Machine Learning Approach for Evaporation Duct Nowcast
Abstract
The Evaporation Duct Height (EDH) and Strength (EDS) are properties of the evaporation duct that affects electromagnetic (EM) signal propagation close to the air-sea interface. Hence, the accuracies of EDH and EDS affect radar and communication propagation, which can be exploited for detection and counter-detection operations. The EDH/EDS can be calculated utilizing meteorological and oceanographical (METOC) data collected onboard naval ships, including air temperature, sea surface temperature, wind direction, wind speed, sea level pressure, and relative humidity. In this work, we explore the utilization of artificial intelligence/machine learning (AI/ML) algorithms to demonstrate the feasibility to nowcast (up to six-hour forecast) EDH/EDS while a naval vessel is underway. The tested AI/ML algorithms include linear regression, decision trees, random forest, and neural networks. Datasets from the 2017 Coupled Air-Sea Processes and Electromagnetic Ducting Research (CASPER-West) project were used to train, test, and verify the predictions from the AI/ML algorithms. Two methods to forecast EDH/EDS are tested - one to forecast EDH/EDS directly, the other to calculate EDH/EDS based on the AI/ML forecast variables as input to NAVSLaM. The results are compared to those directly derived from the CASPER measurements. The effectiveness and limitations of the methods and algorithms are discussed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2021
- Accession Number
- AD1151228
Entities
People
- Josue F. Yanez
Organizations
- Naval Postgraduate School