Deep Learning 3D Sparse Inversion of Gravity Data

Gravity prospecting is an important geophysical method for mineral resource exploration and investigating crustal structures. Based on the importance of this method, we propose a novel method that takes advantage of rock data, using a supervised deep fully convolutional neural network, that generates a sparse subsurface distribution from gravity data. During the data preparation phase, we used the random walk to synthesize diverse geological models, in which each model element has only two choices. During network training, we feed the geological model as labels and their corresponding forward modeling of gravity data as the input, after which the network parameters are learned using the Dice coefficient. During network testing, six general types of 3D models were developed, and corresponding gravity data was entered into a trained network to achieve the prediction results in less time. The statistical analysis of two evaluation metrics showed that our network was highly effective using our proposed data set, wherein the recovered models were characterized by distinct boundaries. Furthermore, our approach was validated using real data obtained from the San Nicolas deposit in central Mexico. Plain Language Summary Gravity inversion is an essential tool for guiding subsurface drilling processes; thus, furthering the exploration of potential ore bodies in a deposit. This study presents an inversion method based on a complex training data set to reconstruct a density model from gravity data using artificial intelligence models.

Automated summary

The study proposes a novel method utilizing rock data and supervised deep fully convolutional neural network for gravity prospecting to generate subsurface distribution. Six general types of 3D models were developed and the network was trained using geological models and corresponding gravity data to achieve efficient prediction results. Statistical analysis showed the effectiveness of the network, which was further validated using real data from the San Nicolas deposit in central Mexico.