Quantification of On-Farm Pomegranate Fruit Postharvest Losses and Waste, and Implications on Sustainability Indicators: South African Case Study

Machine Learning Application in Horticulture and Prospects for Predicting Fresh Produce Losses and Waste: A Review

The current review examines the state of knowledge and research on machine learning (ML) applications in horticultural production and the potential for predicting fresh produce losses and waste. Recently, ML has been increasingly applied in horticulture for efficient and accurate operations. Given the health benefits of fresh produce and the need for food and nutrition security, efficient horticultural production and postharvest management are important. This review aims to assess the application of ML in preharvest and postharvest horticulture and the potential of ML in reducing postharvest losses and waste by predicting their magnitude, which is crucial for management practices and policymaking in loss and waste reduction. The review starts by assessing the application of ML in preharvest horticulture. It then presents the application of ML in postharvest handling and processing, and lastly, the prospects for its application in postharvest loss and waste quantification. The findings revealed that several ML algorithms perform satisfactorily in classification and prediction tasks. Based on that, there is a need to further investigate the suitability of more models or a combination of models with a higher potential for classification and prediction. Overall, the review suggested possible future directions for research related to the application of ML in postharvest losses and waste quantification.

Postharvest Diseases of Pomegranate: Alternative Control Means and a Spiderweb Effect

The pomegranate is a fruit known since ancient times for its beneficial properties. It has recently aroused great interest in the industry and among consumers, leading to a significant increase in demand. Consequently, its cultivation has been boosted all over the world. The pomegranate crop suffers considerable yield losses, especially at the postharvest stage, because it is a "minor crop" with few permitted control means. To control latent (Alternaria spp., Botrytis spp., Coniella spp., Colletotrichum spp., and Cytospora spp.) and wound (Aspergillus spp., Penicillium spp., and Talaromyces spp.) fungal pathogens, different alternative compounds, previously evaluated in vitro, were tested in the field on pomegranate cv. Wonderful. A chitosan solution, a plant protein hydrolysate, and a red seaweed extract were compared with a chemical control treatment, all as preharvest (field application) and postharvest treatments and their combinations. At the end of the storage period, the incidence of stamen infections and external and internal rots, and the severity of internal decay were evaluated. Obtained data revealed that pre- and postharvest application of all substances reduced the epiphytic population on stamens. Preharvest applications of seaweed extract and plant hydrolysate were the most effective treatments to reduce the severity of internal pomegranate decays. Furthermore, the influence of spider (Cheiracanthium mildei) cocoons on the fruit calyx as a possible barrier against postharvest fungal pathogens was assessed in a 'Mollar de Elche' pomegranate organic orchard. Compared to no-cocoon fruit (control), the incidence of infected stamens and internal molds in those with spiderwebs was reduced by about 30%, and the mean severity of internal rots was halved. Spiderwebs analyzed via Scanning Electron Microscopy (SEM) disclosed a layered, unordered structure that did not allow for the passage of fungal spores due to its mean mesh size (1 to 20 µm ca). The aims of this research were (i) to evaluate alternative compounds useful to control postharvest pomegranate decays and (ii) to evaluate the effectiveness of spiders in reducing postharvest fungal infections by analyzing related mechanisms of action. Alternative control means proposed in the present work and calyx spider colonization may be helpful to reduce postharvest pomegranate diseases, yield losses, and waste production in an integrated control strategy, satisfying organic agriculture and the planned goals of Zero Hunger Challenge launched by the United Nations.

Vis-NIR and SWIR hyperspectral imaging method to detect bruises in pomegranate fruit

Introduction

Fresh pomegranate fruit is susceptible to bruising, a common type of mechanical damage during harvest and at all stages of postharvest handling. Accurate and early detection of such damages in pomegranate fruit plays an important role in fruit grading. This study investigated the detection of bruises in fresh pomegranate fruit using hyperspectral imaging technique.

Methods

A total of 90 sample of pomegranate fruit were divided into three groups of 30 samples, each representing purposefully induced pre-scanning bruise by dropping samples from 100 cm and 60 cm height on a metal surface. The control has no pre-scanning bruise (no drop). Two hyperspectral imaging setups were examined: visible and near infrared (400 to 1000 nm) and short wavelength infrared (1000 to 2500 nm). Region of interest (ROI) averaged reflectance spectra was implemented to reduce the image data. For all hypercubes a principal components analysis (PCA) based background removal were done prior to segmenting the region of interest (ROI) using the Evince® multi-variate analysis software 2.4.0. Then the average spectrum of the ROI of each sample was computed and transferred to the MATLAB 2022a (The MathWorks, Inc., Mass., USA) for classification. A two-layer feed-forward artificial neural network (ANN) is used for classification.

Results and discussion

The accuracy of bruise severity classification ranged from 80 to 96.7%. When samples from both bruise severity (Bruise damage induced from a 100cm and 60 cm drop heights respectively) cases were merged, class recognition accuracy were 88.9% and 74.4% for the SWIR and Vis-NIR, respectively. This study implemented the method of selecting out informative bands and disregarding the redundant ones to decreases the data size and dimension. The study developed a more compact classification model by the data dimensionality reduction method. This study demonstrated the potential of using hyperspectral imaging technology in sensing and classification of bruise severity in pomegranate fruit. This work provides the foundation to build a compact and fast multispectral imaging-based device for practical farm and packhouse applications.

Deep Learning Based Dual Channel Banana Grading System Using Convolution Neural Network

Deep learning has recently been hailed as the most advanced computer vision technology for image classification. The invention of convolutional neural network (CNN) simplified the effort of feature engineering. Classification of various stages of fruit maturity using machine learning algorithms is a difficult task since it is difficult to distinguish the visual features of the fruits at different maturity stages. Fruit ripeness is critical in agriculture since it impacts the quality of the fruit. Manually determining the maturity of the fruit has various flaws, including the fact that it takes a long time, needs a lot of labor, and can lead to inconsistencies. In developing countries, agriculture is one of the most important economic sectors. Created system can be employed in the food processing business, in real-life applications where the intelligent system’s accuracy, cost, and speed will improve the production rate and allow satisfying consumer demand. With small number of image samples, the system is capable of automating assembly line related work for classifying bananas along with sufficient overall accuracy. The noninvasive method will also be used to classify other clustered fruits or horticultural crops in the future. The system can either replace or aid human operators who can focus their efforts on fruit selection. The combined merits of RGB and HSI (hyperspectral imaging) for classification of bananas were highlighted in the present study; they have possible application as a model for classification of several types of horticultural produce. The multi-input model’s quick processing time can be a useful and handy technique in the farm field during postharvest procedures. Via a combination of CNN and MLP applied to data collected using RGB and hyperspectral imaging, the multi-input model reliably recognizes bananas with an accuracy level of 98.4 percent as well as an F1-score of 0.97. The AI algorithm predicted the size (large, medium, and microscopic) and perspective (front or rear half) of banana classes with 99 percent accuracy. In comparison to previous studies that simply employed RGB imaging, the presented model revealed the value of integrating RGB imaging and HSI approaches.

Postharvest Rot of Pomegranate Fruit in Southern Italy: Characterization of the Main Pathogens

Pomegranate (Punica granatum L.) is an emerging crop in Italy and particularly in southern regions, such as Apulia, Basilicata, and Sicily, due to favorable climatic conditions. The crop is affected by several pathogenic fungi, primarily in the field, but also during postharvest phases. The most important postharvest fungal diseases in pomegranate are gray and blue molds, black heart and black spot, anthracnose, dry rot, and various soft rots. The limited number of fungicides allowed for treatment in the field and the lack of postharvest fungicides make it difficult to control latent, quiescent, and incipient fungal infections. Symptomatic pomegranates from southern Italy were sampled and isolated fungi were morphologically and molecularly characterized. The data obtained revealed that various species of Penicillium sensu lato (including Talaromyces genus), Alternaria spp., Coniella granati, and Botrytis cinerea were the principal etiological agents of postharvest pomegranate fruit diseases; other relevant pathogens, although less represented, were ascribable to Aspergillus sect. nigri, Colletotrichum acutatum sensu stricto, and Cytospora punicae. About two thirds of the isolated pathogens were responsible for latent infections. The results obtained may be useful in planning phytosanitary control strategies from the field to storage, so as to reduce yield losses.

Effects of Gum Arabic Coatings Enriched with Lemongrass Essential Oil and Pomegranate Peel Extract on Quality Maintenance of Pomegranate Whole Fruit and Arils

The effects of gum arabic coatings combined with lemongrass oil and/or pomegranate peel extract on freshly harvested mature 'Wonderful' pomegranate fruit were studied. Fruit were coated with gum arabic (GA) (1.5% w/v) alone or enriched with lemongrass oil (LM) (0.1% v/v) and/or pomegranate peel extract (PP) (1% w/v). Fruit were packed into standard open top ventilated cartons (dimensions: 0.40 m long, 0.30 m wide and 0.12 m high), and stored for 6 weeks at 5 ± 1 °C (90% RH). Evaluations were made every 2 weeks of cold storage and after 5 d of shelf life (20 °C and 65% RH). Fruit coated with GA + PP (4.09%) and GA + PP + LM (4.21%) coatings recorded the least cumulative weight loss compared to the uncoated control (9.87%). After 6 weeks, uncoated control and GA + PP + LM recorded the highest (24.55 mg CO2Kg-1h-1) and lowest (10.76 mg CO2Kg-1h-1) respiration rate, respectively. Coating treatments reduced the incidence of decay and treatments GA + LM + PP and GA + PP recorded the highest total flavonoid content between 2 and 6 weeks of storage. The findings suggest that GA coatings with/without LM and PP can be a beneficial postharvest treatment for 'Wonderful' pomegranates to reduce weight loss and decay development during cold storage.

Pomegranate Fruit Quality and Seed Drying Method: Effect on the Chemical Composition and Bioactivities of the Extracted Oil

The study presents a comparative investigation of the composition and bioactivity of oil extracted from pomegranate seeds of sun-burned fruit (SB) and healthy fruit (HF) for the value-adding potential of pomegranate fruit waste. Seeds from SB and HF were independently freeze dried, sun dried, and oven dried before ultrasound-assisted oil extraction using petroleum ether. The extracted oil was analysed for yield, refractive index, ρ-anisidine value, total phenolic content (TPC), DPPH radical scavenging ability, antimicrobial activity, tyrosinase enzyme inhibition ability, and fatty acid composition. The results showed that oven dried seeds, regardless of fruit quality, yielded the highest oil (20.85–24.70%, dry weight). Regardless of the seed drying method, oil from the seeds of SB exhibited the highest TPC (1.48–2.84 mgGAE/g PSO) than oil from the seeds of HF. The oil from oven dried and freeze dried seeds of SB were more effective in scavenging the DPPH radicals with IC50 values of 34.77 and 39.97 µg/mL, respectively. All the oil samples showed good ability to inhibit tyrosinase enzyme regardless of fruit quality and seed drying method, with monophenolase and diphenolase IC50 ranging between 0.31 and 0.49 mg/mL and 0.64 and 2.43 mg/mL, respectively. Irrespective of the drying method, oil extracted from HF seeds exhibited greater antimicrobial potency against the tested bacteria. The fatty acid composition of the oil samples was neither affected by fruit quality and seed drying method. Generally, all oil samples exhibited high levels of punicic acid (81.21–82.68%) and low omega 6 to omega 3 ratios (0.19–0.37%), suggesting that the oil samples were healthy. Principal component analysis (PCA) established that freeze dried seeds of SB is an excellent source of oil with higher TPC, punicic acid, polyunsaturated fatty acids, and unsaturated fatty acid/saturated fatty acid ratio. It can be concluded that the seed from SB is a good raw material for oil that can be utilised in cosmetic products formulation.

Classification Learning of Latent Bruise Damage to Apples Using Shortwave Infrared Hyperspectral Imaging

Bruise damage is a very commonly occurring defect in apple fruit which facilitates disease occurrence and spread, leads to fruit deterioration and can greatly contribute to postharvest loss. The detection of bruises at their earliest stage of development can be advantageous for screening purposes. An experiment to induce soft bruises in Golden Delicious apples was conducted by applying impact energy at different levels, which allowed to investigate the detectability of bruises at their latent stage. The existence of bruises that were rather invisible to the naked eye and to a digital camera was proven by reconstruction of hyperspectral images of bruised apples, based on effective wavelengths and data dimensionality reduced hyperspectrograms. Machine learning classifiers, namely ensemble subspace discriminant (ESD), k-nearest neighbors (KNN), support vector machine (SVM) and linear discriminant analysis (LDA) were used to build models for detecting bruises at their latent stage, to study the influence of time after bruise occurrence on detection performance and to model quantitative aspects of bruises (severity), spanning from latent to visible bruises. Over all classifiers, detection models had a higher performance than quantitative ones. Given its highest speed in prediction and high classification performance, SVM was rated most recommendable for detection tasks. However, ESD models had the highest classification accuracy in quantitative (>85%) models and were found to be relatively better suited for such a multiple category classification problem than the rest.

Blanching Pre-Treatment Promotes High Yields, Bioactive Compounds, Antioxidants, Enzyme Inactivation and Antibacterial Activity of 'Wonderful' Pomegranate Peel Extracts at Three Different Harvest Maturities

'Wonderful' pomegranate (Punica granatum L.) peel contains a wide range of phytochemicals including vitamins, dietary fibre, phenolic compounds, and antioxidant properties. Yet, it is often used as animal feed or discarded in landfills, which is not the best eco-friendly way to utilize this phenolic-rich bioresource. Finding novel ways of utilizing pomegranate peel waste could prove a more profitable and eco-friendlier alternative that is far more beneficial to the economy. Adding a blanching pre-treatment step at optimal conditions prior to processing of pomegranate peel aids in the inactivation of quality changing enzymes such as polyphenol oxidase (PPO) and peroxidase (POD), which are accountable for the degradation reactions that cause breakdown of nutrients and phytochemicals. This study aimed to determine the effect of blanching at 80 °C for 3 min on the yield, polyphenol content, antioxidant properties, enzyme inactivation, and antibacterial activity of 'Wonderful' pomegranate peel ethanolic extracts from three different harvest maturities (unripe, ripe, and over ripe), including a comprehensive characterization and quantification using liquid chromatography-mass spectrometry (LC-MS). The blanched unripe peel extracts exhibited the highest total phenolic content, total tannin content, 2,2-diphenyl-1-picryl hydrazyl (DPPH) antioxidant activity, 2,2-azino-bis (3-ethylbenzothiazoline-6-sulphonic acid (ABTS) radical scavenging activity and ferric ion reducing antioxidant power (FRAP) at 14.0 mg gallic acid equivalent (GAE)/g dry mass (DM), 1.0 mg GAE/g DM, 359.1 µmol Trolox/g DM, 912.2 µmol Trolox/g DM and 802.5 µmol Trolox/g DM, respectively. There was significant (p < 0.05) decrease in PPO and POD activity of all blanched pomegranate peel extracts. The blanched unripe peel extracts had the lowest PPO activity at 0.2 U/g fresh weight (FW), with a 70% PPO inactivation compared to ripe and over ripe harvest, whereas the highest POD inactivation was recorded at 67% in over ripe peel extracts. All blanched peel extracts, irrespective of harvest maturity, had minimum inhibitory concentration (MIC) values at 160 µg/mL against all four bacteria strains tested, which included two Gram-positive bacterial strains (Bacillus subtilis ATCC 6051 and Staphylococcus aureus ATCC 12600) and two Gram-negative bacteria (Escherichia coli 11775 and Klebsiella pneumonia ATCC 13883). A total of 25 metabolites including phenolic acids (4), organic acids (1), flavonoids (4), ellagitannins (13), and other polyphenols (3) in all three pomegranate peel samples were tentatively identified after LC-MS profiling. The blanched unripe peel extracts showed significantly higher punicalin α and β, β punicalagin, catechin, epicatechin content at 414 mg/g, and 678 mg/g, 151 mg/g, 229 mg/g, respectively, compared to peel extracts from other harvest maturities. This study provides supportive information for the commercial utilization of pomegranate fruit peel as source of value-added ingredients for the development of novel food, cosmetics, and pharmacological products.

The Influence of Internal Packaging (Liners) on Moisture Dynamics and Physical and Physiological Quality of Pomegranate Fruit during Cold Storage

Weight loss and decay are common physiological disorders during postharvest handling and storage of pomegranates. The study focused on relating the ability of plastic liners as internal packaging to modify both gaseous and moisture atmosphere around the fruit to moisture dynamics and physical and physiological quality of pomegranate fruit (cv. Wonderful) during storage. Fruit were packed with no-liner, non-perforated ‘Decco’, non-perforated ‘Zoe’, micro-perforated Xtend^®, 2 mm macro-perforated high density polyethylene (HDPE), and 4 mm macro-perforated HDPE plastic liners. After 84 days of storage at 5 °C and 90–95% relative humidity (RH), fruit packed with no-liner lost 15.6 ± 0.3% of initial weight. Non-perforated (Decco and Zoe) liners minimised losses to 0.79 and 0.82% compared to Xtend^® micro-perforated (4.17%) and 2 mm HDPE (2.44%) and 4 mm macro-perforated HDPE (4.17%) liners, respectively. Clearly, micro- and macro-perforation of liners minimised moisture condensation, fruit decay, and shrivel severity. Micro-perforated Xtend^® and macro-perforated 4 mm HDPE were the best treatments in minimising postharvest losses that are often associated with inadequate environment control inside packaging compared to the use of non-perforated liners.

Effect of Solvent Extraction and Blanching Pre-Treatment on Phytochemical, Antioxidant Properties, Enzyme Inactivation and Antibacterial Activities of ‘Wonderful’ Pomegranate Peel Extracts

‘Wonderful’ pomegranate (Punica granatum L.) peel is rich in phytochemicals which are responsible for its strong antioxidant and antimicrobial activities, but it has low economic value as it is mainly discarded, causing an environmental waste management problem. To examine the best processing regime for pomegranate peel wastes, different solvents (ethanol, methanol and acetone) at various concentrations (50%, 70% and 100%) and blanching at 60, 80 and 100 °C for 1, 3 and 5 min, for each temperature, were tested. Ethanol at 70% (v/v) provided the highest extract yield, total phenolic and total tannin content at 29.46%, 10.61 ± 0.15, and 0.76 ± 0.02 mg GAE/g DM, respectively. Antioxidant activity using the 2,2 diphenyl-1-picryl hydrazyl assay (DPPH), ferric-reducing antioxidant power assay (FRAP) and 2,2-azino-bis(3-ethylbenzothiazoline-6-sulphonic acid assay (ABTS) were reported at 243.97 ± 2.43, 478.04 ± 73.98 and 718.79 ± 2.42 µmol Trolox/g DM, respectively. A blanching temperature of 80 °C for 3 min led to the highest extract that had a total phenolic content of 12.22 ± 0.08 mg GAE/g DM and total tannin content of 1.06 ± 0.06 mg GAE/g DM. This extract also exhibited the best antioxidant activity for the DPPH, FRAP and ABTS assays. Two blanching temperatures, 80 or 100 °C, significantly reduced polyphenol oxidase and peroxidase activities (p < 0.05). Although blanched peel extracts showed a broad-spectrum activity against test bacteria, blanching at 80 °C for 3 or 5 min was most effective. Hot water blanching is thus a suitable environmentally friendly post-harvesting processing method for pomegranate peels that are intended for use as extracts in value-added products with good antioxidant and antibacterial effects.

A Comparative Study of Antimicrobial and Antioxidant Activities of Plant Essential Oils and Extracts as Candidate Ingredients for Edible Coatings to Control Decay in 'Wonderful' Pomegranate

This study determined the antimicrobial and antioxidant activity of lemongrass (LO), thyme (TO), and oregano (OO) essential oils and ethanolic extracts of pomegranate peel (PPE) and grape pomace (GPE) as candidate ingredients for edible coatings. Antifungal effects against Botrytis cinerea and Penicillium spp. were tested using paper disc and well diffusion methods. Radical scavenging activity (RSA) was evaluated using 2,2-diphenyl-1-picrylhydrazyl and 2,2′-azinobis-3-ethylbenzothiazoline-6-sulfonic acid assays. Gas chromatography-mass spectrometry analysis identified limonene (16.59%), α-citral (27.45%), β-citral (27.43%), thymol (33.31%), paracymene (43.26%), 1,8-cineole (17.53%), and trans-caryphellene (60.84%) as major compounds of the essential oils. From both paper disc and well diffusion methods, LO recorded the widest zone of inhibition against tested microbes (B. cinerea and Penicillium spp.). The minimum inhibitory concentrations of LO against B. cinerea and Penicillium spp., were 15 µL/mL and 30 µL/mL, respectively. The highest (69.95%) and lowest (1.64%) RSA at 1 mg/mL were recorded for PPE and OO. Application of sodium alginate and chitosan-based coatings formulated with LO (15 or 30 µL/mL) completely inhibited spore germination and reduced the decay severity of ‘Wonderful’ pomegranate. Lemongrass oil proved to be a potential antifungal agent for edible coatings developed to extend shelf life of ‘Wonderful’ pomegranate.