Into the Noddyverse: a massive data store of 3D geological models for machine learning and inversion applications

Abstract

Abstract. Unlike some other well-known challenges such as facial recognition, where machine learning and inversion algorithms are widely developed, the geosciences suffer from a lack of large, labelled data sets that can be used to validate or train robust machine learning and inversion schemes. Publicly available 3D geological models are far too restricted in both number and the range of geological scenarios to serve these purposes. With reference to inverting geophysical data this problem is further exacerbated as in most cases real geophysical observations result from unknown 3D geology, and synthetic test data sets are often not particularly geological or geologically diverse. To overcome these limitations, we have used the Noddy modelling platform to generate 1 million models, which represent the first publicly accessible massive training set for 3D geology and resulting gravity and magnetic data sets (https://doi.org/10.5281/zenodo.4589883, Jessell, 2021). This model suite can be used to train machine learning systems and to provide comprehensive test suites for geophysical inversion. We describe the methodology for producing the model suite and discuss the opportunities such a model suite affords, as well as its limitations, and how we can grow and access this resource.

Sensing prior constraints in deep neural networks for solving exploration geophysical problems

“…Building a structure model typically requires or involves frequent and intensive human interactions to update the model. When structural modeling is implemented through DNNs ( 84 – 86 ), the most convenient means to incorporate human interactions is to embed them into the inputs of the DNNs. Fig.…”

Integration of automatic implicit geological modelling in deterministic geophysical inversion

“…This may be achieved with little development using models representative of families sampled from the geological model space, e.g., from topological analysis (Pakyuz-Charrier et al, 2019) or a similarity distance (Suzuki et al, 2008) to select starting models for inversion. 565 Following the same idea, it may be possible to use deep learning for 3D geological structure inversion results (Jessell et al, 2022;Guo et al, 2021) as starting points to run series of inversions using the method presented here.…”

DeepISMNet: three-dimensional implicit structural modeling with convolutional neural network

“…Although the existing implicit methods can generate various models by perturbing the inputs to characterize uncertainties, they might not explore a broad range of possible geological patterns and structural relationships in nature through a single model suit for stochastic simulation (Jessell et al, 2022). Working on the automation of modeling workflow, our CNN is beneficial for a flexible interpretation of aleatory and epistemic uncertainties (Pirot et al, 2022) by generating diverse modeling realizations instead of one best realization due to its high computational efficiency.…”

“…Considering that the used training samples are still not sufficiently diverse to support modeling complex and unseen geological settings, future works will focus on expanding the training dataset to a broader range of structural geometries and relationships associated with these settings. For example, we can further augment simulation workflow by adding more complex and various features in the structural models or adopting a recently developed 3-D geological modeling dataset (Jessell et al, 2022) in which dikes, plugs, and unconformities are incorporated.…”