Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199286,
        author = {Rajeshwari and Raksha K L and Sahana M and R Latisha},
        title = {Deep Learning Based SAR-to-Optical Image Translation for Environmental Disaster Assessment},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12338-12343},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199286},
        abstract = {This survey paper will cover an extensive analysis of methods that use Artificial Intelligence to convert images captured using Synthetic Aperture Radar (SAR) into optical images and enable the use of these images in disaster assessments. The benefit of SAR imaging is that the imaging process is robust since it offers data regardless of weather conditions and the time of the day. On the other hand, SAR imaging is complicated, with the presence of speckles making human interpretations almost impossible. Deep learning techniques such as the use of Generative Adversarial Network (GAN) can be applied to translate SAR images into optical images. Some of the major techniques covered include conditional GANs, U-Net, transformers, and PatchGAN discriminators. This paper will analyze some of the most common loss functions used in image generation such as L1, SSIM, adversarial, and perceptual loss functions. Index Terms—SAR Imaging, GAN, Image Translation, Disaster Management, Deep Learning, Transformer, Remote Sensing.},
        keywords = {},
        month = {April},
        }