A hybrid intelligence model for predicting dissolved oxygen in aquaculture water

Dissolved oxygen is an important water quality indicator that affects the health of aquatic products in aquaculture, and its monitoring prediction are great significance. To improve accuracy dissolved series, a hybrid model based on variational mode decomposition (VMD) deep belief network (DBN) optimized by improved slime mould algorithm (SMA) proposed this paper. First, VMD used to decompose nonlinear time series into several relatively stable intrinsic function (IMF) subsequences with different frequency scales. Then, SMA applying elite opposition-based learning convergence factors increase population diversity enhance local search global capabilities. Finally, optimize hyperparameters DBN, aquaculture VMD-ISMA-DBN constructed. The predict each IMF subsequence, ISMA optimization adaptively select optimal DBN model, results accumulated obtain final result series. data from 8 marine ranches Shandong Province, China were verify performance model. Compared stand-alone has been significantly improved, MAE MSE have reduced 43.28% 40.43% respectively, ( R 2 ) increased 8.37%. show higher than other commonly intelligent models (ARIMA, RF, TCN, ELM, GRU LSTM); hence, it can provide reference for accurate regulation quality.