Abstract
Data-driven models based on the methods of machine learning have proven to be accurate tools in predicting various natural phenomena. Their accuracy, however, can be increased if several learning models are combined. A modular model is comprised of a set of specialized models each of which is responsible for particular sub-processes or situations, and may be trained on a subset of the training set. This paper presents the typology of such models and refers to a number of approaches to build them. An issue of combining machine learning with domain expert knowledge is discussed, and new approaches are presented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abebe AJ, Price RK (2004). Information theory and neural networks for managing uncertainty in flood routing. ASCE Journal of Computing in Civil Engineering 18(4): 373–380.
Abrahart RJ, See L (2002). Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments. Hydrology and Earth System Sciences 6(4): 655–670.
Becker A, Kundzewicz ZW (1987) Nonlinear flood routing with multilinear models. Water Resources Research 23: 1043–1048.
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984). Classification and regression trees. Wadsworth International: Belmont.
Breiman L (1996). Stacked regressor. Machine Learning, 24(1): 49–64.
Corzo GA, Solomatine DP (2006) Multi-objective optimization of ANN hybrid committees based on hydrological knowledge. Geophysical Research Abstracts, 8: 09794. EGU General Assembly, Vienna, April 2006.
Corzo GA, Solomatine DP (2007). Baseflow separation techniques for modular artificial neural network modelling in flow forecasting. Hydrological Sciences Journal 52(3), 491–507.
Freund Y, Schapire R (1997). A decision-theoretic generalisation of on-line learning and an application of boosting. Journal of Computer and System Science 55(1): 119–139.
Georgakakos KP, Seo D-J, Gupta H, Schaake J, Butts MB (2004) Towards the characterization of streamflow simulation uncertainty through multimodel ensembles. Journal of Hydrology 298(1): 222–241.
Haykin S (1999) Neural networks: a comprehensive foundation. McMillan, New York.
Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptative mixtures of local experts. Neural Computation 3: 79–87.
Jordan MI, Jacobs RA (1995) Modular and hierarchical learning systems. The Handbook of Brain Theory and Neural Networks, Arbib, M. (Ed.). MIT Press: Cambridge.
Jain A, Srinivasulu S (2006) Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques. Journal of Hydrology 317: 291–306.
Jordan MI, Jacobs RA (1995). Modular and hierarchical learning systems. The Handbook of Brain Theory and Neural Networks, Arbib, M. (Ed.). MIT Press: Cambridge.
Kasabov NK, Song Q (2002). DENFIS: Dynamic Evolving Neural-Fuzzy Inference System and Its Application for Time Series Prediction. IEEE Trans. Fuzzy Systems 2: 144–154.
Kompare B, Steinman F, Cerar U, Dzeroski S (1997) Prediction of rainfall runoff from catchment by intelligent data analysis with machine learning tools within the artificial intelligence tools. Acta Hydrotechnica (in Slovene) 16/17, 79–94.
Kuncheva LI (2004) Combining Pattern Classifiers. Wiley, NJ.
Lekkas DF, Imrie CE, Lees MJ (2001) Improved non-linear transfer function and neural network methods of flow routing for real-time forecasting, Journal of Hydroinformatics 3(3): 153–164.
Quinlan JR (1992) Learning with continuous classes. Proc. AI’92, 5th Australian Joint Conference on Artificial Intelligence, Adams, A. and Sterling, L. (eds.), World Scientific: Singapore, 343–348.
See L, Openshaw S (2000) A hybrid multi-model approach to river level forecasting. Hydrological Sciences Journal 45: 523–536.
Shamseldin AY, O’Connor KM (2001) A non-linear neural network technique for updating of river flow forecasts. Hydrology and Earth System Sciences 5(4): 577–597.
Shrestha DL, Solomatine DP (2006) Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression. Neural Computation 17: 1678–1710.
Solomatine DP, Dulal KN (2003) Model tree as an alternative to neural network in rainfall-runoff modelling. Hydrological Sciences Journal 48(3): 399–411.
Solomatine DP, Siek MB (2004a) Semi-optimal Hierarchical Regression Models and ANNs. Proc. Intern. Joint Conference on Neural Networks, Budapest, Hungary, July 2004, 1173–1177.
Solomatine DP, Siek MB (2004b) Flexible and optimal M5 model trees with applications to flow predictions. Proc. 6th Int. Conference on Hydroinformatics, World Scientific: Singapore.
Solomatine DP, Siek MB (2006) Modular learning models in forecasting natural phenomena. Neural Networks 19: 215–224.
Solomatine DP, Xue Y (2004) M5 model trees and neural networks: application to flood forecasting in the upper reach of the Huai River in China. ASCE J. Hydrologic Engineering 9(6): 491–501.
Solomatine DP, Maskey M, Shrestha DL (2007) Instance-based learning compared to other data-driven methods in hydrologic forecasting. Hydrological Processes, 21 (DOI:10.1002/hyp.6592).
Toth E, Brath A (2002) Flood forecasting using artificial neural networks in black-box and conceptual rainfall-runoff modelling. Proc. of the International Environmental Modelling and Software Society (iEMSs) Meeting. Web: http://www.iemss.org/iemss2002/proceedings/vol2.html.
Xiong LH, Shamseldin AY, O’Connor KM (2001) A non-linear combination of the forecasts of rainfall–runoff models by the first-order Takagi-Sugeno fuzzy system. Journal of Hydrology 245(1–4): 196–217.
Velickov S (2003) Mixture of models: a new framework for modelling complex nonlinear dynamical systems. Proc. XXX IAHR Congress. Thessaloniki, Vol. D, August 2003, 123–130.
Wang W, Van Gelder PHAJM, Vrijling JK, Ma J (2006) Forecasting daily streamflow using hybrid ANN models. Journal of Hydrology 324(1–4): 383–399.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Solomatine, D. (2009). Combining Machine Learning and Domain Knowledge in Modular Modelling. In: Abrahart, R.J., See, L.M., Solomatine, D.P. (eds) Practical Hydroinformatics. Water Science and Technology Library, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-79881-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-79881-1_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-79880-4
Online ISBN: 978-3-540-79881-1
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)