首页|Data from Chengdu University of Technology Advance Knowledge in Machine Learning (Unsupervised Machine Learning-based Multiattributes Fusion Dim Spot Subtle Sa ndstone Reservoirs Identification Utilizing Isolation Forest)
Data from Chengdu University of Technology Advance Knowledge in Machine Learning (Unsupervised Machine Learning-based Multiattributes Fusion Dim Spot Subtle Sa ndstone Reservoirs Identification Utilizing Isolation Forest)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning. According to news reporting out of Chengdu, People's Republic of China, by NewsRx editors, research stated, "Subtle sandstone reservoirs are dif ficult to identify due to their weak seismic responses. Here, we propose to iden tify subtle sandstone reservoirs by an unsupervised machine learning-based multi -attribute fusion scheme using prestack seismic data." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Chengdu University of Technology Postgraduate Innovative Cul tivation Program, Technological Development for Sichuan Province, Natural Scienc e Foundation of Sichuan. Our news journalists obtained a quote from the research from the Chengdu Univers ity of Technology, "The proposed scheme carries out seismic attenuation gradient analysis and prestack simultaneous inversion to obtain the attributes that are sensitive to subtle channel sands, and uses them as the selected multiple attrib utes, and further employs a state-of-the-art unsupervised machine learning algor ithm, called isolation forest, for the multi-attribute anomaly detection and ana lysis to identify subtle sandstone reservoir. To the best of our knowledge, this is the first time to introduce the isolation forest unsupervised anomaly detect ion algorithm in the reservoir identification. Prestack simultaneous inversion c an use multi-angle and multi-scale information as constraints, and the attenuati on gradient reflects the body response of the reservoir. For the field seismic d ata from a subtle channel sandstone reservoir in the western Sichuan basin, Chin a, we found that the proposed scheme has good application effect in identifying subtle reservoirs. The application example demonstrates that the identified resu lts are highly consistent with the actual development results, illustrating the feasibility and effectiveness of this scheme on the characterization for dim spo t subtle sandstone reservoirs."
ChengduPeople's Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine LearningChengdu University of Techn ology
NETL
NSTL
