| 128 | 0 | 315 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】提高地下水位时间序列预测精度对于科学预判地下水位变化趋势、合理开发和利用地下水资源具有重要意义。为提高地下水位时间序列预测精度，解决数据分解组合时间序列预测模型计算规模大、复杂程度高等问题【方法】基于小波包分解(WPT)、入侵杂草优化(IWO)算法/花授粉算法(FPA)/树木生长算法(TGA)/向日葵优化(SFO)算法/食肉植物算法(CPA)/蒲公英优化(DO)算法/常春藤算法(IVYA)/青蒿素优化(AO)算法/苔藓生长优化(MGO)算法/莲花效应优化算法(LEA)共十种“植物”算法和正则化极限学习机(RELM),提出基于WPT分解处理的IWO/FPA/TGA/SFO/CPA/DO/IVYA/AO/MGO/LEA-RELM预测模型，并通过云南省西城、南庄、临安、文澜、者林寨、植物园6个地下水位时间序列预测实例对各模型进行验证。首先，利用1层WPT将实例地下水位时间序列分解为趋势项和波动项，并基于趋势项和波动项训练集构建RELM超参数优化实例目标函数；其次，利用十种“植物”算法对实例目标函数进行极值寻优，获得各算法最优超参数；最后，利用最优超参数构建IWO/FPA/TGA/SFO/CPA/DO/IVYA/AO/MGO/LEA-RELM模型对实例地下水位时间序列趋势项和波动项进行预测和重构。【结果】结果显示：IVYA、CPA、FPA寻优性能优于IWO、AO、SFO、DO,远优于LEA、MGO、TGA;IVYA-RELM、CPA-RELM、FPA-RELM模型预测的平均绝对百分比误差(MAPE)在0.003 0%～0.000 4%之间，平均绝对误差(MAE)在0.038 9～0.006 3 m之间，决定系数(DC)在0.997 7～0.999 8之间，预测精度优于其他对比模型，具有较好的预测效果。【结论】结果表明：十种“植物”算法的寻优性能排名与十种组合模型的拟合精度、预测精度排名具有高度的一致性。总体上，算法寻优能力越强，组合模型的拟合、预测精度越高，性能越好；WPT分解分量少、分量规律性强，是一种简介高效的分解方法。
Abstract：[Objective]Improving the accuracy of groundwater level time series prediction is of great significance for scientifically predicting the change trends of groundwater levels and ensuring the rational development and utilization of groundwater resources. The aim is to improve the accuracy of groundwater level time series prediction and address the issues of large computational scale and high complexity in data decomposition-based combination time series prediction models.[Methods]A WPT-decomposed IWO/FPA/TGA/SFO/CPA/DO/IVYA/AO/MGO/LEA-RELM prediction model was proposed, combining Regularized Extreme Learning Machine(RELM) with ten “plant” optimization algorithms, including Wavelet Packet Decomposition(WPT), Invasive Weed Optimization(IWO), Flower Pollination Algorithm(FPA), Tree Growth Algorithm(TGA), Sunflower Optimization(SFO), Carnivorous Plant Algorithm(CPA), Dandelion Optimization(DO), Ivy Algorithm(IVYA), Artemisinin Optimization(AO), Moss Growth Optimization(MGO), and Lotus Effect Optimization Algorithm(LEA). This model was validated using groundwater level time series prediction examples from six locations in Yunnan Province, including Xicheng, Nanzhuang, Lin'an, Wenlan, Zhelinzhai, and Botanical Garden. First, the example's groundwater level time series were decomposed into trend and fluctuation components using one-level WPT. Based on these components, a RELM hyperparameter optimization objective function for the example was established. Then, the ten “plant” algorithms were used to optimize the objective function to determine the best hyperparameters. Finally, the optimal hyperparameters were used to establish IWO/FPA/TGA/SFO/CPA/DO/IVYA/AO/MGO/LEA-RELM models to predict and reconstruct the trend and fluctuation components of the example's groundwater level time series.[Results]The result showed that IVYA, CPA, and FPA outperformed IWO, AO, SFO, DO in optimization performance, and significantly outperformed LEA, MGO, and TGA. The IVYA-RELM, CPA-RELM, and FPA-RELM models achieved a MEAn absolute percentage error(MAPE) of 0.003 0% to 0.000 4%, a MEA absolute error(MAE) of 0.038 9 m to 0.006 3 m, and a coefficient of determination(DC) of 0.997 7 to 0.999 8, which outperformed other comparison models and demonstrated excellent prediction performance.[Conclusion]The result indicate that the optimization performance of the ten “plant” algorithms is highly consistent with the fitting and prediction accuracy rankings of the ten combined models. Overall, the stronger the optimization ability of the algorithms, the higher the fitting and prediction accuracy, and the better the performance of the combined models. The WPT decomposition, with fewer components and strong regularity, is a simple and efficient decomposition method.
[1] 童光泽，李计生，牛最荣，等.基于CNN-LSTM组合模型在地下水位预测中的应用[J].水利规划与设计，2024(9):58-62.TONG G Z,LI J S,NIU Z R,et al.Application of CNN-LSTM combined model in groundwater level prediction[J].Water Resources Planning and Design,2024(9):58-62.
[2] 田辽西，覃华清.基于多变量LSTM神经网络的地下水位预测方法研究[J].干旱区资源与环境，2024,38(9):138-146.TIAN L X,QIN H Q.Multivariable LSTM model-based groundwater level prediction[J].Journal of Arid Land Resources and Environment,2024,38(9):138-146.
[3] 郑世龙，李虎，王中华，等.基于SSA-RBF神经网络模型在岩溶地下水位预测中的研究[J].城市勘测，2024(4):200-204.ZHENG S L,LI H,WANG Z H,et al.Research on karst groundwater level prediction based on SSA-RBF neural network model[J].Urban Geotechnical Investigation & Surveying,2024(4):200-204.
[4] 侯金霄，黄林显，胡晓农，等.基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用[J].水资源与水工程学报，2023,34(4):92-98.HOU J X,HUANG L X,HU X N,et al.Application of EMD-LSTM coupled model to karst groundwater level prediction in Baotu Spring[J].Journal of Water Resources and Water Engineering,2023,34(4):92-98.
[5] 张建锋，刘见宝，崔树军，等.小波-神经网络混合模型预测地下水水位[J].长江科学院院报，2016,33(8):18-21.ZHANG J F,LIU J B,CUI S J,et al.A wavelet-ANN hybrid model for groundwater level forecasting[J].Journal of Yangtze River Scientific Research Institute,2016,33(8):18-21.
[6] 付智勇，陈文强，唐伟雄，等.基于CEEMD-RF模型的渣土边坡地下水埋深预测[J].人民长江，2020,51(1):141-148.FU Z Y,CHEN W Q,TANG W X,et al.Prediction of groundwater depth in residue slope with CEEMD-RF model based on phase space reconstruction[J].Yangtze River,2020,51(1):141-148.
[7] WU M,FENG Q,WEN X H,et al.Deterministic analysis and uncertainty analysis of ensemble forecasting model based on variational mode decomposition for estimation of monthly groundwater level[J].Water,2021,13(2):139.
[8] 李新华，崔东文.基于WPD-RSA-ELM模型的水文时间序列多步预测[J].水利水电技术(中英文),2022,53(11):69-77.LI X H,CUI D W.Multi-step prediction of hydrological time series based on WPD-RSA-ELM model[J].Water Resources and Hydropower Engineering,2022,53(11):69-77.
[9] 李菊，崔东文.基于WPT-IDBO-RELM和WPT-IDMO-RELM模型的日径流预测[J].水利水电科技进展，2024,44(6):48-55.LI J,CUI D W.Daily runoff prediction based on WPT-IDBO-RELM and WPT-IDMO-RELM models[J].Advances in Science and Technology of Water Resources,2024,44(6):48-55.
[10] MEHRABIAN A R,LUCAS C.A novel numerical optimization algorithm inspired from weed colonization[J].Ecological Informatics,2006,1(4):355-366.
[11] 崔东文，郑斌.几种智能优化算法与支持向量机相融合的月径流预测模型及应用[J].人民珠江，2016,37(3):18-25.CUI D W,ZHENG B.Monthly runoff forecasting model and its application with the integration of several intelligent optimization algorithms and support vector machines[J].Pearl River,2016,37(3):18-25.
[12] YANG X S,KARAMANOGLU M,HE X S.Flower pollination algorithm:A novel approach for multiobjective optimization[J].Engineering Optimization,2014,46(9):1222-1237.
[13] 崔东文，金波.花授粉算法-BP神经网络模型及其在月径流预报中的应用[J].人民珠江，2016,37(4):36-40.CUI D W,JIN B.Flower pollination algorithm-BP neural network model and its application in the prediction of monthly runoff[J].Pearl River,2016,37(4):36-40.
[14] CHERAGHALIPOUR A,HAJIAGHAEI-KESHTELI M,PAYDAR M M.Tree Growth Algorithm (TGA):A novel approach for solving optimization problems[J].Engineering Applications of Artificial Intelligence,2018,72:393-414.
[15] 欧阳晨，卫志农，孙国强.基于树木生长算法的含UPFC的最优潮流计算[J].电力工程技术，2020,39(3):84-91.OUYANG C,WEI Z N,SUN G Q.Optimal power flow with UPFC based on tree growth algorithm[J].Electric Power Engineering Technology,2020,39(3):84-91.
[16] GOMES G F,DA CUNHA S S,ANCELOTTI A C.A sunflower optimization (SFO) algorithm applied to damage identification on laminated composite plates[J].Engineering with Computers,2019,35(2):619-626.
[17] ONG K M,ONG P,SIA C K.A carnivorous plant algorithm for solving global optimization problems[J].Applied Soft Computing,2021,98:106833.
[18] 丁乐天，曹蔚，吴佳军，等.基于CPA-FM-MEM磨粒分析的缸套-活塞系统健康状态评估[J].润滑与密封，2024,49(9):106-116.DING L T,CAO W,WU J J,et al.Health status assessment of cylinder liner-piston system based on CPA-FM-MEM wear debris analysis[J].Lubrication Engineering,2024,49(9):106-116.
[19] ZHAO S J,ZHANG T R,MA S L,et al.Dandelion Optimizer:A nature-inspired metaheuristic algorithm for engineering applications[J].Engineering Applications of Artificial Intelligence,2022,114:105075.
[20] 李伟铭，杨敬辉.改进蒲公英优化算法的有限缓冲区流水车间调度[J].计算机系统应用，2024,33(8):240-249.LI W M,YANG J H.Limited buffer flow workshop scheduling based on improved dandelion optimization algorithm[J].Computer Systems and Applications,2024,33(8):240-249.
[21] GHASEMI M,ZARE M,TROJOVSKY P,et al.Optimization based on the smart behavior of plants with its engineering applications:Ivy algorithm[J].Knowledge-Based Systems,2024,295:111850.
[22] YUAN C,ZHAO D,HEIDARI A A,et al.Artemisinin optimization based on malaria therapy:Algorithm and applications to medical image segmentation[J].Displays,2024,84:102740.
[23] 王平安.基于IAO-SVM的软岩隧道变形预测模型[J].铁道建筑技术，2024(8):93-96.WANG P A.Deformation prediction model for soft rock tunnels based on IAO-SVM[J].Railway Construction Technology,2024(8):93-96.
[24] ZHENG B L,CHEN Y,WANG C F,et al.The moss growth optimization (MGO):Concepts and performanceOpen Access[J].Journal of Computational Design and Engineering,2024,11(5):184-221.
[25] DALIRINIA E,JALALI M,YAGHOOBI M,et al.Lotus effect optimization algorithm (LEA):A lotus nature-inspired algorithm for engineering design optimization[J].The Journal of Supercomputing,2024,80(1):761-799.
[26] 吴忠强，尚梦瑶，申丹丹，等.基于BSA-RELM的纯电动汽车锂离子电池SOC估计[J].计量学报，2019,40(4):693-699.WU Z Q,SHANG M Y,SHEN D D,et al.Estimation of SOC of Li-ion battery in pure electric vehicle by BSA-RELM[J].Acta Metrologica Sinica,2019,40(4):693-699.
[27] 王应武，白栩嘉，崔东文.基于WPT-ISO-RELM模型的月径流时间序列预测研究[J].水力发电，2024,50(3):12-18.WANG Y W,BAI X J,CUI D W.Research on monthly runoff time series prediction based on WPT-ISO-RELM model[J].Water Power,2024,50(3):12-18.
[28] 高雪梅，崔东文.WPT-FLA-RELM模型的马鹿塘水电站入库日径流多步预测[J].云南水力发电，2023,39(11):56-62.GAO X M,CUI D W.WPT-FLA-RELM model for multi-step prediction of daily inflow runoff of Malutang Hydropower Station[J].Yunnan Water Power,2023,39(11):56-62.
[29] 董欣林，崔东文.基于WPT-ITTA-RELM/ELM/LSSVM模型的日径流预测研究[J].三峡大学学报(自然科学版),2024,46(4):16-24.DONG X L,CUI D W.Research on daily runoff prediction based on WPT-ITTA-RELM/ELM/LSSVM model[J].Journal of China Three Gorges University (Natural Sciences),2024,46(4):16-24.
[30] 张代凤，崔东文.基于3种新型群体智能算法优化正则化极限学习机的三峡水库入库日径流预测[J].长江科学院院报，2024,41(7):16-24.ZHANG D F,CUI D W.Prediction of daily inflow runoff of Three Gorges Reservoir using regularized extreme learning machine optimized by three new swarm intelligent algorithms[J].Journal of Changjiang River Scientific Research Institute,2024,41(7):16-24.
基本信息:
DOI：10.13928/j.cnki.wrahe.2025.09.009
中图分类号:P641.7
引用信息:
[1]田宇,崔东文,毛宗波,等.基于数据分解与十种“植物”算法优化的RELM地下水位预测[J].水利水电技术(中英文),2025,56(09):118-130.DOI:10.13928/j.cnki.wrahe.2025.09.009.
基金信息:
国家重点研发计划项目(2021YFC300205-06)