AI increases the accuracy of observing plants

Newswise — Artificial intelligence (AI) can help plant scientists collect and analyze unprecedented amounts of data that would be impossible using conventional methods. Researchers at the University of Zurich (UZH) have now used big data, machine learning and field observations in the university's experimental garden to show how plants respond to environmental changes.

Climate change makes it increasingly important to know how plants can survive and thrive in a changing environment. Laboratory experiments have shown that plants accumulate pigments in response to environmental factors. To date, such measurements were made by taking samples, which required the removal and damage of a part of the plant. “This time-consuming method is not viable when thousands or millions of samples are needed. Moreover, repeated sampling damages plants, which in turn affects observations of how plants respond to environmental factors. “There was no suitable method for long-term observation of individual plants in an ecosystem,” says Reiko Akiyama, first author of the study.

With the support of the UZH University Research Priority Program (URPP) “Evolution in Action”, a team of researchers has now developed a method that allows scientists to observe plants in nature with great precision. PlantServation is a method that combines powerful image acquisition hardware and deep learning-based software to analyze field images and works in any weather.

Millions of images support the evolutionary hypothesis of endurance

Using PlantServation, the researchers collected (top view) images Arabidopsis plants in the experimental plots of UZH's Irchel Campus for three field seasons (lasting five months from autumn to spring) and then analyzed more than four million images using machine learning. The data recorded species-specific accumulation of a plant pigment called “anthocyanin” in response to seasonal and annual fluctuations in temperature, light intensity and precipitation.

PlantServation also allowed scientists to experimentally replicate what happens to a hybrid polyploid species after the natural species. These species evolve from whole genome duplications of their ancestors, a common type of species diversification in plants. Many wild and cultivated plants, such as wheat and coffee, originated this way.

In the current study, the anthocyanin content of hybrid polyploid species A. Kamchatitsa It was similar to its two ancestors: from autumn to winter its anthocyanin content was similar to that of its ancestor species originating from a warmer region, and from winter to spring it was similar to other species from a colder region. “Thus, the results of the study confirm that these hybrid polyploids incorporate the ecological responses of their ancestors, supporting the long-standing hypothesis of polyploid evolution,” says Ri Shimizu-Inatsugi, one of the two corresponding authors of the study.

From Irkhel campus to remote regions

PlantServation was created in the experimental garden of UZH's Irchel Campus. “It was crucial for us to use the Irchel Campus garden to develop PlantServation's hardware and software, but its application goes even further: when combined with solar power, its hardware can be used even in remote locations. With its cost-effective and powerful hardware and open source software, PlantServation paves the way for many more future biodiversity studies that use artificial intelligence to investigate plants other than Arabidopsis – from crops like wheat to wild plants that play an important role in the environment,” says Kentaro Shimizu, corresponding author and co-director of URPP Evolution in Action.

The project is an interdisciplinary collaboration with LPIXEL, a company specializing in AI image analysis, and Japanese research institutes at Kyoto University and Tokyo University, including UZH Global Affairs and International Leaders under the Global Strategy and Partnership Funding Scheme. Japan Society for the Promotion of Science (JSPS) Research Grant Program. The project also received funding from the Swiss National Science Foundation (SNSF).

Strategic partnership with Kyoto University

Kyoto University is one of UZH's strategic partner universities. Strategic partnerships ensure that high-potential research collaborations receive the necessary support to flourish, for example through the UZH Global Strategy and Partnerships funding scheme. Several joint research projects between Kyoto University and UZH have already received funding in recent years, including “PlantServation”.