Multimodal Noisy Segmentation based fragmented burn scars identification in Amazon Rainforest

TL;DR

This paper introduces AmazonNET, a deep learning model that effectively segments wildfire burn scars in Amazon rainforest using multimodal remote sensing data, overcoming challenges of noise and fragmentation.

Contribution

The work presents AmazonNET, a novel deep learning framework combining UNet architecture with multimodal data to improve burn scar segmentation in noisy, partially labelled datasets.

Findings

AmazonNET outperforms existing methods in burn scar detection accuracy.

The model effectively handles noisy and partially labelled datasets.

Demonstrates the first successful application of deep learning for multimodal burn scar segmentation in rainforests.

Abstract

Detection of burn marks due to wildfires in inaccessible rain forests is important for various disaster management and ecological studies. The fragmented nature of arable landscapes and diverse cropping patterns often thwart the precise mapping of burn scars. Recent advances in remote-sensing and availability of multimodal data offer a viable solution to this mapping problem. However, the task to segment burn marks is difficult because of its indistinguishably with similar looking land patterns, severe fragmented nature of burn marks and partially labelled noisy datasets. In this work we present AmazonNET -- a convolutional based network that allows extracting of burn patters from multimodal remote sensing images. The network consists of UNet: a well-known encoder decoder type of architecture with skip connections commonly used in biomedical segmentation. The proposed framework utilises stacked RGB-NIR channels to segment burn scars from the pastures by training on a new weakly labelled noisy dataset from Amazonia. Our model illustrates superior performance by correctly identifying partially labelled burn scars and rejecting incorrectly labelled samples, demonstrating our approach as one of the first to effectively utilise deep learning based segmentation models in multimodal burn scar identification.