AI for Earth: Rainforest Conservation by Acoustic Surveillance

TL;DR

This paper presents a novel acoustic surveillance system utilizing CNN models for rainforest sound classification to aid conservation efforts, demonstrating promising results on multiple datasets and enabling real-world deployment.

Contribution

It introduces new CNN models for environmental sound classification tailored for rainforest conservation, with potential for automation and cloud integration.

Findings

Achieved promising classification accuracy on public and real rainforest datasets.

Models are adaptable for automated machine learning and cloud deployment.

Supports real-time rainforest monitoring for conservation.

Abstract

Saving rainforests is a key to halting adverse climate changes. In this paper, we introduce an innovative solution built on acoustic surveillance and machine learning technologies to help rainforest conservation. In particular, We propose new convolutional neural network (CNN) models for environmental sound classification and achieved promising preliminary results on two datasets, including a public audio dataset and our real rainforest sound dataset. The proposed audio classification models can be easily extended in an automated machine learning paradigm and integrated in cloud-based services for real world deployment.