Journal
ADVANCES IN WATER RESOURCES
Volume 177, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.advwatres.2023.104463
Keywords
Convolutional neural network; Hydraulic tomography; Inverse problem; Karstic aquifer; Multi-task learning; Deep Learning
Categories
Ask authors/readers for more resources
This paper proposes a new approach for simultaneously mapping the fracture/conduit network and the equivalent transmissivity of the rock matrix using hydraulic head measurements. A multitask neural network is used to approximate the joint inversion operator that links hydraulic head data to aquifer hydraulic properties. The network consists of two single-task neural networks, one for fracture structure inversion and the other for transmissivity inversion, and is trained with a large database of synthetic aquifer models.
In this paper, we propose a new approach to simultaneously map the fracture/conduit network and the equiv-alent transmissivity of the rock matrix from hydraulic head measurements acquired during pumping/injection tests in fractured aquifers. The algorithm relies on the use of a multitask neural network to directly approximate the joint inversion operator that links hydraulic head data to aquifer hydraulic properties. In which, the hy-draulic head responses are used as input data while the output consists of the fracture structure and matrix transmissivity field. The multitasking is formed by fusing two single-task neural networks, both based on con-volutional encoder-decoder architectures, one of which processes the fracture map inversion and the other the transmissivity map. Training neural network then relies on a large database, which consists of thousands of synthetic aquifers characterized by the presence of the fracture/conduit network and a heterogeneous trans-missivity field attributed to the rock matrix, both randomly generated. In these aquifer models, the groundwater flow equation is solved in a discrete-continuum concept to numerically simulate the hydraulic head responses associated with sequential pumping/injection tests.Multitasking succeeds in reconstructing the fracture architecture and matrix transmissivity field with higher accuracy in comparison to conventional single-task networks. The difference is due to the transfer mechanism involved in the multi-task network, where the information shared between the tasks effectively enhances the accuracy of both reconstructions. However, as with other inversion techniques, the result accuracy depends on the quality and quantity of the hydraulic head data used in the inversion, as well as the prior information involved in featuring the training models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available