首页|期刊导航|农业大数据学报|基于双通道GWO-KELM的河北省主要蔬菜品种价格预测研究

基于双通道GWO-KELM的河北省主要蔬菜品种价格预测研究OA

Prediction of Main Vegetable Prices in Hebei Province Based on Dual-Channel GWO-KELM

中文摘要英文摘要

针对河北省主要蔬菜价格序列的非线性、非平稳性与高噪声特征,以及核极限学习机(KELM)参数依赖经验设定导致预测精度受限的问题,构建一种融合灰狼优化算法(GWO)与双通道核极限学习机的多变量组合预测模型,以提升蔬菜价格的短期预测精度.以 2021 年 1 月至 2024 年 12 月河北省 10 个主要蔬菜品种(大白菜、洋白菜、西红柿、黄瓜、土豆、青椒、大葱、大蒜、豆角、西葫芦)的周度批发价格数据为研究对象,总样本量 2 080 条.同时采集气象、节日、农资、成品油、微博舆情、百度指数、宏观经济、食品消费等 8 类 28 个外部特征.采用均值插补和 3σ 原则进行数据清洗,Min-Max 归一化消除量纲影响.首先通过格兰杰因果检验验证外部特征与价格的预测性因果关系,并为保证模型简洁性和训练效率,每个品种保留最显著的 8 个特征;进而构建双通道并行 KELM 模型——通道 1 输入价格历史序列(4 周),通道 2 输入筛选后的外部特征,两通道核矩阵通过可学习权重 α 进行加权融合.引入 GWO 算法对正则化系数 C、核参数 σ1、σ2 及融合权重α进行自动寻优,以验证集均方根误差(RMSE)为适应度函数,种群规模 15、迭代 50 次.同时与单通道价格历史模型(M1)、单通道特征拼接模型(M2)以及 SVM、LSTM、GRU 等 3 种主流模型进行对比.双通道 GWO-KELM 模型(M3)在 10 个品种上的平均绝对百分比误差(MAPE)为 7.52%,较 M1(10.59%)降低 3.07 个百分点,较 M2(9.12%)降低 1.60个百分点,显著优于 LSTM(9.87%)、GRU(9.56%)等深度学习方法.在高波动品种大葱上改善尤为显著(MAPE 由 13.76%降至 9.85%).融合权重α显示:价格平稳品种(大蒜 α=0.81,土豆 α=0.76)更依赖历史惯性,高波动品种(大葱 α=0.48,黄瓜 α=0.54)对外部特征依赖更强,α 与价格变异系数呈负相关(r≈-0.73).外部特征贡献度分析表明,气温、农资价格、节日舆情及成品油价格是影响蔬菜价格的重要先行指标.模型在未参与训练的茄子、芹菜、生菜上 MAPE 分别为 7.98%、9.12%、12.06%,各季节误差增幅控制在 1 个百分点以内.本研究构建的双通道 GWO-KELM 组合模型有效解决了 KELM 参数依赖经验设定的问题,通过格兰杰因果验证与双通道核融合机制,实现了时序特征与多源异构外部特征的自适应整合.在河北省主要蔬菜品种价格预测中具有高精度、强泛化能力和良好稳健性,可为政府调控、企业运营和农户生产提供科学决策支持.

To address the nonlinear,non-stationary,and high-noise characteristics of main vegetable price series in Hebei Province,as well as the problem that the kernel extreme learning machine(KELM)relies on empirical parameter settings,which limits its prediction accuracy,this paper constructs a multivariate combined forecasting model integrating the grey wolf optimizer(GWO)and a dual-channel KELM to improve short-term vegetable price prediction accuracy.The weekly wholesale price data of 10 major vegetable varieties(Chinese cabbage,cabbage,tomato,cucumber,potato,green pepper,scallion,garlic,bean,and zucchini)in Hebei Province from January 2021 to December 2024 are collected,with a total sample size of 2,080 records.Eight categories of external features(meteorological,holiday,agricultural material prices,refined oil prices,Weibo public opinion,Baidu index,macro-economic indicators,and food consumption)comprising 28 variables are also collected.Missing values are imputed by mean interpolation,outliers are corrected based on the 3σ principle,and Min-Max normalization is applied to eliminate dimensional effects.First,the Granger causality test is used to verify the predictive causal relationship between external features and vegetable prices,and for the sake of model parsimony and training efficiency,the eight most significant features per variety are retained.Then,a dual-channel parallel KELM model is constructed:Channel 1 takes the price history(4 weeks)and Channel 2 takes the selected external features.The kernel matrices of the two channels are fused by a learnable weight α.The GWO algorithm is introduced to automatically optimize the regularization coefficient C,kernel parameters σ₁ and σ₂,and the fusion weight α,using the root mean square error(RMSE)on the validation set as the fitness function with a population size of 15 and 50 iterations.The proposed model(M3)is compared with a single-channel model using only price history(M1),a single-channel feature-concatenation model(M2),as well as three mainstream models(SVM,LSTM,GRU).The dual-channel GWO-KELM model(M3)achieves an average mean absolute percentage error(MAPE)of 7.52%across the 10 varieties,which is 3.07 percentage points lower than that of M1(10.59%)and 1.60 percentage points lower than that of M2(9.12%),and significantly outperforms deep learning methods such as LSTM(9.87%)and GRU(9.56%).The improvement is particularly significant for highly volatile varieties,such as scallion(MAPE reduced from 13.76%to 9.85%).The fusion weight α shows that price-stable varieties(garlic α=0.81,potato α=0.76)rely more on historical inertia,while highly volatile varieties(scallion α=0.48,cucumber α=0.54)depend more on external features,with a negative correlation between α and the coefficient of price variation(r≈-0.73).Contribution analysis of external features indicates that temperature,agricultural material prices,holiday/opinion indicators,and refined oil prices are important leading indicators for vegetable prices.The model also exhibits good generalization on untrained varieties(eggplant,celery,lettuce),with MAPEs of 7.98%,9.12%,and 12.06%,respectively,and its seasonal error increase is controlled within 1 percentage point.The dual-channel GWO-KELM model constructed in this paper effectively solves the problem of empirical parameter setting of KELM.By integrating Granger causality verification and dual-channel kernel fusion,it achieves adaptive integration of temporal features and heterogeneous external features.The model demonstrates high accuracy,strong generalization ability and good robustness in forecasting main vegetable prices in Hebei Province,and can provide scientific decision support for government regulation,enterprise operations and farmer production.

贾新诚;贾华

大连海洋大学机械与动力工程学院,辽宁 大连 116023||阜平县职业技术教育中心,河北 保定 073200大连海洋大学机械与动力工程学院,辽宁 大连 116023

灰狼优化算法核极限学习机格兰杰因果检验蔬菜价格预测河北省双通道模型

Grey Wolf Optimizerkernel extreme learning machineGranger causality testvegetable price predictionHebei Provincedual-channel model

《农业大数据学报》 2026 (3)

305-312,8

河北省职业教育科学研究"十四五"规划2025年度课题(JZY25181).

10.19788/j.issn.2096-6369.000166

评论