A Glider Simulation Model Based on Optimized Support Vector Regression for Efficient Coordinated Observation

Multi-gliders have been widely deployed as an array in nowadays ocean observation for fine and long-term research, especially deep-sea exploration. However, the strong, variable currents delayed information feedback of gliders are remaining huge challenges deployment glider arrays which may cause that observed data cannot meet study needs bring a prohibitive cost. In this paper, we develop Glider Simulation Model (GSM) based on support vector regression with particle swarm optimization (PSO)-SVR algorithm to integrate from current rapid modeling effectively predict gliders’ trajectories. Based real-time predictive trajectories, each can select future movement strategies. We utilize in-suit datasets obtained by sea-wing train test simulation model. The results show GSM has effective stable performance. approaches be utilized arrays.