Search

This work presents an analysis of low-visibility event persistence and prediction at Villanubla Airport (Valladolid, Spain), considering Runway Visual Range (RVR) time series in winter. The analysis covers long- and short-term persistence and prediction of the series, with different approaches. In the case of long-term analysis, a Detrended Fluctuation Analysis (DFA) approach is applied in order to estimate large-scale RVR time series similarities. The short-term persistence analysis of low-visibility events is evaluated by means of a Markov chain analysis of the binary time series associated with low-visibility events. We finally discuss an hourly short-term prediction of low-visibility events, using different approaches, some of them coming from the persistence analysis through Markov chain models, and others based on Machine Learning (ML) techniques. We show that a Mixture of Experts approach involving persistence-based methods and Machine Learning techniques provides the best results in this prediction problem.

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is $${>}$$ 1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ( $${

The main methods for determining the length of the runway at the landing stage are shown in the given article. The shortcomings of these methods are proved. Statistical data that shows the need of landing distance recalculation for calculation of the required length of the runway are provided. The advanced mathematical model for calculating the required length of the runway at the landing stage is shown.

Two studies (Boeing 777 and 737 simulators) examined flight crews’ use of an Enhanced Flight Vision System (EFVS) for taxiing in low-visibility conditions in lieu of infrastructure for Low-Visibility Operations/Surface Movement Guidance and Control Systems (LVO/SMGCS). Twenty-five flight crews completed 21 short taxi scenarios under combinations of the following variables and levels: Runway visual range (RVR; 300, 500, 1000 ft); Enhanced-Flight-Vision System in head-up display (on/off); airport infrastructure - 3 levels. Two scenarios dealt with detecting obstacles near the taxi path. In both studies, the use of EFVS resulted in fewer route deviations, the majority of which occurred at 300 feet RVR with edge lights and either a standard painted centerline (Level 1) or a painted centerline with LVO/SMGCS “enhancements” but without centerline lights (Level 2). Deviation from taxiway centerline was variable, but was consistent between display conditions (EFVS/no EFVS) (mean

With special geographical and meteorological conditions, it is difficult for planes to fly at High altitude airport. Thus the rate of delay and accident remains very high. Flight accidents mostly happened when the planes was taking off or land. These are directly related with the runway visual range, which is crucial to airport operation. This paper propose a method to obtain the meteorological feature by using the deep auto-encoding network. Guided by this method, we use the auto-encoding network to study the meteorological feature and the Deep auto-coding network to explore the potential information in 2 dimensional data. We have made a real-time prediction of the runway visual range, by using the algorithm of machine learning and deep learning and the monitoring of meteorological characteristic through different dimensions. The precision rate is 91% and the TS score is up to 81.14%, 6% higher than the industry level of 75%. The method based on Ensemble Learnings multiple model fusion was studied to improve the overall performance. The final overall TS score of the fusion model have reached 82%. The study of the runway visual range prediction method in this paper help space dispatcher make a comprehensively and efficiently predict of runway visual range. It is expected to improve airport operation and reduce economic losses caused by flight accident efficiently.

At towered airports, air traffic controllers use an “out-the-window” view for situation awareness of the entire airport environment and for ensuring safe operation on and around airport runways. A controller's view of the runways can be limited by a number of factors, including weather conditions, obstructions, and night operations, making some aircraft movements difficult to detect especially in the absence of surface surveillance systems. In remote tower concepts, the same factors can impact the controller's airport view via cameras. While surface surveillance systems, when available, are designed to supplement the controller's visual surveillance, existing systems do not provide sufficient precision to identify the location of the aircraft nose or tail relative to runway entry and exit points, as designated by hold lines. These limitations can negatively impact the controller's situation awareness and can cause controllers to clear aircraft onto the runway when the runway is occupied, resulting in an operational error. The MITRE Corporation's Center for Advanced Aviation Systems Development (MITRE) conceived of, developed, and tested an airport runway hold line surveillance (HLS) capability that automatically monitors safety critical runway hold lines for aircraft crossings. The capability is envisioned to provide additional surveillance that improves safety but can also positively impact airport efficiency and runway capacity as controllers will no longer have to wait for aircrews to indicate that they are clear of the runway via radio before clearing the next operational use of the runway MITRE CAASD evaluated short-range surveillance sensor technologies and selected a commercially-available automotive radar sensor, then developed and tested a proof-of-concept prototype of the HLS concept. MITRE set up the HLS prototype at Washington Dulles International Airport (IAD) for data collection and analyzed the system's performance. The results of the analysis, measured in terms of positional accuracy, indicate that the concept of detecting aircraft position relative to the hold line using this type of sensor and automation is feasible and could enhance safety in both remote tower and conventional tower environments.

This paper describes operational concepts, certification considerations, and initial user evaluations for using an avionics system for low visibility taxi operations. The ability to taxi to/from the runway safely and efficiently in low visibility conditions is becoming increasingly important as airplanes and aircrews become equipped and approved for low visibility landing and takeoff. Typically in the United States, any surface operations below 1200 ft. Runway Visual Range (RVR) generally encourage the airport authority to have an approved Low Visibility Operations / Surface Movement Guidance and Control System (LVO/SMGCS) plan which specifies certain markings, signs, lighting, and controls in the airport movement area. Operations below 600 ft. RVR, or 500 ft. RVR under U.S. Federal Aviation Administration (FAA) Order 8000.94 enablement, require additional infrastructure in movement and non-movement areas and may also require Airport Surface Detection Equipment (ASDE or ASDE-X) or a suitable substitute1 to allow the ground controllers to adequately monitor surface traffic. Surface operations below 300 ft. RVR are generally precluded (or need extra controls such as the use of a “follow-me” truck). The operational concepts described in this paper show how using on-board systems based on synthetic and enhanced vision systems may substitute for or augment an airport’s existing infrastructure. These on-board systems along with proper additional mitigations under the LVO/SMGCS concept of Protected Low Visibility Taxi Routes (PLOVTR) would enable an appropriately equipped aircraft and qualified crew to safely taxi in low visibility conditions.

Synthetic Vision (SV) and Enhanced Flight Vision Systems (EFVS) may serve as game-changing technologies to meet the challenges of the Next Generation Air Transportation System and the envisioned Equivalent Visual Operations (EVO) concept - that is, the ability to achieve the safety and operational tempos of current-day Visual Flight Rules operations irrespective of the weather and visibility conditions. One significant obstacle lies in the definition of required equipage on the aircraft and on the airport to enable the EVO concept objective. A motion-base simulator experiment was conducted to evaluate the operational feasibility and pilot workload of conducting departures and approaches on runways without centerline lighting in visibility as low as 300 feet runway visual range (RVR) by use of onboard vision system technologies on a Head-Up Display (HUD) without need or reliance on natural vision. Twelve crews evaluated two methods of combining dual sensor (millimeter wave radar and forward looking infrared) EFVS imagery on pilot-flying and pilot-monitoring HUDs. In addition, the impact of adding SV to the dual sensor EFVS imagery on crew flight performance and workload was assessed. Using EFVS concepts during 300 RVR terminal operations on runways without centerline lighting appears feasible as all EFVS concepts had equivalent (or better) departure performance and landing rollout performance, without any workload penalty, than those flown with a conventional HUD to runways having centerline lighting. Adding SV imagery to EFVS concepts provided situation awareness improvements but no discernible improvements in flight path maintenance.

“Welcome everyone to the launch of the World Women’s League of Basketball and its inaugural 10–10 tournament.” A deep male voice boomed into the darkened stadium. Strobe lights slowly swept across the space, packed with celebrities, politicians, fashionistas and media, coming to a stop illuminating a raised platform that extended most of the length of the basketball court.

Closely spaced parallel runways(CSPRs) is the configuration mode frequently employed in planning and construction of the current airport runway. Simmod simulation software was operated here to construct the computer simulation models for different utilization patterns of runways, and made a well-organized analysis and quantitative evaluation of airport capacity and operational efficiency, given in the threshold staggering of CSPRs. Meanwhile, the effects of runway crossover and bypass-taxiing on operational efficiency of airport were also taken into account. The simulation result suggests: Abiding by IFR(instrument flight rules), a set of CSPRs are able to support 800 take-off and landing flights in peak day, while around 55~58 take-off and landing flights in peak hour. When the outside runway threshold is staggered toward the arriving aircraft and provided with the bypass taxiway, the take-off and landing efficiency of airport becomes the highest under the operational pattern(landing on the inside runway and taking off from the outside runway), about 3%~7% higher than that under any other operational pattern.

Low visibility and/or ceiling conditions have a strong impact on airports' traffic and their prediction is still a challenge for meteorologists. In this paper, the local characteristics of Low Visibility Procedure (LVP) conditions are investigated and the artificial neural network (ANN) based on resilient backpropagation as supervised learning algorithm is used to predict such meteorological conditions at Mohamed V international airport, Casablanca, Morocco. This article aims to assess the ANN ability to provide accurate prediction of such events using the meteorological parameters from the Automated Weather Observation Station (AWOS) over the period from January 2009 to March 2015. First, LVP conditions were classified according to their classes (fog LVP and no fog LVP) and their sources (Runway Visual Range -RVR LVP-, Ceiling -HCB LVP- or both) for both runway end points (35R and 17L). It is found that most of LVP conditions are associated with fog and are often due to decreasing of RVR below 600m. Next, Eleven ANNs were developed to produce LVP prediction for consecutive hourly valid forecast times covering the night and early morning. The Multi-Layer Perceptron (MLP) architecture with one hidden layer is used in this study. Results show that ANNs are able to well predict the LVP conditions and are robust to errors in input parameters for a relative error below 10%. Furthermore, it is found that the ANN's skill is less sensitive to LVP type being predicted.