Personal tools
You are here: Home / Invited Speakers

Invited Speakers

Invited Speakers

Learning from Environmental Data: Recent Achievements and New Challenges

Abstract:
The presentation gives an overview of applications of data driven models based on machine learning algorithms (MLA) for environmental data analysis, modelling, and visualization. In general, environmental phenomena must be considered in a high dimensional feature space. They are also nonlinear and highly variable at several spatial and temporal scales. Recently, MLA (e.g., artificial neural networks of different architectures, random forest, support vector machines and other kernel based methods) have been efficiently applied for a wide variety of environmental tasks. This presentation discusses several fundamental problems of primary importance in data driven modelling, in particular, monitoring network optimization via active learning, construction and understanding of feature space and relevant feature selection/extraction, model validation and model selection, predictions and interpretation of the results. Simulated and real data case studies, including topo-climatic modelling, environmental risks, natural hazards and renewable resources, are considered to illustrate the most recent achievements and to highlight new challenges.
kane

Mikhail Kanevski


Institute of Earth Surface Dynamics 
Faculty of Geosciences and Environment
University of Lausanne, Switzerland
Mikhail.Kanevski@unil.ch 

 

  
Biography:
Professor Mikhail Kanevski has a MS degree in physics and PhD degree in plasma physics both from the State University of Moscow. At present, he is a Professor of geomatics at the Institute of Earth Surface Dynamics, Faculty of Geosciences and Environment, University of Lausanne, Switzerland. His main scientific interests concern general topics in geomatics (Geographical Information Systems and remote sensing), as well as environmental modelling, geostatistics (predictions and simulations), space-time point patterns analysis, time series predictions, chaos and fractals. An important part of his research deals with geospatial data mining and application of cutting-edge machine learning algorithms to environmental risks and natural hazards (landslides, forest fires, avalanches) assessments. Current research topics include also analysis of socio-economic, financial and demographic data, visual data mining and visualization of high dimensional data. Prof. Kanevski has published two books and more than 100 peer-reviewed papers and conference proceedings on corresponding topics.
 

On the use of active and passive satellite Remote sensing in archaeology

Abstract:
During the last twenty years, the use of EO technologies in archaeology has been strongly increasing for several reasons:

i) the improvement of spectral and spatial resolution of satellite sensors; ii) the availability of user-friendly software and routines for data processing and analysis; iii) the interests of archaeologists to study the dynamics of human frequentation in relation to environmental changes. Moreover, archaeologists are ever more aware of the benefits of remote sensing applications for their investigations, such as: i) reduction of costs, time and risk associated with archaeological excavations; ii) creation of site strategies addressed to conservation and preservation.
The lecture will be focused on:
A) Overview on active and passive satellite remote sensing technologies in archaeology
B) Remarkable case studies will be presented have been selected from within Europe, Africa, Asia and Southern America in order to evaluate how satellite remote sensing can support archaeological investigations in different environmental setting, ranging from desert to vegetated covers, climate conditions, from arid to temperate ecosystems, and different archaeological deposits (buried remains, filled ditches) and building materials (stone, bricks, adobe, etc..).
Rosa Lasaponara

Rosa Lasaponara

CNR-IMAA

Istituto di Metodologie di Analisi Ambientale,
Potenza, Italy

e-mail: rosa.lasaponara@imaa.cnr.it

  
Biography:

Chief of ARGON (Earth Observation for ARchaeoloGy and EnvirONment) laboratory at IMAA-CNR. Main Research activities: (i) Integration of active and passive techniques for risk estimation, landscape evolution, biosphere monitoring, (ii) Reconstruction of palaeo-environmental scenarios aimed at understanding the mutual relationships between the dynamics of environmental changes and evolutionary processes of human presence: The specific objectives are the development of algorithms and methodologies concerning the extraction of information from historical data series collected by active and passive sensors (airborne and satellite platforms) for the characterization of phenomena and processes with particular reference to the identification of changes (on various spatial and temporal scales) and the operational monitoring of land degradation, natural and anthropic risks.

She has long experience in the organisation of scientific events (since 2007) acquired as Chair (EGU, SPIE, EARSeL, ICCSA) or co-Chair of international Conferences and workshops.

Editor of NHESS Natural Hazards and Earth System Sciences, (ii) member Editorial Board of numerous international journals, such as Sensors; Remote Sensing, Photo-interpretation.

- She is PI of numerous international and national projects funded by EU, MIUR, MAE
 

Compressed data structures for spatial data representation

Abstract:
The amount of data to manage in now a day applications is growing so fast that Big Data technologies are becoming a hot topic of research. Big Data includes a wide range of strategies and technologies oriented to guarantee the efficient process of huge volume of data.
Among those strategies data compression can play a important roll not completely explored yet. Compressed data structures not only avoid storage space, band width and disc- main memory transference, but also processing time. This saving of processing time is due to the fact that data can be processed and queries can be answered without decompress the data, that is, data can be used directly in the compressed representation.
In this presentation compression data structures for store and process spatial data will be presented in a conceptual way with the objective to easily introduce the public of the conference to this active research field.
Brisaboa

Nieves R. Brisaboa

Computer Science Department
University of A Coruña, Spain
brisaboa@udc.es

 

  
Biography:
Prof. Nieves R. Brisaboa founded the Database Laboratory (LBD, https://lbd.udc.es) at the Faculty of Informatics, University of A Coruña, Spain, and leads it since 1996.
She published a good number of scientific papers in first level conferences (SIGIR, ECDL, SPIRE, ECIR, ACM GIS, DCC, ADBIS etc.) and ISI Journals (ACM TOIS, IR, SP&E, IPM, Geoinformatica, etc) and her contributions, specifically in text compression and indexing are internationally cited. She has been the responsible for a number of research projects funded by public and private institutions. In 2002, LBD created a spin-off enterprise, ENXENIO https://www.enxenio.es, to commercialize the technology developed in LBD.
Prof. Brisaboa actively participates for more than 10 years as external evaluator of research projects for the Spanish government. During the last 4 years she has also participated in Spanish committees for evaluation of research project, people and scientific infrastructures.
From 2006 to 2009 Prof. Brisaboa acted as manager of the “Information Society” research program for the Galician (region of Spain) government, with responsibilities to assign evaluators to the research projects, to inform about the quality of the different proposals according the peer review external evaluations. She also monitored the project development and results.
Since 2009 she is the manager for the National Research and Development Program, in the Information Technologies subprogram. As manager of this subprogram, she manages the evaluation, funding and control, following the scientific execution, of the Spanish projects in Informatics.
 

The World is Your Browser

Abstract:
Augmented reality and printed electronics are two major building blocks for the Internet of Things. Yvsion is a platform to interact with objects in an augmented world. Printoo makes things alive by adding a "brain" to printed objects. Both Yvision and Printoo enable the interaction with the physical reality preserving the capabilities of the digital World. Educational, entertainment and retail applications illustrate this "World is your Browser" conceptual view.
Câmara

António Câmara

Faculty of Science and Technology
Universidade Nova de Lisboa, Portugal
asc@fct.unl.pt

  
Biography:
António Câmara obtained his BSc in Civil Engineering at IST (1977), MSc (1979) and PhD (1982) in Environmental Systems Engineering at Virginia Tech. He was a Post-Doctoral Associate at MIT in 1983.
He is a Professor at the New University of Lisbon. He was a Visiting Professor at Cornell University (1988-89) and MIT (1998-99).
During his career, António Câmara supervised 35 PhD students, and published more than 200 papers and 4 books, including “Environmental Systems” by Oxford University Press in 2002. He has been the keynote speaker at more than 50 international conferences.
António Câmara is a co-founder and CEO of YDreams, and the Chairman of Ynvisible, YDreams Robotics and Azorean, three companies he also co-founded. The work of his companies has been covered by Wired, Fast Company, Forbes, Business Week, Economist, Time, New York Times, Guardian, Liberation, El Pais, Huffington Post, Engadget, Tech Crunch, Cool Hunting, Gizmodo, CNN, CNBC, France 24 and many other international and national media.
António Câmara is also a Member of the Board of Audience Entertainment and Semapa, and of the Roundatable of Entrepreneurs of the European Institute of Technology.
He received many national and international awards during his career, including Premio Pessoa 2006 in Portugal, and one of the European Entrepreneur Awards by the European Union in 2009.
 

Aiding to decide in public policy making: new challenges

Abstract:
The talk aims at introducing a number of new concepts as well as to describe a number of challenges for decision sciences and technologies in supporting public policy decision making processes, besides suggesting ways to handle them. We first address the issue of characterising what makes public policy making peculiar with respect to other decision processes. We then introduce the concept of "policy analytics'' as a general framework within which we can shape the type of demand for decision analysis we face today. Once such a framework designed we can sketch a methodology allowing to consider decision support both from a theoretical (validity) and a practical (how to?) point of view. A number of precise theoretical and technological challenges will then be addressed in order to show how new research fields can contribute to the above frameworks: design of alternatives, argumentation theory, capabilities measurement etc.. 
alexis

Alexis Tsoukias

Laboratoire d'Analyse et Modélisation de Systèmes pour l'Aide à la DEcision
Université Paris Dauphine, France
tsoukias@lamsade.dauphine.fr
https://www.lamsade.dauphine.fr/~tsoukias

 

  
Biography:
Alexis Tsoukiαs (Greece, 1959) is a CNRS research director at LAMSADE, Université Paris Dauphine. He holds (1989) a PhD in Computer Science and Systems Engineering from Politecnico di Torino (Italy) where he also graduated engineering studies. His research interests include subjects such as: multiple criteria decision analysis, non conventional preference modelling, policy analytics, applied non classical logics, ordinal mathematical programming, artificial intelligence and decision theory. He is the co-author of two books and more than 70 journal articles and book contributions. He has been vice-president of ROADEF (the french OR society) as well as President of EURO (the European association of OR societies). Since 2007 he was coordinator of the European COST Action IC0602, Algorithmic Decision Theory funded within the FP7. He served the Research Administration in several positions, the last being the National Committee of the CNRS (elected member since 2008). Presently he is the Director of the LAMSADE. Besides teaching to several post-graduate classes in Paris and world wide, he ocasionally practices decision support, mainly in the area of public policy. He has been invited to more than 30 Universities world wide. He is member of several editorial boards, besides editing special issues of journals and conference volumes. He has been involved in the Programme and Organisation Committee of several conferences in Decision Analysis, OR and AI. Personal web page: https://www.lamsade.dauphine.fr/~tsoukias.