EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Latent Diffusion Model for Chlorophyll Remote Sensing Spectral Synthesis Integrating Bio-Optical Priors and Band Attention Mechanisms

Jinming Liu, Haoran Zhang, Jianlong Huang, Hanbin Wen, Qinpei Chen, Jiayi Liu, Chaowen Wen, Huiling Tang, Zhaohua Sun

Applied Sciences · 17.04.2026 · 16 (8) · 3892

DOI: 10.3390/app16083892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 17.04.2026. Verfasst von Jinming Liu und 8 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Southern University of Science and Technology Research Project on Optical Intelligent Sensors and Intelligent Algorithms, Wuhan East Lake “Air-Space-Ground-Water” Integrated Observation Project, Guangdong Basic and Applied Basic Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Global freshwater resources face severe water quality degradation, with chlorophyll-a (Chl-a) concentration serving as a critical eutrophication indicator. While deep learning methods enable accurate Chl-a retrieval from remote sensing reflectance (Rrs) spectra, the scarcity of paired Rrs-Chl-a samples limits model generalization and causes overfitting, particularly in optically complex inland waters. To address this data bottleneck, we propose a physics-constrained latent diffusion model for synthesizing high-fidelity paired Rrs-Chl-a data to augment limited training sets for deep learning-based water quality retrieval. Our framework integrates three key innovations: (1) a lightweight variational autoencoder achieving 8.6:1 latent space compression, reducing computational overhead while preserving spectral features; (2) band-selective attention mechanisms targeting chlorophyll-sensitive wavelengths (440, 550, 680, and 700–750 nm) based on bio-optical principles; and (3) physics-guided conditional encoding that captures concentration-dependent spectral responses across oligotrophic to eutrophic regimes. Evaluated on the GLORIA dataset, our model demonstrates superior performance in spectral similarity (0.535), sample diversity (0.072), and distribution matching (Fréchet distance 0.0008) compared to conventional generative models. When applied to data augmentation, synthetic spectra improved downstream Chl-a retrieval from R2= 0.75 to 0.91, reducing RMSE by 39%. This physics-informed generative approach addresses data scarcity in aquatic remote sensing research, supporting global needs for enhanced understanding of inland and coastal water quality dynamics in data-limited regions.

Förderung

  • Southern University of Science and Technology Research Project on Optical Intelligent Sensors and Intelligent Algorithms
  • Wuhan East Lake “Air-Space-Ground-Water” Integrated Observation Project
  • Guangdong Basic and Applied Basic Research Foundation

Zitieren

APA

Liu, J., Zhang, H., Huang, J., Wen, H., Chen, Q., Liu, J., Wen, C., Tang, H., & Sun, Z. (2026). Latent Diffusion Model for Chlorophyll Remote Sensing Spectral Synthesis Integrating Bio-Optical Priors and Band Attention Mechanisms. Applied Sciences, 16(8), 3892. https://doi.org/10.3390/app16083892

Vancouver

Liu J, Zhang H, Huang J, Wen H, Chen Q, Liu J, et al. Latent Diffusion Model for Chlorophyll Remote Sensing Spectral Synthesis Integrating Bio-Optical Priors and Band Attention Mechanisms. Applied Sciences. 2026;16(8):3892. doi:10.3390/app16083892

BibTeX
@article{Liu2026,
  author = {Liu, Jinming and Zhang, Haoran and Huang, Jianlong and Wen, Hanbin and Chen, Qinpei and Liu, Jiayi and Wen, Chaowen and Tang, Huiling and Sun, Zhaohua},
  title = {Latent Diffusion Model for Chlorophyll Remote Sensing Spectral Synthesis Integrating Bio-Optical Priors and Band Attention Mechanisms},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {3892},
  doi = {10.3390/app16083892}
}
Kostenlos starten →