24 August 2021 in Geophysics
Conventional interpretation of airborne electromagnetic data has been conducted by solving the inverse problem. However, with recent advances in machine learning (ML) techniques, a 1D deep neural network inversion that predicts a 1D resistivity model using multifrequency vertical magnetic fields and sensor height information at one location has been applied. Nevertheless, since the final interpretation of this 1D approach relies on connecting 1D resistivity models, 1D ML interpretation has low accuracy for the estimation of an isolated anomaly, as in conventional 1D inversion. Thus, we have developed a 2D interpretation technique that can overcome the limitations of 1D interpretation and consider spatial continuity by using a recurrent neural network (RNN). We generate various 2D resistivity models, calculate the ratio of primary and induced secondary magnetic fields of the vertical direction in ppm scale using a vertical magnetic dipole source, and then train the RNN using the resistivity models and the corresponding electromagnetic (EM) responses. To verify the validity of 2D RNN inversion, we apply the trained RNN to synthetic and field data. Through application of the field data, we demonstrate that the design of the training data set is crucial to improve prediction performance in a 2D RNN inversion. In addition, we investigate changes in the RNN inversion results of field data dependent on the data preprocessing. We demonstrate that using two types of data, logarithmic transformed data and linear-scale data, having different patterns of input information can enhance the prediction performance of the EM inversion results.
21 November 2023 in Geophysics
We develop an integrated workflow that uses deep-learning (DL)-based approaches for processing and inverting airborne transient electromagnetic (ATEM) data. Our novel workflow automates these preprocessing steps and enables real-time inversion in the field. Thus, we develop an entire inversion workflow using three DL networks that cover all steps from preprocessing to imaging. The preprocessing DL network performs interpolation to discard data that are severely noise contaminated and suppress the effects of noise in a late-time channel. We use an inversion DL network and a depth of investigation (DOI) network to generate images of subsurface resistivities exclusively within the DOI range where reliable predictions can be made. To optimize the inversion process, our approach focuses on designing the inversion DL network to simultaneously minimize data misfit and model misfit. By addressing these two aspects, we ensure a more robust outcome in the final resistivity images. The practical applicability of the workflow is verified by comparing the imaging results of the field data with those of conventional inversion and geologic interpretation. Each workflow is nearly automatic and very fast; we expect that our workflow will contribute to the development of real-time imaging software for the ATEM survey, which expands the applications of the ATEM survey in various fields.
12 June 2023 in IEEE Transactions on Geoscience and Remote Sensing
Deep neural networks (DNNs) have recently been used to interpret frequency-domain electromagnetic (EM) data, therefore vast amounts of information can be rapidly interpreted. However, in airborne surveys that include mountainous regions, severe topographic changes distort the EM data and they can lead to unreasonable interpretations. DNN-based inversions that reduce the effects of topographic changes have not yet been proposed whereas some conventional inversion techniques can correct topographic distortions. Since DNN-based interpretation needs various training dataset and its performance depends on the characteristics of training dataset, it is important to generate various AEM data and resistivity model pairs. However, it is almost impossible to derive the EM responses of two-dimensional (2D) or 3D resistivity models incorporating diverse topographic patterns because such models require many variables and computation costs are limited. Therefore, we suggested the pseudo 1D interpretation of EM data which can consider the topographic changes using EM responses and topographic information at three neighboring data points. We include topographic information in DNN training as slope angle between the data points. Compared to conventional inversion, our trained DNN model recovers the synthetic resistivity models more reasonably. In addition, we used the trained DNN model to evaluate a real AEM dataset from south-central Alaska. The trained DNN provided reasonable interpretation results despite that the data were acquired at mountainous area with rough topography. Since the trained DNN model can provide predictions rapidly, the interpretation time was drastically reduced. We believe that this research can increase the practical field applicability of AEM survey.
30 June 2025 in Journal of the Korean Society of Mineral and Energy Resources Engineers
The development of artificial intelligence (AI) technology following the Fourth Industrial Revolution has driven innovation across various industries, significantly altering economic and social structures. The advancement of AI models has heightened the demand for high-performance semiconductors capable of extensive computation, making them critical components in data centers, autonomous vehicles, 5G/6G telecommunications, cloud computing, and other sectors. Consequently, the semiconductor industry's rapid growth has emphasized the necessity of securing stable supply chains for essential minerals and raw materials required for semiconductor manufacturing. However, recent supply chain risks have intensified due to factors such as China's restrictions on critical mineral exports, disruptions caused by the Russia-Ukraine conflict, tightening ESG regulations, and global fluctuations in raw material prices. This study identifies key minerals essential to the semiconductor industry and analyzes the associated supply chain risks, providing foundational data to ensure the stable operation of the semiconductor sector, a critical national industry.
7 January 2025 in Geophysics
The assessment of manmade structures such as dams and embankments is vital for protecting property and human life. Consequently, regular and accurate geophysical monitoring of these infrastructures is widely practiced. However, the iterative numerical procedures typically used for geophysical data inversion can become computationally intensive, especially in resource-constrained field surveys. Recent advances in machine learning, particularly deep neural networks (DNNs), offer an alternative solution by significantly reducing the time required to generate subsurface images once the network has been trained. In this study, we develop a DNN-based interpretation method for frequency-domain electromagnetic (FDEM) data. Beyond producing inverted images of the subsurface, our approach also estimates uncertainty by comparing the predicted electromagnetic (EM) response with the original input data. We highlight a key pitfall in traditional network architectures: if a data predictor is trained jointly and from scratch alongside the model predictor, it may replicate the input data — giving the misleading impression that every inversion is highly accurate. To address this, we develop a transfer learning-based training procedure where a pretrained data predictor’s weights are fixed. This ensures that the predicted EM response genuinely reflects the inverted subsurface model rather than reproducing the input data. We validate our method using FDEM data collected at the Saemangeum seawall in South Korea, comparing the DNN inversion results with those from conventional inversion. Our technique successfully detects potential hazards in the seawall while also providing a practical measure of reliability for the interpreted results.
3 January 2025 in Geophysics
As the world’s dams and seawalls age, there has been increasing attention toward the safety of these structures and monitoring of their condition using various geophysical methods. However, assessing seaward slopes, which are directly impacted by waves and tides and a seawater-filled riprap stone deposit structure, has been challenging due to the highly conductive environment and the difficulty in installing contact equipment. This study examines the feasibility of using electromagnetic (EM) surveys to monitor seawall slopes by analyzing and interpreting multifrequency EM data measured across a two-year period along the seawall slope of the Saemangeum Seawall in South Korea, which is recognized as the world’s longest seawall. The repeatability of data measured at the same survey line across the two years substantiates the reliability of EM survey data. The field data are inverted using a 2.5D regularized Gauss-Newton method. The EM responses calculated from the inverted resistivity model closely mirror the field data. The inversion results consistently indicate the presence of an isolated conductive anomaly with seawater resistivity below the survey line on the seaward slope. This suggests scouring erosion by seawater and affirms the applicability of the EM surveys to seaward slope monitoring. In addition, the EM responses are affected significantly by sea level changes during the survey; these variations are quantified in this study. Thus, our results indicate the effectiveness of the EM method in monitoring the seaward slope to assess the safety of seawalls and provide a comprehensive overview of the entire data analysis and inversion processes, as a valuable reference for those using EM technology in their work.