Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

For more than a century, coastal wetlands have been recognized for their ability to stabilize shorelines and protect coastal communities. However, this paradigm has recently been called into question by small-scale experimental evidence. Here, we conduct a literature review and a small meta-analysis of wave attenuation data, and we find overwhelming evidence in support of established theory. Our review suggests that mangrove and salt marsh vegetation afford context-dependent protection from erosion, storm surge, and potentially small tsunami waves. In biophysical models, field tests, and natural experiments, the presence of wetlands reduces wave heights, property damage, and human deaths. Meta-analysis of wave attenuation by vegetated and unvegetated wetland sites highlights the critical role of vegetation in attenuating waves. Although we find coastal wetland vegetation to be an effective shoreline buffer, wetlands cannot protect shorelines in all locations or scenarios; indeed large-scale regional erosion, river meandering, and large tsunami waves and storm surges can overwhelm the attenuation effect of vegetation. However, due to a nonlinear relationship between wave attenuation and wetland size, even small wetlands afford substantial protection from waves. Combining man-made structures with wetlands in ways that mimic nature is likely to increase coastal protection. Oyster domes, for example, can be used in combination with natural wetlands to protect shorelines and restore critical fishery habitat. Finally, coastal wetland vegetation modifies shorelines in ways (e.g. peat accretion) that increase shoreline integrity over long timescales and thus provides a lasting coastal adaptation measure that can protect shorelines against accelerated sea level rise and more frequent storm inundation. We conclude that the shoreline protection paradigm still stands, but that gaps remain in our knowledge about the mechanistic and context-dependent aspects of shoreline protection.

The present and future role of coastal wetland vegetation in protecting shorelines: answering recent challenges to the paradigm

The Global Energy Assessment (GEA) brings together over 300 international researchers to provide an independent, scientifically based, integrated and policy-relevant analysis of current and emerging energy issues and options. It has been peer-reviewed anonymously by an additional 200 international experts. The GEA assesses the major global challenges for sustainable development and their linkages to energy; the technologies and resources available for providing energy services; future energy systems that address the major challenges; and the policies and other measures that are needed to realize transformational change toward sustainable energy futures. The GEA goes beyond existing studies on energy issues by presenting a comprehensive and integrated analysis of energy chalenges, opportunities and strategies, for developing, industrialized and emerging economies. This volume is a invaluable resource for energy specialists and technologists in all sectors (academia, industry and government) as well as policymakers, development economists and practitioners in international organizations and national governments.

Global Energy Assessment: Toward a Sustainable Future

http://www.catalytics.asia/wp-content/themes/catalytics/flood/Bates%20et%20al%202010%20new%20lisflood.pdf

A simple inertial formulation of the shallow water equations for efficient two-dimensional flood inundation modelling.

Over the past 15 years, artificial neural networks (ANNs) have been used increasingly for prediction and forecasting in water resources and environmental engineering. However, despite this high level of research activity, methods for developing ANN models are not yet well established. In this paper, the steps in the development of ANN models are outlined and taxonomies of approaches are introduced for each of these steps. In order to obtain a snapshot of current practice, ANN development methods are assessed based on these taxonomies for 210 journal papers that were published from 1999 to 2007 and focus on the prediction of water resource variables in river systems. The results obtained indicate that the vast majority of studies focus on flow prediction, with very few applications to water quality. Methods used for determining model inputs, appropriate data subsets and the best model structure are generally obtained in an ad-hoc fashion and require further attention. Although multilayer perceptrons are still the most popular model architecture, other model architectures are also used extensively. In relation to model calibration, gradient based methods are used almost exclusively. In conclusion, despite a significant amount of research activity on the use of ANNs for prediction and forecasting of water resources variables in river systems, little of this is focused on methodological issues. Consequently, there is still a need for the development of robust ANN model development approaches.

Review: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions

This paper describes benchmark testing of six two-dimensional (2D) hydraulic models (DIVAST, DIVASTTVD, TUFLOW, JFLOW, TRENT and LISFLOOD-FP) in terms of their ability to simulate surface flows in a densely urbanised area. The models are applied to a 1·0 km × 0·4 km urban catchment within the city of Glasgow, Scotland, UK, and are used to simulate a flood event that occurred at this site on 30 July 2002. An identical numerical grid describing the underlying topography is constructed for each model, using a combination of airborne laser altimetry (LiDAR) fused with digital map data, and used to run a benchmark simulation. Two numerical experiments were then conducted to test the response of each model to topographic error and uncertainty over friction parameterisation. While all the models tested produce plausible results, subtle differences between particular groups of codes give considerable insight into both the practice and science of urban hydraulic modelling. In particular, the results show that the terrain data available from modern LiDAR systems are sufficiently accurate and resolved for simulating urban flows, but such data need to be fused with digital map data of building topology and land use to gain maximum benefit from the information contained therein. When such terrain data are available, uncertainty in friction parameters becomes a more dominant factor than topographic error for typical problems. The simulations also show that flows in urban environments are characterised by numerous transitions to supercritical flow and numerical shocks. However, the effects of these are localised and they do not appear to affect overall wave propagation. In contrast, inertia terms are shown to be important in this particular case, but the specific characteristics of the test site may mean that this does not hold more generally.

/pdf/benchmarking-2d-hydraulic-models-for-urban-flooding-4epkxyg0fl.pdf

Benchmarking 2D hydraulic models for urban flooding

Modelling dam-break flows over mobile beds using a 2D coupled approach

Comparison between TVD-MacCormack and ADI-type solvers of the shallow water equations

Hydro-environmental modelling for bathing water compliance of an estuarine basin

SUMMARY An efficient numerical scheme is outlined for solving the SWEs (shallow water equations) in environmental flow; this scheme includes the addition of a five-point symmetric total variation diminishing (TVD) term to the corrector step of the standard MacCormack scheme. The paper shows that the discretization of the conservative and non-conservative forms of the SWEs leads to the same finite difference scheme when the source term is discretized in a certain way. The non-conservative form is used in the solution outlined herein, since this formulation is simpler and more efficient. The time step is determined adaptively, based on the maximum instantaneous Courant number across the domain. The bed friction is included either explicitly or implicitly in the computational algorithm according to the local water depth. The wetting and drying process is simulated in a manner which complements the use of operator-splitting and two-stage numerical schemes. The numerical model was then applied to a hypothetical dam-break scenario, an experimental dam-break case and an extreme flooding event over the Toce River valley physical model. The predicted results are free of spurious oscillations for both sub- and super-critical flows, and the predictions compare favourably with the experimental measurements. Copyright q 2006 John Wiley & Sons, Ltd.

BinLiang Lin

Papers

Benchmarking 2D hydraulic models for urban flooding

Modelling dam-break flows over mobile beds using a 2D coupled approach

Comparison between TVD-MacCormack and ADI-type solvers of the shallow water equations

Hydro-environmental modelling for bathing water compliance of an estuarine basin

Simulation of rapidly varying flow using an efficient TVD–MacCormack scheme