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 that 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 minimization (SRM) induction principle that aims at minimizing a bound on the generalization error of a model, rather than minimizing only 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 (modeling) 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 analyzed by comparing its results with that of ANNs on the same data sets.

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 a component of the Arctic Freshwater Synthesis, we review the central freshwater processes in the terrestrial Arctic drainage and how they function and change across seven hydrophysiographical regions (Arctic tundra, boreal plains, shield, mountains, grasslands, glaciers/ice caps, and wetlands). We also highlight links between terrestrial hydrology and other components of the Arctic freshwater system. In terms of key processes, snow cover extent and duration is generally decreasing on a pan‐Arctic scale, but snow depth is likely to increase in the Arctic tundra. Evapotranspiration will likely increase overall, but as it is coupled to shifts in landscape characteristics, regional changes are uncertain and may vary over time. Streamflow will generally increase with increasing precipitation, but high and low flows may decrease in some regions. Continued permafrost thaw will trigger hydrological change in multiple ways, particularly through increasing connectivity between groundwater and surface water and changing water storage in lakes and soils, which will influence exchange of moisture with the atmosphere. Other effects of hydrological change include increased risks to infrastructure and water resource planning, ecosystem shifts, and growing flows of water, nutrients, sediment, and carbon to the ocean. Coordinated efforts in monitoring, modeling, and processing studies at various scales are required to improve the understanding of change, in particular at the interfaces between hydrology, atmosphere, ecology, resources, and oceans.

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.