Forecasting Cyanobacteria with Bayesian and Deterministic Artificial Neural Networks
Kingston, G.B.
Maier, H.R.
Lambert, M.F.
Adelaide Univ., Adelaide;
This paper appears in: Neural Networks, 2006. IJCNN '06. International Joint Conference on
Publication Date: 0-0 0
On page(s): 4870-4877
Location: Vancouver, BC,
ISBN: 0-7803-9490-9
INSPEC Accession Number: 9723396
Digital Object Identifier: 10.1109/IJCNN.2006.247166
Current Version Published: 2006-10-30
Abstract
Cyanobacteria blooms are a major water quality problem in the River Murray and models are needed In provide warnings of such blooms and to investigate the response of cyanobacteria to different management strategies. However, the data, available this problem, are subject to considerable errors and consequently, it can be expected that the performance of any data-driven model will be limited. Two ANN models, developed using deterministic and Bayesian approaches, are compared to assess the strengths and limitations of these data-driven modelling approaches in the face of this data uncertainty. The resulting ANNs are assessed in terms of their usefulness as forecasting models and as tools for gaining information about the system.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
