Estimating Runway Friction using Flight Data

Midtfjord, Alise Danielle; Huseby, Arne Bang

doi:10.3850/978-981-14-8593-0_3717-cd

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At Oslo airport, was set to zero as the contribution in retardation due to slope was negligible. More details about calculating the braking coefficient can be found in Midtfjord & Huseby [44] and Klein-Paste et al [33].…”

Section: Calculating the Response Variablementioning

confidence: 99%

A Machine Learning Approach to Safer Airplane Landings: Predicting Runway Conditions using Weather and Flight Data

Midtfjord,

De Bin,

Huseby

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The presence of snow and ice on runway surfaces reduces the available tire-pavement friction needed for retardation and directional control and causes potential economic and safety threats for the aviation industry during the winter seasons. To activate appropriate safety procedures, pilots need accurate and timely information on the actual runway surface conditions. In this study, XGBoost is used to create a combined runway assessment system, which includes a classification model to predict slippery conditions and a regression model to predict the level of slipperiness. The models are trained on weather data and data from runway reports. The runway surface conditions are represented by the tire-pavement friction coefficient, which is estimated from flight sensor data from landing aircrafts. To evaluate the performance of the models, they are compared to several state-of-the-art runway assessment methods. The XGBoost models identify slippery runway conditions with a ROC AUC of 0.95, predict the friction coefficient with a MAE of 0.0254, and outperforms all the previous methods. The results show the strong abilities of machine learning methods to model complex, physical phenomena with a good accuracy when domain knowledge is used in the variable extraction. The XGBoost models are combined with SHAP (SHapley Additive exPlanations) approximations to provide a comprehensible decision support system for airport operators and pilots, which can contribute to safer and more economic operations of airport runways.

show abstract

Section: Calculating the Response Variablementioning

confidence: 99%

A Machine Learning Approach to Safer Airplane Landings: Predicting Runway Conditions using Weather and Flight Data

Midtfjord,

De Bin,

Huseby

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although existing ASTM tests provide relevant information regarding the texture of the runway, which is important for the braking procedure of aircraft, more information is still needed to confirm the nature of contaminants on the surface. Efforts have been made to use weather and flight data to estimate surface conditions at landing using data analysis, machine learning and fusion and model correlation [15][16][17]. A few sensors exist in the market that are mounted in the runway to predict the type of contaminant present [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Assessment of Runway Surface Conditions by British Pendulum Testing under the Global Reporting Format Winter Conditions

et al. 2022

View full text Add to dashboard Cite

Poor braking performance on runways during winter is one of the most significant factors causing runway excursions. The International Civil Aviation Organization (ICAO) proposed a standardized method, named the Global Reporting Format (GRF), to establish runway surface conditions based on human observers. The GRF includes the description of most winter conditions. This work aimed at reproducing the GRF winter conditions in the laboratory, and to monitor the effect of the surface conditions, both without surface treatment and with surface treatment using liquid runway de-icing products (RDP) in both de-icing and anti-icing modes, using the British Pendulum Tester (BPT). The reproduction of the GRF winter conditions was possible in the laboratory since the BPT results correlated well with the GRF ratings. The worst conditions retained snow on ice. Wet conditions obtained with water and RDPs (potassium formate KFO, potassium acetate KAC and hybrid glycol-KAC HYB) behave similarly, indicating that RDPs alone on a runway for prevention are not any more dangerous than just water. The range from wet to dry, equivalent to a British Pendulum Number (BPN) from ~40 to ~50, was considered as good conditions on the runway. All the RDPs tested in the study improved the BPN from untreated conditions. In most of the conditions, the RDPs improved the BPN to values in the range of favorable conditions. KFO and KAC reacted almost in the same way for each condition. However, the HYB was better in conditions with ice. The obtained results demonstrated that simulated laboratory winter conditions could be used to determine the efficiency of RDPs in both de-icing and anti-icing modes.

show abstract

Estimating Runway Friction using Flight Data

Cited by 2 publications

References 0 publications

A Machine Learning Approach to Safer Airplane Landings: Predicting Runway Conditions using Weather and Flight Data

A Machine Learning Approach to Safer Airplane Landings: Predicting Runway Conditions using Weather and Flight Data

Assessment of Runway Surface Conditions by British Pendulum Testing under the Global Reporting Format Winter Conditions

Contact Info

Product

Resources

About