ripe mango plus pectin or corn starch showed maximum pH values of 3.7 and 3.8, respectively, but lower acidity (0.6 %). The jams with 60 % ripe mango and pectin or corn starch had higher levels of dietary fiber (1.42 and 1.47 %) and protein (0.97 and 0.79 %), with no differences from the control. In terms of texture, the formulation with 60 % ripe mango plus pectin was statistically superior to the other jams. The jam with 60 % ripe mango and corn starch had the highest sensory color and was comparable to the control, but in hue, it was instrumentally different from the other formulations. Changes in fruit maturity from 60 to 100 % and the type of gelling agent modified the physicochemical properties and sensory color of ‘Kent’ mango jam, confirming the effect of formulation on the attributes evaluated.

Postharvest characteristics of Ataulfo mango grown in Soconusco, Chiapas

Objective: To determine the main indices of evolution of postharvest maturity of theAtaulfo mango from Soconusco, Chiapas, Mexico.Design/methodology/approach: The analyzed variables were color of skin L*, a* and b*, starch, total soluble solids (°Brix), pH, skin instrumental firmness, and color/skin firmness correlation.Results: It was found that, as fruit maturity progresses, from stage 1 to stage 5, the values of the variables skin color L, a* and b*, TSS and pH also increase, but starch concentration and instrumental firmness of the fruit decrease. The negative correlation between color L, a* and b* with the firmness of the fruit, suggest the use of the color variable, as a measure of the maturity of the Ataulfo mango.Limitations on study/implications: The evolution of mango ripening has been studied in varieties such as Tommy Atkins, Keitt, Alphonso, among others, and in Ataulfo grown in other regions of Mexico. Knowing the physicochemical evolution process of the Ataulfo mango grown in Soconusco, Chiapas, is essential for producers.Findings/conclusions: The results obtained could be useful to determine the maturity stage of the Ataulfo mango fruit under the environmental conditions of Soconusco, Chiapas.

Effect of pulsed light fluences on quality, biochemistry and physiology of fresh-cut mangoes during refrigerated storage

This study evaluated the quality of minimally processed mangoes irradiated with six different fluences (0, 1.5, 3.0, 4.2, 5.7 and 7.2 × 104 J m−2) of nonthermal pulsed light (PL). On the 1st, 7th and 14th days of storage at 5 °C, the mango cubes were evaluated for several quality indicators and components of physical products, such as color (L * and b *), electrolyte leakage (EL), titratable acidity (TA), pH, soluble solids (SS), vitamin C, pectinamethylesterase and polygalacturonase activity, histological evaluations, antioxidant enzyme activities, and firmness severely. Independent dose fluency treatment, it was observed that PL did not change enzymatic antioxidant system and firmness of fresh-cut mango, keeping its cell wall integrity, which could be verified by optical microscopy. On the other hand, the intensity of the applied PL exhibited different effects for the postharvest quality maintenance of fresh cut mango, evidenced also by principal component analysis (PCA). The lower fluences of PL (1.5 and 3.0 × 104 J m−2) did not affect the color (L * and b *), membrane permeability (indicated by EL), vitamin C content and the SS/TA ratio, suggesting maintenance of the maturity of fresh-cut mango. Meanwhile, higher fluences (5.7 and 7.2 × 104 J m−2) promoted a slight loss in the vitamin C content. Some variables associated with color, such as b* and C, showed decreased values during refrigerated storage. These results suggest that the application of lower fluences of PL exhibited the best results for fresh-cut mango postharvest.

Using Fuzzy Logic to Increase Accuracy in Mango Maturity Index Classification: Approach for Developing a Portable Near-Infrared Spectroscopy Device

Grading is a decisive step in the successful distribution of mangoes to customers according to their preferences for the maturity index. A non-destructive method using near-infrared spectroscopy has historically been used to predict the maturity of fruit. This research classifies the maturity indexes in five classes using a new approach involving classification modeling and the application of fuzzy logic and indirect classification by measuring four parameters: total acidity, soluble solids content, firmness, and starch. These four quantitative parameters provide guidelines for maturity indexes and consumer preferences. The development of portable devices uses a neo spectra micro development kit with specifications for the spectrum of 1350-2500 nm. In terms of computer technology, this study uses a Raspberry Pi and Python programming. To improve the accuracy performance, preprocessing is carried out using 12 spectral transformation operators. Next, these operators are collected and combined to achieve optimal performance. The performance of the classification model with direct and indirect approaches is then compared. Ultimately, classification of the direct approach with preprocessing using linear discriminant analysis offered an accuracy of 91.43%, and classification of the indirect approach using partial least squares with fuzzy logic had an accuracy of 95.7%.

High-Intensity Ultrasound-Assisted Extraction of Pectin from Mango Wastes at Different Maturity.

Valorisation of food processing by-products is a welcome and developing area. The mango processing industry produces 40% to 60% of the fruit as solid waste, in which components of industrial interest, such as pectin, are lost. This study reports on energy-efficient high-intensity ultrasound-assisted extraction (HIUAE) to extract pectin from mango peels. The analysis considered the ripening stage of the fruit (0, 2, and 4), HIUAE frequency (37 kHz and 80 kHz), and extraction time (20 min, 25 min, and 30 min). Extractions of pectin from mango peels with HIUAE have been fairly studied. However, this work differs from those studies in including mango maturity grade as a factor. Pectin extraction yields ranged from 13% to 30%, with no influence (p > 0.05) of time, and the highest yields were obtained at the lowest maturity stage (0) and lowest frequency (37 kHz). This latest condition (37 kHz) also yielded pectin with the highest gel strength, purity, and quality. This work demonstrated that the mango maturity stage influenced pectin extraction yield. Ultrasound-assisted extraction of pectin from mango peels could be an efficient approach toward waste valorisation and extraction of pectin with high yield and good quality attributes for the food industry.

Impact of Special Drying Schemes on Color Stability of Mangoes with Different Maturity Degrees.

A previous study demonstrated that the color of 4 mm mango slices is altered very slightly by drying for 5 h at 60 °C, 30% RH and 1 m/s. The objectives of this complementary study were to determine the impact of various drying procedures encountered in the drying units on color alterations of sulfite-free mango slices from heterogeneous raw material due to variable maturity degrees of mangoes. Drying procedures with various temperature/humidity/duration combinations were performed to analyze their effects on the color of natural dried mangoes according to the degree of fruit maturity. They were dried at an air speed of 1.0 m/s for 5 h according to 3 schemes: standard drying (SD) at 60 °C and 30% RH; wet drying (WD) for 1 h at 60 °C and 60% RH, followed by 4 h SD; and finally, hot drying (HD) for 4 h SD, followed by 1 h at 80 °C and 30% RH. The color of the mango slices was analyzed before and after drying. SD preserves the color of fresh mangoes very well, whatever their maturity stage. A relatively slow drying onset corresponding to WD has a highly adverse impact, which becomes greater as the degree of maturity increases. There is already significant browning on mangoes with near-optimum quality (L* = 75; H* = 92). Applying high temperature at the end of the drying procedure (HD) for 20% of the time has a more limited adverse impact with immature mangoes that are the most sensitive. Linear regressions were assessed to represent the relationships of color differences between drying schemes according to mango maturity degrees. These statistical models showed a significant increase in color degradation in the case of WD and a decrease in color differences in the case of HD with the advance in fruit maturity.

Local polynomial bi-responses multi-predictors nonparametric regression for predicting the maturity of mango (Gadung Klonal 21): a theoretical discussion and simulation

Local polynomial bi-responses multi-predictors nonparametric regression for predicting the maturity of mango (Gadung Klonal 21): a theoretical discussion and simulation

EFFECT OF THE LENGTH OF THE FLOWERING-HARVEST INTERVAL ON THE RIPENING AND QUALITY OF THE 'KENT' MANGO IN CÔTE D'IVOIRE

The physiological stage of mango maturity at harvest affects fruit quality at the time it is commercialized. The objective assessment of the mango maturity stage at harvest remains a challenge because of the multiple interactions between the visual aspect, the physicochemical composition, and the morphology of the fruit. This study aims to quantify the optimal harvest date to guarantee the maturity and quality of mango cv. ‘Kent’. In this study, which took place in Korhogo in northern Côte d’Ivoire, the maturity stage and the quality of fruits were measured on 240 Kent mangoes harvested at four different harvest dates (90, 95, 100, and 105 days after flowering). A morphological, physical, and chemical characterization (length, width, mass, soluble sugar content, dry matter, skin appearance, and mass loss) was carried out at each date on 30 fruits at harvest and 30 fruits after ripening at room temperature. The number of days necessary for ripening was quantified. The results showed that the optimal harvest date is 100 days after flowering for Kent mangoes in Côte d’Ivoire. Mangoes harvested at this date developed better organoleptic characteristics (less wrinkled skin, lower mass losses, and a shorter ripening time). Assessment of the harvest date, guaranteeing better ripening of the fruit, is of utmost importance for organizing harvests in the mango sectors in West Africa, and especially in Côte d’Ivoire.

Mango maturity classification instead of maturity index estimation: A new approach towards handheld NIR spectroscopy

Estimation of on-tree mango maturity is essential for the prediction of harvest time. Dry matter (DM) is a useful index in deciding mango maturity, and post-harvest quality. Existing NIR based maturity meters employ machine learning regressors to predict a maturity index value (such as DM, oBrix, or etc.) and then impose a hard threshold on predicted value to estimate maturity state of the fruit. In this paper, a new approach for non-destructive hand-held fruit maturity meter is investigated. The developed approach directly classifies the maturity state (mature/immature) using a classifier trained on maturity labels assigned through standard DM thresholds for investigated mango varieties. To develop the hardware of the device, a commercial-off-the-shelf development kit of NIR micro-spectrometer in the spectral range of 400–1100 nm was used with an embedded computational hardware, a micro-halogen lamp, a lithium battery, and a display. The application software (developed in C++) is designed to collect interactance spectra, remove noise, reduce dimensionality, and classify maturity state. Performance of the developed approach is evaluated by on-tree test samples of mango fruit of different season. Comparison of both the literature reported indirect maturity estimation and proposed direct maturity classification is conducted. The test results show that the maximum accuracy achieved using indirect maturity estimation using hard thresholds is 55.9%. Whereas direct maturity classification using KNN achieved 88.2% accuracy in predicting the maturity state (mature/immature) of the test mangoes. Overall results show that the developed DM mango maturity method has considerable potential to detect maturity state of mangoes in practical situations.

Spectral filter design based on in-field hyperspectral imaging and machine learning for mango ripeness estimation

Hyperspectral imaging (HSI) is a powerful technology already used for many objectives in agriculture. Applications include disease monitoring, plant phenotyping, yield estimation or fruit composition and ripeness. However, the cost of hyperspectral sensors is typically an order of magnitude higher than simpler RGB cameras, which can be prohibitive. Given that in HSI processing the spectral data often contains redundancies, the full spectra are not always required for a specific application and there is an opportunity to design a lower cost multi-spectral sensing system by dimensionality reduction. In past work, HSI dimensionality reduction has been applied in the form of band selection to achieve faster computation times. If, however, the objective is to design a lower cost multi-spectral camera system, band selection is poorly suited because real-world sensor and optical filter responses do not typically replicate the individual bands of a hyperspectral sensor. The objective of this paper is to develop a new methodology for filter selection by simulating several imaging devices with different real-world optical filters, to use a high cost HSI device to design a lower cost multi-spectral solution for a specific application. In this paper, we apply the technique to the specific task of mango fruit maturity estimation (dry matter), which was recently shown to be possible using HSI. Mango HSI acquired under field conditions from an UGV was used as input for the experiments. These involved the simulation of imaging devices, using support vector machines for modelling, and testing several filter combinations by brute force or optimisation with genetic algorithms. The mango prediction performance of the simulations was compared to the best performance obtained with full HSI data, which had an R2 of 0.74. The best values came from the simulation of a four-sensor device with four distinct filters, achieving R2 up to 0.69 for mango dry matter estimation. The results showed that genetic algorithms, when compared to brute force approaches, were able to obtain the best solution in an efficient way, and that a good performance for mango ripeness estimation can be achieved from the combination of four spectral filters that would allow to implement them into a low-cost, custom-made multi-spectral sensor. The methods exposed in this paper are more broadly applicable to applications beyond mango maturity estimation.

Maturity estimation of mangoes using hyperspectral imaging from a ground based mobile platform

Monitoring the maturity of fruit in commercial orchards can help growers optimise the time of harvest. Dry matter content (DM) of fruit is used as an indicator of mango maturity, measured in-field with a hand-held spectrometer. This approach is labour intensive, limiting the extent to which DM variability can be measured across an orchard block, which would enable selective harvesting. This paper proposes an alternative approach that utilises a hyperspectral camera, LIDAR sensor and navigation system mounted to a ground vehicle to predict fruit DM individually for hundreds of trees in a mango orchard block. First, the challenges faced due to tree geometry and shadows in mango orchards are addressed. Then the ability to predict DM at a distance using hyperspectral imaging (411.3–867.0 nm) was demonstrated. Two regression methods, partial least squares (PLS) and a convolutional neural network (CNN) were compared and tested against DM results from a hand-held NIR spectrometer using harvested (n=468,σ=2.32%w/w) and on-tree fruit (n=662,σ=1.79%w/w). The CNN achieved a cross validation RCV2=0.64 and RMSECV=1.08%w/w in fruit on tree, while PLS achieved RCV2=0.58 and RMSECV=1.17%w/w. In order to discriminate mango and non-mango pixels, PLS discriminant analysis (PLS-DA) and a CNN were also compared, where both methods achieved good classification performance with a mean F1>0.97. Having established mango classification and DM prediction performance, hyperspectral data were processed for a full orchard block and projected to world coordinates using AGV position and orientation as provided by the navigation system. Trees were segmented using corresponding LIDAR data, which allowed association of projected DM predictions to individual trees. Repeated scans of the orchard block over two days allowed a measure of repeatability, which was achieved with an RMSE<0.29%w/w. The results provide strong evidence that predicting maturity at a distance for all trees in an orchard is feasible using a hyperspectral camera, which will be an important management tool for growers to optimise harvest timing and yield.

Microwave Technique for Moisture Content and pH Determination during Pre- Harvest of Mango cv. Chok Anan

The maturity of mango is usually assessed by the determination of its moisture content (m.c.), soluble solid content (SSC) and pH. However, these techniques are either time consuming, tedious or destructive. In this research, we extend the application of the open-ended coaxial probe technique to determine m.c. and pH of Chok Anan mango from its dielectric properties from week 5 to week 17 after anthesis. The effects of frequency and m.c. on the values of the dielectric constant and loss factor were also investigated. The critical frequency separating the different polarizations was found to be inversely proportional to m.c. Also, in this research we proposed a new classification of fruit ripeness related to the number of weeks after anthesis. The actual dielectric properties, m.c., SSC and pH of Chok Anan mango were measured using standard methods. Relationships were established between the dielectric constant, loss factor, critical frequency, pH and m.c. The accuracy for the determination of m.c. and pH using the coaxial probe was within 1.7% and 3.0%, respectively.

Determination of ‘Palmer’ mango maturity indices using portable near infrared (VIS-NIR) spectrometer

‘Palmer’ mango cultivar is a late season variety which is greatly accepted by European consumers. However, it is common to get reports of fruit quality problems, mainly due to maturity. Thus, the objective of this study was to develop calibration models for soluble solids content (SSC) and dry matter (DM) of ‘Palmer’ mangoes using portable (VIS-NIR) spectrometer. Interactance spectra were obtained with a portable F-750 spectrometer in the wavelength range of 306–1140nm, 8nm spectrum resolution, and 4 scans averaged per spectra. Spectra were used to develop SSC and DM models using partial least square regression (PLSR) with full cross validation. The best SSC calibration model was developed using spectra pre-processed with standard normal variate (SNV), first derivative of Savitzky–Golay and window of 699–999nm. It was observed a RMSECV of 1.39%, with a RCV2 of 0.87, and RPD of 2.77. Better results were observed for the DM calibration model which was built with raw spectra using the window of 699–981nm (RMSECV of 8.81gkg−1, RCV2 of 0.84, and RPD of 2.51). Poor calibration models were obtained for firmness. The results indicated that portable VIS-NIR spectrometer can be used as a non-destructive technique to assess SSC and DM content for ‘Palmer’ mangoes. It is necessary to incorporate more sources of variation, to reduce RMSE values and improve robustness, especially for fruit SSC and DM prediction.

Mango Fruit Sortation System using Neural Network and Computer Vision

Mango has different colors and sizes that indicate the level of maturity. Mango maturity level often makes farmers confused when choosing a mango that has a good maturity. Sometimes, mango farmers still use manual methods to distinguish mango maturity, while the way that human labor is often inaccurate and different in its determination. The difference is due to the different perceptions of each person. From these problems then the need of machine sorting system on agriculture is felt important. Therefore, researchers will conduct research on mango sortation system. Mango has many types such as “Harum Manis”, “Apple”, “Gincu”, etc. In this study type of mango that will be studied is mango “Gincu” because has a good color distribution. The goal of the research is to create a system that can sort mango that ripe or unripe. The method that used to do this research is separated into few step: problem identification, algorithm development, implementation and evaluation. The system is made using C language, Computer Vision and ANN (Artificial Neural Network) so the system can detect the color of mango that has been ripe or unripe. The output of this research will be compared to related research. The final output of this research is the system can detect the ripe or unripe mango with 94% accuracy.

Identification of the mango maturity level by the analysis of volatiles based on long optical-path FTIR spectroscopy and a molecular sieve

The maturity level of mangoes can be identifiedviatheir volatiles using infrared spectroscopy.

USE OF THE REFLECTANCE SPECTRA AS A NON-DESTRUCTIVE INDICATOR OF QUALITY, I.E., COLOR, AND MATURITY, I.E., PIGMENT CONTENT, OF MANGO FRUIT

Appearance is the primary factor in quality judgments of fruits and vegetables. Poor coloration of mango peel is an important factor in grade and commercial value reduction. Furthermore, fruit quality is highly dependent to its maturity stage at harvest, which is more related to chlorophyll content in the peel rather than epidermis coloration because mangoes are generally harvested before any visible color changes. Reflectance spectra in the visible range let to access both pigment contents and color coordinates. Therefore, this study proposes a methodology to estimate, from visible spectra of mango peel, an indicator of external fruit quality, the fruit color, and an indicator of the fruit maturity stage, the chlorophyll content in the peel. This methodology was applied to three cultivars: 'Tommy Atkins', 'Kent' and 'Nam Doc Mai'. Our results showed that mango cultivars had heterogeneous peel color which can be differentiated using the distribution of the hue angle values as criteria. In addition, the peel chlorophyll content was accurately estimated from reflectance indices using a partial least square regression (R2 > 0.98). Significant differences in the peel chlorophyll contents were established between cultivars. This study suggested that reflectance measurements in the visible region could be a practical tool to assess non-destructively the peel color and the mango maturity stage. (Resume d'auteur)

Response of paclobutrazol treatment on flowering, fruit maturity, yield and quality of mango (Mangifera indica) cv Totapuri

A field trial was conducted at Indian Institute of Horticultural Research Bangalore during 2007-2011 to study the effect of different doses and time of application of paclobutrazol on flowering, fruiting behavior and quality of 22 years old mango (Mangifera indica L.) cv Totapuri under South Indian Condition. There were nine treatments involving two doses of paclobutrazol 2.5g and 5.0g a.i/plant with four times of application (last week of July, August, September and October) along with control. All the paclobutrazol applied treatments induced early flowering to an extent by 20- 25 days with increased percentage of flowering of 30-65% compared to control. The harvest maturity was also influenced by paclobutrazol application with an advancement of 3-4 weeks compared to control. The fruit yield was also affected and most pronounced effect was with T5-treatment (2.5g a.i. applied during last week of September) which recorded mean cumulative fruit yield of 141.1 kg/ Plant, which is 55% higher compared to control (91.1 kg/ plant). However, fruit quality attributes such as TSS and acidity were not affected by different dose and time of application of paclobutrazol. Cost benefit ratio was maximum (1:3.02) with the treatment 2.5g a.i. paclobutrazol applied during the last week of September month.

Nondestructive prediction of maturity of mango using near infrared spectroscopy

This study proposes a formula for prediction of maturity index (Im) using physico-chemical characteristics and overall acceptability (OA) of a sensory panel for mangoes from orchards of nine Indian states. Computed Im values were found to be in agreement with both OA scores and the perceptions of experienced farmers. NIR spectra of 1180 mangoes were acquired. Multiple-linear regression (MLR) and partial least square (PLS) models were developed in the wavelength range of 1200–2200nm to predict Im. The best prediction was achieved using PLS model after MSC data treatment in the wavelength range of 1600–1800nm. Multiple correlation coefficients (R) for calibration and validation of PLS model were 0.74 and 0.68, respectively. Lower difference in standard errors of calibration (0.305) and prediction (0.335), indicated the potential of NIRS in prediction of the maturity non-destructive.

NON-DESTRUCTIVE TECHNIQUE FOR DETERMINING MANGO MATURITY

Mango (Mangifera indica L.) is an important tropical fruit that has great potential in international markets. Currently, major markets for mango include North America, Europe, and Japan. The acceptance of exported mango in destination countries depends largely on eating quality, which is affected by maturity at harvest. Mango maturity can be judged visually, based on skin color, or determined chemically based on soluble solids content, acid content, and solids:acid ratio. Maturity determination based on visual observation is unreliable and prone to errors. On the other hand, determination based on sugar or soluble solids to acid ratio is destructive. Therefore, it is important to develop a simple, reliable and non-destructive technique for mango maturity determination. In this study, a reliable and non-destructive technique has been developed and tested. This technique uses a digital camera to capture an image of the mango skin. Images obtained were analyzed using an image processing software (Adobe Photoshop) to obtain color parameters (L, a, b values). Each of the color parameters was plotted against soluble solids content, total acid content, and solids:acid ratio and curve fitting was then applied to obtain polynomial equations. Results indicate that the color parameters can adequately predict the above maturity indices and, therefore, can be used to predict maturity of mango.