Building AI To Save The Planet

From counting penguins in Antarctica to identifying elephants in Africa, Gramener, a data science consulting company is building AI tools in partnership with Microsoft to help biodiversity conservation.

While there is a lot of work happening to support biodiversity conservation, most organizations lack the data resources required for quick and accurate reportage of wildlife and natural species.

Take the case of counting Penguins in the Antarctic. Their secluded existence means there is very little data available, and manned missions are difficult, especially during the harsh winters. To solve the data challenge, projects like Oxford University’s Penguin Watch have set up time-lapse cameras to monitor penguin colonies and click a photo every hour over many years. But this creates a problem of its own – every camera generates hundreds of photographs, making it impossible to count penguins in every photo manually.

Enter Gramener. One of the earliest partners for Microsoft’s AI for Earth program, Gramener specializes in solving organizational challenges by creating AI and machine learning-based models for large enterprises, and converting these insights into easily consumable data stories. Working on the Microsoft Azure platform, they used a Convolutional Neural Network model to come up with a solution that can identify and count penguins with a high degree of accuracy. The model can potentially help researchers speed up their studies around the status of penguin populations.

The team is now working on the classification, identification and counting of other species using similar deep learning techniques. To read more about how they are leveraging AI for social good using Microsoft Azure, click here.