Final Report Summary - DENOT-EM-CI (Developing Nonlinear Tools for Environmental Modeling and Chemoinformatics)
The researcher, Federico Montesino Pouzols, has recently obtained his phD degree in computer science from University of Seville, Spain. He joined in June 2009 the centre of excellence in adaptive informatics of the Academy of Finland, department of information and computer science (ICS), Helsinki University of technology (HUT), under the supervision of Dr Amaury Lendasse, docent and senior researcher, head of the time series prediction and chemoinformatics group (TSPCi). In January 2010, Helsinki University of technology became part of the newly created Aalto University. The host group is part of a department with a high research profile. The ICS department obtained the top ranking in the Aalto University research assessment exercise in 2009, where the department was rated at the outstanding international level for scientific quality of research and impact as well as research environment and future potential.
The interests of the researcher had been so far in the area of modeling nonlinear systems by computational intelligence methods, with a focus on neuro-fuzzy techniques. As a consequence of his previous professional and research interests, the main area of application of these techniques has been network traffic performance analysis and control. The broad aim of this project was to develop nonlinear tools for environmental modeling and chemoinformatics. In particular, the tools developed will be applied to modeling environmental changes in the Baltic Sea in close cooperation with experts in the field.
This Marie Curie intra-european fellowship (IEF) provided the researcher a solid foundation for attaining a senior researcher profile in areas of increasing importance, and one of the major themes of the seventh framework programme. After the fellowship the researcher is expected to start a long-term career in academic and/or research institutions concerned with the aforementioned areas. In the next paragraphs we describe the progress of training activities and give an overview of the work progress compared to the original work programme.
Description of the progress of training activities
The research has taken take place mainly at the adaptive informatics centre of excellence at Helsinki University of technology, hosted by the ICS department. The focus of the ICS department's research and teaching activity is on advanced computational methods for modeling, analysing, and solving complex tasks in technology and science. The research aims at the development of fundamental computer science methods for the analysis of large and high-dimensional data sets, and to the modeling and design of complex software, networking and other computational systems.
The research topics and main objectives detailed in the original project proposal have been addressed, as further discussed in the next section. The main areas of application are in biological and environmental sciences. These lie within what can be broadly named as biological informatics, which embraces applications of informatics to a wide spectrum of diverse areas such as bimolecular informatics (microbiology, genetics and genomics), environmental informatics (fisheries, contaminant biology, terrestrial, freshwater and marine ecosystems), biodiversity informatics, neuroinformatics, health or medical informatics, etc
Among these applications we have focused our research on application areas where we have tight collaboration links with experts in the field. During this period the researcher has focused his activities on the specific topics discussed in the next section. This has effectively broadened the spectrum of application fields which the researcher is familiar with. In addition he is developing new capacities regarding biological and environmental modeling (with specific background, objectives as well as data acquisition and measurement procedures).
The multidisciplinary research environment provided by the host group and the ICS department in general has exposed the fellow to the state-of-the-art in the field of adaptive informatics. The research has been trained in the field of the proposed project within a dynamic group and an international network of experts. More specifically, throughout the project the fellow is working in close cooperation not only with the members of the TSPCi group but also with experts in nonlinear analysis from Université Catholique de Louvain, experts in environmental modeling from University of Turku, Leibniz Institute for Baltic Sea research, Germany, and Baltic Nest Institute, Sweden, among others. This is providing him with a high-level training environment.
As specified in the career development plan, the training objectives for the researcher are:
- Achieve an in-depth understanding of current methods, tools and models and their limitations.
- Continue his research on variable selection and ranking in the context of demanding applications, and in cooperation with experts in these areas.
- Further develop is expertise in automatic modeling methods, getting acquainted with the needs of experts in biological and environmental sciences.
- Extend his research interests to very long-term prediction methods as well as biological and environmental modeling.
The researcher has progressed towards getting fully acquainted with the state of the art in nonlinear modeling, especially in the field of time series prediction and its applications to environmental modeling and chemoinformatics, at a national, European and worldwide level. To this end, the researcher has been extending his expertise in high-performance and parallel computing, employing the services provided by CSC, IT center for science Ltd, administered by the Finnish Ministry of education and culture. This includes the NorduGrid and EGEE (enabling grids for e-science) grid computing infrastructures.
As advanced in the career development plan, the researcher has actively engaged in teaching activities. In particular, he has organised the special seminar course 'Nonlinear, nonstationary data analysis: The Hilbert-Huang transform and its applications', for graduate students in the fall semester of 2009, at the Dpt of information and computer sScience. The course included students from different international masters programmes. The researcher also instructed several students in a number of extended academic projects around the analysis of environmental data in the Baltic region. This included topics such as 'Analysing oxygen levels in the Baltic Sea with empirical mode decomposition,v and 'Analysis of the evolution of salinity in different regions of the Baltic Sea.' In addition, the researcher is currently preparing a special course 'Evolving intelligent systems. methodology and applications', for graduate students, scheduled for the fall semester of 2010. He is also collaborating in the supervision of students at the master's and phD levels. The researcher has specially developed his skills as a result of his active cooperation within the AMBER (assessment and modelling of Baltic ecosystem response) project (part of the BONUS+ EEIG ERA-NET), with ongoing cooperation with a number of experts in biological and environmental sciences in the Baltic region. Since spring 2010, he has taken on the role of principal investigator from Aalto University in this project.
The interests of the researcher had been so far in the area of modeling nonlinear systems by computational intelligence methods, with a focus on neuro-fuzzy techniques. As a consequence of his previous professional and research interests, the main area of application of these techniques has been network traffic performance analysis and control. The broad aim of this project was to develop nonlinear tools for environmental modeling and chemoinformatics. In particular, the tools developed will be applied to modeling environmental changes in the Baltic Sea in close cooperation with experts in the field.
This Marie Curie intra-european fellowship (IEF) provided the researcher a solid foundation for attaining a senior researcher profile in areas of increasing importance, and one of the major themes of the seventh framework programme. After the fellowship the researcher is expected to start a long-term career in academic and/or research institutions concerned with the aforementioned areas. In the next paragraphs we describe the progress of training activities and give an overview of the work progress compared to the original work programme.
Description of the progress of training activities
The research has taken take place mainly at the adaptive informatics centre of excellence at Helsinki University of technology, hosted by the ICS department. The focus of the ICS department's research and teaching activity is on advanced computational methods for modeling, analysing, and solving complex tasks in technology and science. The research aims at the development of fundamental computer science methods for the analysis of large and high-dimensional data sets, and to the modeling and design of complex software, networking and other computational systems.
The research topics and main objectives detailed in the original project proposal have been addressed, as further discussed in the next section. The main areas of application are in biological and environmental sciences. These lie within what can be broadly named as biological informatics, which embraces applications of informatics to a wide spectrum of diverse areas such as bimolecular informatics (microbiology, genetics and genomics), environmental informatics (fisheries, contaminant biology, terrestrial, freshwater and marine ecosystems), biodiversity informatics, neuroinformatics, health or medical informatics, etc
Among these applications we have focused our research on application areas where we have tight collaboration links with experts in the field. During this period the researcher has focused his activities on the specific topics discussed in the next section. This has effectively broadened the spectrum of application fields which the researcher is familiar with. In addition he is developing new capacities regarding biological and environmental modeling (with specific background, objectives as well as data acquisition and measurement procedures).
The multidisciplinary research environment provided by the host group and the ICS department in general has exposed the fellow to the state-of-the-art in the field of adaptive informatics. The research has been trained in the field of the proposed project within a dynamic group and an international network of experts. More specifically, throughout the project the fellow is working in close cooperation not only with the members of the TSPCi group but also with experts in nonlinear analysis from Université Catholique de Louvain, experts in environmental modeling from University of Turku, Leibniz Institute for Baltic Sea research, Germany, and Baltic Nest Institute, Sweden, among others. This is providing him with a high-level training environment.
As specified in the career development plan, the training objectives for the researcher are:
- Achieve an in-depth understanding of current methods, tools and models and their limitations.
- Continue his research on variable selection and ranking in the context of demanding applications, and in cooperation with experts in these areas.
- Further develop is expertise in automatic modeling methods, getting acquainted with the needs of experts in biological and environmental sciences.
- Extend his research interests to very long-term prediction methods as well as biological and environmental modeling.
The researcher has progressed towards getting fully acquainted with the state of the art in nonlinear modeling, especially in the field of time series prediction and its applications to environmental modeling and chemoinformatics, at a national, European and worldwide level. To this end, the researcher has been extending his expertise in high-performance and parallel computing, employing the services provided by CSC, IT center for science Ltd, administered by the Finnish Ministry of education and culture. This includes the NorduGrid and EGEE (enabling grids for e-science) grid computing infrastructures.
As advanced in the career development plan, the researcher has actively engaged in teaching activities. In particular, he has organised the special seminar course 'Nonlinear, nonstationary data analysis: The Hilbert-Huang transform and its applications', for graduate students in the fall semester of 2009, at the Dpt of information and computer sScience. The course included students from different international masters programmes. The researcher also instructed several students in a number of extended academic projects around the analysis of environmental data in the Baltic region. This included topics such as 'Analysing oxygen levels in the Baltic Sea with empirical mode decomposition,v and 'Analysis of the evolution of salinity in different regions of the Baltic Sea.' In addition, the researcher is currently preparing a special course 'Evolving intelligent systems. methodology and applications', for graduate students, scheduled for the fall semester of 2010. He is also collaborating in the supervision of students at the master's and phD levels. The researcher has specially developed his skills as a result of his active cooperation within the AMBER (assessment and modelling of Baltic ecosystem response) project (part of the BONUS+ EEIG ERA-NET), with ongoing cooperation with a number of experts in biological and environmental sciences in the Baltic region. Since spring 2010, he has taken on the role of principal investigator from Aalto University in this project.