Simulation of future dissolved oxygen distribution in pond culture based on sliding window-temporal convolutional network and trend surface analysis

Abstract Dissolved oxygen (DO) is a key ecological factor to measure the quality of water in the aquaculture. As the pond water body is affected by the breeding environment, the spatial distribution of DO shows a certain law in the entire pond. Therefore, to simulate the distribution of DO in aquaculture waters and grasp the temporal and spatial variation of DO is the key to achieving precise regulation of DO. For this purpose, this paper proposed a method for simulating the temporal and spatial distribution of DO in pond culture based on a sliding window-temporal convolutional network together with trend surface analysis (SW-TCN-TSA). This paper first utilized SW to construct DO data sets with different prediction durations, and then used the improved TCN model to realize one-dimensional time series prediction for DO at single monitoring point. Based on the prediction results of DO, a TSA method was performed on the predicted values of DO at the extreme moments of all discrete monitoring points, so as to realize the simulation of the temporal and spatial distribution of DO in the pond. Experimental results show that the SW-TCN model has better prediction performance for one-dimensional time series prediction of DO. Compared with traditional deep networks, such as CNN, GRU, LSTM, CNN-GRU and CNN-LSTM, the values of evaluation indicators (MSE, MAE and RMSE) have been greatly improved. In the process of trend surface fitting, all fitting R2 of DO at different water depths are higher than 0.9, indicating that the TSA can accurately reflect the temporal and spatial distribution of DO. This method can provide a basis for the prediction and early warning of DO in the three-dimensional space of the pond and has high practicability in aquaculture.