Abstract
Water quality is an important factor that affects aquaculture. Water quality parameters have the characteristics of a time series, and display instability and nonlinearity, and are coupled by complex relationships. Therefore, accurate prediction of water quality parameters is challenging. This paper constructs a water quality parameter prediction model combining the Discrete Hidden Markov model (DHMM) and K-means clustering methods.The model was used to predict the dissolved oxygen saturation and turbidity of six marine ranches in the Bohai Rim. Based on the analysis of the correlations between the water quality parameters, the hidden state of the DHMM that affects the target water quality parameters is determined, and the adaptability of the model has been improved. The number of hidden states is determined by K-means clustering, and a water quality parameter prediction model based on DHMM is established to realize the prediction of dissolved oxygen saturation and turbidity. The model is of low complexity and has strong explanatory power. Experimental results show that compared with other water quality parameter prediction algorithms,under the same conditions, there are fewer training parameters proposed in the article in regard to the water quality parameter prediction method, and better prediction performance is shown. The results of this study can provide references for predicting water quality parameters of marine pastures and sustainable management of aquaculture ecosystems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.