What is it about?
Traditional water level prediction methods have insufficient information mining ability and unclear algorithmic mechanism, so this paper proposes for the first time a water level prediction method based on the fusion of blockchain technology and Long Short-Term Memory (LSTM) network, which provides technical support for real-time scheduling of the South-to-North Water Diversion Project.
Featured Image
Photo by matthew Feeney on Unsplash
Why is it important?
In this paper, the flow compensation strategy is proposed for the first time to compensate the monitoring data with large deviation accordingly and reduce the prediction error from the source. The results show that the Blockchain-LSTM combination model has the smallest prediction error after adopting the compensation strategy, which has high prediction accuracy and practicability, and provides technical support for the real-time scheduling of the South-to-North Water Diversion Reservoir.
Perspectives
Writing this article was very rewarding as it contributed to the cause of smart water. This article also gave me and my co-collaborators the opportunity to learn from each other and share experiences on a larger platform.
Zhang Mengxiao
Read the Original
This page is a summary of: Water level prediction model based on blockchain and LSTM, Journal of Intelligent & Fuzzy Systems, January 2024, IOS Press,
DOI: 10.3233/jifs-231411.
You can read the full text:
Resources
Contributors
The following have contributed to this page
