Artificial Neural Network (ANN): Applied to aircraft emissions
KHARDI ; KURNIAWANI ; KATIL ; MOERSIDI
Type de document
RAPPORT
Langue
anglais
Auteur
KHARDI ; KURNIAWANI ; KATIL ; MOERSIDI
Résumé / Abstract
Air transportation growth has increased continuously over the years. The rise in air transport activity has been accompanied by an increase in the amount of energy used to provide air transportation services. It is also assumed to increase environmental impacts, in particular aircraft noise and pollutant emissions. Traditionally, the environmental impacts of aircraft have been addressed in two separate ways; aircraft noise and pollutant emissions occurring during the landing and take-off (LTO) phase (local) which are the focus of this study, and the non-LTO phase (global/regional). There are many methods to asses aircraft noise and pollutant emissions used by various countries; however, using different and separate methodology will cause a variation in results, some lack of information and the use of certain methods will require justification and reliability that must be demonstrated and proven. In relation to this issue and considering there is no methods of the combination for assessing aircraft pollutant and noise emissions, the research will identify, improve, develop and combined the methodologies of pollutant and noise emissions, integrated with the ICAO concept of Balanced Approach for short term and long term prediction. The Integrated Noise Monitoring (INM) and Emission Dispersion Modeling System (EDMS) tools will be used for data analysis and Artificial Neural Network (ANN) for modeling the combination effects of aircraft pollutant and noise emissions around airport. Air traffic and Meteorology Data from Soekarno Hatta International Airport - Jakarta and Lyon International Saint Exupery Airport will be used in this research and compared the pollutant and noise emissions of those two airports. The model will help Airport Authorities, Air Traffic Control, Political decision makers to decide, to manage and to provide reliable information on the impacts of aircraft pollutant and noise emissions in short term and long term prediction. Key-words: Aircraft, Pollutant and Noise Emissions, Assessment, Combined Methodologies, Artificial Neural Network.
Editeur
INRETS
