Details

Autor(en) / Beteiligte

• Zhan, Chuanjun
• Dai, Zhenxue
• Samper, Javier
• Yin, Shangxian
• Ershadnia, Reza
• Zhang, Xiaoying
• Wang, Yanwei
• Yang, Zhijie
• Luan, Xiaoyan
• Soltanian, Mohamad Reza

Titel

An integrated inversion framework for heterogeneous aquifer structure identification with single-sample generative adversarial network

Ist Teil von

• Journal of hydrology (Amsterdam), 2022-07, Vol.610, p.127844, Article 127844

Ort / Verlag

Elsevier B.V

Erscheinungsjahr

2022

Link zum Volltext

Quelle

Access via ScienceDirect (Elsevier)

Beschreibungen/Notizen

• •An aquifer structure inversion framework is developed based on the single-sample generative adversarial network.•The training speed of the aquifer structure generation with the framework is more than ten times less than that of multi-sample-based models.•Heterogeneous aquifer structures can be identified reasonably by assimilating flow and transport response data. 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.