Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A Deep Learning-Enhanced Adaptive Kalman Filter with Multi-Scale Temporal Attention for Airborne Gravity Denoising.

Lili Li¹, Junxiang Liu¹, Guoqing Ma¹

¹State Key Laboratory of Deep Earth Exploration and Imaging, College of Geoexploration Science and Technology, Jilin University, Changchun 130026, China.

Sensors (Basel, Switzerland)

|April 14, 2026

Summary

Related Concept Videos

Application of Linearization and Approximation

Application of Linearization and Approximation

A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...

Measuring Acceleration Due to Gravity

Measuring Acceleration Due to Gravity

Consider a coffee mug hanging on a hook in a pantry. If the mug gets knocked, it oscillates back and forth like a pendulum until the oscillations die out.
A simple pendulum can be described as a point mass and a string. Meanwhile, a physical pendulum is any object whose oscillations are similar to a simple pendulum, but cannot be modeled as a point mass on a string because its mass is distributed over a larger area. The behavior of a physical pendulum can be modeled using the principles of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Unlocking Azulene Functionalization via Strain-Induced Azulyne Intermediates.

Journal of the American Chemical Society·2026

Same author

Phosphorus-Deficiency-Induced Development of Root Apoplastic Barriers Restricts Cadmium Translocation in <i>Salix caprea</i>.

Plants (Basel, Switzerland)·2026

Same author

Determination of the ED90 and ED99 of Liposomal versus Conventional Bupivacaine for Ultrasound-Guided Stellate Ganglion Block: A Biased-Coin Design Study.

Drug design, development and therapy·2026

Same author

Construction of β-Heteroarylated Aliphatic Aldehydes via Pd-Catalyzed and Ag-Mediated Redox-Relay Oxidative Heck Reactions.

Organic letters·2026

Same author

Integrating epidemiologic modeling and explainable machine learning to evaluate body roundness index for WHO-defined high cardiovascular risk: evidence from the ChinaHEART-Luohe screening cohort.

Frontiers in nutrition·2026

Same author

Polycyclic Aromatic Hydrocarbon Pollution Stress Impairs Soil Enzyme Activity and Microbial Community.

Microorganisms·2026

A new adaptive Kalman Filter (AKF) method using multi-scale CNN, Bi-LSTM, and attention enhances airborne gravity data denoising. This approach improves geological interpretation by accurately estimating filter parameters and reducing noise.

Area of Science:

Geophysics
Remote Sensing
Signal Processing

Background:

Airborne gravity surveys are crucial for mapping subsurface geology and mineral targets.
Raw gravity data is susceptible to noise from airflow and platform instability.
Kalman Filter (KF) is effective for denoising but sensitive to parameter selection.

Purpose of the Study:

To develop a novel method for high-precision airborne gravity data denoising.
To adaptively estimate Kalman Filter parameters for improved accuracy.
To enhance geological interpretation of airborne gravity data.

Main Methods:

Proposed the multi-scale CNN-LSTM-attention adaptive Kalman Filter (MSC-LA-AKF).
Utilized multi-scale CNN for feature extraction at various scales.

Keywords:

Bi-LSTM adaptive Kalman Filter airborne gravity data multi-scale CNN

Related Experiment Videos

Employed bidirectional LSTM (Bi-LSTM) for time-varying noise identification.

Integrated a multi-head attention mechanism for adaptive parameter optimization.

Main Results:

MSC-LA-AKF demonstrated superior denoising accuracy compared to FIR and wavelet filters on simulated data.
The method effectively removed noise from real airborne gravity data.
Enhanced geological interpretation was achieved through noise reduction.

Conclusions:

The MSC-LA-AKF method offers a significant advancement in airborne gravity data processing.
Adaptive parameter estimation is key to improving KF-based denoising performance.
This technique provides more reliable data for geological exploration.