{"id":6287,"date":"2020-07-27T09:50:23","date_gmt":"2020-07-27T08:50:23","guid":{"rendered":"https:\/\/www.innovationnewsnetwork.com\/?p=6287"},"modified":"2020-07-27T09:50:23","modified_gmt":"2020-07-27T08:50:23","slug":"innovators-train-ai-models-to-help-measure-biodiversity-in-birds","status":"publish","type":"post","link":"https:\/\/www.innovationnewsnetwork.com\/innovators-train-ai-models-to-help-measure-biodiversity-in-birds\/6287\/","title":{"rendered":"Innovators train AI models to help measure biodiversity in birds"},"content":{"rendered":"
A new study demonstrates for the first time that AI can be used to train computers<\/a> to recognise individual birds, allowing researchers to accurately measure the biodiversity of birds.<\/p>\n “We show that computers can consistently recognise dozens of individual birds, even though we cannot ourselves tell these individuals apart. In doing so, our study provides the means of overcoming one of the greatest limitations in the study of wild birds – reliably recognising individuals.” Said Dr Andr\u00e9 Ferreira at the Center for Functional and Evolutionary Ecology<\/a> (CEFE), France, and lead author of the study.<\/p>\n Distinguishing individual animals from each other is important for the long-term monitoring of the biodiversity of birds and protecting species from climate change. Humans can identify individual birds by assessing colour variations and size differences, this method is often time consuming and prone to error.<\/p>\nTraining AI models to identify individual birds<\/h3>\n