1887

Abstract

Summary

Satellite Super-Resolution (SSR) technology, powered by deep learning, provides an affordable and scalable way to obtain high-resolution satellite imagery for the energy industry. By enhancing the resolution of open-source imagery, SSR empowers companies to optimize their operations, monitor assets efficiently, and make informed, data-driven decisions.

This abstract highlights SSR’s capabilities, including its energy industry applications in asset tracking, site evaluation, and environmental monitoring. ThinkOnward’s SSR model, designed for research and validation, combines Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to produce super-resolved images with 10 times more detail than the original input. This hybrid approach leverages the strengths of both architectures, with CNNs focusing on local pixel neighborhoods and ViTs capturing global relationships and long-range dependencies, surpassing models that rely solely on one.

The thorough preprocessing of training data, including image selection, multi-sample augmentation, and color-space augmentation, ensures optimal model performance. The result is a cost-efficient solution that provides high-quality, super-resolved imagery, enabling more accurate geospatial analyses and superior interpretations for subsequent machine learning models. This innovative SSR model supports the energy industry in making more informed decisions, proactively mitigating risks, and optimizing resource allocation.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202539021
2025-03-24
2026-02-11

  • From This Site

    /content/papers/10.3997/2214-4609.202539021
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. An, T., Zhang, X., Huo, C., Xue, B., Wang, L. and Pan, C. [2022]. TR-MISR: Multiimage Super-An, T., Zhang, X., Huo, C., Xue, B., Wang, L. and Pan, C. [2022]. TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With Transformers. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 1373–1388.
     [Google Scholar]
  2. Conde, M.V., Choi, UJ., Burchi, M., Timofte, R. [2023]. Swin2SR SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision - ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, 13802, 669–687.
     [Google Scholar]
  3. Cornebise, J., Oršolić, I. and Kalaitzis, F. [2022]. The WorldStrat Dataset: Open High-Resolution Satellite Imagery With Paired Multi-Temporal Low-Resolution [Data set]. Zenodo.
     [Google Scholar]
  4. Dong, C., Loy, C.C., He, K., Tang, X. [2014]. Learning a Deep Convolutional Network for Image Super-Resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, 8692, 184–199.
     [Google Scholar]
  5. Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., Jegou, H., Douze, M. [2021]. LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 12259–12269.
     [Google Scholar]
  6. Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S. and Shah, M. [2022]. Transformers in Vision: A Survey. ACM Comput. Surv. 54, 10s, Article 200, 1–41.
     [Google Scholar]
  7. Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., Timofte, R. [2021]. SwinIR: Image Restoration Using Swin Transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 1833–1844.
     [Google Scholar]
  8. Wang, C., Zhang, X., Yang, W., Wang, G., Zhao, Z., Liu, X. and Lu, B. [2023]. Landsat-8 to Sentinel-2 Satellite Imagery Super-Resolution-Based Multiscale Dilated Transformer Generative Adversarial Networks. Remote Sensing. 15(22):5272.
     [Google Scholar]
  9. Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L. and Zhang, L. [2021]. CvT: Introducing Convolutions to Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 22–31.
     [Google Scholar]
  10. Yang, F., Yang, H., Fu, J., Lu, H. and Guo, B. [2020]. Learning Texture Transformer Network for Image Super-Resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5791–5800.
     [Google Scholar]
  11. Zabalza, M. and Bernardini, A. [2022]. Super-Resolution of Sentinel-2 Images Using a Spectral Attention Mechanism. Remote Sensing. 14(12):2890.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202539021
Loading
Enhancing Satellite Imagery for Energy Applications with Deep Learning-Based Super-Resolution
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202539021
/content/papers/10.3997/2214-4609.202539021
/content/papers/10.3997/2214-4609.202539021
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error