Effect of Data Pre-Processing on the Performance of Neural Networks for 1-D Transient Electromagnetic Forward Modeling

• Published in: IEEE access Vol. 9; pp. 34635 - 34646
• Main Authors: Asif, Muhammad Rizwan, Bording, Thue S., Barfod, Adrian S., Grombacher, Denys J., Maurya, Pradip K., Christiansen, Anders V., Auken, Esben, Larsen, Jakob J.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Computational modeling; Computer architecture; Conductivity; Data models; Data normalization; data pre-processing; Errors; forward modelling; inverse modelling; Inverse problems; Logic gates; Model accuracy; Neural networks; Numerical models; Optimization; Performance evaluation; Physical properties; Scaling
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3061761

Geophysical modelling and data inversion are important tools for interpreting the physical properties of Earth's subsurface. Solving the inverse problem involves several computational steps and is generally a time consuming task. Artificial neural networks have the potential to speed up large computations. Such networks provide the means to model the relationship between the inputs and outputs without needing to know the physical model of the underlying problem. There are two main aspects that affect the performance of neural networks: optimization of network architecture and pre-processing of data. In this article, we investigate several traditional pre-processing techniques including the min-max scaling, z-score scaling, and the logarithmic transform scaling, and propose some novel data pre-processing approaches for the 1-D forward modelling of time-domain electromagnetic data based on signal characteristics. We evaluate the performance of the conventional and the proposed pre-processing methods against a 3% relative error metric, which corresponds to the typical data uncertainty, to show that forward data pre-processing has significant effect on the performance of neural networks. The proposed gate-wise min-max scaling achieves the best performance with 96% of gates within a 3% relative error, while the commonly used logarithmic transform results only in 75% of gates within a 3% relative error. We provide insights into how various pre-processing methods affect the performance of these networks and recommend optimal pre-processing strategies that may be used where similar data content is encountered to achieve superior performance. Finally, we show the effect of forward modelling accuracy in inverse modelling.