Data-driven trajectory prediction with weather uncertainties: A Bayesian deep learning approach

Abstract Trajectory prediction is an essential component of the next generation national air transportation system. Reliable trajectory prediction models need to consider uncertainties coming from multiple sources. Environmental factor is one of the most significant reasons affecting trajectory prediction models and is the focus of this study. This paper propose an advanced Bayesian Deep Learning method for aircraft trajectory prediction considering weather impacts. A brief review of both deterministic and probabilistic trajectory prediction methods is given, with a specific focus on learning-based methods. Next, a deterministic trajectory prediction model with classical deep learning methods is proposed to handle both spatial and temporal information using a nested convolution neural network, recurrent neural network, and fully-connected neural network. Following this, the deterministic neural network model is extended to be a Bayesian deep learning model to consider uncertainties where the posterior distributions of parameters are estimated with variational inference for enhanced efficiency. Both mean prediction and confidence intervals are obtained giving the last on-file flight plans and weather data in the region. The proposed methodology is validated using air traffic and weather data from the Sherlock data warehouse. Data pre-processing procedures for big data analytics are discussed in detail. Demonstration and metrics-based validation are performed during severe convective weather conditions for several air traffic control centers. The results show a significant reduction in prediction variance. A comparison with existing methods is also performed. Several conclusions and future works are given based on the proposed study.

[1]  Heinz Erzberger,et al.  Automated Conflict Resolution, Arrival Management and Weather Avoidance for ATM , 2010 .

[2]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[3]  Chung Choo Chung,et al.  Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Jean-Marc Alliot,et al.  Using Neural Networks to Predict Aircraft Trajectories , 1999, IC-AI.

[6]  Giulio Avanzini,et al.  Frenet-Based Algorithm for Trajectory Prediction , 2004 .

[7]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[8]  R. DeLaura.  Modeling Convective Weather Avoidance in Enroute Airspace , 2008 .

[9]  Michelle M. Eshow,et al.  Architecture and capabilities of a data warehouse for ATM research , 2014, 2014 IEEE/AIAA 33rd Digital Avionics Systems Conference (DASC).

[10]  Tysen Mueller,et al.  Strategic Aircraft Trajectory Prediction Uncertainty and Statistical Sector Traffic Load Modeling , 2002 .

[11]  Max Mulder,et al.  A Machine Learning Approach to Trajectory Prediction , 2013 .

[12]  Yongming Liu,et al.  A Recurrent Neural Network Approach for Aircraft Trajectory Prediction with Weather Features From Sherlock , 2019, AIAA Aviation 2019 Forum.

[13]  Hendrikus G. Visser,et al.  Improved Trajectory Prediction for Air Traffic Management by Simulation of Guidance Logic and Inferred Aircraft Intent using Existing Data-Link Technology , 2012 .

[14]  Banavar Sridhar,et al.  Airspace Complexity and its Application in Air Traffic Management , 1998 .

[15]  Dave Winkler,et al.  Bayesian Regularization of Neural Networks , 2009, Artificial Neural Networks.

[16]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[17]  David M. Blei,et al.  Variational Inference: A Review for Statisticians , 2016, ArXiv.

[18]  Shuai Yi,et al.  Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction , 2020, ECCV.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Meng Wang,et al.  Multimodal Deep Autoencoder for Human Pose Recovery , 2015, IEEE Transactions on Image Processing.

[21]  James DeArmon,et al.  Using Flight Information to Improve Weather Avoidance Predictions , 2013 .

[22]  Avijit Mukherjee,et al.  Design and Evaluation of a Dynamic Programming Flight Routing Algorithm Using the Convective Weather Avoidance Model , 2009 .

[23]  Edward H Phillips.  FREE FLIGHT POSES MULTIPLE CHALLENGES , 1996 .

[24]  Zoubin Ghahramani,et al.  Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference , 2015, ArXiv.

[25]  Jan M. Maciejowski,et al.  Combining Monte Carlo and worst-case methods for trajectory prediction in air traffic control: a case study , 2007 .

[26]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[27]  Heinz Erzberger,et al.  Conflict Probability Estimation for Free Flight , 1997 .

[28]  Dustin Tran,et al.  Bayesian Layers: A Module for Neural Network Uncertainty , 2018, NeurIPS.

[29]  Dustin Tran,et al.  Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches , 2018, ICLR.

[30]  Siddhartha S. Srinivasa,et al.  Planning-based prediction for pedestrians , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  Julien Cornebise,et al.  Weight Uncertainty in Neural Networks , 2015, ArXiv.

[32]  John Lygeros,et al.  A probabilistic approach to aircraft conflict detection , 2000, IEEE Trans. Intell. Transp. Syst..

[33]  M R Endsley,et al.  Sources of situation awareness errors in aviation. , 1996, Aviation, space, and environmental medicine.

[34]  Hanan Samet,et al.  Aircraft Trajectory Prediction Made Easy with Predictive Analytics , 2016, KDD.

[35]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Stephane Mondoloni,et al.  AiAA-ga-4476 A GENETIC ALGORITHM FOR DETERMINING OPTIMAL FLIGHT TRAJECTORIES , 1998 .

[37]  Silvio Savarese,et al.  Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  Yongming Liu,et al.  Aircraft dynamics simulation using a novel physics-based learning method , 2019, Aerospace Science and Technology.

[39]  Shaojie Qiao,et al.  A Self-Adaptive Parameter Selection Trajectory Prediction Approach via Hidden Markov Models , 2015, IEEE Transactions on Intelligent Transportation Systems.

[40]  Dustin Tran,et al.  TensorFlow Distributions , 2017, ArXiv.

[41]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[42]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[43]  Yongming Liu,et al.  Probabilistic Aircraft Trajectory Prediction Considering Weather Uncertainties Using Dropout As Bayesian Approximate Variational Inference , 2020, AIAA Scitech 2020 Forum.

[44]  Max Welling,et al.  Variational Dropout and the Local Reparameterization Trick , 2015, NIPS 2015.

[45]  Lucy Askey,et al.  A Concept for Tactical Reroute Generation, Evaluation and Coordination , 2012 .

[46]  Juan A. Besada,et al.  Automated Aircraft Trajectory Prediction Based on Formal Intent-Related Language Processing , 2013, IEEE Transactions on Intelligent Transportation Systems.

[47]  Ulrich Kressel,et al.  Probabilistic trajectory prediction with Gaussian mixture models , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[48]  Véronique Berge-Cherfaoui,et al.  Vehicle trajectory prediction based on motion model and maneuver recognition , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[49]  Washington Y. Ochieng,et al.  Performance requirements of future Trajectory Prediction and Conflict Detection and Resolution tools within SESAR and NextGen: Framework for the derivation and discussion , 2014 .

[50]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[51]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[52]  Philippe Lauret,et al.  Bayesian neural network approach to short time load forecasting , 2008 .

[53]  Hinrich Schütze,et al.  Book Reviews: Foundations of Statistical Natural Language Processing , 1999, CL.

[54]  Barry E. Schwartz,et al.  Performance of Trajectory Models with Wind Uncertainty , 2009 .

[55]  Miguel Vilaplana,et al.  Identification and initial characterization of sources of uncertainty affecting the performance of future trajectory management automation systems , 2012, ATACCS.

[56]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[57]  Weiyi Liu,et al.  Probabilistic Trajectory Prediction and Conflict Detection for Air Traffic Control , 2011 .

[58]  Stephane Mondoloni,et al.  A Multiple -Scale Model of Wind -Prediction Uncertainty and Application to Trajectory Prediction , 2006 .

[59]  Tao Tang,et al.  Big Data Analytics in Intelligent Transportation Systems: A Survey , 2019, IEEE Transactions on Intelligent Transportation Systems.

[60]  David P. Thipphavong.  Analysis of Climb Trajectory Modeling for Separation Assurance Automation , 2008 .

[61]  Yutian Pang,et al.  A Voice Communication-Augmented Simulation Framework for Aircraft Trajectory Simulation , 2021 .

[62]  Jose Benavides,et al.  Implementation of a Trajectory Prediction Function for Trajectory Based Operations , 2014 .

[63]  Mark Reynolds,et al.  SS-LSTM: A Hierarchical LSTM Model for Pedestrian Trajectory Prediction , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[64]  Mohamed Zaki,et al.  Uncertainty in Neural Networks: Bayesian Ensembling , 2018, ArXiv.

[65]  Albin Cassirer,et al.  Randomized Prior Functions for Deep Reinforcement Learning , 2018, NeurIPS.

[66]  Hollis F. Ryan,et al.  State Vector Based Near Term Trajectory Prediction , 2008 .

[67]  Yongming Liu,et al.  Conditional Generative Adversarial Networks (CGAN) for Aircraft Trajectory Prediction considering weather effects , 2020 .

[68]  Heather M. Arneson.  Sherlock Data Warehouse , 2018 .

[69]  Dustin Tran,et al.  Simple, Distributed, and Accelerated Probabilistic Programming , 2018, NeurIPS.

[70]  Vu Duong,et al.  Trajectory-based Air Traffic Management (TB-ATM) under Weather Uncertainty , 2001 .

[71]  Zoubin Ghahramani,et al.  Variational Bayesian dropout: pitfalls and fixes , 2018, ICML.

[72]  John Lygeros,et al.  Model Based Aircraft Trajectory Prediction during Takeoff , 2006 .

[73]  Dustin Tran,et al.  Edward: A library for probabilistic modeling, inference, and criticism , 2016, ArXiv.

[74]  Mark Hansen,et al.  Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach , 2018, ArXiv.

[75]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[76]  Steven M. Green,et al.  COMMON TRAJECTORY PREDICTION CAPABILITY FOR DECISION SUPPORT TOOLS , 2003 .

[77]  Fawzi Nashashibi,et al.  Real time trajectory prediction for collision risk estimation between vehicles , 2009, 2009 IEEE 5th International Conference on Intelligent Computer Communication and Processing.

[78]  Sankaran Mahadevan,et al.  Bayesian neural networks for flight trajectory prediction and safety assessment , 2020, Decis. Support Syst..

[79]  John Lygeros,et al.  Aircraft and weather models for probabilistic collision avoidance in air traffic control , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[80]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[81]  Mario A. Rotea,et al.  New Algorithms for Aircraft Intent Inference and Trajectory Prediction , 2007 .

[82]  H. Erzberger,et al.  Automated conflict resolution, arrival management, and weather avoidance for air traffic management , 2012 .

[83]  Ioannis Lymperopoulos,et al.  Sequential Monte Carlo methods for multi‐aircraft trajectory prediction in air traffic management , 2010 .

[84]  Chris Dyer,et al.  Pushing the bounds of dropout , 2018, ArXiv.

[85]  Fei-Yue Wang,et al.  Data-Driven Intelligent Transportation Systems: A Survey , 2011, IEEE Transactions on Intelligent Transportation Systems.

[86]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.