{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T10:55:49Z","timestamp":1760784949143,"version":"3.41.2"},"reference-count":43,"publisher":"ASME International","issue":"4","license":[{"start":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T00:00:00Z","timestamp":1614211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The maintenance and improvement of safety are among the most critical concerns in civil aviation operations. Due to the increased availability of data and improvements in computing power, applying artificial intelligence technologies to reduce risk in aviation safety has gained momentum. In this paper, a framework is developed to build a predictive model of future aircraft trajectory that can be utilized online to assist air crews in their decision-making during approach. Flight data parameters from the approach phase between certain approach altitudes (also called gates) are utilized for training an offline model that predicts the aircraft\u2019s ground speed at future points. This model is developed by combining convolutional neural networks (CNNs) and long short-term memory (LSTM) layers. Due to the myriad of model combinations possible, hyperband algorithm is used to automate the hyperparameter tuning process to choose the best possible model. The validated offline model can then be used to predict the aircraft\u2019s future states and provide decision-support to air crews. The method is demonstrated using publicly available Flight Operations Quality Assurance (FOQA) data from the National Aeronautics and Space Administration (NASA). The developed model can predict the ground speed at an accuracy between 1.27% and 2.69% relative root-mean-square error. A safety score is also evaluated considering the upper and lower bounds of variation observed within the available data set. Thus, the developed model represents an improved performance over existing techniques in literature and shows significant promise for decision-support in aviation operations.<\/jats:p>","DOI":"10.1115\/1.4049992","type":"journal-article","created":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T19:04:09Z","timestamp":1611947049000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":19,"title":["Deep Spatio-Temporal Neural Networks for Risk Prediction and Decision Support in Aviation Operations"],"prefix":"10.1115","volume":"21","author":[{"given":"HyunKi","family":"Lee","sequence":"first","affiliation":[{"name":"Aerospace Systems Design Laboratory, School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA 30332"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tejas G.","family":"Puranik","sequence":"additional","affiliation":[{"name":"Aerospace Systems Design Laboratory, School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA 30332"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitri N.","family":"Mavris","sequence":"additional","affiliation":[{"name":"Aerospace Systems Design Laboratory, School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA 30332"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"33","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"year":"2017","author":"Anon","article-title":"Statistical Summary of Commercial Jet Airplane Accidents - Boeing Commercial Airplanes","key":"2021022509141419100_CIT0001"},{"year":"2017","author":"Anon","article-title":"Federal Aviaition Administration Aerospace Forecasts Fiscal Years 2016\u20132036","key":"2021022509141419100_CIT0002"},{"issue":"4","key":"2021022509141419100_CIT0003","doi-asserted-by":"crossref","first-page":"113246","DOI":"10.1016\/j.dss.2020.113246","article-title":"Bayesian Neural Networks for Flight Trajectory Prediction and Safety Assessment","volume":"131","author":"Zhang","year":"2020","journal-title":"Decision Support Syst."},{"year":"2003","author":"Anon","article-title":"Federal Aviation Administration Advisory Circular 120\u201371a","key":"2021022509141419100_CIT0004"},{"issue":"6","key":"2021022509141419100_CIT0005","doi-asserted-by":"crossref","first-page":"2285","DOI":"10.2514\/1.C034196","article-title":"Energy-Based Metrics for Safety Analysis of General Aviation Operations","volume":"54","author":"Puranik","year":"2017","journal-title":"J. Aircraft"},{"key":"2021022509141419100_CIT0006","doi-asserted-by":"crossref","DOI":"10.2514\/6.2018-3198","article-title":"Development of Possible Go-around Criteria for Transport Aircraft","author":"Campbell","year":"2018"},{"issue":"2","key":"2021022509141419100_CIT0007","doi-asserted-by":"crossref","first-page":"104492","DOI":"10.1016\/j.ssci.2019.09.015","article-title":"Applications of Machine Learning Methods for Engineering Risk Assessment\u2014A Review","volume":"122","author":"Hegde","year":"2020","journal-title":"Safety Sci."},{"year":"2011","author":"Anon","article-title":"Federal Aviation Administration, 14 CFR Sec. 121.344 Digital Flight Data Recorders for Transport Category Airplanes","key":"2021022509141419100_CIT0008"},{"year":"2003","author":"Campbell","article-title":"Flight Data Analysis-an Airline Perspective","key":"2021022509141419100_CIT0009"},{"issue":"1","key":"2021022509141419100_CIT0010","doi-asserted-by":"crossref","first-page":"S178","DOI":"10.1016\/j.ijrobp.2007.09.040","article-title":"Error Prevention As Developed in Airlines","volume":"71","author":"Logan","year":"2008","journal-title":"Int. J. Radiation Oncology Biol. Phys."},{"year":"2019","author":"Mart\u0131nez","article-title":"Forecasting Unstable Approaches With Boosting Frameworks and LSTM Networks","key":"2021022509141419100_CIT0011"},{"issue":"6","key":"2021022509141419100_CIT0012","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3390\/aerospace7060073","article-title":"Critical Parameter Identification for Safety Events in Commercial Aviation Using Machine Learning","volume":"7","author":"Lee","year":"2020","journal-title":"Aerospace"},{"issue":"12","key":"2021022509141419100_CIT0013","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.asoc.2018.07.061","article-title":"An Innovative Deep Architecture for Aircraft Hard Landing Prediction Based on Time-Series Sensor Data","volume":"73","author":"Tong","year":"2018","journal-title":"Appl. Soft. Comput."},{"issue":"11","key":"2021022509141419100_CIT0014","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.future.2018.06.023","article-title":"A Novel Deep Learning Method for Aircraft Landing Speed Prediction Based on Cloud-Based Sensor Data","volume":"88","author":"Tong","year":"2018","journal-title":"Fut. Generat. Comput. Syst."},{"year":"2012","author":"Diallo","article-title":"A Predictive Aircraft Landing Speed Model Using Neural Network","key":"2021022509141419100_CIT0015"},{"key":"2021022509141419100_CIT0016","doi-asserted-by":"crossref","DOI":"10.2514\/6.2020-2880","article-title":"A Supervised Learning Approach for Safety Event Precursor Identification in Commercial Aviation","author":"Ackley","year":"2020"},{"key":"2021022509141419100_CIT0017","doi-asserted-by":"crossref","DOI":"10.2514\/6.2021-0776","article-title":"Predicting Adverse Events and Their Precursors in Aviation Using Multi-Class Multiple-Instance Learning","author":"Bleu-Laine","year":"2021"},{"issue":"7553","key":"2021022509141419100_CIT0018","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep Learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"year":"2004","author":"Iverson","article-title":"Inductive System Health Monitoring","key":"2021022509141419100_CIT0019"},{"issue":"2","key":"2021022509141419100_CIT0020","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1049\/iet-its.2016.0208","article-title":"Lstm Network: A Deep Learning Approach for Short-Term Traffic Forecast","volume":"11","author":"Zhao","year":"2017","journal-title":"IET Intel. Transport Syst."},{"key":"2021022509141419100_CIT0021","first-page":"28","article-title":"Aircraft Hard Landing Prediction Using Lstm Neural Network","author":"Zhang","year":"2018"},{"issue":"11","key":"2021022509141419100_CIT0022","doi-asserted-by":"crossref","first-page":"102819","DOI":"10.1016\/j.trc.2020.102819","article-title":"Towards Online Prediction of Safety-critical Landing Metrics in Aviation Using Supervised Machine Learning","volume":"120","author":"Puranik","year":"2020","journal-title":"Trans. Research Part C: Emer. Technol."},{"issue":"1","key":"2021022509141419100_CIT0023","doi-asserted-by":"crossref","first-page":"126","DOI":"10.3141\/2214-16","article-title":"Computation of Aircraft Braking Distances","volume":"2214","author":"Pasindu","year":"2011","journal-title":"Trans. Res. Record"},{"issue":"10","key":"2021022509141419100_CIT0024","doi-asserted-by":"crossref","first-page":"688","DOI":"10.2514\/3.58590","article-title":"Airplane Brake-energy Analysis and Stopping Performance Simulation","volume":"16","author":"Wahi","year":"1979","journal-title":"J. Aircraft"},{"issue":"1\u20134","key":"2021022509141419100_CIT0025","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10846-009-9383-1","article-title":"A Survey of Motion Planning Algorithms From the Perspective of Autonomous Uav Guidance","volume":"57","author":"Goerzen","year":"2010","journal-title":"J. Int. Robot. Syst."},{"key":"2021022509141419100_CIT0026","first-page":"1","article-title":"Literature Survey of Trajectory Predictor Technology","author":"Musialek","year":"2010"},{"key":"2021022509141419100_CIT0027","first-page":"3083","article-title":"Modeling Trajectories With Recurrent Neural Networks","author":"Wu","year":"2017"},{"key":"2021022509141419100_CIT0028","first-page":"21","article-title":"Aircraft Trajectory Prediction Made Easy With Predictive Analytics","author":"Ayhan","year":"2016"},{"issue":"11","key":"2021022509141419100_CIT0029","doi-asserted-by":"crossref","first-page":"105423","DOI":"10.1016\/j.ast.2019.105423","article-title":"Combining Multiple Deep Learning Algorithms for Prognostic and Health Management of Aircraft","volume":"94","author":"Che","year":"2019","journal-title":"Aerospace Sci. Technol."},{"key":"2021022509141419100_CIT0030","first-page":"1","article-title":"LSTM-Based Flight Trajectory Prediction","author":"Shi","year":"2018"},{"key":"2021022509141419100_CIT0031","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2017\/430","article-title":"Modeling Trajectories With Recurrent Neural Networks","author":"Wu","year":"2017"},{"issue":"1","key":"2021022509141419100_CIT0032","doi-asserted-by":"crossref","first-page":"22","DOI":"10.2514\/1.I010582","article-title":"Anomaly Detection in General-Aviation Operations Using Energy Metrics and Flight-Data Records","volume":"15","author":"Puranik","year":"2018","journal-title":"J. Aerospace Inform. Syst."},{"key":"2021022509141419100_CIT0033","first-page":"3913","article-title":"General Aviation Approach and Landing Analysis Using Flight Data Records","author":"Puranik","year":"2016"},{"issue":"Mar","key":"2021022509141419100_CIT0034","first-page":"1157","article-title":"An Introduction to Variable and Feature Selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"2021022509141419100_CIT0035","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/23.589532","article-title":"Importance of Input Data Normalization for the Application of Neural Networks to Complex Industrial Problems","volume":"44","author":"Sola","year":"1997","journal-title":"IEEE. Trans. Nucl. Sci."},{"issue":"1","key":"2021022509141419100_CIT0036","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1076\/1566-0974(200003)7:1;1-V;FT003","article-title":"Safety Paradoxes and Safety Culture","volume":"7","author":"Reason","year":"2000","journal-title":"Injury Control Safety Promotion"},{"key":"2021022509141419100_CIT0037","first-page":"516","article-title":"A Deep Sequence-to-sequence Method for Aircraft Landing Speed Prediction Based on Qar Data","author":"Kang","year":"2020"},{"issue":"8","key":"2021022509141419100_CIT0038","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neur. Comput."},{"key":"2021022509141419100_CIT0039","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/j.procs.2018.05.069","article-title":"Conceptual Understanding of Convolutional Neural Network\u2014A Deep Learning Approach","volume":"132","author":"Indolia","year":"2018","journal-title":"Proc. Comput. Sci."},{"issue":"1","key":"2021022509141419100_CIT0040","first-page":"281","article-title":"Random Search for Hyper-Parameter Optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"2021022509141419100_CIT0041","first-page":"2951","article-title":"Practical Bayesian Optimization of Machine Learning Algorithms","volume":"4","author":"Snoek","year":"2012","journal-title":"Adv. Neur. Inform. Process. Syst."},{"key":"2021022509141419100_CIT0042","first-page":"361","article-title":"Bayesian Optimization in a Billion Dimensions Via Random Embeddings","volume":"55","author":"Wang","year":"2016","journal-title":"J. Art. Intel. Res."},{"issue":"1","key":"2021022509141419100_CIT0043","first-page":"6765","article-title":"Hyperband: A Novel Bandit-based Approach to Hyperparameter Optimization","volume":"18","author":"Li","year":"2017","journal-title":"J. Mach. Learn. Res."}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4049992\/6643914\/jcise_21_4_041013.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4049992\/6643914\/jcise_21_4_041013.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T00:20:33Z","timestamp":1670977233000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/doi\/10.1115\/1.4049992\/1096989\/Deep-Spatio-Temporal-Neural-Networks-for-Risk"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,25]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,8,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4049992","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"type":"print","value":"1530-9827"},{"type":"electronic","value":"1944-7078"}],"subject":[],"published":{"date-parts":[[2021,2,25]]},"article-number":"041013"}}