Plants are essential for life on Earth, but they are also under threat from various factors such as habitat loss, climate change, invasive species and overexploitation. How can we protect them from extinction? One possible solution is to use artificial intelligence (AI) to predict which plants are most at risk and where they need urgent conservation action.
AI is a branch of computer science that aims to create machines or systems that can perform tasks that normally require human intelligence, such as learning, reasoning and decision making. AI can help us analyse large amounts of data and find patterns or trends that are not easily visible to human eyes.
One example of how AI can help plant conservation is the recent study by scientists from the Royal Botanic Gardens, Kew, in Richmond, U.K., who used a machine learning model to estimate the extinction risk of all 328,565 known species of flowering plants. This is the first time that such a comprehensive prediction has been made for the entire group of plants that produce seeds enclosed in a protective structure called a fruit.
The scientists used a Bayesian Additive Regression Trees (BART) model, which is a type of statistical learning technique that can handle complex and nonlinear relationships between variables. They trained the model on a dataset of more than 53,000 plants that have already been assessed by the International Union for Conservation of Nature (IUCN) Red List, which is the most authoritative source of information on the global conservation status of animal, fungi and plant species. They then applied the model to the remaining 275,004 unassessed species, using data on their geographic distribution, habitat preferences, life history traits and threats.
The results showed that 45% of all flowering plants are threatened with extinction, which is higher than the previous estimate of 22% based on a smaller sample of assessed species. The model also identified which regions and countries have the highest proportion of threatened plants, such as Madagascar, Brazil, Indonesia and Colombia. The predictions are freely available online via Kew’s Plants of the World Online portal, where anyone can look up any species and see its probable threat status and the level of confidence in the prediction.
The researchers hope that their study will help accelerate conservation efforts for the plants that are most likely to be threatened but have not been officially assessed by the IUCN Red List yet. They also hope that their method will inspire other scientists to use AI to predict the extinction risk of other groups of organisms, such as fungi, algae and animals.
Recent Blog : Alien Eyes on Earth: Habitable or Not?
RELATED POSTS
View all
