SDC, Data Science and Knowledge

Fabio Guttler

From SDC, Data Science and Knowledge
Revision as of 12:55, 16 March 2016 by Guttler (talk | contribs) (→‎PhD Thesis in Geography (LETG - Brest))
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Post-doc in the SDC team (formerly BFO team) of the ICube laboratory of the University of Strasbourg since May 2015.


Current post-doc position in satellite remote sensing (Icube and LIVE - Strasbourg)

Theme: Change detection and knowledge extraction from time series of satellite images

Key-words: ANR COCLICO, Change detection, Machine learning, Fuzzy classification, Temporal clustering, time series

Research supervisors: Pierre Gançarski and Anne Puissant

Host research units : ICube and LIVE - Strasbourg, France

Previous post-doc position in satellite remote sensing (TETIS and LIRMM - Montpellier)

Theme: Change detection in time series satellite images using data mining techniques

Key-words: Equipex GEOSUD, Spatio-temporal dynamics, Data mining, k-partite graphs, GEOBIA, time series

Research supervisors: Maguelonne Teisseire, Pascal Poncelet and Dino Ienco

Host research units : TETIS and LIRMM - Montpellier, France

PhD Thesis in Geography (LETG - Brest)

Title: Geographical Approach of Danube Delta Waters through Satellite Remote Sensing / Les eaux du delta du Danube : approche géographique par télédétection satellitaire

Supervisor: Yannick LAGEAT (Professor emeritus, Université de Bretagne Occidentale)

Host research unit: LETG - UMR6554 - Université de Bretagne Occidentale (Brest - France)

Key-words: Remote Sensing, GIS, Spatial Analysis, Hydrosystems, Turbidity, Phytoplankton, Macrophytes

Abstract: The Danube River and its contributors cross nineteen European countries before reaching the West coast of the Black Sea. In the context of the Black Sea drainage basin, the Danube River is the most important source of liquid and solid discharges. The fluvial-marine contact zone is quite large because Danube splits up itself into multiple distributaries across a wide deltaic plain (4,142 km²) shared among Romania and Ukraine. Vast areas of compact reedbeds usually surround the three hundred freshwater lakes of the delta. Many of these shallow lakes are connected to channels or canals providing turbid water from the Danube, while others depend on flood events to be supplied by the turbid waters coming from the river. Important seasonal growth of floating and submerged macrophytes also occurs in the majority of the lakes. Thus, Danube Delta presents a complex hydrosystem which has been greatly modified since the first navigation works in the nineteenth century. Since the beginning of the nineties, the Danube Delta became a Biosphere Reserve (MAB-UNESCO), a RAMSAR site and was included on the list of the World Natural Heritage (UNESCO). Analyzing spatial patterns in complex environments, like Danube Delta and its coastal zone, requires non traditional approaches. Remote sensing multi-sensor techniques offer reliable advantages to observe and understand intricate processes operating on different space-time scales and especially in large areas with difficult and sometimes restricted access (e.g. Biosphere Reserve core areas). The main methodological objective of this thesis was to create a procedure for processing heterogeneous optical satellite images. By studying the Danube Delta area (hydrosystems principally) through different space-time scales, we worked with several types of high and moderate spatial resolution images. Based on Danube water levels, we analyzed 85 satellite images from the period 2006-2009 (52 medium resolution images - MERIS and 33 high resolution images - ALOS AVNIR-2, SPOT HVIR, Landsat TM / ETM+). This main satellite data set was completed with more than sixty "historical" images (1972-2005) acquired with the Landsat sensors (MSS, TM and ETM+). Three distinct, but complementary, approaches were used to process the satellite images. The integrated analysis of the satellite results with hydrological and meteo-oceanographical data series enabled us to bring new elements of explanation about the past and present dynamics of Danube Delta.

The thesis manuscript is available at: HAL-TEL


Most of my publications are available at: ResearchGate (the more recent ones are also referenced at: ORCID ID)


Güttler F.N., Ienco D., Poncelet P., Teisseire M., 2016, Combining Transductive and Active Learning to Improve Object-based Remote Sensing Image Classification. Remote Sensing Letters, Vol. 7, n° 4, pp.358-367

Güttler F.N., Niculescu S., Gohin F., 2013, Turbidity retrieval and monitoring of Danube Delta waters using multi-sensor optical remote sensing data: an integrated view from the delta plain lakes to the west-northwestern Black Sea coastal zone, Remote Sensing of Environment, vol. 132, pp.86-101.

Niculescu S., Lardeux C., Güttler F.N., Rudant J.P., 2010, Multisensor systems and flood risk management. Application to the Danube Delta using radar and hyperspectral imagery, Revue Télédétection/Remote Sensing, vol. 9, n°3-4, pp. 271-288.


Kergosien E., Alatrista-Salas H., Gaio M., Güttler F.N., Roche M., Teisseire M., 2015, When Textual Information Becomes Spatial Information Compatible with Satellite Images, In Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, pp. 301-306.

Güttler F.N., Ienco D., Teisseire M., Nin J., Poncelet P., 2014, Towards the Use of Sequential Patterns for Detection and Characterization of Natural and Agricultural Areas, In Information Processing and Management of Uncertainty in Knowledge-Based Systems, Springer International Publishing, pp. 97-106.

Güttler F.N., Alleaume S., Corbane C., Ienco D., Nin J., Poncelet P., Teisseire M., 2014, Exploring high repetitivity remote sensing time series for mapping and monitoring natural habitats – a new approach combining OBIA and k-partite graphs, Proceedings of IGARSS 2014 « IEEE International Geoscience and Remote Sensing Symposium », pp. 3930-3933.

Corbane C., Güttler F.N., Alleaume S., , Ienco D., Teisseire M., 2014, Monitoring the phenology of Mediterranean natural habitats with multispectral sensors – an analysis based on multiseasonal field spectra, Proceedings of IGARSS 2014 « IEEE International Geoscience and Remote Sensing Symposium », pp. 3934-3937.

Güttler F.N., Niculescu S., Gohin F., Lageat Y., Grigoras I., 2011, Comparing turbidity patterns of Danube Delta waters with remote sensing techniques: from deltaic lakes to the western Black Sea coastal zone, Geophysical Research Abstracts, Vol. 13, EGU2011-10459. EGU General Assembly 2011, 03-08 Avril 2011, Vienne, Autriche.

Niculescu S., Güttler F.N., Lardeux C., Lamarche S., Rudant J-P, 2009, Synergy between optical and radar images ALOS satellite for recognition of vegetation structures in coastal wetlands, Proceedings of CoastGIS 09, Itajaí, Brazil.

Niculescu S., Güttler F.N., Lardeux C., Rudant J.P., 2008, Multisensor systems and flood risk management in the Danube Delta, Proceedings of Alos PI Symposium 2008, Rhodes, Greece, 7 p.

Güttler, F.N., Plácido, A.P.F., Pereira, T.A., 2005, Avaliação da ocupação urbana na localidade do pântano do Sul, Florianópolis, SC, Brasil. VII Coloquio Internacional de Geocrítica - Los agentes urbanos y las políticas sobre la ciudad, 24-27 mai 2005, Santiago, Chili.


Roche M., Teisseire M., Crémilleux B., Gancarski P., Sallaberry C., Alatrista-Salas H., Béchet N., Bernhard D., Bringay S., Charnois T., Gaio M., Güttler F.N., Ienco D., Kergosien E., Maurel P., Poncelet P., Sallaberry A., Weber C., 2014, Animitex : Analyse d'Images fondée sur des Informations Textuelles. Revue des Sciences et Technologies de l'Information - Série ISI : Ingénierie des Systèmes d'Information, 19 (3), Lavoisier, pp.163-167.

Güttler F.N., Plácido A.P.F. Ayala L., 2007, Morphological Behavior of Rio das Pacas Beach, Florianópolis–Brazil, PerCursos, Florianópolis, v. 8, n. 2, pp. 72-89.

Teaching activities

2015-2016: Methods of Data Mining and Classification (24 hours including practicals) Courses for Master students in Earth Observation and Geomatics / Environmental Geography. Université de Strasbourg – Faculté de Géographie (Strasbourg - France)

2012-2014: Remote Sensing and Spatial Analysis (108 hours including practicals) Courses for Master students in Ecology and Sustainable Development. Université Catholique de l’Ouest – Institut de Biologie Appliquée (Angers - France)

2009-2011: Remote Sensing (133 hours including practicals) Courses for undergraduate students in Geography. Université de Bretagne Occidentale – Départment de Géographie (Brest - France)


ICube Laboratory
Télécom Physique Strasbourg
300 bd Sébastien Brant - CS 10413
F - 67412 Illkirch cedex
Office: C320
Email: guttler (at) unistra (dot) fr