Download:
|
by Franz Wotawa, Gerhard Wotawa
http://www.dbai.tuwien.ac.at/staff/wotawa/aicom2001.ps.gz
Add To MetaCart
Abstract:
As alternative to physical models, neural networks are a valuable forecast tool in environmental sciences. They can be used effectively due to their learning capabilities and their low computational costs. As far as the relevant variables of the system are measured and put into the network, it works fast and accurately. However, one of the major shortcomings of neural networks is that they do not reveal causal relationships between major system components and thus are unable to improve the explicit knowledge of the user. To overcome this problem, we introduce an approach for deriving qualitative informations out of neural networks. Some of the resulting rules can be directly used by a qualitative simulator for producing possible future scenarios. Because of the explicit representation of knowledge the rules should be easier to understand and can be used as starting point for creating models wherever a physical model is not available. We illustrate our approach using a Network for predicting surface ozone concentrations and discuss open problems and future research directions.
Citations
|
2489
|
Induction of Decision Trees
– Quinlan
- 1986
|
|
1871
|
Neural networks: A Comprehensive Foundation
– Haykin
- 1994
|
|
536
|
Qualitative process theory
– Forbus
- 1984
|
|
366
|
Qualitative simulation
– Kuipers
- 1986
|
|
260
|
A Qualitative Physics Based on Confluences
– Kleer, Brown
- 1984
|
|
154
|
Embracing causality in specifying the indirect effects of actions
– Lin
- 1995
|
|
133
|
Causal theories of action and change
– McCain, Turner
- 1997
|
|
66
|
Methods and problems in data mining
– MANNILA
- 1997
|
|
34
|
Learning qualitative models of dynamic systems
– Bratko, Muggleton, et al.
- 1991
|
|
34
|
Extraction, insertion and refinement of symbolic rules in dynamically driven recurrent neural networks
– Giles, Omlin
- 1993
|
|
28
|
Symbolic interpretation of artificial neural networks
– Taha, Gosh
- 1999
|
|
15
|
Learning causal networks from data: a survey and a new algorithm for recovering possibilistic causal networks
– Sanguesa, Cortes
- 1997
|
|
13
|
Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography
– Hsieh, Tang
- 1998
|
|
8
|
Three techniques for extracting rules from feedforward networks
– Taha, Ghosh
- 1996
|
|
7
|
P.: Transformation of Qualitative Dynamic Models - Application in Hydro-Ecology
– Heller, Struss
- 1996
|
|
7
|
de Velde. Incremental induction of topologically minimal trees
– Van
- 1990
|
|
6
|
Qualitative Reasoning: A Survey of Techniques and Applications
– Dague
- 1995
|
|
5
|
Induction of discrete-state machine by stabilizing a simple recurrent network using clustering
– Das, Das
- 1991
|
|
3
|
Conceptual Modeling in the Environmental Domain
– Heller, Struss
- 1997
|
|
3
|
Local Maximum Ozone Concentration Prediction Using Neural Networks
– Wieland, Wotawa
- 1999
|
|
2
|
Inference of local rainfall using qualitative reasoning
– Oishi, Ikebuchi
- 1996
|
|
1
|
Ranan Banerjii. Learning by experimentation: Acquiring and refining problem-solving heuristics
– Mitchell, Utgoff
- 1983
|
|
1
|
and Benyang Tang, `Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography
– Hsieh
- 1998
|
|
1
|
Shuichi Ikebuchi, `Inference of local rainfall using qualitative reasoning
– Oishi
- 1996
|
