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

Airborne gravity survey serves as a rapid remote sensing technique for mapping subsurface mineral target and geological structure over large areas. The raw gravity data contains significant noise corrupted by airflow and the flight platform's attitude. The Kalman Filter (KF) is an effective method for airborne gravity data denoising, but its processing accuracy is highly dependent on the empirical parameters. The multi-scale CNN-LSTM-attention adaptive Kalman Filter (MSC-LA-AKF) method is proposed to obtain high precision gravity data, which combines the multi-scale CNN (MSC), bidirectional long short-term memory (Bi-LSTM) and attention mechanism for adaptively estimating the parameters of KF. The multi-scale CNN uses convolution kernel of varying sizes to extract signal features at different scales. The Bi-LSTM combines two LSTM layers in opposite directions to extract the signal features at bidirectional time series, and can effectively identify time-varying noise signals. A multi-head attention mechanism with four attention heads (H=4) is incorporated into the output feature layer of the Bi-LSTM to adaptively calculate weights for different features and optimize the parameters of the KF. The simulated data tests demonstrate that the MSC-LA-AKF achieves notably higher denoising accuracy than both the finite impulse response (FIR) and wavelet filters, with detailed quantitative comparisons provided in the experimental section. The proposed method is applied to real airborne gravity data, and effectively removes noise signals and enhances the geological interpretation of gravity maps.