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

Since a spectrum of hydrological and geomorphological conditions produce flood pulse environment in a riverine or a deltaic system, it is essential to have the knowledge on spatial and temporal distributions of river flow and dependent processes for environmental flow requirements, ecosystem maintenance, water resources management, and hydrological forecasting among others. Such systems being complex as the exchange of flows between the main channel and the flood plains are not well understood, flow partitioning dynamics between the various channels on large water bodies are often difficult to represent even with sophisticated models. In view of this, an attempt has been made to apply a short-term stochastic forecasting model-an Auto Regressive Integrated Moving Average (ARIMA) aided by Artificial Neural Networks (ANNs) to partition flows into the downstream tributaries, viz.: Lopis and Gadikwe channels from the Khiandiandavhu-Maunachira (K-M) Junction Junction (the main river channel) river system of the iconic Okavango delta in Botswana. As such, observed monthly flow data between October 2005 and September 2008 at the K-M Junction, and the two downstream tributaries were used to test the performance of these hybrid models for the complex deltaic system. It was found that the partitioned flows at Lopis and Gadikwe agree very well with observations when using a Single Input Multiple Output (SIMO) ANN (i.e. an inverse variant of the widely used Multi Input Single Output (MISO) ANN architecture) and an ARIMA (1,1,1) model. The Mean Squared Errors (MSEs) in the forecasts were also minimal, thus giving some hope on the use of such a hybrid mode for the rest of the branched river networks of the whole Okavango delta.

A Hybrid Stochastic-ANN Approach for Flow Partitioning in the Okavango Delta of Botswana