Oysters are a major global food product with constantly rising demand. Worldwide an estimate of 5.7 mln. tons of oysters are harvested and distributed each year, totalling to an estimate of 6.1 bln. EUR in market value (stats by UN FAO).
For many working in oyster farming or further down its supply chain, delivering the freshest, highest quality and food-safety compliant oysters to their respective customers is key lasting business success. However, the current oyster aquaculture industry is lacking in flexible, high throughput and easy to implement solutions for oyster quality assessment. Solutions that can be implemented on-site – in the operational environment – are especially needed, as they could help farmers assess oyster quality, growth conditions, evaluating potential risks and operational planning both at oyster growing and harvesting stages, as well as performing oyster quality and freshness monitoring and preventative screening down different supply chain stages.
The approach chosen to address this market lack is the oyster quality assessment service that utilizes NIR spectrometry in combination with machine learning and advanced data analysis techniques. The end result is a service for rapid on-site assessment of oysters, where a customer opens a single oyster from a batch, ‘scans’ its flesh and receives results on its (and by extension the remaining batch) quality parameters.
The service functions on a SaaS (Software-as-a-Service) basis, meaning that customers are able to utilize third-party NIR spectroscopy hardware for oyster flesh ‘scanning’ and submit the data for analysis via a user-friendly web service. Once the data is processed within the machines learning-based analytical system, the customer receives results on the main oyster quality, freshness and potential food risk parameters (moisture level, nutritional value, fats, proteins, glycogens, etc.). This kind of service can also be used as an efficient preventative screening tool to help identify questionable oysters that need further testing using standard laboratory methods.