Work

The importance of realistic noise characteristics in neural network inversion of airborne electromagnetic data

Year: 2026

Type: article

Abstract: SUMMARY Deep learning methods such as neural networks offer a rapid alternative to geophysical inversion and are increasingly applied to airborne electromagnetic (AEM) data for a range of earth science problems. Such networks rely on both the network architecture as well as suitable training data sets to produce realistic earth resistivity models. Here we develop a convolutional neural network to invert AEM data and pay particular attention to the characteristics of the training data set. As well as covering a realistic range of subsurface property distributions, the training data must emulate the noise and data gap characteristics of the target survey data. We find neural networks trained on noise free data, while performing very well on validation data, perform poorly on real world data, often inducing geologically unrealistic artefacts in the resistivity model. Conversely, training data conditioned with noise and data gap characteristics appropriate for the survey of interest, fit the validation data less well, but produce fewer artefacts when applied to survey data. Choice of loss function metric and data normalization method is important and may vary between surveys. Despite strong advances in neural network design, developing training data with broad enough characteristics to be generalized across many surveys and data acquisition platforms remains an important challenge.

Source: Geophysical Journal International

DOI: 10.1093/gji/ggag344

Authors: Alison Kirkby, Craig Miller

Institution: Earth Sciences New Zealand

Language: English

Topic: Geophysical and Geoelectrical Methods

Subfield: Geophysics

Field: Earth and Planetary Sciences

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,416

Funder: Ministry of Business, Innovation and Employment