Historical Track Data Research Articles

Trajectory Prediction of Marine Moving Target Using Deep Neural Networks with Trajectory Data

The position prediction of marine moving targets based on historical trajectories is an important assistance procedure for marine reconnaissance and surveillance. Limited by satellite access period, space-based historic trajectory data have sparse and uneven intervals. However, most current time-series prediction methods require uniform time intervals. For non-uniform time series data, common processing methods first use the interpolation algorithm to fit historical data, and then carry out predictions based on equal interval data after the uniform sample. The disadvantage is that the accuracy of the interpolation data will limit the prediction accuracy. In addition, the time-series prediction methods represented by the grey model (GM) and autoregressive model (ARM) can only deal with equal-interval time prediction, in which it is hard to satisfy the prediction demand of non-equidistant time. Aiming at the limitations of most time series prediction methods and meeting the requirement of long-term variable duration prediction, a novel trajectory prediction method for sparse and non-uniform time series data based on deep neural networks is proposed. Firstly, to maximize the mining of the original data features, the moving behavior features are extracted from the raw historical track data by calculating the information of position, velocity, and position change for feature extension. Then, because of the temporal coherence of the track data, and inspired by the design idea of local correlation of the convolutional neural network (CNN), the CNN model is used to excavate the navigation rules to achieve position prediction. Finally, training of the network model is accomplished based on historical track samples. The experiments are carried out based on the space-borne automatic identification system (AIS) observation data. Experimental results illustrate that the method behaves better than other methods with the superiority of lower requirements for sampling, stronger adaptability to data characteristics, and higher forecasting accuracy for long-term prediction. When applied to the satellite search of marine moving targets, the track prediction has the potential to reduce the uncertainty of target location and guide satellite searching missions, thereby significantly improving the searching efficiency of targets.

Development of Storm Surge Inundation Model and Database for Enhanced Climate Services in Bangladesh

Bangladesh's vulnerability to storm surge and success in reducing their impacts on the coastal communities are well-known. However, global warming is expected to increase both the frequency and the intensity of tropical cyclones. Also, the country still lacks in good quality data and information that can offer enhanced services to effectively design coastal defense systems and adapt to climate changes. This study developed a storm surge inundation model and database using the available tropical cyclones' database and simulated inundation for the past 31 cyclones in the Bay of Bengal, near the coastal regions of Bangladesh. The model uses a suite of Delft3D hydrodynamic and Delft Dashboard cyclone models. The model was calibrated and validated for two major cyclones, namely Sidr and Aila, using the available data for different bed roughness, track sources, and wind drag coefficient conditions. The results suggested that spatially varying bed roughness and wind varying drag conditions provide a more reliable prediction of inundation over the coast. The results also show that historical track data from Indian Meteorological Department optimize the model performances. The inundation database indicates that depending on the intensity and location, tropical cyclones can cause the maximum inundation of 1–5 m in the coastal lands of Bangladesh. More than 70% of the storms lead to the maximum inundation of more than 2 m, and about 25 and 7% of the storms can cause the maximum inundation of more than 3 and 4 m, respectively. The study also discusses the potential applications and shares insights on the implications of the inundation database that can offer improved information for enhanced climate services in Bangladesh. The database can be advanced with information about sectoral loss and damage as well as citizen science that will not only provide necessary information to design coastal protection structures and emergency measurements but also contribute to build long-term climate adaptation plans in the data-scarce region.

Track Pairs Collision Detection with Applications to Ship Collision Risk Assessment

The port waterway network plays an important role in the organization and management of port ship traffic. Due to limited ship operations, conflicts, congestion, and safety issues often arise in port waters. Conflicts between ships can be predicted by collision detection between ships. A novel collision detection algorithm for trajectory pairs is proposed by introducing variable time interval variables. In addition, to improve the overall accuracy of trajectory compression and reduce redundant calculation in collision detection, a multi-factor Douglas-Peucker algorithm adapted to ship trajectory compression is proposed with the consideration of speed and turn constraints. The maximum speed difference of the algorithm is increased by 1.5–2.5%, and the average speed difference increased by 2.0–4.5%. Based on the method mentioned above, the risk assessment framework of maritime collision is established and the risk situation of the waters near Ningbo Zhoushan Port is evaluated and analyzed by using ship historical track data.

Novel trajectory prediction algorithms for hypersonic gliding vehicles based on maneuver mode on-line identification and intent inference

Aiming at the trajectory prediction problem in hypersonic glide vehicle defense, novel trajectory prediction algorithms based on maneuver mode on-line identification and intent inference are proposed. For solving the maneuver mode identification and modeling problems, the auto-regressive method is introduced to reveal the hidden internal law in the historical tracking data and present the parametric model of the maneuver mode, thereby realizing the accurate trajectory prediction. To deal with the maneuver mode mutation problem, a novel intent inference based long-term trajectory prediction algorithm is proposed: firstly, the cost function of maneuver intent is constructed reasonably. Then, to solve the vehicle’s intent recursive calculation problem, the recurrence formula of the vehicle’s intent is derived based on Bayesian estimation theory, and the vehicle’s reachable region rapid resolution and discretization methods are proposed. Finally, the vehicle’s state recursive formula is derived with Bayesian estimation theory, and the trajectory prediction problem is transformed into the probability prediction problem of the vehicle appearing in a specific region. To avoid the large calculation problem in long-term trajectory prediction, the random sampling shooting method is adopted. The proposed trajectory prediction algorithms are combined to are combined to realize complementary advantages and provide as much valuable prediction information as possible for the defender. The simulation results show that the proposed trajectory prediction algorithms share high prediction accuracy and applicability.

Leveraging Individual and Collective Regularity to Profile and Segment User Locations from Mobile Phone Data

The dynamic monitoring of home and workplace distribution is a fundamental building block for improving location-based service systems in fast-developing cities worldwide. Inferring these places is challenging; existing approaches rely on labor-intensive and untimely survey data or ad hoc heuristic assignment rules based on the frequency of appearance at given locations. Motivated by the regularities in human behavior, we propose a novel method to infer the home, workplace, and third place based on an individual’s spatial-temporal patterns inferred from Call Detail Records. To capture the individual regularity, our method develops, for each person-location, the probability distribution that the person will appear in that location at a specific time of day using geo-temporal travel patterns a panel of individuals. To reveal the collective regularity, we apply eigen-decomposition to the matrix of historical geo-temporal data. Unsupervised machine learning techniques are then used to extract commonalities across locations for different groups of travelers, making inferences, such as home and workplace. Testing the methodology on real-world data with known location labels shows that our method identifies home and workplace with significant accuracy, improving upon the best practices in the literature by 79% and 34%, respectively. The methodology proposed is computationally efficient and is highly scalable to other real-world applications with historical tracking data. It provides a basis to improve location-based services, such as mobile commerce, social events recommendations, and urban transit design.

Research on Method of Trajectory Prediction in Aircraft Flight Based on Aircraft Performance and Historical Track Data

Traditional 4D trajectory prediction based on aircraft performance models and flight procedures does not consider control handover rules. Meanwhile, method based on historical data mining cannot accurately couple with real-time conditions such as weather and also cause computational efficiency problems. This project collected a large amount of historical data to form a control experience database and mined the historical database to obtain control experience and flight intention. On the basis of the traditional aircraft performance model, this paper puts forward the aircraft maneuver mode using strategy and introduces the high-altitude wind information from the weather information into the aircraft 4D model to optimize the aircraft 4D trajectory calculation model. By comparing the flight forecast time with the real crossing time, it is found that the average error of the improved 4D forecast crossing time is less than 5% of the flight time, which is obviously better than that before optimization. It is proved that the optimized method based on historical track data is effective and reliable, and the accuracy of 4D track prediction is improved greatly.

Examining expansion and trends in higher education in Mozambique, Africa

Concerns about expansion in higher education (HE) have increasingly become a focus of educational policymakers in sub-Saharan countries. However, critical analysis and discussion of the expansion of higher education in Mozambique and changes in its composition have received little attention. We used historical track data provided by the Ministry of Science and Technology, Higher and Professional and Technical Education of Mozambique (MCTESTP) from 2008 to 2015 to examine the growth from 58,643 to 116,037 students in the social sciences, humanities and social services (SSHSS). The natural sciences, engineering, agriculture and healthcare (NSEAH) registered growth from 15,051 to 41,092 students. The total number of students registered annually in SSHSS and NSEAH in 49 public and private institutions averaged 84,083 and 28,114 students, respectively, totalling approximately 174,680 students. The data allowed assessing the expansion and trends of HE rooted in practices of isomorphism reflected in diversification and fragmentation of the country’s HE system. Our analyses identified coercive and mimetic practices in general patterns of the expansion of HE, revealed by drastic expansion from 2 to 49 institutions, which since 1995 have been fragmented and restructured in response to labour market, political forces, economic and educational market forces. The information presented will support educational policy makers to reformulate suitable models of expansion of higher education for a mass public in Mozambique, framed in the sub-Saharan and international contexts.

A degree-100 lunar gravity model from the Chang’e 5T1 mission

Context.Chinese lunar missions have grown in number over the last ten years, with an increasing focus on radio science investigations. In previous work, we estimated two lunar gravity field models, CEGM01 and CEGM02. The recently lunar mission, Chang’e 5T1, which had an orbital inclination between 18 and 68 degrees, and collected orbital tracking data continually for two years, made an improved gravity field model possible.Aims.Our aim was to estimate a new lunar gravity field model up to degree and order 100, CEGM03, and a new tidal Love number based on the Chang’e 5T1 tracking data combined with the historical tracking data used in the solution of CEGM02. The new model makes use of tracking data with this particular inclination, which has not been used in previous gravity field modeling.Methods.The solution for this new model was based on our in-house software, LUGREAS. The gravity spectrum power, post-fit residuals after precision orbit determination (POD), lunar surface gravity anomalies, correlations between parameters, admittance and coherence with topography model, and accuracy of POD were analyzed to validate the new CEGM03 model.Results.We analyzed the tracking data of the Chang’e 5T1 mission and estimated the CEGM03 lunar gravity field model. We found that the two-way Doppler measurement accuracy reached 0.2 mm s−1with 10 s integration time. The error spectrum shows that the formal error for CEGM03 was at least reduced by about 2 times below the harmonic degree of 20, when compared to the CEGM02 model. The admittance and correlation of gravity and topography was also improved when compared to the correlations for the CEGM02 model. The lunar potential Love numberk2was estimated to be 0.02430±0.0001 (ten times the formal error).Conclusions.From the model analysis and comparison of the various models, we identified improvements in the CEGM03 model after introducing Chang’e 5T1 tracking data. Moreover, this study illustrates how the low and middle inclination orbits could contribute better accuracy for a low degree of lunar gravity field.

LSTM-Based Deep Learning Model for Predicting Individual Mobility Traces of Short-Term Foreign Tourists

The increasing availability of trajectory recordings has led to the mining of a massive amount of historical track data, allowing for a better understanding of travel behaviors by revealing meaningful motion patterns. In the context of human mobility analysis, the problem of motion prediction assumes a central role and is beneficial for a wide range of applications, including for touristic purposes, such as personalized services or targeted recommendations, and sustainability studies related to crowd management and resource redistribution. This paper tackles a particular case of the trajectory prediction problem, focusing on large-scale mobility traces of short-term foreign tourists. These sparse trajectories, short and non-repetitive, lack spatial and temporal regularity, making prediction analysis based on individual historical motion data unreliable. To face this issue, we hereby propose a deep learning-based approach, taking into account the collective mobility of tourists over the territory. The underlying semantics of motion patterns are captured by means of a long short-term memory (LSTM) neural network model trained on pre-processed location sequences, aiming to predict the next visited place in the trajectory. We tested the methodology on a real-world big dataset, demonstrating its higher feasibility with respect to traditional approaches.

On-demand assessment of air traffic impact of blocking airspace

ABSTRACTThe Federal Aviation Administration often blocks strategically located airspace volumes to ensure safety during a variety of operations that are potentially hazardous to aircraft, such as space launches. As the frequency of these operations increases, there is a growing need to deepen collaboration and transparency between stakeholders regarding the use of airspace. This collaboration can be supported by models and capabilities to quickly assess the impact of airspace closures, up to 12 months into the future. This paper presents a technique to enable a ‘what-if’ analysis capability coupled with a prediction model, whereby changes in airspace dimension, location, and activation time are reflected instantaneously as measures of projected impact. The technique can also be used for quick post-operations analysis using historical traffic data and to develop air traffic impact assessment capabilities accessible to a broad range of users outside of the air traffic domain. This research has three key components: developing a model to predict air traffic demand up to 12 months into the future, modelling air traffic impact to the affected traffic, and reducing this information into a data structure that can support on-demand analysis. The focus of this paper is on new techniques to predict demand using a large set of historical track data and further encode these projections to support the quick assessment of the impact of blocking various airspace volumes. Initial results show that the proposed data reduction scheme accurately represented the traffic crossing an airspace and resulted in data size reduction by over 50%. The projection model performed well, the actual number of impacted flights were within the estimated range of approximately 80% of the time. Finally, the responsiveness of the web-based prototype developed to illustrate the concept demonstrated the model’s ability to support an on-demand assessment of the air traffic impact of blocking airspace. A significant limitation of the projection model is that it is based on the historical traffic pattern within the U.S. airspace; separate analysis is needed to adapt it to other geographical location.

Impact of aerosols on tropical cyclone-induced precipitation over the mainland of China

In this study, we investigate the impacts of aerosols on tropical cyclone (TC) precipitation that occurred from 1980 to 2014 over China mainland. The TC-induced precipitation is objectively identified based on Western North Pacific (WNP) TC historical track data and daily precipitation data from meteorological stations. Aerosol optical depth (AOD) from the Second Modern-Era Retrospective Analysis for Research and Applications (MERRA-2) is used to represent the amount of aerosol pollution. The long-term variations in AOD and TC precipitation from the past 35 years are analyzed. A significant increasing trend is found for both the relative percentage of TC rainstorm days and the amount of aerosol loading. Together with the decreasing trend in the annual number of TCs affecting China, this indicates that aerosols are invigorating TC precipitation. For the TC precipitation during the study period, the relative occurrence of light rain shows a decreasing trend, while the proportion of heavy rain and rainstorms shows an increasing trend. Meanwhile, the intensity of the TC daily precipitation increases with the elevated pollution level, particularly during the TC initial period and for heavy TC rainfall. These statistical results based on long-term observations suggest that aerosols have a substantial impact on TC precipitation through microphysical effects and have the potential to impact the track, intensity, size, and lifespan of TCs over Southeast Asia.

Estimation of shipping emissions using vessel Long Range Identification and Tracking data

ABSTRACTShipping is a growing source of air pollutants and greenhouse gases, which are emitted mainly over an international territory, the seas, for which only shared responsibility by all countries is felt. The international community, in particular the International Maritime Organisation, is called to look for appropriate mitigation of these emissions. This starts with the reporting of emissions in an inventory and its mapping over the international territory to be able to then evaluate the effect of emission reduction policies on the environment. Under the European Monitoring and Evaluation Programme, Member States are required to provide gridded emissions for the different sectors but the spatial allocation of ship emissions requires a supranational setup to avoid transboundary inconsistencies. By using vessel density maps extracted from historical Long Range Identification and Tracking (LRIT) data, accurate high-resolution maps of emissions can be obtained in support of policy development, implementation and monitoring in the interrelated fields of air quality and climate.

GridiLoc: A Backtracking Grid Filter for Fusing the Grid Model with PDR Using Smartphone Sensors.

Although map filtering-aided Pedestrian Dead Reckoning (PDR) is capable of largely improving indoor localization accuracy, it becomes less efficient when coping with highly complex indoor spaces. For instance, indoor spaces with a few close corners or neighboring passages can lead to particles entering erroneous passages, which can further cause the failure of subsequent tracking. To address this problem, we propose GridiLoc, a reliable and accurate pedestrian indoor localization method through the fusion of smartphone sensors and a grid model. The key novelty of GridiLoc is the utilization of a backtracking grid filter for improving localization accuracy and for handling dead ending issues. In order to reduce the time consumption of backtracking, a topological graph is introduced for representing candidate backtracking points, which are the expected locations at the starting time of the dead ending. Furthermore, when the dead ending is caused by the erroneous step length model of PDR, our solution can automatically calibrate the model by using the historical tracking data. Our experimental results show that GridiLoc achieves a higher localization accuracy and reliability compared with the commonly-used map filtering approach. Meanwhile, it maintains an acceptable computational complexity.

Lunar gravity field determination using SELENE same-beam differential VLBI tracking data

A lunar gravity field model up to degree and order 100 in spherical harmonics, named SGM100i, has been determined from SELENE and historical tracking data, with an emphasis on using same-beam S-band differential VLBI data obtained in the SELENE mission between January 2008 and February 2009. Orbit consistency throughout the entire mission period of SELENE as determined from orbit overlaps for the two sub-satellites of SELENE involved in the VLBI tracking improved consistently from several hundreds of metres to several tens of metres by including differential VLBI data. Through orbits that are better determined, the gravity field model is also improved by including these data. Orbit determination performance for the new model shows improvements over earlier 100th degree and order models, especially for edge-on orbits over the deep far side. Lunar Prospector orbit determination shows an improvement of orbit consistency from 1-day predictions for 2-day arcs of 6 m in a total sense, with most improvement in the along and cross-track directions. Data fit for the types and satellites involved is also improved. Formal errors for the lower degrees are smaller, and the new model also shows increased correlations with topography over the far side. The estimated value for the lunar GM for this model equals 4902.80080±0.0009 km3/s2 (10 sigma). The lunar degree 2 potential Love number k 2 was also estimated, and has a value of 0.0255 ± 0.0016 (10 sigma as well).

A Climatology of Inland Winds from Tropical Cyclones for the Eastern United States

Abstract Tropical cyclones pose a significant threat to life and property along coastal regions of the United States. As these systems move inland and dissipate, they can also pose a threat to life and property, through heavy rains, high winds, and other severe weather such as tornadoes. While many studies have focused on the impacts from tropical cyclones on coastal counties of the United States, this study goes beyond the coast and examines the impacts caused by tropical cyclones on inland locations. Using geographical information system software, historical track data are used in conjunction with the radial maximum extent of the maximum sustained winds at 34-, 50-, and 64-kt (1 kt ≈ 0.5 m s−1) thresholds for all intensities of tropical cyclones and overlaid on a 30-km equal-area grid that covers the eastern half of the United States. The result is a series of maps with frequency distributions and an estimation of return intervals for inland tropical storm– and hurricane-force winds. Knowing where the climatologically favored areas are for tropical cyclones, combined with a climatological expectation of the inland penetration frequency of these storms, can be of tremendous value to forecasters, emergency managers, and the public.

An improved lunar gravity field model from SELENE and historical tracking data: Revealing the farside gravity features

A new spherical harmonic solution of the lunar gravity field to degree and order 100, called SGM100h, has been developed using historical tracking data and 14.2 months of SELENE tracking data (from 20 October 2007 to 26 December 2008 plus 30 January 2009). The latter includes all usable 4‐way Doppler data collected which allowed direct observations of the farside gravity field for the first time. The new model successfully reveals farside features in free‐air gravity anomalies which are characterized by ring‐shaped structures for large impact basins and negative spots for large craters. SGM100h produces a correlation with SELENE‐derived topography as high as about 0.9, through degree 70. Comparison between SGM100h and LP100K (one of the pre‐SELENE models) shows that the large gravity errors which existed in LP100K are drastically reduced and the asymmetric error distribution between the nearside and the farside almost disappears. The gravity anomaly errors predicted from the error covariance, through degree and order 100, are 26 mGal and 35 mGal for the nearside and the farside, respectively. Owing to the 4‐way Doppler measurements the gravity coefficients below degree and order 70 are now determined by real observations with contribution factors larger than 80 percent. With the SELENE farside data coverage, it is possible to estimate the gravity field to degree and order 70 without applying any a priori constraint or regularization. SGM100h can be used for global geophysical interpretation through degree and order 70.

GLGM‐3: A degree‐150 lunar gravity model from the historical tracking data of NASA Moon orbiters

In preparation for the radio science experiment of the Lunar Reconnaissance Orbiter (LRO) mission, we analyzed the available radio tracking data of previous NASA lunar orbiters. Our goal was to use these historical observations in combination with the new low‐altitude data to be obtained by LRO. We performed Precision Orbit Determination on trajectory arcs from Lunar Orbiter 1 in 1966 to Lunar Prospector in 1998, using the GEODYN II program developed at NASA Goddard Space Flight Center. We then created a set of normal equations and solved for the coefficients of a spherical harmonics expansion of the lunar gravity potential up to degree and order 150. The GLGM‐3 solution obtained with a global Kaula constraint (2.5 × 10−4l−2) shows good agreement with model LP150Q from the Jet Propulsion Laboratory, especially over the nearside. The levels of data fit with both gravity models are very similar (Doppler RMS of ∼0.2 and ∼1–2 mm/s in the nominal and extended phases, respectively). Orbit overlaps and uncertainties estimated from the covariance matrix also agree well. GLGM‐3 shows better correlation with lunar topography and admittance over the nearside at high degrees of expansion (l> 100), particularly near the poles. We also present three companion solutions, obtained with the same data set but using alternate inversion strategies that modify the power law constraint and expectation of the individual spherical harmonics coefficients. We give a detailed discussion of the performance of this family of gravity field solutions in terms of observation fit, orbit quality, and geophysical consistency.

Hurricane frequency and landfall distribution for coastal wetlands of the Gulf coast, USA

The regularity and severity of tropical storms are major determinants controlling ecosystem structure and succession for coastal ecosystems. Hurricane landfall rates vary greatly with high and low frequency for given coastal stretches of the southeastern United States. Site-specific meteorological data of hurricane wind speeds and direction, however, are only available for select populated cities of relatively sparse distribution and inland from the coast. A spatial simulation model of hurricane circulation, HURASIM, was applied to reconstruct chronologies of hurricane wind speeds and vectors for northern Gulf coast locations derived from historical tracking data of North Atlantic tropical storms dating back to 1851. Contrasts of storm frequencies showed that tropical storm incidence is nearly double for Florida coastal ecosystems than the westernmost stretches of Texas coastline. Finer-scale spatial simulations for the north-central Gulf coast exhibited sub-regional differences in storm strength and frequency with coastal position and latitude. The overall pattern of storm incidence in the Gulf basin indicates that the disturbance regime of coastal areas varies greatly along the coast, inland from the coast, and temporally over the period of record. Field and modeling studies of coastal ecosystems will benefit from this retrospective analysis of hurricane incidence and intensity both on a local or regional basis.

Adaptive Eulerian Modeling for Air Traffic Flow Management

A method for deriving an Eulerian traffic flow model in real time without depending on online integration of aircraft trajectories is introduced. In this method, online model derivation starts with a baseline Eulerian airspace model, which is derived offline using historical track data. In real time, parameters of this baseline model are adapted depending on the differences in flight plans and control volume aircraft counts between the baseline model and the real world. The baseline model derivation method is based on bookkeeping of control volume aircraft counts and, hence, the model produces control decisions in terms of whole number aircraft counts, unlike the fractional counts produced by Eulerian models based on average aircraft speeds. The bookkeeping-based model indirectly retains trajectory information and aircraft identities. Hence, it serves as an excellent tradeoff between Eulerian and trajectory-based modeling approaches. Most importantly, as an improvement over previous approaches, we take into consideration the control-dependent nature of the Eulerian model while computing optimal flow-control decisions. A key feature of this model is the use of interstream jump (y) parameters. These parameters make the model easily amenable to emulate a wide variety of control actions like rerouting. As a proof of concept, we derive a baseline model for the Fort Worth center from recorded track data for a period of 1 h on 13 March 2005 and adapt it it to predict sector counts for another time period. An application of the adaptive model to optimal rerouting is also presented.

Statistical modelling of North Atlantic tropical cyclone tracks

We present a statistical model of North Atlantic tropical cyclone tracks from genesis site through lysis. To propagate tracks we use the means and variances of latitudinal and longitudinal displacements and model the remaining anomalies as autoregressive. Coefficients are determined by averaging near-neighbour historical track data, with ‘near’ determined optimally by using jackknife out-of-sample validation to maximize the likelihood of the observations. The number of cyclones in a simulated year is sampled randomly from the historical record, and the cyclone genesis sites are simulated with a spatial probability density function using kernels with optimized bandwidths. Simulated cyclones suffer lysis with a probability again determined from optimal averaging of historical lysis rates. We evaluate the track model by comparing an ensemble of 1950–2003 simulations to the historical record using several diagnostics, including landfall rates. In most regions, but not all, the observations fall within the variability across the ensemble members, indicating that the simulations and observations are statistically indistinguishable. An intensity component to the TC model, necessary for risk assessment applications, is currently under development.