The Water Deficits Prediction of SC and NC by Bayesian Network

DOI

10.2991/wartia-16.2016.190How to use a DOI?

Keywords

Bayesian network, Water deficits,Prediction.

Abstract

In order to predict the water situation in 15 years, this paper develops Bayesian Artificial neural network system. The directed cyclic graph is built and the conditional probability tables are calculated. It represents the relationships among variable nodes in the graph. The Bayesian network makes the prediction error of Artificial neural network smaller, which relies on the probabilistic inference. This paper predicts the water demand, water supply and value of water consumption in several critical indicators The final prediction results show that the water deficits of South Carolina and North Carolina have an ease .The total water deficit presented a decreasing trend from 1081.51 to 467.62 million tons, which proves the effectiveness of the intervention plan.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yilin Li
PY  - 2016/05
DA  - 2016/05
TI  - The Water Deficits Prediction of SC and NC by Bayesian Network
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 898
EP  - 901
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.190
DO  - 10.2991/wartia-16.2016.190
ID  - Li2016/05
ER  -