对虾养殖溶解氧浓度组合预测模型EMD-RF-LSTM

doi:10.12133/j.smartag.2021.3.2.202106-SA008

Smart Agriculture ›› 2021, Vol. 3 ›› Issue (2): 115-125.doi: 10.12133/j.smartag.2021.3.2.202106-SA008

对虾养殖溶解氧浓度组合预测模型EMD-RF-LSTM

尹航^1,^3,^4,⁶(), 李祥铜^1,^3,^4,⁶, 徐龙琴^1,^3,^4,⁶, 李景彬², 刘双印^1,^2,^3,^4,^5,⁶, 曹亮^1,^3,⁴, 冯大春^1,^3,^4,⁶, 郭建军^1,^3,^4,⁶, 李利桥²()

^1.仲恺农业工程学院信息科学与技术学院，广东广州 510225
^2.石河子大学机械电气工程学院，新疆石河子，832000
^3.仲恺农业工程学院智慧农业创新研究院，广东广州 510225
^4.仲恺农业工程学院广东省高校智慧农业工程技术研究中心，广东广州 510225
^5.仲恺农业工程学院广东省水禽健康养殖重点实验室，广东广州 510225
^6.仲恺农业工程学院广东省农产品安全大数据工程技术研究中心，广东广州 510225

收稿日期:2021-06-11 修回日期:2021-06-28 出版日期:2021-06-30
基金资助:
国家自然科学基金项目(61871475);广东省自然科学基金项目(2021A1515011605);现代农业机械兵团重点实验室开放课题资助(BTNJ2021002);广东省科技厅重点领域研发计划项目(2020B0202080002);北京市自然科学基金项目(4182023);广东省科技计划项目(2019B020215003);广州市重点研发计划项目(20210300003);广州市创新平台建设计划项目(201905010006);广东省农业技术研发项目(2018LM2168)
作者简介:尹航（1978－），男，博士，副教授，研究方向为人工智能和重大装备健康管理。E-mail：736028008@qq.com。
通信作者:

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

YIN Hang^1,^3,^4,⁶(), LI Xiangtong^1,^3,^4,⁶, XU Longqin^1,^3,^4,⁶, LI Jingbin², LIU Shuangyin^1,^2,^3,^4,^5,⁶, CAO Liang^1,^3,⁴, FENG Dachun^1,^3,^4,⁶, GUO Jianjun^1,^3,^4,⁶, LI Liqiao²()

^1.Zhongkai University of Agriculture and Engineering, College of Information Science and Technology, Guangzhou, 510225, China
^2.Shihezi University, College of Mechanical and Electric Engineerings, Shihezi, 832000, China
^3.Zhongkai University of Agriculture and Engineering, Academy of Smart Agricultural Engineering Innovations, Guangzhou 510225, China
^4.Zhongkai University of Agriculture and Engineering, Smart Agriculture Engineering Research Center of Guangdong Higher Education Institutes, Guangzhou 510225, China
^5.Zhongkai University of Agriculture and Engineering, Guangdong Key Laboratory of Waterflow Health Breeding, Guangzhou 510225, China

Received:2021-06-11 Revised:2021-06-28 Online:2021-06-30

摘要/Abstract

摘要：

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。

关键词: 对虾养殖, 溶解氧浓度预测, 经验模态分解, 随机森林, 长短时记忆神经网络

Abstract:

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.

Key words: prawn pond, dissolved oxygen prediction, empirical mode decomposition, random forest, short and long-term memory neural network

中图分类号:

TP391

尹航, 李祥铜, 徐龙琴, 李景彬, 刘双印, 曹亮, 冯大春, 郭建军, 李利桥. 对虾养殖溶解氧浓度组合预测模型EMD-RF-LSTM[J]. 智慧农业（中英文）, 2021, 3(2): 115-125.

YIN Hang, LI Xiangtong, XU Longqin, LI Jingbin, LIU Shuangyin, CAO Liang, FENG Dachun, GUO Jianjun, LI Liqiao. EMD-RF-LSTM: Combination Prediction Model of Dissolved Oxygen Concentration in Prawn Culture[J]. Smart Agriculture, 2021, 3(2): 115-125.

参考文献

1	于道德, 宋静静, 叶海斌, 等. 生态理念下对虾健康养殖发展建议[J].生态学杂志, 2021, 40(2): 568-576.
1	YU D, SONG J, YE H, et al. Suggestions on the development of healthy shrimp culture under ecological framework[J]. Chinese Journal of Ecology, 2021, 40(2): 568-576.
2	朱林, 车轩, 刘兴国, 等. 简易式工厂化循环水对虾养殖系统构建及试验[J]. 农业工程学报, 2020, 36 (15): 210-216.
2	ZHU L, CHE X, LIU X, et al. Construction and experiment of simple industrial recirculating water shrimp culture system[J]. Transactions of the CSAE, 2020, 36(15): 210 -216.
3	吴静, 李振波, 朱玲, 等. 融合ARIMA模型和GAWNN的溶解氧含量预测方法[J].农业机械学报, 2017, 48(S1): 205-210.
3	WU J, LI Z, ZHU L, et al. Hybrid model of ARIMA model and GAWNN for dissolved oxygen content prediction[J]. Transactions of the CSAM, 2017, 48(S1): 205-210.
4	陈英义, 程倩倩, 方晓敏, 等. 主成分分析和长短时记忆神经网络预测水产养殖水体溶解氧[J]. 农业工程学报, 2018, 34(17): 183-191.
4	CHEN Y, CHENG Q, FANG X, et al. Principal component analysis and long short-term memory neural network for predicting dissolved oxygen in water for aquaculture[J]. Transactions of the CSAE, 2018, 34 (17): 183-191.
5	SWETA B, AMBIKA H, MAHESHAWARI J., Simple rapid and on spot dye-based sensor for the detection of Vibrio load in shrimp culture farms[J]. Archives of Clinical Microbiology, 2021 (1): 1-8.
6	LIU S, XU L, JIANG Y, et al. A hybrid WA-CPSO-LSSVR model for dissolved oxygen content prediction in crab culture[J]. Engineering Applications of Artificial Intelligence, 2014, 29(3): 114-124.
7	徐龙琴, 陈跃霞, 张军, 等. 基于WA-ABC-WLSSVR的南美白对虾工厂化育苗溶解氧预测模型[J]. 武汉大学学报(工学版), 2017, 50(4): 608-617.
7	XU L, CHEN Y, ZHANG J, et al. Prediction model of dissolved oxygen in industrialized vannamei breeding based on wavelet analysis and weighted least squares support vector regression optimized by artificial bee colony algorithm[J]. Engineering Journal of Wuhan University, 2017, 50(4): 608-617.
8	HUAN J, LI H, LI M, et al. Prediction of dissolved oxygen in aquaculture based on gradient boosting decision tree and long short-term memory network: A study of Changzhou fishery demonstration base, China[J]. Computers and Electronics in Agriculture, 2020, DOI: 10.1016/j.compag.2020.105530.
9	朱南阳, 吴昊, 尹达恒, 等. 基于长短时记忆网络(LSTM)的蟹塘溶解氧估算优化方法[J]. 智慧农业(中英文), 2019, 1(3): 67-76.
9	ZHU N, WU H, YIN D, et al. An improved method for estimating dissolved oxygen in crab ponds based on Long Short-Term Memory[J]. Smart Agriculture, 2019, 1(3): 67-76.
10	CAO W, HUAN J, LIU C, et al. A combined model of dissolved oxygen prediction in the pond based on multiple-factor analysis and multi-scale feature extraction[J]. Aquacultural Engineering, 2019, 84: 50-59.
11	RAHMAN A, DABROWSKI J, MCCULLOCH J. Dissolved oxygen prediction in prawn ponds from a group of one step predictors[J]. Information Processing in Agriculture, 2020, 7(2): 307-317.
12	施珮, 匡亮, 袁永明, 等. 基于改进极限学习机的水体溶解氧预测方法[J]. 农业工程学报, 2020, 36 (19): 225-232.
12	SHI P, KUANG L, YUAN Y, et al. Dissolved oxygen prediction for water quality of aquaculture using improved ELM network[J]. Transactions of the CSAE, 2020, 36(19): 225-232.
13	REN Q, WANG X, LI W, et al. Research of dissolved oxygen prediction in recirculating aquaculture systems based on deep belief network[J]. Aquacultural Engineering, 2020, 90: ID 102085.
14	LIU Y, ZHANG Q, SONG L, et al. Attention-based recurrent neural networks for accurate short-term and long-term dissolved oxygen prediction[J]. Computers and Electronics in Agriculture, 2019, 165: ID 104964.
15	樊宇星, 任妮, 田港陆, 等. 基于DeepAR-RELM的池塘溶解氧时空预测方法研究[J]. 农业机械学报, 2020, 51(S1): 405-412.
15	FAN Y, REN N, TIAN G, et al. Spatio-temporal prediction method of dissolved oxygen in ponds based on DeepAR-RELM[J]. Transactions of the CSAM, 2020, 51(S1): 405-412.
16	饶伟, 杨卫中, 位耀光, 等. 鱼菜共生水体溶解氧时空变化规律及其影响因素研究[J]. 农业机械学报, 2017, 48(S1): 374-380.
16	RAO W, YANG W, WEI Y, et al. Temporal and spatial variability of water dissolved oxygen with influence factors in aquaponics system[J]. Transactions of the CSAM, 2017, 48(S1): 374-380.
17	于辉辉. 基于机器学习的池塘养殖水质关键因子预测方法研究[D]. 北京: 中国农业大学, 2017.
17	YU H. Research on prediction method of key factors of pond aquaculture water quality based on machine learning[D]. Beijing: China Agricultural University, 2017.
18	胡茑庆, 陈徽鹏, 程哲, 等. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7): 9-18.
18	HU N, CHEN H, CHENG Z, et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering, 2019, 55(7): 9-18.
19	杨建华, 韩帅, 张帅, 等. 强噪声背景下滚动轴承微弱故障特征信号的经验模态分解[J]. 振动工程学报, 2020, 33(3): 582-589.
19	YANG J, HAN S, ZHANG S, et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Vibration Engineering, 2020, 33(3): 582-589.
20	刘云, 许自强, 董王英, 等. 基于经验模态分解和长短期记忆神经网络的变压器油中溶解气体浓度预测方法[J]. 中国电机工程学报, 2019, 39(13): 3998-4008.
20	LIU Y, XU Z, DONG W, et al. Concentration prediction of dissolved gases in transformer oil based on empirical mode decomposition and long short-term memory neural networks[J]. Proceedings of The Chinese Society for Electrical Engineering, 2019, 39(13): 3998-4008.
21	徐龙琴, 张军, 李乾川, 等. 基于EMD和ELM的工厂化育苗水温组合预测模型[J]. 农业机械学报, 2016, 47(4): 265-271.
21	XU L, ZHANG J, LI Q, et al. Combined prediction model of water temperature in industrialized cultivation based on empirical mode decomposition and extreme learning machine[J]. Transactions of the CSAM, 2016, 47(4): 265-271.
22	施珮, 袁永明, 匡亮, 等. 基于EMD-IGA-SELM的池塘养殖水温预测方法[J]. 农业机械学报, 2018, 49 (11): 312-319.
22	SI P, YUAN Y, KUANG L, et al. Water temperature prediction in pond aquaculture based on EMD-IGA-SELM neural network[J]. Transactions of the CSAM, 2018, 49(11): 312-319.
23	杨亮, 刘春红, 郭昱辰, 等. 基于EMD-LSTM的猪舍氨气浓度预测研究[J]. 农业机械学报, 2019, 50 (S1): 353-360.
23	YANG L, LIU C, GUO Y, et al. Prediction of ammonia concentration in fattening piggery based on EMD-LSTM[J]. Transactions of the CSAM, 2019, 50(S1): 353-360.
24	戴邵武, 陈强强, 刘志豪, 等. 基于EMD-LSTM的时间序列预测方法[J]. 深圳大学学报(理工版), 2020, 37(3): 265-270.
24	DAI S, CHEN Q, LIU Z, et al. Time series prediction based on EMD-LSTM model[J]. Journal of Shenzhen University (Science & Engineering), 2020, 37(3): 265-270.
25	赵晓东, 苏公瑾, 李克利, 等. 一种融合EMD分解和LSTM网络的频谱占用度预测模型[J]. 计算机科学, 2020, 47(S1): 294-298.
25	ZHAO X, SU G, LI K, et al. Spectrum occupancy prediction model based on EMD decomposition and LSTM networks[J]. Computer Science, 2020, 47(S1): 294-298.
26	秦喜文, 吕思奇, 李巧玲, 等. 利用整体经验模态分解和随机森林的脑电信号分类研究[J]. 中国生物医学工程学报, 2018, 37(6): 665-672.
26	QIN X, LYU S, LI Q. Recognition of EEG based on ensemble empirical mode decomposition and random forest[J]. Chinese Journal of Biomedical Engineering, 2018, 37(6): 665-672.
27	ANNA C, SALAH S, BRETT W. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review[J]. Computers and Electronics in Agriculture, 2018, 151: 61-69.
28	DHIVYA E, DURAI R, VISHAL S, et al. Forecasting yield by integrating agrarian factors and machine learning models: A survey[J]. Computers and Electronics in Agriculture, 2018, 155: 257-282.
29	刘峻明, 和晓彤, 王鹏新, 等. 长时间序列气象数据结合随机森林法早期预测冬小麦产量[J]. 农业工程学报, 2019, 35(6): 158-166.
29	LIU J, HE X, WANG P, et al. Early prediction of winter wheat yield with long time series meteorological data and random forest method[J]. Transactions of the CSAE, 2019, 35(6): 158-166.
30	陈英义, 方晓敏, 梅思远, 等. 基于WT-CNN-LSTM的溶解氧含量预测模型[J]. 农业机械学报, 2020, 51(10): 284-291.
30	CHEN Y, FANG X, MEI S, et al. Principal component analysis and long short-term memory neural network for predicting dissolved oxygen in water for aquaculture[J]. Transactions of the CSAM, 2020, 51(10): 284-291.
31	金秀章, 刘岳, 于静, 等. 基于变量选择和EMD-LSTM网络的出口SO₂浓度预测[J/OL]. 中国电机工程学报, (2021-04-19). .
31	JIN X, LIU Y, YU J, et al. Prediction of outlet SO₂ concentration based on variable selection and EMD-LSTM[J/OL]. Proceedings of The Chinese Society for Electrical Engineering, (2021-04-19). .

[1]	魏永康, 杨天聪, 丁信尧, 高越之, 袁鑫茹, 贺利, 王永华, 段剑钊, 冯伟. 基于不同空间分辨率无人机多光谱遥感影像的小麦倒伏区域识别方法[J]. 智慧农业(中英文), 2023, 5(2): 56-67.
[2]	赖佳政, 李贝贝, 程翔, 孙丰, 陈炬廷, 王晶, 张芊, 叶协锋. 基于无人机高光谱遥感的烤烟叶片叶绿素含量估测[J]. 智慧农业(中英文), 2023, 5(2): 68-81.
[3]	左敏, 胡天宇, 董微, 张可心, 张青川. 基于Informer神经网络的农产品物流需求预测分析——以华中地区为例[J]. 智慧农业(中英文), 2023, 5(1): 34-43.
[4]	范承志, 王梓文, 杨兴超, 罗永开, 徐学欣, 郭斌, 李振海. 基于地物高光谱和无人机多光谱的黄河三角洲土壤盐分机器学习反演模型[J]. 智慧农业(中英文), 2022, 4(4): 61-73.
[5]	庄家煜, 许世卫, 李杨, 熊露, 刘克宝, 钟志平. 基于深度学习的多种农产品供需预测模型[J]. 智慧农业(中英文), 2022, 4(2): 174-182.
[6]	李东博, 黄铝文, 赵旭博. 基于介电特征的苹果霉心病检测方法[J]. 智慧农业(中英文), 2021, 3(4): 66-76.
[7]	刘恬琳, 朱西存, 白雪源, 彭玉凤, 李美炫, 田中宇, 姜远茂, 杨贵军. 土壤有机质含量高光谱估测模型构建及精度对比[J]. 智慧农业（中英文）, 2020, 2(3): 129-138.
[8]	邵国敏, 王亚杰, 韩文霆. 基于无人机多光谱遥感的夏玉米叶面积指数估算方法[J]. 智慧农业（中英文）, 2020, 2(3): 118-128.

对虾养殖溶解氧浓度组合预测模型EMD-RF-LSTM

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

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价