TY - GEN UR - http://lib.ugent.be/catalog/pug01:792704 ID - pug01:792704 LA - eng TI - Evolutionary regression modeling with active learning: an application to rainfall runoff modeling PY - 2009 SN - 978-3-642-04920-0 SN - 0302-9743 PB - Berlin AU - Couckuyt, Ivo TW05 000080790791 802000527068 0000-0002-9524-4205 AU - Gorissen, Dirk UGent 802000284467 AU - Rouhani, Hamed AU - Laermans, Eric AU - Dhaene, Tom AU - Kolehmainen, Mikko editor AU - Toivanen, Pekka editor AU - Beliczynski, Bartlomiej editor AB - Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a feasible alternative. However, due to the computational cost of these high fidelity simulations, the use of neural networks, kernel methods, and other surrogate modeling techniques has become indispensable. Surrogate models are compact and cheap to evaluate, and have proven very useful for tasks such as optimization, design space exploration, visualization, prototyping, and sensitivity analysis. Consequently, there is great interest in techniques that facilitate the construction of such regression models, while minimizing the computational cost and maximizing model accuracy. The model calibration problem in rainfall runoff modeling is an important problem from hydrology that can benefit from advances in surrogate modeling and machine learning in general. This paper presents a novel, fully automated approach to tackling this problem. Drawing upon advances in machine learning, hyperparameter optimization, model type selection, and sample selection (active learning) are all handled automatically. Increasing the utility of such methods for the domain expert. ER -Download RIS file
00000nam^a2200301^i^4500 | |||
001 | 792704 | ||
005 | 20170102095258.0 | ||
008 | 091201s2009------------------------eng-- | ||
020 | a 978-3-642-04920-0 | ||
022 | a 0302-9743 | ||
024 | a 000279120700056 2 wos | ||
024 | a 1854/LU-792704 2 handle | ||
024 | a 10.1007/978-3-642-04921-7_56 2 doi | ||
040 | a UGent | ||
245 | a Evolutionary regression modeling with active learning: an application to rainfall runoff modeling | ||
260 | a Berlin, Germany b Springer c 2009 | ||
520 | a Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a feasible alternative. However, due to the computational cost of these high fidelity simulations, the use of neural networks, kernel methods, and other surrogate modeling techniques has become indispensable. Surrogate models are compact and cheap to evaluate, and have proven very useful for tasks such as optimization, design space exploration, visualization, prototyping, and sensitivity analysis. Consequently, there is great interest in techniques that facilitate the construction of such regression models, while minimizing the computational cost and maximizing model accuracy. The model calibration problem in rainfall runoff modeling is an important problem from hydrology that can benefit from advances in surrogate modeling and machine learning in general. This paper presents a novel, fully automated approach to tackling this problem. Drawing upon advances in machine learning, hyperparameter optimization, model type selection, and sample selection (active learning) are all handled automatically. Increasing the utility of such methods for the domain expert. | ||
598 | a P1 | ||
100 | a Couckuyt, Ivo u TW05 0 000080790791 0 802000527068 0 0000-0002-9524-4205 9 FC259E64-F0ED-11E1-A9DE-61C894A0A6B4 | ||
700 | a Gorissen, Dirk u UGent 0 802000284467 0 000070774432 9 F9B6F010-F0ED-11E1-A9DE-61C894A0A6B4 | ||
700 | a Rouhani, Hamed | ||
700 | a Laermans, Eric u TW05 0 801000974707 9 F4D5BCE8-F0ED-11E1-A9DE-61C894A0A6B4 | ||
700 | a Dhaene, Tom u TW05 0 801000729981 9 F945C52A-F0ED-11E1-A9DE-61C894A0A6B4 | ||
700 | a Kolehmainen, Mikko e editor | ||
700 | a Toivanen, Pekka e editor | ||
700 | a Beliczynski, Bartlomiej e editor | ||
650 | a Earth and Environmental Sciences | ||
653 | a MONTE-CARLO-SIMULATION | ||
653 | a OPTIMIZATION | ||
653 | a DESIGN | ||
773 | t International Conference on Adaptive and Natural Computing Algorithms (ICANNGA 2009) g Lect. Notes Comput. Sci. 2009. Springer. 5495 p.548-558 q 5495:<548 | ||
856 | 3 Full Text u https://biblio.ugent.be/publication/792704/file/1137969 z [ugent] y Couckuyt_2009_LNCS_5495_548.pdf | ||
856 | 3 Full Text u https://biblio.ugent.be/publication/792704/file/1137970 z [ugent] y 3877.PDF | ||
920 | a confcontrib | ||
Z30 | x EA 1 TW05 | ||
922 | a UGENT-EA |
All data below are available with an Open Data Commons Open Database License. You are free to copy, distribute and use the database; to produce works from the database; to modify, transform and build upon the database. As long as you attribute the data sets to the source, publish your adapted database with ODbL license, and keep the dataset open (don't use technical measures such as DRM to restrict access to the database).
The datasets are also available as weekly exports.