English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In order to increase the accuracy of serial-propagatedlong-range multi-step-ahead (MSA) prediction, which has high practical valuebut also great implementary difficulty because of huge error accumulation, anovel wavelet neural network hybrid model – CDW-NN – combining continuous and discretewavelet transforms (CWT and DWT) and neural networks (NNs), is designed asthe MSA predictor for the effective long-term forecast of hydrologicalsignals. By the application of 12 types of hybrid and pure models inestuarine 1096-day river stages forecasting, the different forecastperformances and the superiorities of CDW-NN model with correspondingdriving mechanisms are discussed. One type of CDW-NN model, CDW-NF, whichuses neuro-fuzzy as the forecast submodel, has been proven to be the mosteffective MSA predictor for the prominent accuracy enhancement during theoverall 1096-day long-term forecasts. The special superiority of CDW-NFmodel lies in the CWT-based methodology, which determines the 15-day and28-day prior data series as model inputs by revealing the significantshort-time periodicities involved in estuarine river stage signals.Comparing the conventional single-step-ahead-based long-term forecastmodels, the CWT-based hybrid models broaden the prediction range in eachforecast step from 1 day to 15 days, and thus reduce the overall forecastingiteration steps from 1096 steps to 74 steps and finally create significantdecrease of error accumulations. In addition, combination of the advantagesof DWT method and neuro-fuzzy system also benefits filtering the noisydynamics in model inputs and enhancing the simulation and forecast abilityfor the complex hydro-system

Multi-step-ahead predictor design for effective long-term forecast of hydrological signals using a novel wavelet neural network hybrid model