首页|Studies from Tsinghua University Reveal New Findings on Machine Learning (Machine Learning-enhanced Interpolation of Gravityassisted Magnetic Data)
Studies from Tsinghua University Reveal New Findings on Machine Learning (Machine Learning-enhanced Interpolation of Gravityassisted Magnetic Data)
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 DailyNews Daily News - Researchers detail new data in Machine Learning. According to news reporting originatingin Beijing, People’s Republic of China, by NewsRx journalists, research stated, “The acquisition ofmagnetic anomaly data is generally considered a process of information degradation, with its content significantlyimpacting subsequent tasks involving data processing, inversion, and interpretation. Traditionalinterpolation methods often rely on t he spatial distribution and sampling density of data, thus strugglingto handle complex nonlinear relationships effectively.”Financial support for this research came from National Natural Science Foundatio n of China (NSFC).The news reporters obtained a quote from the research from Tsinghua University, “To address thesechallenges, this study employs deep learning algorithms for in terpolating magnetic anomaly data, aimingto enhance the resolution of magnetic data. Additionally, gravity data are incorporated as supplementaryinformation t o improve the quality of magnetic anomaly data interpolation. Similar to magneti c data,gravity data also exhibit a certain degree of spatial correlation, as a single geological source may produceanomalies in both gravity and magnetic resp onses simultaneously. Through the training and predictionof deep learning netwo rks, it is observed that the intelligent interpolation retains the subtle featur es ofmagnetic anomaly data in space while avoiding staircase-like erroneous ano malies generated by linear interpolation. Furthermore, gravity data assist in co nstraining the results of magnetic anomaly interpolation,enhancing their accura cy. Finally, the trained network is applied to measured data, with the input dat abeing downsampled.”
BeijingPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningTsinghua University
NETL
NSTL
