According to one aspect, a computer-implemented method for detecting an earthquake includes detecting vibrations in a trackpad of a computing device using an inductive element and force sensing circuitry of the trackpad and, processing, by a microcontroller of the computing device, the vibrations for detection of an earthquake vibration signal. In response to detecting the earthquake vibration signal, communicating, by the computing device, the earthquake vibration signal to a remote server and receiving, at the computing device, an earthquake alert from the remote server.

The invention describes a method for monitoring vibrations produced by an operating area, comprising the following steps: (El): dividing an operating frequency range into a plurality of frequency sub-ranges; (E2): for each frequency sub-range, defining an associated vibration threshold; (E3): continuously acquiring vibration measurements produced by the operating area; (E4): periodically transmitting vibration data resulting from the vibration measurements, the vibration data being transmitted to a remote server (200) via an LPWAN network; (E5) detecting a vibration event corresponding to at least one vibration threshold being exceeded in the associated frequency sub-range; (E6): when a vibration event is detected, transmitting a warning to the remote server (200) via the LPWAN network.

This disclosure describes systems, methods, and apparatuses for preventing wireline sticking during hydraulic fracturing operations, the system comprising: a sensor coupled to a fracking wellhead, circulating fluid line, or standpipe of a well and configured to convert acoustic vibrations measured in fracking fluid in the wellhead, fluid line, or standpipe into an electrical signal in a time domain; a memory configured to store the electrical signal; a converter configured to access the electrical signal from the memory and convert the time domain electrical signal into a frequency domain spectrum; a machine-learning system configured to classify the current frequency domain spectrum as associated with increasing wireline friction, the machine-learning system trained on previous frequency domain spectra measured during previous wireline operations and previously classified by the machine-learning system; and a user interface configured to return an indication of the increasing wireline friction to an operator of the hydraulic fracturing operations.

Aspects of the technology described herein identify geologic features within seismic data using modern computer analysis. An initial step is the development of training data for the machine classifier. The training data comprises an image of seismic data paired with a label identifying points of interest that the classifier should identify within raw data. Once the training data is generated, a classifier can be trained to identify areas of interest in unlabeled seismic images. The classifier can take the form of a deep neural network, such as a U-net. Aspects of the technology described herein utilize a deep neural network architecture that is optimized to detect broad and flat features in seismic images that may go undetected by typical neural networks in use. The architecture can include a group of layers that perform aspect ratio compression and simultaneous comparison of images across multiple aspect ratio scales.

Techniques for determining a wellbore drilling path includes identifying input seismic data associated with a subterranean zone that includes a wellbore drilling target. The input seismic data includes primary seismic events and multiple seismic events. The input seismic data is processed to remove the multiple seismic events and at least one of the primary seismic events from the input seismic data. An orthogonalization of the processed input seismic data is performed to recover the at least one primary seismic event into a seismic image of the subterranean zone that excludes at least a portion of the multiple seismic events. A wellbore path is determined from a terranean surface toward the wellbore drilling target for a drilling geo-steering system based on the seismic image of the subterranean zone.

A method and apparatus of locating subsurface geohazards in a geographical area that includes: receiving a plurality of seismic trace signals in the geographical area based on a shot gather from a seismic shot source; isolating and stacking the plurality of seismic trace signals to generate a windowed trace signal associated with refraction traces from the seismic shot source; transforming the windowed trace signal to a frequency domain; calculating a low frequency to high frequency ratio for the transformed trace signal; outputting the calculated ratio to a two-dimensional array representing the geographical area at a source location and at a mean receiver location; repeating the steps for a plurality of other shot gathers in the geographical area; and multiplying each source location ratio with one or more mean receiver location ratios on the two-dimensional array to generate a final frequency ratio map.

A mechanical-model based earthquake-induced landslide hazard assessment method in earthquake-prone mountainous area includes: obtaining the cohesion and internal friction angle through a geological map of the study area and a geotechnical physical parameter; obtaining simulated ground motions by combining a pulse-like ground motion effect model and a pulse-like ground motion response model; calculating slope permanent displacement according to the simulated ground motions, the cohesion, the internal friction angle and other parameters; obtaining a statistical relationship between the permanent displacement and a landslide probability according to permanent displacement data derived from historical earthquake-induced landslides and historical strong earthquake records; and predicting earthquake-induced landslide probability according to the slope permanent displacement and the statistical relationship between the permanent displacement and the landslide probability, and quantitatively evaluating earthquake-induced landslide hazard through the earthquake-induced landslide probability.

A computer implemented method for analyzing a reservoir grid modeling a reservoir geological formation is provided in which the reservoir grid corresponds to a 3D grid of cells associated to respective values of at least one geological property. The method includes obtaining a 4D seismic image of the reservoir geological formation. A skeleton of the 4D seismic image is calculated, and the skeleton extends between at least one origin and a plurality of extremities. Each point of the skeleton is associated to a value of the at least one geological property of the reservoir grid. Flow time values are calculated for a fluid flowing from the origin to the extremities along the skeleton, based on the at least one geological property values associated to the points of the skeleton. The reservoir grid is calculated based on the flow time values.

A method of identifying events includes obtaining an acoustic signal from a sensor, determining one or more frequency domain features from the acoustic signal, providing the one or more frequency domain features as inputs to a plurality of event detection models, and determining the presence of one or more events using the plurality of event detection models. The one or more frequency domain features are obtained across a frequency range of the acoustic signal, and at least two of the plurality of event detection models are different.

Provided are a device, method, and computer-readable recording medium for detecting an earthquake in a microelectromechanical system (MEMS)-based auxiliary seismic observation network. The method includes performing detrending of removing a moving average from original acceleration data received from single sensors of an MEMS-based auxiliary seismic observation network to preprocess the acceleration data, calculating a short-term average/long-term average (STA/LTA) value using a filter parameter value specified on the basis of the preprocessed acceleration data, generating an event occurrence message or event end message on the basis of the calculated STA/LTA value and transmitting the event occurrence message or event end message, when the event occurrence message is generated, calculating an earthquake probability through an earthquake detection deep learning model using the preprocessed acceleration data as an input, and analyzing noise by calculating a power spectral density (PSD) from the original acceleration data which is merged at certain intervals.