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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

There is increasing need for highly predictive and stable models for theprediction of drought as an aid to better planning for drought response. Thispaper presents the performance of both homogenous and heterogenous modelensembles in the prediction of drought severity using the study case techniquesof artificial neural networks (ANN) and support vector regression (SVR). Foreach of the homogenous and heterogenous model ensembles, the study investigatesthe performance of three model ensembling approaches: linear averaging(non-weighted), ranked weighted averaging and model stacking using artificialneural networks. Using the approach of 'over-produce then select', the studyused 17 years of data on 16 selected variables for predictive droughtmonitoring to build 244 individual ANN and SVR models from which 111 modelswere selected for the building of the model ensembles. The results indicatemarginal superiority of heterogenous to homogenous model ensembles. Modelstacking is shown to realize models that are superior in performance in theprediction of future vegetation conditions as compared to the linear averagingand weighted averaging approaches. The best performance from the heterogenousstacked model ensembles recorded an R2 of 0.94 in the prediction of futurevegetation conditions as compared to an R2 of 0.83 and R2 of 0.78 for both ANNand SVR respectively in the traditional champion model approaches to therealization of predictive models. We conclude that despite the computationalresource intensiveness of the model ensembling approach to drought prediction,the returns in terms of model performance is worth the investment, especiallyin the context of the recent exponential increase in computational power.

Model ensembles of artificial neural networks and support vector regression for improved accuracy in the prediction of vegetation conditions