A Modular Data Analysis for Ocean Surface Wind Prediction using Artificial Intelligence-based Semantic Verification

A Modular Data Analysis for Ocean Surface Wind Prediction using Artificial Intelligence-based Semantic Verification

Predicting ocean surface winds aids in forecasting precise weather conditions and tides for residential and commercial purposes. A Multi-Modular Semantic Data Analysis (M2SDA) method is proposed to address the missing data errors across different accumulation regions to improve the forecast precision. Large volumes of data from multiple oceanic regions are gathered by sensors deployed across the ocean bed and buoy sense. Artificial intelligence-based analysis was used to identify missing data errors. Considering that the time factor is confined, the forecast endurance based on sensing and aggregation time factors is considered in the identification process, which is required for preventing breaks in data analysis. The M2SDA’s performance is validated using precision, error, analysis time, identification ratio, and analysis rate. Experimental results showed that the suggested M2SDA enhances precision, identification, and analysis ratio of 9.16%, 9.9%, and 8.19%. Error and analysis time are decreased by 8.75% and 10.63%.