Project
Sensing Potential
Food supply chains are under constant pressure to provide increasingly more food, with better quality and in a sustainable manner. Data-driven advances and innovations in sensor technologies play a key role in addressing these challenges. This project explores the sensor innovations to tackle different challenges across the food supply chain.
In this project, we are interested in exploring the potential of sensors and the insight it can provide to tackle different challenges across the food supply chain. In particular, this is about the necessity to measure non-destructively, non-invasively and on a smaller scale than is currently common: from batch level to product level; from population segment to an individual. For this, we need to consider a number of technological hurdles and advances in the areas of non-destructive sensing. The goal of this project is to be able to measure and make better decisions based on the measured product properties. In particular, the necessity to measure non-destructively, non-invasively and on a smaller scale than is currently common: from batch level to product level; from population segment to an individual.
The developments and investigations in this project are being demonstrated in five case studies: monitoring animal welfare; sensing of crop development and performance indicators for indoor farming; quality measurements of fresh food products; food intake and food properties measurement for personalized nutritional advice; non-invasive detection of food adulteration.
These case studies allow application of novel sensing technologies to some of the pressing problems in multiple scientific domains - livestock, plant sciences, post-harvest, food safety and consumer science. In particular, the focus on non-invasive sensing will allow for a transition towards focus on individual (animal, plant, food item, consumer) rather than groups/batches/samples which is the standard practice. Moreover, the ambition of this project is to also investigate if new sensor technologies, supported by data-driven analysis, will be able to address problems which conventional sensors could not capture.