[[{“value”:”

Researchers recently developed a machine learning model that helps assess the quality of tomatoes before harvest. The pioneering method could make tomato harvest easier, more cost efficient and sustainable.

In a study recently published in the Computers and Electronics in Agriculture scientific journal, scientists from the Hebrew University of Jerusalem (HUJI) said their model recognizes the key parameters of tomato quality with exceptional accuracy.

Why tomatoes? The coauthors explain that the tomato is “one of the most substantial crops grown worldwide, with significant economic and nutritional values.”

In 2020, the global gross production of tomatoes was 189 million tons. Tomatoes are nutritionally rich, offering sugars, organic acids, lycopene, and ascorbic acid (vitamin C) and may even reduce the risk of several cancers, cardiovascular conditions, and age-related macular degeneration.

However, traditional methods of determining the quality of tomato crops happen only after harvest and have many drawbacks.

The HUJI researchers, in collaboration with researchers from Bar-Ilan University and the government’s Volcani Center Agricultural Research Organization, employed hyperspectral imaging to develop a machine learning model for pre-harvest assessment.

Hyperspectral images of specific ranges of light wavelengths, known as spectral bands, are used to study the properties of objects based on how they reflect light.

The scientists used a handheld hyperspectral camera to collect data from 567 tomato fruits across five cultivars.

They then employed machine learning algorithms to predict seven critical tomato quality parameters: weight, firmness, total soluble solids, citric acid, ascorbic acid, lycopene, and pH.

The model demonstrated high prediction accuracy.

The researchers said the study highlights potential for integration of the method into agricultural practices to evaluate produce quality during ripening stages, optimizing harvest timing, as well in supermarkets at later stages.

“Our research aims to bridge the gap between advanced imaging technology, AI, and practical agricultural applications,” said David Helman from HUJI’s Faculty of Agriculture, Food and Environment, who led the study.

“This work has the potential to revolutionize quality monitoring not only in tomatoes but also in other crops. Our next step is to build a low-cost device — ToMAI-SENS — based on our model that will be used across the fruit value chain, from farms to consumers,” he added.

The post Pioneering method determines if tomatoes are ready to pick appeared first on ISRAEL21c.

The post Pioneering method determines if tomatoes are ready to pick appeared first on ISRAEL21c.

“}]]