EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Differential Approach to the Generation and Quality Assessment of Synthetic Data for Environmental Monitoring

Artem Liubas, Ryskhan Satybaldiyeva, Galina Bovykina, Alexander Kondakov

Data · 11.07.2026 · 11 (7) · 173

DOI: 10.3390/data11070173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data, online erschienen am 11.07.2026. Verfasst von Artem Liubas und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-quality synthetic datasets are critical for environmental monitoring due to the high cost of primary geochemical data collection. However, selection criteria for generative frameworks under small-sample constraints remain poorly defined. This study evaluates two architectures—the deep-learning-based Tabular Variational Autoencoder (TVAE) and the parametric Gaussian copula—using an empirical geochemical dataset (N = 297) of 25 log-transformed elements. Synthesis quality was benchmarked via marginal distribution fidelity (KSComplement), correlation preservation (CorrelationSimilarity), privacy (LogisticDetection), and a composite QualityScore, supplemented by divergence metrics and a rare-earth element (REE+Th+U) subgroup analysis. In this dataset, the Gaussian copula demonstrated superior global correlation preservation (CorrelationSimilarity: 0.9633 vs. 0.9482), particularly for weak-to-moderate dependencies. Conversely, TVAE better replicated marginal distributions (KSComplement: 0.8742 vs. 0.8596), maintained localized correlations (MAD: 0.0728 vs. 0.1196), and showed enhanced privacy (LogisticDetection: 0.5757 vs. 0.3063). These complementary profiles suggest that, for this case study, the Gaussian copula may be preferable for dependency modeling, while TVAE appears better suited for secure open-data dissemination. Further validation on additional datasets is needed to assess the generalizability of these findings.

Förderung

  • Russian Science Foundation

Zitieren

APA

Liubas, A., Satybaldiyeva, R., Bovykina, G., & Kondakov, A. (2026). A Differential Approach to the Generation and Quality Assessment of Synthetic Data for Environmental Monitoring. Data, 11(7), 173. https://doi.org/10.3390/data11070173

Vancouver

Liubas A, Satybaldiyeva R, Bovykina G, Kondakov A. A Differential Approach to the Generation and Quality Assessment of Synthetic Data for Environmental Monitoring. Data. 2026;11(7):173. doi:10.3390/data11070173

BibTeX
@article{Liubas2026,
  author = {Liubas, Artem and Satybaldiyeva, Ryskhan and Bovykina, Galina and Kondakov, Alexander},
  title = {A Differential Approach to the Generation and Quality Assessment of Synthetic Data for Environmental Monitoring},
  journal = {Data},
  year = {2026},
  volume = {11},
  number = {7},
  pages = {173},
  doi = {10.3390/data11070173}
}
Kostenlos starten →