Ikechukwu Kingsley Opara

Dr. Ikechukwu Kingsley Opara

Food Science, Stellenbosch University, Stellenbosch, South Africa
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 May 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
Ikechukwu Kingsley OparaIkechukwu Kingsley Opara
Ikechukwu Kingsley Opara
Olaniyi FawoleOlaniyi Fawole
Olaniyi Fawole
CKCandice Kelly
Candice Kelly
Umezuruike Linus OparaUmezuruike Linus Opara
Umezuruike Linus Opara
While there is a growing body of scientific knowledge on improved techniques and procedures for the production and handling of quality pomegranate fruit to meet market demand, little is known about the magnitude of losses that occur at the farm and post-farmgate. This study revealed the amount of pomegranate fruit lost on the farm and the causes of loss and estimated the impacts of losses. The direct measurement method, which involved sorting and counting of individual fruit, was used since physical identification of the causes of fruit losses on individual fruit was necessary for data collection. Furthermore, qualitative data were collected by physical observation during harvesting and interaction with farm workers. At the case study farm in Wellington, Western Cape Province of South Africa, a range of 15.3–20.1% of the harvested crop was considered lost, as the quality fell below marketable standards for retail sales. This amounted to an average of 117.76 tonnes of pomegranate fruit harvested per harvest season in the case study farm, which is removed from the value chain and sold mainly at a low value for juicing and other purposes and translates to an estimated R10.5 million ($618,715.34) economic loss to the farmer. Environmental factors are the main causes of on-farm fruit losses. In the three pomegranate cultivars studied, sunburn and crack were identified as the leading cause of fruit loss, accounting for about 43.9% of all on-farm fruit losses. The lost fiber, carbohydrate, protein, iron and ascorbic acid contents associated with lost fruit were estimated to meet the daily recommended nutrition intake of 2, 9, 4, 2 and 24 people, respectively. Strategies to control and reduce pomegranate fruit losses and waste at the farm level should focus on environmental factors and mechanical damage since they account for the highest sources of fruit losses. This will ensure improved revenue to farmers, sustainable use of natural resources, reduction of the environmental impacts of the fruit industry, and more availability of quality fruit for nutritional security.

6 May 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
Ikechukwu Kingsley OparaIkechukwu Kingsley Opara
Ikechukwu Kingsley Opara
Olaniyi FawoleOlaniyi Fawole
Olaniyi Fawole
Umezuruike Linus OparaUmezuruike Linus Opara
Umezuruike Linus Opara
Pomegranate fruit, like other types of fresh horticultural produce, are susceptible to high incidence preharvest and postharvest losses and waste. Several studies have been done to improve the production and handling of pomegranate fruit to meet market standards, but little has been done in loss quantification, especially in the early stage of the value chain such as the packhouse. Therefore, the aim of this study was to quantify the magnitude of pomegranate fruit losses at the packhouse, identify the causes, and estimate the impacts of losses. The study was conducted on a case study packhouse in the Western Cape Province of South Africa from February to March 2020. The direct measurement method, which involved physical identification of the causes of loss on individual fruit, was used for data collection. Loss quantification involved the calculation of lost fruit proportional to the amount put in the packhouse processing line. The results showed that losses ranged between 6.74% to 7.69%, which translated to an average of 328.79 tonnes of pomegranate fruit removed during packhouse operation per production season at the investigated packhouse. This magnitude of lost fruit was equivalent to over ZAR 29.5 million (USD 1,754,984) in revenue, in addition to the opportunity costs of resources used to produce lost fruit.

25 April 2024 in Plants
Verified
Journal Article
Open access
PDF file
Ikechukwu Kingsley OparaIkechukwu Kingsley Opara
Ikechukwu Kingsley Opara
Umezuruike Linus OparaUmezuruike Linus Opara
Umezuruike Linus Opara
JOJude Awele Okolie
Jude Awele Okolie
Olaniyi FawoleOlaniyi Fawole
Olaniyi Fawole
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.

27 May 2025 in Journal of Agriculture and Food Research
Verified
Journal Article
Open access
Ikechukwu Kingsley OparaIkechukwu Kingsley Opara
Ikechukwu Kingsley Opara
DDDouglas Chinenye Divine
Douglas Chinenye Divine
YSYardjouma Silue
Yardjouma Silue
Umezuruike Linus OparaUmezuruike Linus Opara
Umezuruike Linus Opara
JOJude A. Okolie
Jude A. Okolie
Olaniyi FawoleOlaniyi Fawole
Olaniyi Fawole

1 October 2022 in Acta Horticulturae
Verified
Journal Article
Closed access
Ikechukwu Kingsley OparaIkechukwu Kingsley Opara
Ikechukwu Kingsley Opara
OFO.A. Fawole
O.A. Fawole
UOU.L. Opara
U.L. Opara
ISHS V International Symposium on Pomegranate and Minor Mediterranean Fruits Pomegranate production and export during the past decade in South Africa and incidence of postharvest losses

21 October 2026
Verified
Preprint
Open access
PDF file
RMRovhona Mudau
Rovhona Mudau
FIFrederic Isingizwe
Frederic Isingizwe
Ikechukwu Kingsley OparaIkechukwu Kingsley Opara
Ikechukwu Kingsley Opara
CNClement Nyirenda
Clement Nyirenda
Postharvest losses of fresh produce threaten food security, particularly in resource-constrained supply chains where quality is still assessed by subjective manual inspection. This study presents a two-component system: a MobileNetV2 convolutional neural network that classifies images of produce as fresh or rotten, and a browser-based web application that runs the classifier entirely client-side using TensorFlow.js, without a server or specialised hardware. Using a public dataset of roughly 30,000 labelled images spanning nine produce types, the model achieved 98.46% accuracy on a held-out test set, with a macro-averaged F1-score of 0.985 and an ROC-AUC of 0.9989. The confidence output, presented to users as a Visual Freshness Index (VFI), was well calibrated against the binary label (Expected Calibration Error: 0.0051), making it a dependable indicator of classification confidence. Trained with native preprocessing, the heavier baselines ResNet50, EfficientNetB0, and VGG16 achieved comparable accuracy, so MobileNetV2 was retained for its small footprint and suitability for deployment. The shelf-life and storage suggestions shown by the application are indicative heuristics, not validated model outputs. Its offline, browser-based design makes the system potentially suited to resource-constrained and low-connectivity agricultural settings.