An ANN model-based method is proposed to retrieve the ocean surface wind speed from Cyclone Global Navigation Satellite System (CYGNSS) L1 observation data. The proposed method is embedded with an input features and output results filtering module based on a machine learning (ML) algorithm, abbreviated as the MF-ANN method. By studying the relationship between physical observation variables from CYGNSS L1 data and the wind speed of the European Centre for Medium-Range Weather Forecast (ECMWF) reanalysis dataset and Cross-Calibrated Multiplatform (CCMP) dataset, a feature parameter selection module based on the XGBoost algorithm and Pearson correlation coefficient is designed to automatically select the optimal combination of feature parameters related to the ocean surface wind speed and input the feature parameters into the ANN model. An outlier filtering module based on the unsupervised ML algorithm is designed to identify and eliminate the outliers in the wind speed data retrieved by the ANN model, reducing the errors that cannot be eliminated by the fixed threshold of the quality flag providing in the CYGNSS L1 product. The experiments show that the RMSEs of the MF-ANN model can be reduced by 11.73% and 15.31% compared with those of a single ANN model by adding feature selection modules and quality filtering modules, respectively. The RMSE of the MF-ANN model combining these two modules can be reduced by 29.08%.
Driven by the high data transmission requirement of low earth orbit enhanced global navigation satellite system (LeGNSS), multiplexed code shift keying (MCSK) has emerged as a novel modulation. The numerous satellites and the high dynamic variation in the LeGNSS constellation pose great challenges to the efficient acquisition of MCSK signals. We propose a high efficient three-dimensional acquisition algorithm for LeGNSS MCSK signals (TDA-M), searching for Doppler, primary code phase, and secondary code phase. Our scheme employs phase rotation code to enhance acquisition efficiency and utilizes the dynamic dual-layer partial matched filter with fast fourier transform to maintain high performance in the large dynamic regions. Numerical simulation results show that TDA-M is 17 times faster than existing scheme under the same code multiplexing level and Doppler search range. In high dynamic scenarios, the dynamic search factor improves secondary code phase estimation accuracy by up to 50% compared with the case without it, and the probability of Doppler estimation error falls within FFT spectral resolution exceeds 97%.