Analysis of Several Optimization Strategies of BP Neural Network in GNSS Height Anomaly Fitting

Several optimization algorithms based on the Back Propagation (BP) neural network are often used to improve fitting accuracy of GNSS height anomaly. However, performance and applicability these have not been systematically studied. This study takes two kinds GNSS/leveling points with different spatial distributions as examples, evaluates commonly genetic algorithm (GA), simulated annealing (SA), particle swarm (PSO), latest sparrow search (SSA) methods in improving BP network. Additionally, this also attempts add input data related terrain for first time analyze whether it can under uneven point distribution. Results show that significantly stability results, PSO SSA indicate best improvement. when distribution is uneven, adding appropriate effectively reliability