EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Synthetic AI-Generated Satellite Imagery to Improve Earth Observation-Based Neural Networks

Enrique Albalate-Prieto iD, Noelia Vallez iD, José Luis Espinosa-Aranda iD, Aubrey Dunne, Raúl Barba-Rojas iD

Sensors · 18.06.2026 · 26 (12) · 3895

DOI: 10.3390/s26123895 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.06.2026. Verfasst von Enrique Albalate-Prieto und 4 weiteren Autor:innen. Beteiligte Einrichtung: Ubotica Technologies, DCU Alpha, Old Finglas Road 11, Glasnevin, D11KXN4 Dublin, Ireland. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in satellite technology have significantly progressed, yet acquiring high-quality images with meaningful labels for Earth observation missions remains a costly and time-intensive process. Furthermore, captured scenes frequently exhibit defects such as misaligned color channels, extensive cloud cover, or repetitive patterns in similar environments. Fortunately, the evolution of generative artificial intelligence offers a solution by enabling the creation of realistic synthetic scenes, simulating the characteristics of any targeted imager, and thereby mitigating the scarcity of authentic data. This paper demonstrates the feasibility of transferring knowledge from specialized AI-generated datasets to Earth observation missions. Leveraging a novel dataset of Spanish map tiles, Pix2Pix, CUT, and ControlNet models were implemented to synthesize satellite imagery. To analyze structural and topological generalizability, identical U-Net instances were trained on the resulting collections for building, road, and water segmentation tasks, and subsequently tested on independent authentic imagery. The results reveal a clear decoupling between visual realism and functional utility. Incorporating synthetic samples into hybridized training datasets successfully surpassed the limitations of using real data alone, increasing maximum Dice scores by 0.9% (to 54.1% for buildings), 2.3% (to 38.6% for roads), and 4.1% (to 46.5% for waterbodies). This systematic validation establishes structural-guided synthetic data augmentation as a robust, adaptable strategy for Earth observation applications across diverse sensors and geometric objectives.

Schlagwörter

Stichwörter der Autor:innen

data augmentationearth observationgenerative AIremote sensing

Autor:innen und Institutionen

  • Ubotica Technologies, DCU Alpha, Old Finglas Road 11, Glasnevin, D11KXN4 Dublin, Ireland.
  • E.T.S. Ingeniería Industrial, Avda, Camilo José Cela, S/N, 13071 Ciudad Real, Spain.

ORCID-Profile: Enrique Albalate-Prieto, Noelia Vallez, José Luis Espinosa-Aranda, Raúl Barba-Rojas

Zitieren

APA

Albalate-Prieto, E., Vallez, N., Espinosa-Aranda, J. L., Dunne, A., & Barba-Rojas, R. (2026). Synthetic AI-Generated Satellite Imagery to Improve Earth Observation-Based Neural Networks. Sensors, 26(12), 3895. https://doi.org/10.3390/s26123895

Vancouver

Albalate-Prieto E, Vallez N, Espinosa-Aranda JL, Dunne A, Barba-Rojas R. Synthetic AI-Generated Satellite Imagery to Improve Earth Observation-Based Neural Networks. Sensors. 2026;26(12):3895. doi:10.3390/s26123895

BibTeX
@article{AlbalatePrieto2026,
  author = {Albalate-Prieto, Enrique and Vallez, Noelia and Espinosa-Aranda, José Luis and Dunne, Aubrey and Barba-Rojas, Raúl},
  title = {Synthetic AI-Generated Satellite Imagery to Improve Earth Observation-Based Neural Networks},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3895},
  doi = {10.3390/s26123895}
}
Kostenlos starten →