scholarly journals Application of Geologically Constrained Machine Learning Method in Characterizing Paleokarst Reservoirs of Tarim Basin, China

Water ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1765
Author(s):  
Wei Xin ◽  
Fei Tian ◽  
Xiaocai Shan ◽  
Yongjian Zhou ◽  
Huazhong Rong ◽  
...  
Keyword(s):  
Machine Learning ◽  
Seismic Data ◽  
Machine Learning Algorithms ◽  
Seismic Exploration ◽  
Seismic Signals ◽  
Time Frequency ◽  
Mode Decomposition ◽  
New Perspective ◽  
Geological Constraints ◽  
Frequency Features

As deep carbonate fracture-cavity paleokarst reservoirs are deeply buried and highly heterogeneous, and the responded seismic signals have weak amplitudes and low signal-to-noise ratios. Machine learning in seismic exploration provides a new perspective to solve the above problems, which is rapidly developing with compelling results. Applying machine learning algorithms directly on deep seismic signals or seismic attributes of deep carbonate fracture-cavity reservoirs without any prior knowledge constraints will result in wasted computation and reduce the accuracy. We propose a method of combining geological constraints and machine learning to describe deep carbonate fracture-cavity paleokarst reservoirs. By empirical mode decomposition, the time–frequency features of the seismic data are obtained and then a sensitive frequency is selected using geological prior constraints, which is input to fuzzy C-means cluster for characterizing the reservoir distribution. Application on Tahe oilfield data shows the potential of highlighting subtle geologic structures that might otherwise escape unnoticed by applying machine learning directly.

Refinement Analysis for Time-Frequency Characteristic of Blasting Seismic Exploration Signals

2014 ◽  
Vol 926-930 ◽  
pp. 3541-3544
Author(s):  
Ming Shou Zhong ◽  
Quan Min Xie ◽  
Tao Guo ◽  
Xing Bo Xie ◽  
Hao Quan Liu ◽  
...  
Keyword(s):  
Wavelet Transformation ◽  
Seismic Exploration ◽  
Blasting Vibration ◽  
Seismic Signals ◽  
Analysis Method ◽  
Effect Analysis ◽  
Time Frequency ◽  
Vibration Effect ◽  
New Research ◽  
Frequency Features

Accurate extraction of time-frequency features for blasting vibration signals has great significance for blasting seismic exploration, so time-frequency analysis method for blasting seismic signals was researched based on frequency slice wavelet transformation technology, and separation and extraction of time-frequency features were were successfully achieved. Frequency slice wavelet transformation can be introduced into blasting vibration effect analysis fields, it can provide a new research idea for refinement analysis of time-frequency characteristics, and it also has great significance for improving the effect of blasting seismic exploration in China.

scholarly journals Hierarchical Tactile Sensation Integration from Prosthetic Fingertips Enables Multi-Texture Surface Recognition

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4324
Author(s):  
Moaed A. Abd ◽  
Rudy Paul ◽  
Aparna Aravelli ◽  
Ou Bai ◽  
Leonel Lagos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Sliding Contact ◽  
Tactile Sensation ◽  
Support Vector ◽  
Textured Surfaces ◽  
K Nearest Neighbor ◽  
Tactile Sensors ◽  
Time Frequency

Multifunctional flexible tactile sensors could be useful to improve the control of prosthetic hands. To that end, highly stretchable liquid metal tactile sensors (LMS) were designed, manufactured via photolithography, and incorporated into the fingertips of a prosthetic hand. Three novel contributions were made with the LMS. First, individual fingertips were used to distinguish between different speeds of sliding contact with different surfaces. Second, differences in surface textures were reliably detected during sliding contact. Third, the capacity for hierarchical tactile sensor integration was demonstrated by using four LMS signals simultaneously to distinguish between ten complex multi-textured surfaces. Four different machine learning algorithms were compared for their successful classification capabilities: K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and neural network (NN). The time-frequency features of the LMSs were extracted to train and test the machine learning algorithms. The NN generally performed the best at the speed and texture detection with a single finger and had a 99.2 ± 0.8% accuracy to distinguish between ten different multi-textured surfaces using four LMSs from four fingers simultaneously. The capability for hierarchical multi-finger tactile sensation integration could be useful to provide a higher level of intelligence for artificial hands.

Machine Learning analysis of seismic signals recorded at Stromboli Volcano

2021 ◽  
Author(s):  
Darius Fenner ◽  
Georg Rümpker ◽  
Horst Stöcker ◽  
Megha Chakraborty ◽  
Wei Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Seismic Data ◽  
Noise Level ◽  
Volcanic Eruptions ◽  
Time Varying ◽  
Seismic Signals ◽  
Machine Learning Model ◽  
Automatic Adaptation ◽  
Consistent Manner ◽  
Recent Developments

<p>At Stromboli, minor volcanic eruptions occur at time intervals of approximately five minutes on average, making it one of the most active volcanoes worldwide. In addition to these mostly harmless events, there are also stronger eruptions and paroxysms which pose a serious threat to residents and tourists. In light of recent developments in Machine Learning, this study attempts to apply these new tools for the analysis of the time-varying volcanic eruptions at Stromboli. As input for the Machine-Learning approach, we use continuous recordings of seismic signals from two seismometers on the island. The data is available from IRIS  and includes records starting in 2012 up to the present. </p><p>One primary challenge is to label and classify the data, i.e., to discriminate events of interest from noise. The variety of signal-appearance in the recorded data is wide, in some periods the events are clearly distinguishable from noise whereas, in other cases relevant events are obscured by the high noise level. To enable the event-detection in all cases, we developed the following algorithm: in the first step, the seismic data is pre-processed with an STA/LTA-Filter, which allows detection of events based on a prominence threshold. However, due to the diversity of signal patterns, a fixed set of hyperparameters (STA- and LTA-window length, prominence threshold, correlation coefficient) fails to reliably extract the relevant events in a consistent manner. Therefore, the (time-varying) noise level of the recordings is used as an additional key indicator. After this, the hyperparameters are optimized. The automatic adaptation is then used for labeling the continuous seismic data.</p><p>After extracting the events based on this approach, a machine learning model is trained to analyze the recordings for possible patterns in the interval times and the event amplitudes. This study is expected to provide constraints on the possibility to detect complex time-dependent patterns of the eruption history at Stromboli.</p>

A comparison of deep machine learning and Monte Carlo methods for facies classification from seismic data

Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. WA41-WA52 ◽  
Author(s):  
Dario Grana ◽  
Leonardo Azevedo ◽  
Mingliang Liu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Monte Carlo ◽  
Monte Carlo Methods ◽  
Seismic Data ◽  
Transition Probabilities ◽  
Machine Learning Algorithms ◽  
Data Set ◽  
Facies Classification ◽  
The Neural Network

Among the large variety of mathematical and computational methods for estimating reservoir properties such as facies and petrophysical variables from geophysical data, deep machine-learning algorithms have gained significant popularity for their ability to obtain accurate solutions for geophysical inverse problems in which the physical models are partially unknown. Solutions of classification and inversion problems are generally not unique, and uncertainty quantification studies are required to quantify the uncertainty in the model predictions and determine the precision of the results. Probabilistic methods, such as Monte Carlo approaches, provide a reliable approach for capturing the variability of the set of possible models that match the measured data. Here, we focused on the classification of facies from seismic data and benchmarked the performance of three different algorithms: recurrent neural network, Monte Carlo acceptance/rejection sampling, and Markov chain Monte Carlo. We tested and validated these approaches at the well locations by comparing classification predictions to the reference facies profile. The accuracy of the classification results is defined as the mismatch between the predictions and the log facies profile. Our study found that when the training data set of the neural network is large enough and the prior information about the transition probabilities of the facies in the Monte Carlo approach is not informative, machine-learning methods lead to more accurate solutions; however, the uncertainty of the solution might be underestimated. When some prior knowledge of the facies model is available, for example, from nearby wells, Monte Carlo methods provide solutions with similar accuracy to the neural network and allow a more robust quantification of the uncertainty, of the solution.

White noise attenuation of seismic trace by integrating variational mode decomposition with convolutional neural network

Geophysics ◽  
2019 ◽  
Vol 84 (5) ◽  
pp. V307-V317 ◽  
Author(s):  
Hao Wu ◽  
Bo Zhang ◽  
Tengfei Lin ◽  
Fangyu Li ◽  
Naihao Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
White Noise ◽  
Seismic Data ◽  
Prior Information ◽  
Training Procedure ◽  
Noise Attenuation ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Mode Decomposition

Seismic noise attenuation is an important step in seismic data processing. Most noise attenuation algorithms are based on the analysis of time-frequency characteristics of the seismic data and noise. We have aimed to attenuate white noise of seismic data using the convolutional neural network (CNN). Traditional CNN-based noise attenuation algorithms need prior information (the “clean” seismic data or the noise contained in the seismic) in the training process. However, it is difficult to obtain such prior information in practice. We assume that the white noise contained in the seismic data can be simulated by a sufficient number of user-generated white noise realizations. We then attenuate the seismic white noise using the modified denoising CNN (MDnCNN). The MDnCNN does not need prior clean seismic data nor pure noise in the training procedure. To accurately and efficiently learn the features of seismic data and band-limited noise at different frequency bandwidths, we first decomposed the seismic data into several intrinsic mode functions (IMFs) using variational mode decomposition and then apply our denoising process to the IMFs. We use synthetic and field data examples to illustrate the robustness and superiority of our method over the traditional methods. The experiments demonstrate that our method can not only attenuate most of the white noise but it also rejects the migration artifacts.

scholarly journals Detection of Startle-Type Epileptic Seizures using Machine Learning Technique

2018 ◽  
Vol 05 (02) ◽  
pp. 092-098
Author(s):  
Pushpa Balakrishnan ◽  
S. Hemalatha ◽  
Dinesh Nayak Shroff Keshav
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Brain Activity ◽  
Epileptic Seizures ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Absolute Deviation ◽  
Mode Decomposition ◽  
Life Threatening

Abstract Background Epilepsy is a common neurological disorder characterized by seizures and can lead to life-threatening consequences. The electroencephalogram (EEG) is a diagnostic test used to analyze brain activity in various neurological conditions including epilepsy and interpreted by the clinician for appropriate diagnosis. However, the process of EEG analysis for diagnosis can be automated using machine learning algorithms (MLAs) to aid the clinician. The objective of the study was to test different algorithms that could be used for the detection of seizures. Materials and Methods Video EEG (vEEG) was collected from subjects diagnosed to have episodes of seizures. The epilepsy dataset thus obtained was subjected to empirical mode decomposition (EMD) and the signal was decomposed into intrinsic mode functions (IMFs). The first five levels of decomposition were considered for analysis as per the established protocol. Statistical features such as interquartile range (IQR), entropy, and mean absolute deviation (MAD) were extracted from these IMFs. Results In this study, different MLAs such as nearest neighbor (NN), naïve Bayes (NB), and support vector machines (SVMs) were used to distinguish between normal (interictal) and abnormal (ictal) states. The demonstrated accuracy rates were 97.32% for NN, 99.02% for NB, and 93.75% for SVM. Conclusion Based on this accuracy and sensitivity, it may be posited that the NB classifier provides significantly better results for the detection of abnormal signals indicating that MLA can detect the seizure with better accuracy.

scholarly journals ELM and K-nn machine learning in classification of breath sounds signals

2020 ◽  
Vol 10 (4) ◽  
pp. 3528
Author(s):  
Z. Neili ◽  
M. Fezari ◽  
A. Redjati
Keyword(s):  
Machine Learning ◽  
Binary Classification ◽  
Machine Learning Algorithms ◽  
Permutation Entropy ◽  
Intrinsic Mode Functions ◽  
Electronic Stethoscope ◽  
Mode Decomposition ◽  
Breath Sounds ◽  
Learning Machine

The acquisition of Breath sounds (BS) signals from a human respiratory system with an electronic stethoscope, provide and offer prominent information which helps the doctors to diagnosis and classification of pulmonary diseases. Unfortunately, this BS signals with other biological signals have a non-stationary nature according to the variation of the lung volume, and this nature makes it difficult to analyze and classify between several diseases. In this study, we were focused on comparing the ability of the extreme learning machine (ELM) and k-nearest neighbour (K-nn) machine learning algorithms in the classification of adventitious and normal breath sounds. To do so, the empirical mode decomposition (EMD) was used in this work to analyze BS, this method is rarely used in the breath sounds analysis. After the EMD decomposition of the signals into Intrinsic Mode Functions (IMFs), the Hjorth descriptors (Activity) and Permutation Entropy (PE) features were extracted from each IMFs and combined for classification stage. The study has found that the combination of features (activity and PE) yielded an accuracy of 90.71%, 95% using ELM and K-nn respectively in binary classification (normal and abnormal breath sounds), and 83.57%, 86.42% in multiclass classification (five classes).

Successful leveraging of image processing and machine learning in seismic structural interpretation: A review

2018 ◽  
Vol 37 (6) ◽  
pp. 451-461 ◽  
Author(s):  
Zhen Wang ◽  
Haibin Di ◽  
Muhammad Amir Shafiq ◽  
Yazeed Alaudah ◽  
Ghassan AlRegib
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
Seismic Data ◽  
Domain Knowledge ◽  
Machine Learning Algorithms ◽  
Hydrocarbon Exploration ◽  
Machine Learning Techniques ◽  
Structural Interpretation ◽  
Salt Domes

As a process that identifies geologic structures of interest such as faults, salt domes, or elements of petroleum systems in general, seismic structural interpretation depends heavily on the domain knowledge and experience of interpreters as well as visual cues of geologic structures, such as texture and geometry. With the dramatic increase in size of seismic data acquired for hydrocarbon exploration, structural interpretation has become more time consuming and labor intensive. By treating seismic data as images rather than signal traces, researchers have been able to utilize advanced image-processing and machine-learning techniques to assist interpretation directly. In this paper, we mainly focus on the interpretation of two important geologic structures, faults and salt domes, and summarize interpretation workflows based on typical or advanced image-processing and machine-learning algorithms. In recent years, increasing computational power and the massive amount of available data have led to the rise of deep learning. Deep-learning models that simulate the human brain's biological neural networks can achieve state-of-the-art accuracy and even exceed human-level performance on numerous applications. The convolutional neural network — a form of deep-learning model that is effective in analyzing visual imagery — has been applied in fault and salt dome interpretation. At the end of this review, we provide insight and discussion on the future of structural interpretation.

Sign in / Sign up

Export Citation Format

Share Document