摘要
针对现有卷积神经网络土壤有机质(SOM)预测模型用在小样本数据集存在建模效果差,预测精度不够高等问题,为更加精准预测土壤SOM含量,以广西国有黄冕林场和国有雅长林场采集的206个土壤样品为研究对象,提出了一种改进时间卷积网络(SATCN)的红壤有机质高光谱预测模型。对土壤样品进行Savitaky-Golay(SG)平滑以及一阶微分(1DR)、二阶微分(2DR)、标准正态变量(SNV)和多元散射校正(MSC)四种变换,对比分析长短记忆网络(LSTM)、偏最小二乘回归(PLSR)和支持向量机(SVM)在不同光谱预处理下的建模效果,结果表明,采用SG处理后的光谱一阶微分预处理方法,建模效果最好;在时间卷积网络(TCN)架构上,采用浅层网络结构,在TCN残差结构中加入自注意力层,提高模型特征学习能力;每个卷积核权重加入L2正则化,防止过拟合;选取一阶微分作为光谱预处理,建立ResNet-13、VGGNet-7、时间卷积网络(TCN)和改进时间卷积网络(SATCN)四种模型,对比分析四种模型建模效果,以及SATCN模型在不同网络深度下模型建模效果。结果表明,在一阶微分光谱预处理的情况下,浅层SATCN模型建模效果优于深层模型;SATCN模型中的自注意力残差结构,不仅能够强化光谱序列重要特征,模型特征学习能力和预测精度也有显著提高。相比于CNN、TCN等建模方法,提出的SATCN模型建模效果最好,拥有更高的精确度和极好的模型估测能力,验证集的决定系数(R^(2))为0.943,均方根误差(RMSE)为3.042 g·kg^(-1),相对分析误差(RPD)为4.273。综上所述,SOM含量的最佳预测模型是采用SG平滑后一阶微分光谱预处理基础上建立的SATCN预测模型,对广西林地土壤有机质含量进行更加了精准预测。
The existing convolutional neural network soil organic matter(SOM)prediction models suffer from low modeling effectiveness and low prediction accuracy under small sample data sets.In order to predict the content of organic matter in the soil more accurately,this paper proposes a hyperspectral prediction model of red soil organic matter with an improved Self Attention Temporal Convolutional Network(SATCN)using 206 collected soil samples as the research object.In this paper,after Savitaky-Golay(SG)smoothing is performed on soil samples,four transformations are performed:first-order differential(1DR),second-order differential(2DR),standard normal variable(SNV)and multivariate scattering correction(MSC).The modeling effects of Long Short-Term Memory(LSTM),Partial Least Squares Regression(PLSR)and Support Vector Machine(SVM)under different spectral preprocessing were compared and analyzed.The results show that the first-order differential preprocessing method of the spectrum after SG processing has the best modeling effect.A shallow network structure is applied in the temporal convolutional network(TCN)architecture,a self-attention layer is added to the TCN residual structure to improve the model feature learning capability,and L2 regularization is added to each convolutional kernel weight to prevent overfitting.First-order differentiation is selected as the spectral preprocessing,and four models of ResNet-13,VGGNet-7,TCN and improved temporal convolutional network(SATCN)are constructed to compare and analyze the modeling effects of the four models,as well as the modeling effects of SATCN models at different network depths.The results show that the shallow SATCN modeling is better than the deep model in the case of first-order differential spectral preprocessing;the self-attention residual structure in the SATCN model not only enhanced the important features of the spectral sequence,but also significantly improved the model feature learning ability and prediction accuracy.Compared with modeling methods such as CNN and TCN,the proposed SATCN model has higher accuracy and excellent model estimation capability with a coefficient of determination(R^(2))of 0.943,root mean square error(RMSE)of 3.042 g·kg^(-1),and relative analysis error(RPD)of 4.273 for the validation set.In summary,the best budget SOM content of this paper model is the SATCN prediction model based on the first-order differential spectral preprocessing after SG smoothing,which provides a more accurate prediction of soil organic matter in Guangxi woodlands.
作者
邓昀
牛照文
冯琦尧
王宇
DENG Yun;NIU Zhao-wen;FENG Qi-yao;WANG Yu(Guangxi Key Laboratory of Embedded Technology and Intelligent System,Guilin 541004,China;School of Information Science and Engineering,Guilin University of Technology,Guilin 541004,China)
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2023年第9期2942-2951,共10页
Spectroscopy and Spectral Analysis
基金
国家自然科学基金项目(61662017),广西自然科学基金项目(2018GXNSFAA281235)资助。
关键词
土壤
高光谱
有机质
自注意力机制
时间卷积网络
Soil
Hyperspectral
Organic matter
Self-attentive mechanism
Time-convolutional network
作者简介
邓昀,1980年生,桂林理工大学教授,e-mail:574359451@qq.com;通讯作者:王宇,e-mail:2007002@glut.edu.cn。
