Though the volume of geophysical data is large, available labels are scarce. The lack of training samples in geophysical applications compared to those in other industries is the most critical of these challenges. The main difficulties include a shortage of training samples, low signal-to-noise ratios, and strong nonlinearity. What are some difficulties in applying deep learning in the geophysical community?ĭespite the success of DL in some geophysical applications, such as earthquake detectors or pickers, its use as a tool for most practical geophysics is still in its infancy.ĭespite the success of deep learning in some geophysical applications its use as a tool for most practical geophysics is still in its infancy. Traditional methods cannot handle some cases, such as multimodal data fusion and inversion.For example, geophysical inversion requires good initial values and high accuracy modeling and suffers from local minimization. Traditional methods have difficulties and bottlenecks.Traditional methods are time-consuming and require intensive human labor and expert knowledge, such as in the first-arrival selection and velocity selection in exploration geophysics.In our review article, we suggest a roadmap for applying DL to different geophysical tasks, divided into three levels: For instance, on the Stanford earthquake data set, the earthquake detection accuracy improved to 100 percent compared to 91 percent accuracy with the traditional method. In your opinion, what are some of the most exciting opportunities for deep learning applications in geophysics?ĭL has already provided some surprising results in geophysics. Fifth, DL can be used for discovering physical concepts, such as the solar system is heliocentric, and may even provide discoveries that are not yet known. Fourth, DL can provide a high computational efficiency after the training is complete thus enabling the characterization of Earth with a high resolution. Third, an accurate description of the physical model is not required, which is useful when the physical model is not known partially. Second, DL can utilize historical data and experience which are usually not considered in traditional methods. First, DL can handle big data naturally where it causes a computational burden in traditional methods. Traditional methods suffer from inaccurate modeling and computational bottlenecks with large-scale and complex geophysical systems DL could be helpful to solve this. What advantages does deep learning have over traditional methods in geophysical data processing and analysis? DL can be used in other fields in a similar manner. Then the trained neural network can predict locations of new coming seismic events. The parameters in the neural network are optimized to minimize the mismatch between the output of the neural network and the true locations. Therefore, the waveforms and locations serve as the input and output of a neural network. The historical records of seismic stations contain useful information such as the waveforms of an earthquake and corresponding locations. By providing a large database, you can train a DL architecture to perform geophysical inferring. Credit: Yu and Ma, Figure 4aĭL has the potential to be applied to most areas of geophysics. How can deep learning be used by the geophysical community?ĭeep learning-based geophysical applications. In terms of information science, DL extracts useful information from a large set of redundant data. In terms of mathematics, DL is a high-dimensional nonlinear optimization problem DL constructs a mapping from the input samples to the output labels. In terms of biology, DL is a bionic approach imitating the neurons in the human brain a computer can learn knowledge as well as draw inferences like a human. “Deep” means the system consists of a structure with multiple layers.ĭL can be understood from different angles. How would you describe “deep learning” in simple terms to a non-expert?ĭeep learning (DL) optimizes the parameters in a system, a so-called “neural network,” by feeding it a large amount of training data. We asked the authors some questions about the connection between deep learning and the geosciences. A new article in Reviews of Geophysics examines one popular AI technique, deep learning (DL). As artificial intelligence (AI) continues to develop, geoscientists are interested in how new AI developments could contribute to geophysical discoveries.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |