The Terminal Aerodrome Forecast (TAF) is one of the most prominent and widely accepted forecasting tools for flight planning. The reliability of this instrument is crucial for its practical applicability, and its quality may further affect the overall air transport safety and economic efficiency. The presented study seeks to objectify the assessment of the success rate of TAFs in the full breadth of their scope, unlike alternative approaches that typically analyze one selected element. It aspires to submit a complex survey on TAF realization in the context of ANNEX 3 (a regulation for Meteorological Service for International Air Navigation issued by the International Civil Aviation Organization (ICAO)) defined methodology and to provoke a discussion on the clarification and completion of ANNEX 3. Moreover, the adherence of TAFs to ICAO ANNEX 3 (20th Edition) is examined and presented on the example of reports issued in the Czech Republic. The study evaluates the accuracy of TAF forecast verified by Aerodrome Routine Meteorological Report (METAR) and Special Meteorological Report (SPECI), whose quality was assessed first. The required accuracy of TAFs was achieved for most evaluated stations. A discrepancy in terms of formal structure between actually issued reports and the ANNEX 3 defined form was revealed in over 90% of reports. The study identifies ambiguities and contradictions contained in ANNEX 3 that lead to loose interpretations of its stipulations and complicate the objectification of TAF evaluation.

No abstract

No abstract

No abstract

Accurate visibility forecasting is essential for safe aircraft operations. This study examines how various configurations of the Random Forest model can enhance visibility predictions. Preprocessing techniques are employed, including correlation analysis to identify fundamental relationships in weather observations. Time-series data is transformed into a regular Data Frame to facilitate analysis. This study proposes a classification framework for organizing visibility data and phenomena, which is then used to develop a visibility forecast using the Random Forest method. The study also presents procedures for hyperparameter tuning, feature selection, data balancing, and accuracy evaluation for this dataset. The main outcomes are the Random Forest model parameters for a three-hour visibility forecast, along with an analysis of errors in low visibility forecasts. Additionally, models for one-hour forecasts and visibility forecasting under precipitation are also examined. The resulting models demonstrate a deterministic forecast accuracy of approximately 78%, with a false alarm rate of around 6%, providing a comprehensive overview of the capabilities of the Random Forest model for visibility forecasting. As anticipated, the model demonstrated limitations in accurately simulating fast radiative cooling or abrupt decreases in visibility caused by precipitation. Specifically, in relation to precipitation, the model achieved an accuracy of 79%, yet exhibited a false alarm rate of 19%. Additionally, this method sets a foundation for enhancing prediction accuracy through the inclusion of supplementary forecast data, while its implementation on real-world datasets expands the reach of machine learning techniques to the members of the meteorological community.