This site is promoted by The Innaxis Research Institute to encourage the aviation community to use data analytic techniques to strengthen existing operational concepts and envision new ways to build safer and more efficient aviation systems.


Data science in aviation entails the study of data extracted from the system, with the goal of detecting signals and developing new data-driven operational concepts. It builds on the basic assumption that the data generated by air transport fully characterises the system, as most operational events cannot be considered random in nature; and thus the forces underlying those events should be encoded in the data. Due to the capacity surge to acquire, store and analyse large datasets in the last years, traditional models are being challenged by powerful data analysis solutions in various industries.

Data science is also a multi-disciplinary endeavour combining a range of skills from a variety of fields. Utilising best practices from data science, many professionals are exploring the intersection with different disciplines: complexity science, statistical physics, network theory, data mining, knowledge discovery, computer science, indexing techniques, stream data processing, data-evaluation environments, scalable analytics, visualization and, very importantly, strong domain expertise.

Within the aviation sector in particular, a large amount of unstructured, heterogeneous data from diverse stakeholders and of a diverse nature is gathered and stored, including: safety data and reports, flight plans, navigation data, airport data, radar tracks, etc. From airlines to ANSPs or airports, the ability to collect information through different data sensors is growing exponentially. Nevertheless, how the different stakeholders take advantage of these data has not evolved so rapidly and there is still a large gap for improvement.

A promising field is examining the historical analysis of aviation data. Through descriptive analytics, data science paves the way for depicting and understanding what is hidden in past data. Advanced techniques, or predictive analytics are used to provide a prediction based on analyzing large quantities of data. Those techniques leverage historical analysis and allow the creation and automated selection of more sophisticated features, such as combinations that normally escape human direct observation due to the complexity of the data. This is implemented through a data fusion from different sources; safety data and reports, flight plans, navigation data, airport data, radar tracks, etc, which provide a 360-degree view of air transport related events.

It is important to note that while automated data analysis, classification and understanding attracted the public attention since the late 80’s, it presents scientific and technical hurdles. First, every result will still need to be carefully validated by human personnel before being automated and implemented. Data management, storage, cleaning, indexing and analysis needs to be streamlined and designed so that the system is capable of responding in the appropriate reaction time for each application (whether it be strategic oversight, real time or post-analysis).

We, at INNAXIS, strongly believe that the application of data science principles to the aviation sector can open the gate to significant improvements in many key aspects of aviation such as safety enhancement, flight efficiency, environmental-impact mitigation or delay reduction.


Samuel Cristobal

Science and Technology Director of Innaxis, former Air Transport performance modeller and Researcher. He holds a MSc in Advanced Mathematics and Applications (Universidad Autónoma of Madrid); a BCs (with honors) in Mathematics (Universidad Complutense de Madrid); and a BEng (valedictorian) in Telecommunication Systems (Universidad Politécnica de Madrid). Samuel has a strong theoretical mathematical background and vast experience in mathematical models, data science, simulation, and software architectures applied to solve air transport modelling problems. He has conceived different mathematical models within several SESAR, FP6, FP7 and H2020 funded projects and Innaxis internal air transport performance assessment tools. Samuel has been the architect of many innovative models for ATM, creating a breakthrough in ATM modelling by incorporating Complexity Networks, stochastic functions, even-driven simulation and agent based modelling; The culmination of that line of research is the Mercury platform.

Inés Gómez

Inés is in charge of visual communications at Innaxis. She holds an Honours B.A. degree 2:1 in Design from the Universidad Complutense de Madrid, where she specialized in graphic design. She also studied art direction and photography during her Erasmus at the Limerick School of Art and Design in Ireland. Her background as dedicated to typography, data visualization and photography has defined her profile as a visual designer. She also works closely with research after having collaborated on various projects dedicated to theories of art and design and social design both in Spain and abroad.

Paula López-Catalá

Programme Director at Innaxis, received her master’s degree in Aerospace Engineering at the Polytechnic University of Madrid. She has more than 9 years of experience in the field of Air Transport Research holding different positions. Paula started as a researcher in FP6 and then she was responsible of the International Innovation Unit supporting the Ministry in fostering the participation of Spanish entities in international Aeronautics, Air Transport and Space research programmes. After coordinating the SESAR WPE ComplexWorld Network she is the coordinator of the H2020 project aimed at improving aviation safety based on big data tools. In addition to her project management skills, Paula follows the different European research programmes and initiatives with strong commitment to innovation as well as its policy framework. Her professional trajectory has provided her a broad knowledge of the field of Air Transport Research and Innovation.

Jorge Martín

Jorge Martín, Data Engineer at Innaxis, is currently performing research and software development for different initiatives within SESAR, H2020 and EUROCONTROL. Previously, he obtained a master’s degree in Computer Science (MP with honors) from the Polytechnic University of Madrid. During his studies, Jorge has experience in Knowledge and Intelligent systems (Department of Artificial Intelligence, UPM, Madrid). He worked in different research projects related to hydrology, ATM and Unmanned Vehicles with different partners. He also has relevant experience in project management for projects related with real state data. Additionally, Jorge has a valuable experience on software development in modeling and simulating complex systems and in dealing with complex datasets.

Darío Martínez

Darío Martínez is the resident Data Scientist at Innaxis. Darío holds a master’s degree in Telecommunication Engineering at the Polytechnic University of Madrid and specialises in Data Science backed with several years of experience in data-driven European initiatives. He worked as intern (Full Stack developer – Data Analyst) at the New Generation Internet Group (GING) at the Polytechnic University of Madrid during his studies. Darío developed his master’s thesis through his Data Scientist position at the Distributed Information Systems Laboratory (LSIR), EPFL, Lausanne. Darío is particularly interested in AI, NLP, Data Mining and Machine Learning algorithms in Big Data environments.

David Pérez

Director of Tadorea, received his master’s degree in Aerospace Engineering and Air Transport from the Polytechnic University of Madrid. His more than 20 years of professional experience on a variety of aviation stakeholders, in Europe as well as in the USA. David is responsible for Tadorea, overviewing the applicability of data science to the aviation field David, leveraging on the scientific breakthroughs, and methods and tools developed by Innaxis. David has focused most of his career in research in the Air Transport sector, including technical and project management functions.

Damir Valput

Damir is a Junior Researcher at Innaxis. He holds a MSc degree (magna cum laude) in Electrical Engineering and Information Technology from the University of Zagreb, Croatia, as well as a BSc in Electrical Engineering and Information Technology from the same university. His main interests include data science, artificial intelligence, software modelling, applied mathematics and statistics. Damir has a strong background and extensive experience in developing machine learning models, mathematical modelling, simulation, and algorithm design. Upon graduation, he spent several years working in fundamental scientific research studying algorithm complexity and software modelling. Before joining Innaxis, he worked on applications of machine learning algorithms in the area of air pollution and traffic forecasting.


Enrique Díaz

Héctor Ureta

Massimiliano Zanin

Seddik Belkoura