Skip to main content

Interactive Toolset for Understanding Trade-offs in ATM Performance

Periodic Reporting for period 3 - INTUIT (Interactive Toolset for Understanding Trade-offs in ATM Performance)

Reporting period: 2017-03-01 to 2017-08-31

The ongoing ATM modernisation programmes, including SESAR, build on ICAO Global ATM Operational Concept, one of whose cornerstones is performance orientation. A performance-based approach is defined by ICAO as one based on: (i) strong focus on desired/required results; (ii) informed decision making, driven by the desired/required results; and (iii) reliance on facts and data for decision making. While a lot of effort has traditionally been devoted to the development of microscopic performance models, there is a lack of useful macro approaches able to translate local improvements or specific regulations into their impact on high-level, system-wide KPIs. The goal of INTUIT is to explore the potential of visual analytics, machine learning and systems modelling techniques to improve our understanding of the trade-offs between ATM KPAs, identify cause-effect relationships between indicators at different scales, and develop new decision support tools for ATM performance monitoring and management. The specific objectives of the project are:
1. to conduct a systematic characterisation of the ATM performance datasets available at different spatial and temporal scales;
2. to propose new metrics and indicators providing new angles of analysis of ATM performance;
3. to develop a set of visual analytics and machine learning algorithms for the extraction of relevant and understandable patterns from ATM performance data;
4. to investigate new data-driven modelling techniques able to provide new insights about cause-effect relationships between performance drivers and performance indicators;
5. to integrate the newly developed analytical and visualisation functionalities into an interactive dashboard supporting multidimensional performance assessment and decision making.
The work done during the first 18 months of the project (1 March 2016 - 31 August 2017) includes:
• producing the Project Management Plan and other management documentation;
• gathering the different datasets that will be analysed throughout the project;
• selecting and launching a number of case studies based on the research questions previously identified;
• launching the development of a prototype performance monitoring and decision support tool based on the results of the case studies.

The work dealing with data acquisition and quality assessment has been documented in deliverables D2.1 Performance Data Inventory and Quality Assessment and D2.2 Qualitative analysis of performance drivers and trade-offs. The main outcomes documented in D2.1 are: the INTUIT data repository; a set of data quality factsheets; and a performance data guide, which helps identify the most suitable databases to find the desired performance data. D2.2 includes a set of research challenges grouped into seven threads: ATCO workload; interdependencies between environment, capacity and cost efficiency; effects of uncertainty on the performance of the network; safety impacts of the targets in other KPAs; definition of quantitative indicators to assess access and equity; new KPIs for future SES reference periods; and new forms of KPI visualisation.

Taking these research challenges as a starting point, a combination of visual analytics and machine learning techniques are being used to study interdependencies between KPAs/KPIs. The work has been structured in the form of case studies that address one or more of the research questions outlined above. During the first 18 months of the project, three case studies have been launched:
• CS-1. Modelling of airline route choices and the influence of unit rates on performance. The goal is to develop new models able to predict airline route choices between different airport pairs in order to evaluate the performance trade-offs arising from these decisions (e.g. cost efficiency vs environment). The proposed approach has shown significant potential to improve the understanding of route choices, and it is of potential application to the problem of pre-tactical traffic forecast.
• CS-2. Multi-scale representation of performance data. This case study aims to disaggregate traffic data and performance indicators at sector and/or traffic volume level, with different levels of temporal disaggregation, and later on model the relationship between these variables at different scales (e.g. what is the influence of individual sector characteristics on the aggregated performance of a certain ANSP?).
• CS-3. Identification of sources of en-route flight inefficiency. The case study aims to investigate the causes of inefficient routes in the European Network and their effects on performance. This case study is conducted in collaboration with the SESAR ER projects AURORA and APACHE.

In order to explore the datasets used for the abovementioned case studies and inform the performance modelling work, different visualisation and visual analytics tools have been developed. This work is documented in deliverable D3.1 Visual Analytics Exploration of Performance Data.

During the last 6 months of the project, the case studies will be completed, and their results will be documented in deliverable D4.1 Performance Metrics and Predictive Models. Finally, the visualisation tools and the new modelling approaches developed in the context of these case studies will be integrated into a prototype ATM performance monitoring and management dashboard.
INTUIT has analysed the main public and restricted-access databases regarding performance data in the ECAC area. This work, documented in deliverables D2.1 and D2.2 will be helpful for other research projects in order to select the data necessary for their research. The project has also performed a thorough literature review and an extensive stakeholder consultation to select the most relevant research threads in the field of ATM performance modelling, which has led to the work documented in deliverables D3.1 and D4.1:
• The development of a route choice predictor in the pre-tactical planning horizon is expected to contribute to fill the current gap in pre-tactical traffic forecast and improve the effectiveness of Demand and Capacity Balancing processes.
• The multiscale representation of performance data will enhance ATM performance monitoring by allowing the identification of low-performing sectors.
• The assessment of the cause and effects of en-route flight inefficiency will enable enhanced ATM performance monitoring capabilities, by helping detect and analyse low-performing routes in the European Network.

The outcomes of the project are expected to have impact at different levels. The methods and tools developed by the project will help set effective mechanisms to encourage ANSPs to improve performance and lead to a better tuning of local regulatory targets, and will provide a deeper understanding of the high-level impact of local improvements. The contributions to the improvement of the cost-efficiency and the quality of service of the ATM system will ultimate benefit all the stakeholders of the aviation sector. Additionally, the INTUIT partners are taking advantage of the project to take a leading position in the application of data analytics to ATM performance analysis. The INTUIT results are expected to feed into the subsequent stages of the R&I lifecycle and be the basis for the future development of new products and services for ATM performance monitoring and management.