Super-Resolution of BVOC Emission Maps Via Domain Adaptation

TL;DR

This paper introduces a novel deep learning and domain adaptation approach to improve the resolution of satellite-derived BVOC emission maps by leveraging simulated data, addressing data scarcity challenges.

Contribution

It pioneers the application of domain adaptation techniques for super-resolution of satellite BVOC emission maps, combining simulated and observed data for enhanced reconstruction.

Findings

Domain adaptation improves super-resolution accuracy.

Varying data quantities impacts adaptation effectiveness.

First application of DA in satellite BVOC map enhancement.

Abstract

Enhancing the resolution of Biogenic Volatile Organic Compound (BVOC) emission maps is a critical task in remote sensing. Recently, some Super-Resolution (SR) methods based on Deep Learning (DL) have been proposed, leveraging data from numerical simulations for their training process. However, when dealing with data derived from satellite observations, the reconstruction is particularly challenging due to the scarcity of measurements to train SR algorithms with. In our work, we aim at super-resolving low resolution emission maps derived from satellite observations by leveraging the information of emission maps obtained through numerical simulations. To do this, we combine a SR method based on DL with Domain Adaptation (DA) techniques, harmonizing the different aggregation strategies and spatial information used in simulated and observed domains to ensure compatibility. We investigate the effectiveness of DA strategies at different stages by systematically varying the number of simulated and observed emissions used, exploring the implications of data scarcity on the adaptation strategies. To the best of our knowledge, there are no prior investigations of DA in satellite-derived BVOC maps enhancement. Our work represents a first step toward the development of robust strategies for the reconstruction of observed BVOC emissions.