对虾养殖溶解氧浓度组合预测模型EMD-RF-LSTM

溶解氧（DO）浓度是对虾养殖水质检测的核心指标。为提高对虾养殖溶解氧浓度的预测精度，本研究提出了一种基于经验模态分解、随机森林和长短时记忆神经网络（EMD-RF-LSTM）的对虾养殖溶解氧浓度组合预测模型。首先采用经验模态分解（EMD）对养殖水质溶解氧浓度时序数据进行多尺度特征提取，得到不同尺度下的固有模态分量（IMF）；然后分别采用长短时记忆神经网络（LSTM）和随机森林（RF）对高、低频不同尺度IMF进行建模；最后结合各分量预测结果构建叠加模型，实现对溶解氧浓度时序数据的综合预测。本研究模型在广东省湛江市南三岛对虾养殖基地展开了试验及应用，在基于真实数据集的性能测试中，经验模态分解后EMD-ELM模型与极限学习机（ELM）模型对比，平均绝对误差（MAPE）、均方根误差（RMSE）和平均绝对误差（MAE）分别降低了30.11%、29.60%和32.95%。在经验模态分解基础上用RF和LSTM对不同特征尺度的本征模态分量分别预测后叠加求和，EMD-RF-LSTM模型预测的精度指标MAPE、RMSE和MAE分别为0.0129、0.1156和0.0844，其中关键指标MAPE较EMD-ELM、EMD-RF和EMD-LSTM分别降低了84.07%、57.57%和49.81%，预测精度显著提高。结果表明，本研究针对经验模态分解后高、低频分量分别预测的策略可有效提升综合性能，表明本研究模型具有较高的预测精度，能够较准确地实现对虾养殖水体中溶解氧浓度预测。

EMD-RF-LSTM: Combination Prediction Model of Dissolved Oxygen Concentration in Prawn Culture

Dissolved oxygen is an important environmental factor for prawn breeding. In order to improve the prediction accuracy of dissolved oxygen concentration in prawn pond, and solve the problem of low prediction accuracy of different frequency domain modal classification after empirical modal decomposition of nonlinear time series data when there are few training samples, an combination prediction model based on empirical mode decomposition (EMD), random forest (RF) and long short term memory neural network (LSTM) was proposed in this research. Firstly, the time series data of prawn breeding dissolved oxygen concentration were decomposed at multiple scales by EMD to obtain a set of stationary intrinsic mode function (IMF). Secondly, with fewer training samples, poor predicts effects on the low-frequency were verified component by LSTM. Then, IMF1－IMF4 were divided into high-frequency components through test results and used for LSTM model. IMF5－IMF7, Rn were divided for RF model, the EMD-RF-LSTM combination model was constructed to improve the prediction accuracy. Modeled low-frequency and high-frequency components IMF using RF and LSTM, then predictions of each component were accumulated and the prediction value of dissolved oxygen of sequence data were got. Finally, the performance of the model was compared with the limit learning machine (ELM), RF, standard LSTM, EMD-ELM and EMD-RF, EMD-LSTM, etc. In the test based on real dataset, the EMD-ELM model contrasted with ELM model, reduced the mean absolute error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) by 30.11%, 29.60% and 32.95%, respectively. The MAPE, RMSE, MAE for the proposed models were 0.0129,0.1156,0.0844, respectively. MAPE decreased by 84.07%, 57.57%, and 49.81% compared with EMD-ELM, EMD-RF and EMD-LSTM, respectively, the prediction accuracy was significantly improved. The results show that the proposed model EMD-RF-LSTM has good prediction performance and generalization ability, which is meets the actual demand of accurate prediction of dissolved oxygen concentration in prawn culture, and can provide reference for the prediction and early warning of prawn pond water quality.