CN111523258B - Microseism effective signal first arrival pickup method and system based on MS-Net network - Google Patents
Microseism effective signal first arrival pickup method and system based on MS-Net network Download PDFInfo
- Publication number
- CN111523258B CN111523258B CN202010051610.XA CN202010051610A CN111523258B CN 111523258 B CN111523258 B CN 111523258B CN 202010051610 A CN202010051610 A CN 202010051610A CN 111523258 B CN111523258 B CN 111523258B
- Authority
- CN
- China
- Prior art keywords
- data set
- training
- arrival
- loss function
- net network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 56
- 238000005070 sampling Methods 0.000 claims description 7
- 230000002123 temporal effect Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/288—Event detection in seismic signals, e.g. microseismics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/36—Effecting static or dynamic corrections on records, e.g. correcting spread; Correlating seismic signals; Eliminating effects of unwanted energy
- G01V1/362—Effecting static or dynamic corrections; Stacking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Geophysics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention relates to the technical field of microseism data processing, in particular to a microseism effective signal first arrival pickup method and system based on an MS-Net network. The method includes generating an original dataset; calibrating a data set; inputting the data set into a constructed MS-Net network for training to obtain optimal network model parameters, wherein the training comprises the steps of performing supervised training on one part of the samples subjected to calibration and performing unsupervised training on the other part of the samples not subjected to calibration; calculating the probability distribution of the data set point by point; the system comprises a data set making module, a data set training module and an output module; according to the embodiment of the invention, the non-supervision loss and the supervised loss are weighted and summed to form the total loss through the combination of an MS-Net network and a semi-supervision method, and the network model parameters are optimized through minimizing the total loss, so that the accurate prediction and identification of the initial point of the effective signal are finally realized; the number of the training set marking labels is reduced, and the quality and the detection precision of the training set are improved.
Description
Technical Field
The invention relates to the technical field of microseism data processing, in particular to a microseism effective signal first arrival pickup method and system based on an MS-Net network.
Background
The microseism detection method has important effects in engineering construction, geological disaster prevention and control and the like, meanwhile, the microseism signals have the characteristics of weak signal energy and easiness in interference of background noise, so that first arrival of the microseism signals cannot be accurately picked up, positioning of microseism events is inaccurate, and therefore the microseism effective signal detection method is one of the important points in the field of microseism data processing.
The traditional signal detection technology comprises the steps of performing spectrum analysis, wavelet, curvelet and shear wave transformation on signals through fast Fourier transformation, performing time-frequency conversion and the like so as to achieve the purpose of removing noise and keeping effective signals. However, if the conventional method is directly applied to microseism data, satisfactory effects cannot be obtained, and the quality and accuracy of microseism monitoring are directly affected. Signal monitoring based on deep learning is recently receiving wide attention, and the main reason is that the system has the characteristics of multiple parameters and large capacity, so that the network has strong processing capacity for mass data; the novel network model of the MS-Net consists of a UNet++ network, a Denseblock (Gao Huang, zhuang Liu, laurens van der Maaten, kilian Q.Weinberger.2017) block is added to deepen the network structure, the main and fine features of signals are extracted through a layer jump and pruning structure in the UNet++ network, meanwhile, the problems of feature stacking and overfitting are avoided, and the problem that deep feature identification is not obvious due to the fact that the number of layers of the UNet++ network is small is solved by adding the Denseblock, so that the MS-Net network can be constructed by accurately acquiring deep and shallow features, and the fine extraction of the signal features is improved to a certain extent.
The method has the defects that the label dataset needs to be manually marked and input into a network for reinforcement training learning, the quality of the training set is low, the time consumption is long, and the accuracy is low.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides a method and a system for picking up the first arrival of microseism effective signals based on an MS-Net network, which can reduce the number of training set marking labels and improve the quality and detection precision of the training set.
In one aspect, the embodiment of the invention provides a method for picking up first arrival of microseism effective signals based on an MS-Net network, which comprises the following steps:
s1, generating an original data set; under different models generated by finite difference forward modeling, a large number of analog signals with main frequency ranging from 20 Hz to 1000Hz and actual data form an original data set together;
s2, calibrating a data set; picking up a part of samples in the original data set at first arrival, selecting signal waveforms of first arrival and non-first arrival of each signal sampling point, and calibrating the signal waveforms respectively, wherein the other part of samples are not calibrated;
s3, inputting the data set into a constructed MS-Net network for training to obtain optimal network model parameters; the method specifically comprises the steps of performing supervised training on the part of the samples subjected to calibration, and performing unsupervised training on the other part of the samples not subjected to calibration;
s4, calculating probability distribution of the data set point by point; the method specifically comprises the steps of outputting probabilities point by utilizing a softmax function, obtaining two kinds of probabilities of all points, and selecting probability peaks of first arrival categories as first arrival points.
On the other hand, the embodiment of the invention provides a micro-seismic effective signal first arrival pickup system based on an MS-Net network, which comprises the following steps:
the data set making module is used for generating an original data set; under different models generated by finite difference forward modeling, a large number of analog signals with main frequency ranging from 20 Hz to 1000Hz and actual data form an original data set together; calibrating a data set; picking up a part of samples in the original data set at first arrival, selecting signal waveforms of first arrival and non-first arrival of each signal sampling point, and calibrating the signal waveforms respectively, wherein the other part of samples are not calibrated;
the data set training module inputs the data set into the constructed MS-Net network for training to obtain optimal network model parameters; the method specifically comprises the steps of performing supervised training on the part of the samples subjected to calibration, and performing unsupervised training on the other part of the samples not subjected to calibration;
the output module calculates the probability distribution of the data set point by point; the method specifically comprises the steps of outputting probabilities point by utilizing a softmax function, obtaining two kinds of probabilities of all points, and selecting probability peaks of first arrival categories as first arrival points.
The embodiment of the invention provides a method and a system for picking up a first arrival of a microseism effective signal based on an MS-Net network, wherein an unsupervised loss and a supervised loss are weighted and summed to form a total loss through the combination of the MS-Net network and a semi-supervised method Temporal Ensembling, and network model parameters are optimized through minimizing the total loss, so that accurate prediction and identification of the first arrival point of the effective signal are finally realized; the number of the training set marking labels is reduced, and the quality and the detection precision of the training set are improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the technical description of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for picking up first arrival of microseism effective signals based on an MS-Net network in an embodiment of the invention;
FIG. 2 is a schematic diagram of a semi-supervised method in combination with MS-Net network training process according to an embodiment of the present invention;
FIG. 3 is a graph showing the probability prediction of the first arrival position of an effective signal in an MS-Net network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a micro-seismic effective signal first-arrival pickup system based on an MS-Net network according to an embodiment of the present invention;
reference numerals:
data set making module-1 data set training module-2 output module-3
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
FIG. 1 is a schematic flow chart of a method for picking up first arrival of microseism effective signals based on an MS-Net network in an embodiment of the invention; as shown in fig. 1, the method comprises the following steps:
s1, generating an original data set; under different models generated by finite difference forward modeling, a large number of analog signals with main frequency ranging from 20 Hz to 1000Hz and actual data form an original data set together;
s2, calibrating a data set; picking up a part of samples in the original data set at first arrival, selecting signal waveforms of first arrival and non-first arrival of each signal sampling point, and calibrating the signal waveforms respectively, wherein the other part of samples are not calibrated;
s3, inputting the data set into a constructed MS-Net network for training to obtain optimal network model parameters; the method specifically comprises the steps of performing supervised training on the part of the samples subjected to calibration, and performing unsupervised training on the other part of the samples not subjected to calibration;
s4, calculating probability distribution of the data set point by point; the method specifically comprises the steps of outputting probabilities point by utilizing a softmax function, obtaining two kinds of probabilities of all points, and selecting probability peaks of first arrival categories as first arrival points.
Specifically, fig. 3 is a graph of predicting first arrival position probability of an effective signal of an MS-Net network according to an embodiment of the present invention; as shown in fig. 3, a part of samples of the original data set are picked up in a first arrival mode, signal waveforms of first arrival and non-first arrival positions of each signal sampling point are selected and calibrated respectively, and the other part of samples are not calibrated; simultaneously inputting the two samples into a network training model by combining an MS-Net network with a semi-supervision method for training, and correspondingly performing supervised training and unsupervised training to obtain optimal network model parameters, namely a data set effective signal first arrival position probability prediction curve graph; calculating the probability distribution of the data set point by point, outputting the probability point by utilizing a softmax function to obtain the two classification probabilities of each point, and selecting the probability peak value of the first arrival category as the first arrival point, wherein the formula is as follows:
wherein q i (x) Representing the prediction probability distribution of each category to which x is respectively dependent, wherein x represents each point of the output f (x) of the last layer of the full convolution network; predictive probability distribution q i (x) When the value is 0, the value of i is 2, which represents a non-first arrival point; the probability value q i (x) When the value is 1, the initial point is represented, and the value of i is 1; k (x) represents a category, and k=1, 2 represents two categories, namely a first arrival point and a non-first arrival point.
FIG. 2 is a schematic diagram of a semi-supervised method in combination with MS-Net network training process according to an embodiment of the present invention; as shown in fig. 2, in the step S3, the optimal network model parameters specifically include: the method comprises the steps of weighting and summing an unsupervised loss function and a supervised loss function to construct a total loss function, and obtaining the minimum total loss function; minimizing the total loss function value is less than 0.1.
Specifically, in the process of combining the semi-supervision method with the MS-Net network training, the total loss function is as follows:
wherein C is the number of different categories, B is a small batch index set; the evaluation results of the two branches are divided into two different phases: firstly, the training set is classified without updating the weight, then, different expansion and deletion training are carried out on the network under the same input, and the prediction obtained just before is used as the target of the unsupervised loss component.
After each training is finished, the extracted feature vector V is updated j ←aV j +(1-a)v j Output v of network j Accumulated to output
Wherein a is the aggregate dynamic term,>
is the result of the integration of predictive values of multiple rounds of xi during training. />
A weighted average of the network aggregate outputs from the previous training period is included, but the most recent period is weighted more than the distant period. To produce training to target V, we need to correct the start-up bias in V by dividing by a factor (1-at), resulting in
In this process, we can assign the unsupervised weight function W (t) for the first training period to be zero.
Current output V j Integrated results with multiple-round xi predictors
Forming an unsupervised loss by a square-difference function, a current output V j And forming a supervised loss with the marked sample through a cross entropy function, forming a total loss value of the network model through weighted summation of the two loss values, and obtaining an optimal network model through minimizing the total loss value.
The embodiment of the invention provides a microseism effective signal first arrival pickup method based on an MS-Net network, which combines an unsupervised loss and a supervised loss weighted sum to construct a total loss through the MS-Net network and a semi-supervised method Temporal Ensembling, and optimizes network model parameters by minimizing the total loss, so that the accurate prediction and identification of the effective signal first arrival point are finally realized; the number of the training set marking labels is reduced, and the quality and the detection precision of the training set are improved.
Based on the above embodiments, fig. 4 is a schematic structural diagram of a first arrival picking system of microseism effective signals based on an MS-Net network according to an embodiment of the present invention; as shown in fig. 4, includes:
the data set making module 1 generates an original data set; under different models generated by finite difference forward modeling, a large number of analog signals with main frequency ranging from 20 Hz to 1000Hz and actual data form an original data set together; calibrating a data set; picking up a part of samples in the original data set at first arrival, selecting signal waveforms of first arrival and non-first arrival of each signal sampling point, and calibrating the signal waveforms respectively, wherein the other part of samples are not calibrated;
the data set training module 2 inputs the data set into the constructed MS-Net network for training to obtain optimal network model parameters; the method specifically comprises the steps of performing supervised training on the part of the samples subjected to calibration, and performing unsupervised training on the other part of the samples not subjected to calibration;
the output module 3 calculates the probability distribution of the data set point by point; the method specifically comprises the steps of outputting probabilities point by utilizing a softmax function, obtaining two kinds of probabilities of all points, and selecting probability peaks of first arrival categories as first arrival points.
The embodiment of the invention provides a micro-seismic effective signal first arrival pickup system based on an MS-Net network, which executes the method, combines a semi-supervision method Temporal Ensembling with the MS-Net network, weights and sums unsupervised loss and supervised loss to construct total loss, optimizes network model parameters by minimizing the total loss, and finally realizes accurate prediction and identification of effective signal first arrival points; the number of the training set marking labels is reduced, and the quality and the detection precision of the training set are improved.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (2)
1. The method for picking up the first arrival of the microseism effective signal based on the MS-Net network is characterized by comprising the following steps:
s1, generating an original data set; the method specifically comprises the steps of generating a large number of analog signals with main frequency range of 20-1000 Hz and actual data to form an original data set under different models by utilizing finite difference forward modeling;
s2, calibrating a data set; picking up a part of samples in the original data set at first arrival, selecting signal waveforms of first arrival and non-first arrival of each signal sampling point, and calibrating the signal waveforms respectively, wherein the other part of samples are not calibrated;
s3, inputting the data set into a constructed MS-Net network for training to obtain optimal network model parameters; the method specifically comprises the steps of performing supervised training on the part of the samples subjected to calibration, and performing unsupervised training on the other part of the samples not subjected to calibration; in step S3, inputting the data set into the constructed MS-Net network for training, where obtaining the optimal network model parameters specifically includes: combining an unsupervised loss function and a supervised loss function through an MS-Net network with a semi-supervised method Temporal Ensembling, and carrying out weighted summation on the unsupervised loss function and the supervised loss function to construct a total loss function, so as to obtain a minimum total loss function; the minimum total loss function value is less than 0.1;
s4, calculating probability distribution of the data set point by point; the method specifically comprises the steps of outputting probabilities point by utilizing a softmax function, obtaining two kinds of probabilities of all points, and selecting probability peaks of first arrival categories as first arrival points.
2. A microseism effective signal first arrival pickup system based on an MS-Net network, comprising:
the data set making module is used for generating an original data set; the method specifically comprises the steps of generating a large number of analog signals with main frequency range of 20-1000 Hz and actual data to form an original data set under different models by utilizing finite difference forward modeling; calibrating a data set; picking up a part of samples in the original data set at first arrival, selecting signal waveforms of first arrival and non-first arrival of each signal sampling point, and calibrating the signal waveforms respectively, wherein the other part of samples are not calibrated;
the data set training module inputs the data set into the constructed MS-Net network for training to obtain optimal network parameters; the method specifically comprises the steps of performing supervised training on the part of the samples subjected to calibration, and performing unsupervised training on the other part of the samples not subjected to calibration; the data set training module inputs the data set into a constructed MS-Net network for training, and the obtaining of the optimal network model parameters specifically comprises the following steps: combining an unsupervised loss function and a supervised loss function through an MS-Net network with a semi-supervised method Temporal Ensembling, and carrying out weighted summation on the unsupervised loss function and the supervised loss function to construct a total loss function, so as to obtain a minimum total loss function; the minimum total loss function value is less than 0.1;
the output module calculates the probability distribution of the data set point by point; the method specifically comprises the steps of outputting probabilities point by utilizing a softmax function, obtaining two kinds of probabilities of all points, and selecting probability peaks of first arrival categories as first arrival points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010051610.XA CN111523258B (en) | 2020-01-17 | 2020-01-17 | Microseism effective signal first arrival pickup method and system based on MS-Net network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010051610.XA CN111523258B (en) | 2020-01-17 | 2020-01-17 | Microseism effective signal first arrival pickup method and system based on MS-Net network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111523258A CN111523258A (en) | 2020-08-11 |
| CN111523258B true CN111523258B (en) | 2023-06-13 |
Family
ID=71900472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010051610.XA Active CN111523258B (en) | 2020-01-17 | 2020-01-17 | Microseism effective signal first arrival pickup method and system based on MS-Net network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523258B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114637045A (en) * | 2022-02-25 | 2022-06-17 | 三峡大学 | Method for picking up microseism P wave first arrival based on UNet + + combined Clique Block |
| CN115113269B (en) * | 2022-06-04 | 2024-07-05 | 三峡大学 | First arrival pickup method of microseism effective signals based on UGATIT and PSPNet combination |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5181171A (en) * | 1990-09-20 | 1993-01-19 | Atlantic Richfield Company | Adaptive network for automated first break picking of seismic refraction events and method of operating the same |
| CN106405640A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Automatic microseismic signal arrival time picking method based on depth belief neural network |
| CN110018517A (en) * | 2019-05-07 | 2019-07-16 | 西安石油大学 | A kind of multiple dimensioned ground micro-seismic inverse time interference localization method |
| CN110032975A (en) * | 2019-04-15 | 2019-07-19 | 禁核试北京国家数据中心 | A kind of pick-up method of seismic phase |
| CN110210296A (en) * | 2019-04-25 | 2019-09-06 | 长江大学 | A kind of microseism useful signal detection method of combination U-net network and DenseNet network |
-
2020
- 2020-01-17 CN CN202010051610.XA patent/CN111523258B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5181171A (en) * | 1990-09-20 | 1993-01-19 | Atlantic Richfield Company | Adaptive network for automated first break picking of seismic refraction events and method of operating the same |
| CN106405640A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Automatic microseismic signal arrival time picking method based on depth belief neural network |
| CN110032975A (en) * | 2019-04-15 | 2019-07-19 | 禁核试北京国家数据中心 | A kind of pick-up method of seismic phase |
| CN110210296A (en) * | 2019-04-25 | 2019-09-06 | 长江大学 | A kind of microseism useful signal detection method of combination U-net network and DenseNet network |
| CN110018517A (en) * | 2019-05-07 | 2019-07-16 | 西安石油大学 | A kind of multiple dimensioned ground micro-seismic inverse time interference localization method |
Non-Patent Citations (8)
| Title |
|---|
| Gao Huang，Zhuang Liu，Laurens van der Maaten.Densely Connected Convolutional Networks.《arXiv》.2017,全文. * |
| Laine, Samuli, Aila, Timo.TEMPORAL ENSEMBLING FOR SEMI-SUPERVISED LEARNING.《Neural and Evolutionary Computing》.2016,1-13. * |
| Qingchang Zhu , Zhenghua Chen , Yeng Chai Soh.A Novel Semisupervised Deep Learning Method for Human Activity Recognition.《IEEE》.2019,第15卷(第7期),12-19. * |
| TINGTING SUN , CHUNHONG ZHANG, YANG JI, AND ZHENG HU.MSnet: Multi-Head Self-Attention Network for Distantly Supervised Relation Extraction.《IEEE》.2019,第7卷54472-54482. * |
| Weilin Huang.Seismic signal recognition by unsupervised machine learning.《Geophysical Journal International》.2019,第219卷(第2期),1163-1180. * |
| Yun Long , Jun Lin, Bin Li, Hongchao Wang, and Zubin Chen.Fast-AIC Method for Automatic First Arrivals Picking of Microseismic Event With Multitrace Energy Stacking Envelope Summation.《IEEE》.2019,第17卷(第10期),1832-1836. * |
| 丁建群，何永清，郭锐，宁宏晓，吕盼盼.基于U-Net网络的地震数据初至自动拾取方法.《2019年油气地球物理学术年会论文集》.2019,全文. * |
| 贾佳，王夫运，吴庆举.机器学习在地震检测与震相识别的应用综述.《地震工程学报》.2019,第41卷(第41期),1419-1425. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111523258A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563706A (en) | Multivariable logistics freight volume prediction method based on LSTM network | |
| CN110502806B (en) | Wireless spectrum occupancy rate prediction method based on LSTM network | |
| CN114254561A (en) | Waterlogging prediction method, waterlogging prediction system and storage medium | |
| CN112446419A (en) | Time-space neural network radar echo extrapolation forecasting method based on attention mechanism | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN111931983B (en) | Precipitation prediction method and system | |
| CN111505705B (en) | Microseism P wave first arrival pickup method and system based on capsule neural network | |
| CN111523258B (en) | Microseism effective signal first arrival pickup method and system based on MS-Net network | |
| CN110633859B (en) | Hydrologic sequence prediction method integrated by two-stage decomposition | |
| CN115951430A (en) | Geomagnetic index forecasting method based on LSTM | |
| CN116228754A (en) | Surface defect detection method based on deep learning and global difference information | |
| Qiao et al. | Effective ensemble learning approach for SST field prediction using attention-based PredRNN | |
| CN117392564B (en) | River water quality inversion method based on deep learning, electronic equipment and storage medium | |
| CN113689026A (en) | Meteorological data prediction method, equipment and storage medium | |
| CN116312860B (en) | Agricultural product soluble solid matter prediction method based on supervised transfer learning | |
| CN112616160B (en) | Intelligent short-wave frequency cross-frequency-band real-time prediction method and system | |
| CN114065822B (en) | Electromagnetic identification method and system for ocean tide fluctuation | |
| CN113011597B (en) | Deep learning method and device for regression task | |
| CN113035363B (en) | Probability density weighted genetic metabolic disease screening data mixed sampling method | |
| CN115406911A (en) | Troposphere atmosphere temperature and humidity profile inversion method based on multi-target genetic algorithm | |
| CN113052388A (en) | Time series prediction method and device | |
| CN118552907B (en) | Perimeter invader detection method and system based on optimized downsampling scale | |
| CN118378178B (en) | Transformer fault identification method and system based on residual map convolution neural network | |
| CN113688774B (en) | Advanced learning-based high-rise building wind induced response prediction and training method and device | |
| CN111382761B (en) | CNN-based detector, image detection method and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |