Fast automatic two-stage nonlinear model identification based on the extreme learning machine

It is convenient and effective to solve nonlinear problems with a model that has a linear-in-the-parameters (LITP) structure. However, the nonlinear parameters (e.g. the width of Gaussian function) of each model term needs to be pre-determined either from expert experience or through exhaustive search. An alternative approach is to optimize them by a gradient-based technique (e.g. Newton’s method). Unfortunately, all of these methods still need a lot of computations. Recently, the extreme learning machine (ELM) has shown its advantages in terms of fast learning from data, but the sparsity of the constructed model cannot be guaranteed. This paper proposes a novel algorithm for automatic construction of a nonlinear system model based on the extreme learning machine. This is achieved by effectively integrating the ELM and leave-one-out (LOO) cross validation with our two-stage stepwise construction procedure [1]. The main objective is to improve the compactness and generalization capability of the model constructed by the ELM method. Numerical analysis shows that the proposed algorithm only involves about half of the computation of orthogonal least squares (OLS) based method. Simulation examples are included to confirm the efficacy and superiority of the proposed technique.

Technical Note: Assessing a 24/7 solution for monitoring water quality loads in small river catchments

Quantifying nutrient and sediment loads in catchments is dif?cult owing to diffuse controls related to storm hydrology. Coarse sampling and interpolation methods are prone to very high uncertainties due to under-representation of high discharge, short duration events. Additionally, important low-?ow processes such as diurnal signals linked to point source impacts are missed. Here we demonstrate a solution based on a time-integrated approach to sampling with a standard 24 bottle autosampler con?gured to take a sample every 7 h over a week according to a Plynlimon design. This is evaluated with a number of other sampling strategies using a two-year dataset of sub-hourly discharge and phosphorus concentration data. The 24/7 solution is shown to be among the least uncertain in estimating load (inter-quartile range: 96% to 110% of actual load in year 1 and 97% to 104% in year 2) due to the increased frequency raising the probability of sampling storm events and point source signals. The 24/7 solution would appear to be most parsimonious in terms of data coverage and certainty, process signal representation, potential laboratory commitment, technology requirements and the ability to be widely deployed in complex catchments.

Extreme events and the morphodynamics of gravel-dominated coastal barriers: Strengthening uncertain ground

The long-term morphodynamic ordering of gravel-dominated coastal systems (GDCS), many of which serve as coastal defences in northwest Europe, is dominated by extreme events that generate barrier crest overflow. An understanding of this morphodynamic ordering is fraught with several unresolved difficulties. These are related to the twin problems of the inadequacy of pertinent morphodynamic parameterisation and of obtaining data from modern shores enabling such parameterisation. Major uncertainties concern the timing of over-crest flow in terms of return period of extreme elevation; the intensity and structure of the overflow field; antecedent beachface characteristics in response to storms; the rate of relative sea-level change; tidal stage control; and barrier resistance to forcing, itself determined by a number of unknowns including barrier form and size, sediment size and mosaics, and barrier resilience. While generalised extreme value modelling may provide a means of characterising overwashing return-period and its variability, exceptional tsunami events are outside the scope of such modelling. The characterisation of GDCS morphodynamics in terms of the forcing extreme events will necessitate integrating some or all of these parameters into a single model.

Developments in Performance Monitoring of Concrete Exposed to Extreme Environments

The performance of the surface zone of concrete is acknowledged as a major factor governing the rate of deterioration of reinforced concrete structures as it provides the only barrier to the ingress of water containing dissolved ionic species such as chlorides which, ultimately, initiate corrosion of the reinforcement. In-situ monitoring of cover-zone concrete is therefore critical in attempting to make realistic predictions as to the in-service performance of the structure. To this end, this paper presents developments in a remote interrogation system to allow continuous, real-time monitoring of the cover-zone concrete from an office setting. Use is made of a multi-electrode array embedded within cover-zone concrete to acquire discretized electrical resistivity and temperature measurements, with both parameters monitored spatially and temporally. On-site instrumentation, which allows remote interrogation of concrete samples placed at a marine exposure site, is detailed, together with data handling and processing procedures. Site-measurements highlight the influence of temperature on electrical resistivity and an Arrhenius-based temperature correction protocol is developed using on-site measurements to standardize resistivity data to a reference temperature; this is an advancement over the use of laboratory-based procedures. The testing methodology and interrogation system represents a robust, low-cost and high-value technique which could be deployed for intelligent monitoring of reinforced concrete structures.

Observations of enhanced extreme ultraviolet continua during an X-class solar flare using SDO/EVE.

Observations of extreme ultraviolet (EUV) emission from an X-class solar flare that occurred on 2011 February 15 at 01: 44 UT are presented, obtained using the EUV Variability Experiment (EVE) on board the Solar Dynamics Observatory. The complete EVE spectral range covers the free-bound continua of H I (Lyman continuum), He I, and He II, with recombination edges at 91.2, 50.4, and 22.8 nm, respectively. By fitting the wavelength ranges blueward of each recombination edge with an exponential function, light curves of each of the integrated continua were generated over the course of the flare, as was emission from the free-free continuum (6.5-37 nm). The He II 30.4 nm and Ly alpha 121.6 nm lines, and soft X-ray (SXR; 0.1-0.8 nm) emission from GOES are also included for comparison. Each free-bound continuum was found to have a rapid rise phase at the flare onset similar to that seen in the 25-50 keV light curves from RHESSI, suggesting that they were formed by recombination with free electrons in the chromosphere. However, the free-free emission exhibited a slower rise phase seen also in the SXR emission from GOES, implying a predominantly coronal origin. By integrating over the entire flare the total energy emitted via each process was determined. We find that the flare energy in the EVE spectral range amounts to at most a few percent of the total flare energy, but EVE gives us a first comprehensive look at these diagnostically important continuum components.

Measurement of single mode imprint in laser ablative drive of a thin Al foil by extreme ultraviolet laser radiography

The temporal development of laser driven single mode perturbations in thin A1 foils has been measured using extreme ultraviolet (XUV) laser radiography. 15, 30, 70 and 90 mu m single modes were imprinted on 2 mu m thick A1 foils with an optical driver laser at 527 nm for intensities in the range 5 x 10(12) to 1.5 x 10(13) W cm(-2). The magnitude of the imprinted perturbation at the time of shock break out was determined by fitting to the data estimated curves of growth of the Rayleigh-Taylor instability after shock break out. The efficiency of imprinting is independent of perturbation wavelength in the parameter range of this experiment, suggesting little influence of thermal conduction smoothing. The results are of interest for directly driven inertially confined fusion. (C) 1998 American Institute of Physics.

Short-pulse, extreme-ultraviolet continuum emission from a table-top laser plasma light source

We have observed extreme-ultraviolet (XUV) ''line-free'' continuum emission from laser plasmas of high atomic number elements using targets irradiated with 248 nm laser pulses of 7 ps duration at a power density of similar to 10(13) W/cm(2). Using both dispersive spectroscopy and streak camera detection, the spectral and temporal evolution of XUV continuum emission for several target atomic numbers has been measured on a time scale with an upper limit of several hundred picoseconds limited by amplified spontaneous emission. (C) 1997 American Institute of Physics.