Yonas B. Dibike

Model Induction with Support Vector Machines: Introduction and Applications

The rapid advance in information processing systems in recent decades had directed engineering research towards the development of intelligent systems that can evolve models of natural phenomena automatically, ‘by themselves’, so to speak. In this respect, a wide range of machine learning techniques like decision trees, artificial neural networks (ANNs), Bayesian methods, fuzzy-rule based systems and evolutionary algorithms have been successfully applied to model different civil engineering systems. In this study, the possibility of using yet another machine learning paradigm which is firmly based on the theory of statistical learning, namely that of the Support Vector Machine (SVM), is investigated. An interesting property of this approach is that it is an approximate implementation of a structural risk minimisation (SRM) induction principle that aims at minimising a bound on the generalisation error of a model, rather than only minimising the mean square error over the data set. In this paper, the basic ideas underlying statistical learning theory and SVM are reviewed and the potential of the SVM for feature classification and multiple regression (modelling) problems is demonstrated by applying the method to two different cases of model induction from empirical data. The relative performance of the SVM is then analysed by comparing its results with that of ANNs on the same data sets.

River flow forecasting using artificial neural networks

Abstract River flow forecasting is required to provide basic information on a wide range of problems related to the design and operation of river systems. The availability of extended records of rainfall and other climatic data, which could be used to obtain stream flow data, initiated the practice of rainfall-runoff modelling. While conceptual or physically-based models are of importance in the understanding of hydrological processes, there are many practical situations where the main concern is with making accurate predictions at specific locations. In such situation it is preferred to implement a simple “black box” (data-driven, or machine learning) model to identify a direct mapping between the inputs and outputs without detailed consideration of the internal structure of the physical process. Artificial neural networks (ANNs) is probably the most successful machine learning technique with flexible mathematical structure which is capable of identifying complex non-linear relationships between input and output data without attempting to reach understanding as to the nature of the phenomena. In this study the applicability of ANNs for downstream flow forecasting in the Apure river basin (Venezuela) was investigated. Two types of ANN architectures, namely multi-layer perceptron network (MLP) and a radial basis function network (RBF) were implemented. The performances of these networks were compared with a conceptual rainfall-runoff model and they were found to be slightly better for this river flow-forecasting problem.

Downscaling Precipitation and Temperature with Temporal Neural Networks

The issues of downscaling the outputs of a global climate model (GCM) to a scale that is appropriate to hydrological impact studies are investigated using a temporal neural network approach. The time-lagged feed-forward neural network (TLFN) is proposed for downscaling daily total precipitation and daily maximum and minimum temperature series for the Serpent River watershed in northern Quebec (Canada). The downscaling models are developed and validated using large-scale predictor variables derived from the National Centers for Environmental Prediction–National Center for Atmospheric Research (NCEP– NCAR) reanalysis dataset. Atmospheric predictors such as specific humidity, wind velocity, and geopotential height are identified as the most relevant inputs to the downscaling models. The performance of the TLFN downscaling model is also compared to a statistical downscaling model (SDSM). The downscaling results suggest that the TLFN is an efficient method for downscaling both daily precipitation and temperature series. The best downscaling models were then applied to the outputs of the Canadian Global Climate Model (CGCM1), forced with the Intergovernmental Panel on Climate Change (IPCC) IS92a scenario. Changes in average precipitation between the current and the future scenarios predicted by the TLFN are generally found to be smaller than those predicted by the SDSM model. Furthermore, application of the downscaled data for hydrologic impact analysis in the Serpent River resulted in an overall increasing trend in mean annual flow as well as earlier spring peak flow. The results also demonstrate the emphasis that should be given in identifying the appropriate downscaling tools for impact studies by showing how a future climate scenario downscaled with different downscaling methods could result in significantly different hydrologic impact simulation results for the same watershed.

2006 Special issue: Temporal neural networks for downscaling climate variability and extremes

Global climate models (GCMs) are inherently unable to present local subgrid-scale features and dynamics and consequently, outputs from these models cannot be directly applied in many impact studies. This paper presents the issues of downscaling the outputs of GCMs using a temporal neural network (TNN) approach. The method is proposed for downscaling daily precipitation and temperature series for a region in northern Quebec, Canada. The performance of the temporal neural network downscaling model is compared to a regression-based statistical downscaling model with emphasis on their ability in reproducing the observed climate variability and extremes. The downscaling results for the base period (1961- 2000) suggest that the TNN is an efficient method for downscaling both daily precipitation as well as daily temperature series. Furthermore, the different model test results indicate that the TNN model significantly outperforms the statistical models for the downscaling of daily precipitation extremes and variability.

Temporal neural networks for downscaling climate variability and extremes

Global climate models (GCMs) are inherently unable to present local subgrid-scale features and dynamics and consequently, outputs from these models cannot be directly applied in many impact studies. This paper presents the issues of downscaling the outputs of GCMs using a temporal neural network (TNN) approach. The method is proposed for downscaling daily precipitation and temperature series for a region in northern Quebec, Canada. The performance of the temporal neural network downscaling model is compared to a regression-based statistical downscaling model with emphasis on their ability in reproducing the observed climate variability and extremes. The downscaling results for the base period (1961- 2000) suggest that the TNN is an efficient method for downscaling both daily precipitation as well as daily temperature series. Furthermore, the different model test results indicate that the TNN model significantly outperforms the statistical models for the downscaling of daily precipitation extremes and variability.

On the encapsulation of numerical-hydraulic models in artificial neural network

The optimal control of hydraulic networks often necessitates making a considerable number of very rapid simulations of flows, such as is not practical using existing, computationally-demanding, numerical-hydraulic models. However, the site-specific knowledge and data that is encapsulated in any such numerical model can be encapsulated in its turn in an artificial neural network (ANN), and this can provide much faster simulations. In this study, a number of possible types and configurations of ANNs are investigated for their suitability to this class of application. When regarded from a hydroinformatics point of view, this study becomes one of identifying the most suitable ANN encapsulations of numerical-hydraulic encapsulations of generic hydraulic knowledge and site-specific data.

Arctic terrestrial hydrology : A synthesis of processes, regional effects, and research challenges

Terrestrial hydrology is central to the Arctic system and its freshwater circulation. Water transport and water constituents vary, however, across a very diverse geography. In this paper, which is ...

Automatic calibration of groundwater models using global optimization techniques

Abstract The problem of a groundwater model calibration is posed as a multiextremum (global) optimization problem, rather than the more widely considered single-extremum (local) optimization problem. Several algorithms of randomized search incorporated in the global optimization tool GLOBE are considered (including the canonical genetic algorithm and more recently developed adaptive cluster covering), and applied to the calibration of the groundwater model TRIWACO. The results show the usefulness of global optimization algorithms in the automatic calibration of even complex models having considerable running times.

Application of artificial neural networks to the simulation of a two dimensional flow

The practice of numerical simulation of flows and other processes occurring in water has now matured into an established and efficient part of hydraulics. At the same time, however, the models themselves often become very extended. In many situations, given the divergence between the response-time requirements and the computational- time requirements of numerical models, the need arises to reduce the time needed to simulate the impact of given input events on hydraulics systems. In this study the possibility of using systems composed of agents consisting only of artificial neural networks (ANNs) as modelling tools for the simulation of tidal flow in a two-dimensional flow field is investigated. In particular this involves the modelling of a process that evolves in time and the ANNs themselves function as non-linear dynamic systems that effectively reproduce the behaviour of the fluid at any one place and any one time from the behavior at other places at earlier times. Different types of ANN-agent architec...

Modeling the Arctic freshwater system and its integration in the global system: Lessons learned and future challenges

The first two authors have contributed equally to the publication. The Arctic Freshwater Synthesis has been sponsored by the World Climate Research Programme’s Climate and the Cryosphere project (WCRP-CliC), the International Arctic Science Committee (IASC), and the Arctic Monitoring and Assessment Programme (AMAP). C.L. acknowledges support from the UK Natural Environment Research Council. M.M.H. acknowledges support from NSF PLR-1417642. D.M.L. is supported by funding from the U.S. Department of Energy BER, as part of its Climate Change Prediction Program, Cooperative Agreement DE-FC03-97ER62402/A010, and NSF grants AGS-1048996, PLS-1048987, and PLS-1304220. J.A.S. is supported by Natural Environment Research Council grant NE/J019585/1. Y.D. is supported by Environment Canada’s Northern Hydrology program. We acknowledge the World Climate Research Programme’s Working Group on Coupled Modelling, which is responsible for CMIP, and we thank the climate modeling groups for producing and making available their model output. For CMIP, the U.S. Department of Energy’s Program for Climate Model Diagnosis and Intercomparison provides coordinating support and led development of software infrastructure in partnership with the Global Organization for Earth System Science Portals. The CMIP data and CESM-LE data are available through the relevant Web data portals