基于麻雀搜索算法优化的四种神经网络模型在三七茎粗预测中的效果评估  

Evaluation of four neural network models optimized based on sparrow search algorithm for predicting the stem thickness of Panax notoginseng

作　　者：商晓剑 张瑞 SHANG Xiao-jian;ZHANG Rui(College of Water Conservancy/Key Laboratory of Urban and Rural Water Security,Water Conservation and Emission Reduction in Yunnan Province’s Universities/Yunnan International Joint Research and Development Center for Smart Agriculture and Water Security,Yunnan Agricultural University,Kunming 650201,China)

机构地区：[1]云南农业大学水利学院/云南省高校城乡水安全与节水减排重点实验室/云南省智慧农业与水安全国际联合研发中心,昆明650201

出　　处：《湖北农业科学》2024年第8期72-77,95,共7页Hubei Agricultural Sciences

基　　金：2022年水利部重大科技项目(SKS-2022057);2022年云南省重点研发计划项目(202203AC100004)。

摘　　要：以1年生三七(Panax notoginseng)为研究对象,通过正交试验考察光、水、营养物质对三七茎粗的影响,利用麻雀搜索算法(Sparrow search algorithm,SSA)优化4种模型,分别为反向传播神经网络(Back propagation neural network,BPNN)、长短期记忆神经网络(Long short term memory,LSTM)、随机森林(Random forest,RF)和广义回归神经网络(General regression neural network,GRNN),并应用这4种模型对三七茎粗进行预测。结果表明,光照、水肥等非生物因素对三七茎粗具有明显影响,各因素对三七茎粗的影响程度依次为遮光层数>土壤含水量>矿源黄腐酸钾含量>光照时长。SSA-GRNN模型的决定系数最高,为0.865 6,其次为SSA-RF模型、SSA-BPNN模型、SA-LSTM模型;SSA-GRNN模型的MAE和MSE分别为0.064 1、0.008 7,均低于SSA-BPNN模型、SSA-LSTM模型、SSA-RF模型;SSA-RF模型和SSA-LSTM模型的适应度较大,且陷入了局部最优的情况,从而无法达到全局最优解,SSA-GRNN模型的适应度最小且以最少的迭代次数达到了最佳的适应度。Taking 1-year-old Panax notoginseng as the research object,the effects of light,water,and nutrients on the stem diame⁃ter of Panax notoginseng were investigated through orthogonal experiments,sparrow search algorithm(SSA)was used to optimize four models,namely back propagation neural network(BPNN),Long short term memory(LSTM),random forest(RF),and general re⁃gression neural network(GRNN),and these four models were applied to predict the stem thickness of Panax notoginseng.The results showed that non-biological factors such as light,water,and fertilizer had a significant impact on the stem diameter of Panax notogin⁃seng.The degree of influence of each factor on the stem diameter of Panax notoginseng was shading layer>soil moisture content>potas⁃sium fulvic acid content from mineral sources>light duration.The SSA-GRNN model had the highest coefficient of determination,which was 0.8656,followed by the SSA-RF model,SSA-BPNN model,and SA-LSTM model;the MAE and MSE of the SSA-GRNN model were 0.0641 and 0.0087,respectively,which were lower than those of the SSA-BPNN model,SSA-LSTM model,and SSARF model;the fitness of SSA-RF model and SSA-LSTM model was relatively high,and they were trapped in local optima,making it impossible to achieve a global optimal solution.SSA-GRNN model had the lowest fitness and achieved the best fitness with the least number of iterations.

关 键 词：三七(Panax notoginseng) 茎粗 神经网络模型 麻雀搜索算法 预测 

分 类 号：S274.3[农业科学—农业水土工程] S567.51[农业科学—农业工程] TP183[自动化与计算机技术—控制理论与控制工程]