An integrated inversion framework for heterogeneous aquifer structure identification with single-sample generative adversarial network
Use this link to cite
http://hdl.handle.net/2183/35245
Except where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 3.0 España
Collections
Metadata
Show full item recordTitle
An integrated inversion framework for heterogeneous aquifer structure identification with single-sample generative adversarial networkAuthor(s)
Date
2022Citation
Zhan, C., Dai, Z., Samper, J., Yin, S., Ershadnia, R., Zhang, X., ... & Soltanian, M. R. (2022). An integrated inversion framework for heterogeneous aquifer structure identification with single-sample generative adversarial network. Journal of Hydrology, 610, 127844. https://doi.org/10.1016/j.jhydrol.2022.127844
Abstract
[Abstract:] Generating reasonable heterogeneous aquifer structures is essential for understanding the physicochemical processes controlling groundwater flow and solute transport better. The inversion process of aquifer structure identification is usually time-consuming. This study develops an integrated inversion framework, which combines the geological single-sample generative adversarial network (GeoSinGAN), the deep octave convolution dense residual network (DOCRN), and the iterative local updating ensemble smoother (ILUES), named GeoSinGAN-DOCRN-ILUES, for more efficiently generating heterogeneous aquifer structures. The performance of the integrated framework is illustrated by two synthetic contaminant experiments. We show that GeoSinGAN can generate heterogeneous aquifer structures with geostatistical characteristics similar to those of the training sample, while its training time is at least 10 times faster than that of typical approaches (e.g., multi-sample-based GAN). The octave convolution layer and multi-residual connection enable the DOCRN to map the heterogeneity structures to the state variable fields (e.g., hydraulic head, concentration distributions) while reducing the computational cost. The results show that the integrated inversion framework of GeoSinGAN and DOCRN can effectively and reasonably generate the heterogeneous aquifer structures.
Keywords
Heterogeneous aquifer structure
Inversion
Generative adversarial network
Residual network
Deep learning
Inversion
Generative adversarial network
Residual network
Deep learning
Description
Versión aceptada de https://doi.org/10.1016/j.jhydrol.2022.127844
Editor version
Rights
Atribución-NoComercial-SinDerivadas 3.0 España