Zurich, Switzerland – Researchers at the University of Zurich (UZH) have developed a groundbreaking method that harnesses artificial intelligence (AI) and big data to monitor plant responses to changing environmental conditions. This innovative approach, known as PlantServation, enables scientists to collect and analyze vast amounts of data without harming the plants, providing critical insights into how plants adapt to their surroundings.
The study, published in Nature Communications, addresses the growing importance of understanding how plants can thrive and adapt in an era of climate change. Traditionally, scientists relied on labor-intensive methods that involved taking plant samples, damaging the specimens in the process.
Reiko Akiyama, the first author of the study, explained, “This labor-intensive method isn’t viable when thousands or millions of samples are needed. Moreover, taking repeated samples damages the plants, which in turn affects observations of how plants respond to environmental factors. There hasn’t been a suitable method for the long-term observation of individual plants within an ecosystem.”
PlantServation, developed with support from UZH’s University Research Priority Program (URPP) “Evolution in Action,” is a groundbreaking solution to this challenge. It combines advanced image-acquisition hardware with deep learning-based software, allowing for precise observations of plants in their natural environment, regardless of weather conditions.
To test the method, the researchers collected top-view images of Arabidopsis plants at UZH’s Irchel Campus over three field seasons, spanning five months from fall to spring. They analyzed over four million images using machine learning to understand how these plants accumulate a pigment called “anthocyanin” in response to seasonal and annual fluctuations in temperature, light intensity, and precipitation.
PlantServation also enabled the scientists to replicate the natural speciation of a hybrid polyploid species. These species arise from the duplication of an entire genome of their ancestors, a common process in plant diversification.
The study found that the anthocyanin content of the hybrid polyploid species A. kamchatica mirrored that of its two ancestors: during the fall to winter transition, it resembled the ancestor species from a warm region, while from winter to spring, it resembled the other ancestor from a colder region. This discovery supported a long-standing hypothesis about the evolution of polyploid species.
Rie Shimizu-Inatsugi, one of the study’s corresponding authors, emphasized, “The results of the study thus confirm that these hybrid polyploids combine the environmental responses of their progenitors, which supports a long-standing hypothesis about the evolution of polyploids.”
Kentaro Shimizu, corresponding author and co-director of the URPP Evolution in Action, highlighted the versatility of PlantServation: “With its economical and robust hardware and open-source software, PlantServation paves the way for many more future biodiversity studies that use AI to investigate plants other than Arabidopsis—from crops such as wheat to wild plants that play a key role for the environment.”
PlantServation represents a significant leap forward in plant research, offering scientists a powerful tool to study plant responses to environmental changes with unprecedented precision and without causing harm to the plants. The method holds great promise for advancing our understanding of how plants adapt to the challenges of a changing world.