Identification of Weather Influences on Flight Punctuality Using Machine Learning Approach

One of the top long-term threats to airport resilience is extreme climate-induced conditions, which negatively affect and flight operations. Recent examples, including hurricanes, storms, temperatures (cold/hot), heavy rains, have damaged facilities, interrupted air traffic, caused higher operational costs. With development civil aviation pre-COVID-19 surging demand for flights, passengers’ complaints delay increased, according FoxBusiness. This study aims discover weather factors affecting punctuality determine a high-dimensional scale consequences stemming from conditions aspects. Machine learning has been developed in correlation with statistical data operations at Birmingham Airport as case study. The cross-correlated datasets kindly provided by Meteorological Office. scope emphasis this placed on machine application practical prediction relation climate conditions. Random forest, artificial neural network, support vector machine, linear regression are used develop predictive models. Grid-search cross-validation select best parameters. model can grasp trend rates well where R2 0.80 root mean square error (RMSE) less than 15% using random forest technique. insights derived will help Authorities Insurance industry predicting order promptly enact enable adaptative plans, traffic rescheduling, financial variances