| 引用本文: | 徐鸣谦,张枫,叶雪松,冯威,董双石,赵振豪.改进GOOSE-SVM的土壤有机质质量分数反演研究[J].哈尔滨工业大学学报,2026,58(6):109.DOI:10.11918/202510106 |
| XU Mingqian,ZHANG Feng,YE Xuesong,FENG Wei,DONG Shuangshi,ZHAO Zhenhao.Study on inversion of soil organic matter mass fraction based on improved GOOSE-SVM[J].Journal of Harbin Institute of Technology,2026,58(6):109.DOI:10.11918/202510106 |
|
| |
|
|
| 本文已被：浏览 988次 下载 68次 |
码上扫一扫！ |
|
|
| 改进GOOSE-SVM的土壤有机质质量分数反演研究 |
|
徐鸣谦1,2,张枫1,2,叶雪松1,2,冯威1,2,董双石1,2,赵振豪1,2
|
|
(1．地下水资源与环境教育部重点实验室(吉林大学),长春 130021; 2．吉林省水资源与水环境重点实验室(吉林大学),长春 130021)
|
|
| 摘要: |
| 为解决土壤有机质（SOM）高维非线性光谱反演中模型易陷入局部最优、精度不足的问题,提出一种基于改进鹅群优化算法（IGOOSE）优化支持向量机（SVM）的土壤有机质反演方法。以黑龙江典型农场区域土壤样本为研究对象,采用马氏距离法剔除异常样本,并基于偏最小二乘回归（PLSR）建模结果筛选最优光谱预处理方法；通过构建最优预处理条件下全波段SVM、随机森林（RF）与极限学习机（ELM）模型,确定最优基础反演模型；进一步采用连续投影算法（SPA）、随机青蛙特征重要性筛选（RFROG）和竞争自适应重加权采样（CARS）进行光谱特征降维,选取最优降维方法所得特征作为模型输入。在模型参数优化过程中,通过动态调整种群规模,并融合Lévy飞行策略、随机扰动机制及混合邻域搜索方法,对基础鹅群优化算法（GOOSE）进行三阶段自适应改进,构建IGOOSE算法。经标准测试函数验证其有效性后,将IGOOSE用于SVM参数优化,并与原始GOOSE算法进行对比,以辨识性能更优的土壤有机质反演模型。结果表明:一阶导数（D1）预处理后构建的PLSR模型精度显著优于其他预处理方法；基于全波段D1数据构建的最优基础模型为SVM,其五折交叉验证平均决定系数（R2）达0.762 4；CARS为最优光谱特征降维方法,基于其所选特征构建的CARS-SVM模型五折交叉验证平均R2为0.753 7；IGOOSE-SVM泛化能力与预测稳定性方面均显著优于GOOSE-SVM,训练集与测试集R2分别提升0.106 6与0.041 1,均方根误差（RMSE）分别降低2.541 3 g/kg与0.528 7 g/kg,最终训练集与测试集R2分别达到0.925 2与0.841 6,RMSE分别为4.418 9 g/kg与7.040 7 g/kg。研究表明,所提出的改进策略有效缓解了高维非线性光谱数据导致的建模困难,IGOOSE-SVM模型为实现土壤有机质的高精度反演提供了可靠途径,并为优化算法在光谱建模领域的应用与改进提供了理论依据。 |
| 关键词: 土壤有机质质量分数 高光谱遥感 支持向量机 智能优化算法 |
| DOI：10.11918/202510106 |
| 分类号:X87 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(5240100851)；北大荒黑土地土壤有机质提升技术研究集成与应用(BDHYJY-YJ-02-I-2023-1211048) |
|
| Study on inversion of soil organic matter mass fraction based on improved GOOSE-SVM |
|
XU Mingqian1,2,ZHANG Feng1,2,YE Xuesong1,2,FENG Wei1,2,DONG Shuangshi1,2,ZHAO Zhenhao1,2
|
|
(1.Key Laboratory of Groundwater Resources and Environment(Jilin University),Ministry of Education, Changchun 130021, China; 2.Jilin Provincial Key Laboratory of Water Resources and Environment (Jilin University), Changchun 130021, China)
|
| Abstract: |
| To address the problems that models easily fall into local optima and have insufficient accuracy in the high-dimensional nonlinear spectral inversion of soil organic matter (SOM), this paper proposed an inversion method of SOM based on a Support Vector Machine (SVM) optimized by an improved goose swarm optimization (IGOOSE) algorithm. Taking soil samples from typical farm areas in Heilongjiang Province as the research object, this paper used the Mahalanobis distance method to remove abnormal samples and screened the optimal spectral preprocessing method based on partial least squares regression (PLSR) modeling results; by constructing full-band SVM, random forest (RF), and extreme learning machine (ELM) models under the optimal preprocessing condition, this paper determined the optimal basic inversion model; furthermore, this paper used the successive projection algorithm (SPA), random frog feature importance selection (RFROG), and competitive adaptive reweighted sampling (CARS) to conduct spectral feature dimensionality reduction and selected the features obtained by the optimal dimensionality reduction method as the model input. In the process of model parameter optimization, by dynamically adjusting the population size and integrating the Lévy flight strategy, random perturbation mechanism, and hybrid neighborhood search method, this paper conducted a three-stage adaptive improvement on the basic goose swarm optimization (GOOSE) algorithm to construct the IGOOSE algorithm. After verifying its effectiveness via standard test functions, this paper applied IGOOSE to SVM parameter optimization and compared it with the original GOOSE algorithm to identify the inversion model of SOM with better performance. The results show that the accuracy of the PLSR model constructed after first derivative (D1) preprocessing is significantly superior to other preprocessing methods; the optimal basic model constructed based on full-band D1 data is SVM, and its five-fold cross-validation average coefficient of determination (R2) reaches 0.762 4; CARS is the optimal spectral feature dimensionality reduction method, and the five-fold cross-validation average R2 of the CARS-SVM model constructed based on its selected features is 0.753 7; IGOOSE-SVM is significantly superior to GOOSE-SVM in terms of generalization ability and prediction stability, and the R2 of the training set and test set increase by 0.106 6 and 0.041 1, respectively, while the root mean square error (RMSE) decreases by 2.541 3 g/kg and 0.528 7 g/kg, respectively. Finally, the R2of the training set and test set reach 0.925 2 and 0.841 6, respectively, and the RMSE is 4.418 9 g/kg and 7.040 7 g/kg, respectively. The research indicates that the proposed improvement strategy effectively mitigates the modeling difficulties caused by high-dimensional nonlinear spectral data. The IGOOSE-SVM model provides a reliable approach for achieving high-precision inversion of SOM and provides a theoretical basis for the application and improvement of optimization algorithms in the field of spectral modeling. |
| Key words: soil organic matter mass fraction hyperspectral remote sensing Support Vector Machine intelligent optimization algorithm |
|
|
|
|
