LS Bauinformatik
Refine
Document Type
- Conference Proceeding (47)
- Article (9)
- Part of a book (chapter) (3)
- Doctoral thesis (3)
- Habilitation (2)
- Scientific journal article peer-reviewed (1)
- Book (1)
Keywords
- ICT (2)
- collaborative engineering (2)
- wavelet transform (2)
- Approximationsverfahren (1)
- CSCL (1)
- CSCW (1)
- FE-Method (1)
- GIS (1)
- Hochbauprojekte (1)
- Hochwassergefahren (1)
- Information Management (1)
- Internet (1)
- Internet services (1)
- Kosten (1)
- Objektorientierte Modellierung (1)
- Ontology (1)
- Savitzky-Golay filter (1)
- WWW-Tools (1)
- WWW-based (1)
- Web Services (1)
- Web application (1)
- Web service (1)
- artificial neural networks (1)
- coastal morphological study (1)
- coastal morphology (1)
- communication support (1)
- data reduction (1)
- distributed numerical simulation (1)
- dyke breach (1)
- e-learning (1)
- environment water (1)
- flood Inundation (1)
- flood management (1)
- flood prone areas (1)
- hybrid river modeling (1)
- hydro-science (1)
- hydroengineering (1)
- hydroinformatics (1)
- hydrological studies (1)
- hydromorphological studies (1)
- information management (1)
- information sharing (1)
- mathematical modelling (1)
- neural network (1)
- neural networks (1)
- neuronale Netze (1)
- prognostic simulations (1)
- quadtree (1)
- real-time water level presentation (1)
- risk reduction (1)
- runoff modelling (1)
- shallow water (1)
- short-term prediction (1)
- software engineering (1)
- virtual laboratory (1)
- web-based support (1)
- web-basiert (1)
- wind-wave-waterlevel (1)
Minderung von Hochwassergefahren durch Web-basierte Simulation, Kommunikation und Kooperation
(2004)
Modern information and communication technology (ICT) enables new technical solutions to support collaboration in environmental engineering over distance. The establishment of "virtual laboratories" including application of Internet based project platforms, distributed team work and collaboration methods require new kinds of soft skills, knowledge and experience and a new "technological culture" to be generated just by doing - a task for education, training and profession in Hydro-Informatics. This is a challenge for the European dimension, where in future experts and engineers from different countries with different languages, different mentalities as well as different specialization and professional experience have to collaborate in research, teaching and practice. Training of collaborating in such new environment is the challenge of the courses HydroWeb and HydroEurope which by collaboration of 23 universities world-wide will help to establish common high quality university teaching courses and establish links between students from the involved countries. The students are solving a given environmental engineering task in distributed teams in the Internet. The students acquired in this course experience in interdisciplinary team work, net based project co-ordination and Web based reporting. They strengthened their social competence to collaborate in heterogeneous teams with members of different habits, nationalities, ages, educational backgrounds. The described experiment might be the basis to introduce Web based collaborative engineering in the regular course programme of water-environment related curricula at universities.
A comparative study on a short-term water level prediction using artificial neural networks (ANN) and neuro-fuzzy system is addressed in this paper. The performance of the traditional approaches applied for such a hydrological task can often be constrained by data availability and simplifying assumptions in the processes description. In this paper, the ANN and neuro-fuzzy approaches are used for handling the situations with scarce data, where the predictions are based on the upstream hydrological conditions only. The models have been tested on two different river reaches in Germany. Moreover, the obtained results are compared to those of linear statistical models. Both ANN and neuro-fuzzy systems have performed comparably well and accurate for the purpose, explicitly outperforming the linear statistical models for a longer prediction horizon. The trained neural networks are partly implemented on-line, as a prototype of a web-based water level predictor.