Recent advancements in machine learning and the availability of massive data sets now facilitate the development of neural network models to predict aviation noise based on aircraft trajectories. In this paper, we use a long short-term memory recurrent neural network to predict aviation noise at a ground location near Washington National Airport. The model is developed using over 10 months of achieved radar data and noise readings. Beyond trajectory information, meta-data regarding the aircraft type and weather data is integrated into the model. While specific to a ground station and airport, the model is able to accurately predict aviation noise above 55 db with a mean absolute error of 2.3 dB.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Ground Level Aviation Noise Prediction: A Sequence to Sequence Modeling Approach Using LSTM Recurrent Neural Networks


    Contributors:


    Publication date :

    2020-10-11


    Size :

    2023224 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Vehicle Trajectory Prediction based on LSTM Recurrent Neural Networks

    Ip, Andre / Irio, Luis / Oliveira, Rodolfo | IEEE | 2021



    SEQUENCE-TO-SEQUENCE PREDICTION OF VEHICLE TRAJECTORY VIA LSTM ENCODER-DECODER ARCHITECTURE

    Park, Seong Hyeon / Kim, ByeongDo / Kang, Chang Mook et al. | British Library Conference Proceedings | 2018


    Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture

    Park, Seong Hyeon / Kim, ByeongDo / Kang, Chang Mook et al. | IEEE | 2018