Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation

TL;DR

This paper explores deep learning models to simulate optical images from SAR data, demonstrating successful multi-temporal data fusion for improved optical image generation with potential applications in cloud removal and superresolution.

Contribution

It introduces two deep learning models for optical image simulation from SAR data, highlighting the effectiveness of multi-temporal data fusion and analyzing model sensitivity.

Findings

Multi-temporal SAR-optical data fusion successfully simulates optical images.

Simple SAR data alone fails to produce accurate optical simulations.

Models show potential for applications like cloud removal and superresolution.

Abstract

In this paper, we present the optical image simulation from a synthetic aperture radar (SAR) data using deep learning based methods. Two models, i.e., optical image simulation directly from the SAR data and from multi-temporal SARoptical data, are proposed to testify the possibilities. The deep learning based methods that we chose to achieve the models are a convolutional neural network (CNN) with a residual architecture and a conditional generative adversarial network (cGAN). We validate our models using the Sentinel-1 and -2 datasets. The experiments demonstrate that the model with multi-temporal SAR-optical data can successfully simulate the optical image, meanwhile, the model with simple SAR data as input failed. The optical image simulation results indicate the possibility of SARoptical information blending for the subsequent applications such as large-scale cloud removal, and optical data temporal superresolution. We also investigate the sensitivity of the proposed models against the training samples, and reveal possible future directions.