How AI Can Help Crop Quality

Over the past few decades, the food industry has boomed, prompting a remarkable transformation. In the past, consumers would visit their local grocers to purchase fresh fruits and vegetables, usually in a small store offering limited choices sourced from local farms. Today’s consumers, however, have a huge variety of options, including multiple supermarkets in every town, online shopping, and even same-day delivery. Suppliers are now competing on a global scale in which stores receive produce from much further afield. This explosive growth in the food market has led to increased expectations among consumers, who now demand a wider variety of high-quality products, year round, at lower prices.

To meet these ever-evolving demands, the food industry has started to leverage the power of artificial intelligence (AI) and big data analytics to optimize every stage of the production process, starting with the growing of raw ingredients in the field.

For food manufacturers, the challenge lies in balancing these demands with the increasing costs of food production. As we have seen recently with inflating costs of food products and intermittent supply chain interruptions, this task can be incredibly challenging. If food producers are unable to keep up with the rising costs of energy and other inputs, it means that food production is no longer a viable business option. In countries like the UK, this challenge has led to a shortage of various ingredients, a scarcity first seen in eggs and then extending to a huge host of fruits and vegetables such as peppers, cucumbers, and raspberries. In the U.S., we have also seen food suppliers struggling with staving off viruses in products such as lettuce and oranges, efforts that, in turn, are creating a national and global shortage.

Crop Quality

The food supply value chain encompasses a vast network, stretching from selecting and planting the initial seeds to stocking the shelves of stores and supermarkets with finished products. Big data can now be harnessed right from the outset of food production, particularly during the crucial growing stage. These tools assist with fundamental tasks such as fertilization, irrigation, and crop disease management; however, the applications and benefits of this data go far beyond these underlying aspects, extending further along the production line, especially to the food manufacturing process, where crop quality becomes paramount.

Traditionally, food manufacturers have paid a fixed price per truckload of product, regardless of the quality of the load. Unfortunately, any issues related to quality often surface only during the manufacturing process, when the goods have already been received and paid for. For example, consider the case of pomegranates: Nutritional inputs during the growing stage of the fruit determine its acidity levels, which influence whether the pomegranate is suitable for juice production or for sale as a fresh fruit, showing the knock-on effect of agricultural practices on the food manufacturer, months down the line. This inconsistency in fruit quality poses a significant challenge for juice producers who strive to maintain a consistent product standard for consumers; not only is their supply of fruits for juice variable, but the flavor of the fruits can vary dramatically, producing inconsistent batches.

Similar variability can be observed in almonds, where properly fertilized trees yield almonds with superior oil qualities. Higher quality almonds offer better health benefits, as well as a longer shelf life, enabling producers to offer a healthier, longer-lasting product to their customers.

When a truckload of produce fails to meet a food manufacturer’s quality criteria, it may have to be completely discarded. This results in substantial waste but, crucially for the food manufacturer, it means an uncertain output of their final product per truckload. In the event of large quantities of low-quality input ingredients, food manufacturers must pay for additional sorting to salvage the usable portions while covering the added cost of unacceptable product disposal. Lastly, they must make up the difference by finding last-minute additional produce, usually at a significantly higher price. Although rare, should manufacturers receive higher-quality, higher-yielding produce, they may need to source costly storage space to cope with the additional raw materials and yield produced. These challenges have a direct impact on the bottom line for food manufacturers and lead to additional costs throughout the supply chain. For many players in the industry, this can lead to increasing product prices and risking their competitive advantage in the market.