.. Apprendre-une-commande-de-poussée and .. La-masse-et-la-poussée, 138 6.3.2 Évaluation de la qualité d'une commande de poussée, Résultats, p.142

.. Comparaison-des-différentes-méthodes, 161 6.5.1 Apprendre directement l'altitude, p.167

. Dans-le-chapitre, un avion à partir des points passés d'une trajectoire. Les variables intervenant dans ces estimations sont uniquement des variables apparaissant dans le modèle physique Dans ce chapitre, on utilise des méthodes d'apprentissage en se servant de L'application de méthodes d'apprentissage sur ces deux sous problèmes permet de réduire l'écart entre le profil de vitesse prévu et celui effectivement suivi Ainsi la RMSE entre la vitesse observée et celle prédite est réduite de 35 % comparé à des choix moyens 2 . Plusieurs points peuvent limiter l'amélioration apportée par l'utilisation de méthodes d'apprentissage. En effet, on ne tient pas compte des interactions entre la cas prédite et le M ach prédit dans le calcul de V acible . On a traité séparément la cas et le M ach sans que f n'intervienne. Outre ce problème d'interaction, avoir une erreur nulle sur le couple (cas, M ach) n'engendre pas la même erreur sur V a suivant la trajectoire considérée, En effet, vol.5

. Le-tableau-6, 1 présente tout les algorithmes d'apprentissage testés et la grille d'hyperparamètres associé suivant l'algorithme. Les algorithmes T uneGrid ou T uneGridCV décrits dans 6.1 permettent de choisir les hyper-paramètres des algorithmes d'apprentissage. Les statistiques présentées sont calculées en se servant des prédictions obtenues par, S)

. Les-tableaux-6, 18 et 6.19 présentent les résultats des différentes méthodes. La RMSE sur l'altitude prédite diminue avec l'ajout de variables explicatives. La plus grande diminution de RMSE pour les trajectoires Mode-C se fait sur l

L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and regression trees. Statistics/Probability Series, pp.55-57, 1984.

P. Bühlmann and T. Hothorn, Boosting algorithms : Regularization , prediction and model fitting, Statistical Science, pp.477-505, 2007.

A. Buja and Y. Lee, Data mining criteria for tree-based regression and classification, Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining , KDD '01, pp.27-36, 2001.
DOI : 10.1145/502512.502522

P. G. Calders, Aircraft Performance Model Description Rapport technique 1.0, Eurocontrol, septembre 2002, pp.16-36

S. and ]. J. Santos, Eight-States Free Route Airspace Project : Free Route Airspace Concept, p.12, 2002.

G. Duong, J. Gawinowski, D. Nicolaon, and . Smith, Sector-Less Air Traffic Management Cité p Optimisation de trajectoires pour la résolution de conflits Polynomial roots from companion matrix eigenvalues, International Air Traffic Management R&D Seminar ATM- Mathematics of Computation, vol.17, issue.64 210, pp.12-187, 1995.

F. R. Fletcher-freund and R. E. Schapire, Common Trajectory Prediction Capability A new approach to variable metric algorithms Cité p. 52, 142 [Fox 97] J. Fox Applied regression analysis, linear models, and related methods A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting Greedy Function Approximation : A Gradient Boosting Machine, The Computer Journal Annals of Statistics Computational Statistics Data Analysis, vol.13, issue.38 4, pp.14-317, 1970.

E. Gallo, J. Lopez-leones, M. A. Vilaplana, F. A. Navarro, A. E. Nuic-]-d et al., Méthodes non-paramétriques pour la prévision d'intervalles avec haut niveau de confiance : application à la prévision de trajectoires d'avions Genetic algorithms in search, optimization , and machine learning Cité p. 44, 52, 199 [Goldfarb 70] D. Goldfarb. A Family of Variable-Metric Methods Derived by Variational Means Détection et résolution de conflits aériens : modélisations et analyse Thèse doctorat informatique de l'Ecole PolytechniqueGuyon 03] I. Guyon et A. Elisseeff. An introduction to variable and feature selection Online Learning for Ground Trajectory Prediction Solving ordinary differential equations, I : Nonstiff problems An interval Newton method Multiple view geometry in computer vision The elements of statistical learning, Trajectory Computation Infrastructure Based on BADA Aircraft Performance Model. Digital Avionics Systems Conference Thèse doctorat informatique de l'INPT, 2014. Cité p. 2, 3 Lower Bounds on Learning Decision Lists and Trees. Information and Computation, pp.33-50, 1970.

D. Heath, S. Kasif, and S. Salzberg, Induction of Oblique Decision Trees, Journal of Artificial Intelligence Research, vol.2, issue.2, pp.1-32, 1993.

]. N. Higham, Accuracy and stability of numerical algorithms, Society for Industrial and Applied Mathematics, p.100, 2002.
DOI : 10.1137/1.9780898718027

A. E. Hoerl and R. W. Kennard, Ridge Regression: Biased Estimation for Nonorthogonal Problems, Technometrics, vol.24, issue.1, pp.55-67, 1970.
DOI : 10.2307/1909769

/. Dti and /. Sder, Introduction à la prévision de trajectoire : analyse de cas sur 20 vols Paris, pp.6-832, 2006.

]. I. Jolliffe, A Note on the Use of Principal Components in Regression, Applied Statistics, vol.31, issue.3, pp.300-303, 1982.
DOI : 10.2307/2348005

M. Kaiser, M. Schultz, and H. Fricke, Enhanced jet performance model for high precision 4D flight path prediction, Proceedings of the 1st International Conference on Application and Theory of Automation in Command and Control Systems, pp.33-40, 2011.

]. S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, Optimization by Simulated Annealing, Science, vol.220, issue.4598, pp.671-680, 1983.
DOI : 10.1126/science.220.4598.671

R. Kohavi and G. H. John, Wrappers for feature subset selection, Artificial Intelligence, vol.97, issue.1-2, pp.273-324, 1997.
DOI : 10.1016/S0004-3702(97)00043-X

M. A. Konyak, D. Warburton, J. Lopez-leones, and P. C. Parks, A Demonstration of an Aircraft Intent Interchange Specification for Facilitating Trajectory-Based Operations in the National Airspace System, AIAA Guidance, Navigation and Control Conference and Exhibit, p.17, 2008.
DOI : 10.2514/6.2008-7145

L. L. Fablec-99-]-y and . Fablec, Prévision de trajectoires d'avions par réseaux de neurones, Thèse doctorat informatique de l'INPT, p.17, 1999.

M. and L. Merrer, Optimisation de trajectoire d'avion pour la prise en compte du bruit dans la gestion du, p.34, 2012.

J. López-leonés, M. A. Vilaplana, E. Gallo, F. A. Navarro, and C. Querejeta, The aircraft intent description language : a key enabler for air-ground synchronization in trajectorybased operations. Digital Avionics Systems Conference, pp.1-28, 2007.

I. Lymperopoulos, J. Lygeros, and A. L. Visintini, Model Based Aircraft Trajectory Prediction During Takeoff, AIAA Guidance, Navigation, and Control Conference and Exhibit, p.92, 2006.
DOI : 10.2514/6.2006-6098

J. Macqueen, Some methods for classification and analysis of multivariate observations, Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, pp.14-149, 1967.

]. R. Martin, G. Peters, and J. H. Wilkinson, The QR algorithm for real Hessenberg matrices. Handbook for Automatic Computation, pp.359-371, 1971.

W. F. Massy, Principal Components Regression in Exploratory Statistical Research, Journal of the American Statistical Association, vol.108, issue.309, pp.234-256, 1965.
DOI : 10.1080/01621459.1965.10480787

. Mehadhebi-99a-]-k and . Mehadhebi, Lissage en vitesse. Rapport technique, CENA, p.66, 1999.

. Mehadhebi-99b-]-k and . Mehadhebi, Lissage horizontal de trajectoires radar par des splines cubiques. Rapport technique, CENA, p.66, 1999.

]. R. Moore-66 and . Moore, Interval analysis, p.199, 1966.

L. H. Mutuel, P. Neri, and E. Paricaud, Initial 4D Trajectory Management Concept Evaluation, 10th USA/Europe Air Traffic Management Research and Developpment Seminar, p.13, 2013.

J. Nocedal, S. J. Wright, K. Pearson, A. Nuic, V. Mouillet et al., Numerical optimization User Manual for Base of Aircarft DATA (BADA) Rev.3.9. Rapport technique, EUROCONTROL, avril 2011 On lines and planes of closest fit to systems of points in space Base of Aircraft Data (BADA) Aircraft Performance Modelling Report Cité p. 24Poles 10a] D. Poles. Revision of atmosphere model in bada aircraft performance model Advanced aircraft performance modeling for ATM : Analysis of BADA model capabilities Error bounds for derivative estimates based on spline smoothing of exact or noisy data Spline smoothing with model-based penalties Generalized Boosted Models : A guide to the gbm package Pattern recognition and neural networks, Proceedings of the 29th IEEE/AIAA Digital Avionics Systems Conference (DASC) Linear Models : Least Squares and AlternativesReinsch 67] C. H. Reinsch. Smoothing by spline functions. Numerische mathematik, pp.52-66, 1901.

D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Parallel distributed processing : explorations in the microstructure of cognition chapitre Learning internal representations by error propagation, SCA 06] Service de l'Information Aéronautique. Annexe 2 à l'arrêté du 3 mars 2006 modifié, pp.318-362, 1986.

R. E. Schapire, The Strength of Weak Learnability, Machine Learning, p.54, 1990.

]. C. Schultz, D. Thipphavong, and H. Erzberger, Adaptive Trajectory Prediction Algorithm for Climbing Flights, AIAA Guidance, Navigation, and Control Conference, pp.92-95, 2012.
DOI : 10.2514/6.2012-4931

W. Porretta and . Ochieng, High-accuracy four-dimensional trajectory prediction for civil aircraft, Aeronautical Journal, vol.116, issue.1175, pp.45-66, 2012.

D. F. Shanno, Conditioning of quasi-Newton methods for function minimization, Mathematics of Computation, vol.24, issue.111, pp.647-656, 1970.
DOI : 10.1090/S0025-5718-1970-0274029-X

J. Sietsma and R. J. Dow, Creating artificial neural networks that generalize, Neural Networks, vol.4, issue.1, pp.67-79, 1991.
DOI : 10.1016/0893-6080(91)90033-2

B. W. Silverman, Some Aspects of the Spline Smoothing Approach to Non-Parametric Regression Curve Fitting, Journal of the Royal Statistical Society. Series B (Methodological ), vol.47, issue.1, pp.1-52, 1985.

A. Simpkin, Derivative Estimation in Noisy Data ; an Additive Penalty P-Spline Approach, p.66, 2010.

G. L. Slater, Adaptive improvement of aircraft climb performance for air traffic control applications, Proceedings of the IEEE Internatinal Symposium on Intelligent Control, p.92, 2002.
DOI : 10.1109/ISIC.2002.1157831

R. Slattery and Y. Zhao, Trajectory Synthesis for Air Traffic Automation, Journal of Guidance, Control, and Dynamics, vol.20, issue.2, pp.232-238, 1997.
DOI : 10.2514/2.4056

R. Storn and K. Price, Differential Evolution ? A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces, Journal of Global Optimization, vol.11, issue.4, pp.341-359, 1997.
DOI : 10.1023/A:1008202821328

M. Sugiyama, M. Krauledat, and K. Müller, Covariate shift adaptation by importance weighted cross validation, The Journal of Machine Learning Research, vol.8, pp.985-1005, 2007.
DOI : 10.1007/978-3-642-21551-3_31

URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.3425

H. Swenson, R. Barhydt, and M. Landis, Next Generation Air Transportation System (NGATS) Air Traffic Management (ATM)-Airspace Project. Rapport technique, National Aeronautics and Space Administration, p.12, 2006.

]. K. Tastambekov, S. Puechmorel, D. Delahaye, and C. Rabut, Aircraft trajectory forecasting using local functional regression in Sobolev space Transportation Research Part C : Emerging Technologies, Thipphavong 13a] D. P. Thipphavong. chapitre Reducing Aircraft Climb Trajectory Prediction Errors with Top-of-Climb Data. Guidance , Navigation, and Control and Co-located Conferences, pp.1-22, 2013.

R. Tibshirani, Regression Shrinkage and Selection Via the Lasso, Journal of the Royal Statistical Society, Series B, vol.58, pp.267-288, 1994.

D. Trefethen, L. N. Bau, and I. , Numerical linear algebra, Siam, vol.50, pp.50-54, 1984.
DOI : 10.1137/1.9780898719574

P. Van-hentenryck, Numerica : a modeling language for global optimization, Proceedings of the Fifteenth international joint conference on Artifical intelligence, pp.1642-1647, 1997.

V. N. Vapnik and A. Y. Chervonenkis, The necessary and sufficient conditions for consistency of the method of empirical risk minimization. Pattern Recogn, Image Anal, vol.1, issue.3, pp.284-305, 1991.

V. N. Vapnik-]-v and . Vapnik, The nature of statistical learning theory An overview of statistical learning theory, Neural Networks IEEE Transactions on, vol.10, issue.36, pp.38-988, 1995.

A. W. Warren and Y. S. Ebrahimi, Vertical path trajectory prediction for next generation ATM. Digital Avionics Systems Conference, Proceedings, vol.22, pp.11-12, 1998.

A. W. Warren, Trajectory Prediction Concepts for Next Generation Air Traffic Management, Europe ATM R&D Seminar, pp.92-97, 2000.

]. J. Wilkinson, Rounding errors in algebraic processes, p.99, 1994.

M. Xue, H. E. Zhao, and R. Slattery, Improvement of Trajectory Synthesizer for Efficient Descent Advisor AIAA-2011-7020 Capture conditions for merging trajectory segments to model realistic aircraft descents, 11th American Institute of Aeronautics and Astronautics (AIAA) Aviation Technology, Integration, and Operations (ATIO) Conference, pp.33-453, 1996.