BACKGROUND The solid Earth, oceans, and atmosphere together form a complex interacting geosystem. Processes relevant to understanding Earth’s geosystem behavior range in spatial scale from the atomic to the planetary, and in temporal scale from milliseconds to billions of years. Physical, chemical, and biological processes interact and have substantial influence on this complex geosystem, and humans interact with it in ways that are increasingly consequential to the future of both the natural world and civilization as the finiteness of Earth becomes increasingly apparent and limits on available energy, mineral resources, and fresh water increasingly affect the human condition. Earth is subject to a variety of geohazards that are poorly understood, yet increasingly impactful as our exposure grows through increasing urbanization, particularly in hazard-prone areas. We have a fundamental need to develop the best possible predictive understanding of how the geosystem works, and that understanding must be informed by both the present and the deep past. This understanding will come through the analysis of increasingly large geo-datasets and from computationally intensive simulations, often connected through inverse problems. Geoscientists are faced with the challenge of extracting as much useful information as possible and gaining new insights from these data, simulations, and the interplay between the two. Techniques from the rapidly evolving field of machine learning (ML) will play a key role in this effort. ADVANCES The confluence of ultrafast computers with large memory, rapid progress in ML algorithms, and the ready availability of large datasets place geoscience at the threshold of dramatic progress. We anticipate that this progress will come from the application of ML across three categories of research effort: (i) automation to perform a complex prediction task that cannot easily be described by a set of explicit commands; (ii) modeling and inverse problems to create a representation that approximates numerical simulations or captures relationships; and (iii) discovery to reveal new and often unanticipated patterns, structures, or relationships. Examples of automation include geologic mapping using remote-sensing data, characterizing the topology of fracture systems to model subsurface transport, and classifying volcanic ash particles to infer eruptive mechanism. Examples of modeling include approximating the viscoelastic response for complex rheology, determining wave speed models directly from tomographic data, and classifying diverse seismic events. Examples of discovery include predicting laboratory slip events using observations of acoustic emissions, detecting weak earthquake signals using similarity search, and determining the connectivity of subsurface reservoirs using groundwater tracer observations. OUTLOOK The use of ML in solid Earth geosciences is growing rapidly, but is still in its early stages and making uneven progress. Much remains to be done with existing datasets from long-standing data sources, which in many cases are largely unexplored. Newer, unconventional data sources such as light detection and ranging (LiDAR), fiber-optic sensing, and crowd-sourced measurements may demand new approaches through both the volume and the character of information that they present. Practical steps could accelerate and broaden the use of ML in the geosciences. Wider adoption of open-science principles such as open source code, open data, and open access will better position the solid Earth community to take advantage of rapid developments in ML and artificial intelligence. Benchmark datasets and challenge problems have played an important role in driving progress in artificial intelligence research by enabling rigorous performance comparison and could play a similar role in the geosciences. Testing on high-quality datasets produces better models, and benchmark datasets make these data widely available to the research community. They also help recruit expertise from allied disciplines. Close collaboration between geoscientists and ML researchers will aid in making quick progress in ML geoscience applications. Extracting maximum value from geoscientific data will require new approaches for combining data-driven methods, physical modeling, and algorithms capable of learning with limited, weak, or biased labels. Funding opportunities that target the intersection of these disciplines, as well as a greater component of data science and ML education in the geosciences, could help bring this effort to fruition. The list of author affiliations is available in the full article online.

Machine learning for data-driven discovery in solid Earth geoscience

This article provides an overview of current applications of machine learning (ML) in seismology. ML techniques are becoming increasingly widespread in seismology, with applications ranging from identifying unseen signals and patterns to extracting features that might improve our physical understanding. The survey of the applications in seismology presented here serves as a catalyst for further use of ML. Five research areas in seismology are surveyed in which ML classification, regression, clustering algorithms show promise: earthquake detection and phase picking, earthquake early warning (EEW), ground‐motion prediction, seismic tomography, and earthquake geodesy. We conclude by discussing the need for a hybrid approach combining data‐driven ML with traditional physical modeling.

Machine Learning in Seismology: Turning Data into Insights

Seismology is experiencing rapid growth in the quantity of data, which has outpaced the development of processing algorithms. Earthquake detection—identification of seismic events in continuous data—is a fundamental operation for observational seismology. We developed an efficient method to detect earthquakes using waveform similarity that overcomes the disadvantages of existing detection methods. Our method, called Fingerprint And Similarity Thresholding (FAST), can analyze a week of continuous seismic waveform data in less than 2 hours, or 140 times faster than autocorrelation. FAST adapts a data mining algorithm, originally designed to identify similar audio clips within large databases; it first creates compact “fingerprints” of waveforms by extracting key discriminative features, then groups similar fingerprints together within a database to facilitate fast, scalable search for similar fingerprint pairs, and finally generates a list of earthquake detections. FAST detected most (21 of 24) cataloged earthquakes and 68 uncataloged earthquakes in 1 week of continuous data from a station located near the Calaveras Fault in central California, achieving detection performance comparable to that of autocorrelation, with some additional false detections. FAST is expected to realize its full potential when applied to extremely long duration data sets over a distributed network of seismic stations. The widespread application of FAST has the potential to aid in the discovery of unexpected seismic signals, improve seismic monitoring, and promote a greater understanding of a variety of earthquake processes.

https://advances.sciencemag.org/content/advances/1/11/e1501057.full.pdf

Earthquake detection through computationally efficient similarity search.

Recently deep learning (DL), as a new data-driven technique compared to conventional approaches, has attracted increasing attention in geophysical community, resulting in many opportunities and challenges. DL was proven to have the potential to predict complex system states accurately and relieve the “curse of dimensionality” in large temporal and spatial geophysical applications. We address the basic concepts, state-of-the-art literature, and future trends by reviewing DL approaches in various geosciences scenarios. Exploration geophysics, earthquakes, and remote sensing are the main focuses. More applications, including Earth structure, water resources, atmospheric science, and space science, are also reviewed. Additionally, the difficulties of applying DL in the geophysical community are discussed. The trends of DL in geophysics in recent years are analyzed. Several promising directions are provided for future research involving DL in geophysics, such as unsupervised learning, transfer learning, multimodal DL, federated learning, uncertainty estimation, and active learning. A coding tutorial and a summary of tips for rapidly exploring DL are presented for beginners and interested readers of geophysics.

https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2021RG000742

Deep learning for geophysics: Current and future trends

Seismic reflection data were used to monitor the progress of an in‐situ combustion, enhanced oil recovery process. Three sets of three‐dimensional (3-D) data were collected during a one‐year period in order to map the extent and directions of propagation in time. Acquisition and processing parameters were identical for each survey so that direct one‐to‐one comparison of traces could be made. Seismic attributes were calculated for each common‐depth‐point data set, and in a unique application of seismic reflection data, the preburn attributes were subtracted from the midburn and postburn attributes. The resulting “difference volumes” of 3-D seismic data showed anomalies which were the basis for the interpretation shown in this case study. Profiles and horizon slices from the data sets clearly show the initiation and development of a bright spot in the reflection from the top of the reservoir and a dim spot in the reflection from a limestone below it. Interpretation of these anomalies is supported by informa...

AAPG Memoir 42 and SEG Investigations in Geophysics, No. 9, Chapter 9 (Case Histories of Three-Dimensional Seismic Surveys) -- Case History 4: Three-Dimensional Seismic Monitoring of An Enhanced Oil Recovery Process

When an earthquake occurs, seismologists want to use recorded seismograms to infer its location, magnitude and source-focal mechanism as quickly as possible. If such information could be determined immediately, timely evacuations and emergency actions could be undertaken to mitigate earthquake damage. Current advanced methods can report the initial location and magnitude of an earthquake within a few seconds, but estimating the source-focal mechanism may require minutes to hours. Here we present an earthquake search engine, similar to a web search engine, that we developed by applying a computer fast search method to a large seismogram database to find waveforms that best fit the input data. Our method is several thousand times faster than an exact search. For an Mw 5.9 earthquake on 8 March 2012 in Xinjiang, China, the search engine can infer the earthquake's parameters in <1 s after receiving the long-period surface wave data.

/pdf/real-time-earthquake-monitoring-using-a-search-engine-method-5egbv1jr2z.pdf

Real-time earthquake monitoring using a search engine method.

The accurate and automated determination of earthquake locations is still a challenging endeavor. However, such information is critical for monitoring seismic activity and assessing potential hazards in real time. Recently, a convolutional neural network was applied to detect earthquakes from single-station waveforms and approximately map events across several large surface areas. In this study, we locate 194 earthquakes induced during oil and gas operations in Oklahoma, USA, within an error range of approximately 4.9 km on average to the epicenter and 1.0 km to the depth in catalogs with data from 30 network stations by applying the fully convolutional network. The network is trained by 1,013 historic events, and the output is a 3D volume of the event location probability in the Earth. The trained system requires approximately one hundredth of a second to locate an event without the need for any velocity model or human interference.

/pdf/locating-earthquakes-with-a-network-of-seismic-stations-via-2zy32nd9um.pdf

Locating earthquakes with a network of seismic stations via a deep learning method.

The accurate and automated determination of small earthquake (ML   ML ≥ 0.5), and the output is a 3D volume of the event location probability in the Earth. The prediction results suggest that the mean epicenter errors of the testing events (ML ≥ 1.5) vary from 3.7 to 6.4 km, meeting the need of the traffic light system in Oklahoma, but smaller events (ML = 1.0, 0.5) show errors larger than 11 km. Synthetic tests suggest that the accuracy of ground truth from catalog affects the prediction results. Correct ground truth leads to a mean epicenter error of 2.0 km in predictions, but adding a mean location error of 6.3 km to ground truth causes a mean epicenter error of 4.9 km. The automated system is able to distinguish certain interfered events or events out of the monitoring zone based on the output probability estimate. It requires approximately one hundredth of a second to locate an event without the need for any velocity model or human interference.

/pdf/locating-induced-earthquakes-with-a-network-of-seismic-59tl9dbt7r.pdf

Locating induced earthquakes with a network of seismic stations in Oklahoma via a deep learning method.


 It is of great significance and a great challenge to quickly and effectively monitor subsurface time-lapse velocities in the earth. Over the past few decades, regularized iterative methods, such as traveltime and waveform inversions, have been presented to monitor velocity changes. Due to high processing cost, these iterative methods have been hardly employed in practice to investigate the subsurface velocity changes in real time. In this study, we propose a new time-lapse imaging technique that effectively eliminates these limitations and directly produces accurate velocity changes from the time-lapse data. The approach uses a fully convolutional neural network (FCN) to perform the inverse problem. The network architecture consists of a contracting path to quickly extract the features of waveform data and a symmetric expanding path to yield an accurate velocity model. With the known baseline velocity and data, we cast a mapping between time-lapse data and target velocity changes via the proposed FCN algorithm. Along with the observed time-lapse data, this mapping will generate a predictive estimation of the target velocity changes. We demonstrate the efficiency and accuracy of our approach in three 2D synthetic tests. The proposed technique is able to invert the velocity changes successfully with much higher efficiency than the regular double-difference full waveform inversion.

Time-lapse velocity imaging via deep learning

Automatic detection and location are the fundamental demands for microseismic or passive seismic monitoring. With the recent advances in artificial intelligence, we attempt to explore the efficiency of deep learning algorithms to reliably detect and locate microseismic event. We present two convolutional neural networks (CNNs) for the event detection and location. The detection neural network is designed to correctly truncate the time window of the microseismic events with both P and S waves. We utilize the microsesimic events with known locations to train the location neural network. We expect that the location neural network extract the relationship between the waveform feature and the event location, and predict the locations for the truncated waveforms from the detection neural network. We construct an automatic processing scheme by combining the detection and location neural networks for the continuous records. We apply the method into the field datasets, and the results show that the time window of a complete event can be detected effectively even though the CNN model is trained with a small number of samples. In addition, the location distribution predicted by the neural network matches the results from the traditional manual method.

Xiong Zhang

Papers

Real-time earthquake monitoring using a search engine method.

Locating earthquakes with a network of seismic stations via a deep learning method.

Locating induced earthquakes with a network of seismic stations in Oklahoma via a deep learning method.

Time-lapse velocity imaging via deep learning

Automatic microseismic detection and location via the deep-convolutional neural network