Estimating forest carbon stocks from high-resolution remote sensing imagery by reducing domain shift with style transfer

TL;DR

This paper presents a novel approach for estimating forest carbon stocks by applying style transfer and Swin Transformer techniques to remote sensing imagery, aiming to improve accuracy in large-scale forest monitoring.

Contribution

It introduces a style transfer method combined with Swin Transformer to reduce domain shift in remote sensing-based forest carbon stock estimation.

Findings

Enhanced accuracy in carbon stock estimation using style transfer.

Effective global feature extraction with Swin Transformer.

Successful application to Chinese forest imagery.

Abstract

Forests function as crucial carbon reservoirs on land, and their carbon sinks can efficiently reduce atmospheric CO2 concentrations and mitigate climate change. Currently, the overall trend for monitoring and assessing forest carbon stocks is to integrate ground monitoring sample data with satellite remote sensing imagery. This style of analysis facilitates large-scale observation. However, these techniques require improvement in accuracy. We used GF-1 WFV and Landsat TM images to analyze Huize County, Qujing City, Yunnan Province in China. Using the style transfer method, we introduced Swin Transformer to extract global features through attention mechanisms, converting the carbon stock estimation into an image translation.