English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The magnetic inversion method is one of the non-destructive geophysicalmethods, which aims to estimate the subsurface susceptibility distribution fromsurface magnetic anomaly data. Recently, supervised deep learning methods havebeen widely utilized in lots of geophysical fields including magneticinversion. However, these methods rely heavily on synthetic training data,whose performance is limited since the synthetic data is not independently andidentically distributed with the field data. Thus, we proposed to realizemagnetic inversion by self-supervised deep learning. The proposedself-supervised knowledge-driven 3D magnetic inversion method (SSKMI) learns onthe target field data by a closed loop of the inversion and forward models.Given that the parameters of the forward model are preset, SSKMI can optimizethe inversion model by minimizing the mean absolute error between observed andre-estimated surface magnetic anomalies. Besides, there is a knowledge-drivenmodule in the proposed inversion model, which makes the deep learning methodmore explicable. Meanwhile, comparative experiments demonstrate that theknowledge-driven module can accelerate the training of the proposed method andachieve better results. Since magnetic inversion is an ill-pose task, SSKMIproposed to constrain the inversion model by a guideline in the auxiliary loop.The experimental results demonstrate that the proposed method is a reliablemagnetic inversion method with outstanding performance.

Self-Supervised Knowledge-Driven Deep Learning for 3D Magnetic Inversion