Unusual warning system against forest fires

Bird singing is not only a great sound to help us relax. The acoustic signals generated by the birds also carry information about various events taking place in the area. A research team from Indonesia, Brunei and Malaysia has developed an Indonesian forest fire warning system using this phenomenon. A machine learning algorithm based on convolutional neural networks (CNN) was designed. The system detects changes in the singing of birds caused by the reaction of these animals to a fire. The effectiveness of correct fire identification has been demonstrated at the level of 96%.


Permana, Silvester Dian Handy, et al. “Classification of bird sounds as an early warning method of forest fires using Convolutional Neural Network (CNN) algorithm.” Journal of King Saud University-Computer and Information Sciences (2021).

back to all articles

Custom solutions
and services

Please contact us to inquire information about our custom solutions and services.

Get in touch

Work with us

If you’re looking to solve an existing challenge or capitalise on a new opportunity, please get in touch.

    see more see less

    We use cookies (technical and profiling cookies from us and third parties) on KFB-acoustics.com to provide you with a better online experience and to deliver you with online commercial messages tailored on your preferences. If you select “continue” or access any content of our website without customizing your choices, you agree to the use of cookies. Find out more about our cookie policy and how to refuse cookies by clicking here.