Knowledge Resource Center for Ecological Environment in Arid Area
基于FOD和SVMDA-RF的土壤有机质含量高光谱预测 | |
其他题名 | Estimation of Desert Soil Organic Matter through Hyperspectra Based on Fractional-Order Derivatives and SVMDA-RF |
张智韬; 劳聪聪; 王海峰; Arnon Karnieli; 陈俊英; 李宇 | |
来源期刊 | 农业机械学报
![]() |
ISSN | 1000-1298 |
出版年 | 2020 |
卷号 | 51期号:1页码:156-167 |
中文摘要 | 为探讨分数阶微分(FOD)联合支持向量机分类-随机森林模型改善高光谱监测荒漠土壤有机质含量(SOM)的效果,对以色列Sde Boker荒漠地区采集的砂质土(SS)和黏壤土(CLS)样品进行理化分析和室内光谱测定,依据光谱的平均反射率建立支持向量机分类模型(SVMAD),并对不同土质高光谱原始反射率分别经0~2阶(间隔0.2)的分数阶微分处理,构建归一化光谱指数(NDI),分析NDI和SOM之间的二维相关性,并筛选敏感的NDI指数,以此建立不同FOD的随机森林(RF)模型,并以不同土质中的最佳模型进行组合,构建新的SVMDA-RF模型。结果表明:基于光谱平均反射率的SVMDA对土壤质地的分类正确率可达100%;分数阶微分耦合光谱指数具有放大波长间与SOM有关隐含信息的能力,经FOD提升敏感指数的数量在0.6阶时达到峰值,但黏壤土的敏感指数数量远大于沙质土;由不同FOD敏感指数建立的RF模型中,砂质土在1.2阶的模型最佳(R_C~2=0.962,R_P~2=0.920,RMSEP为0.435 g/kg,RPD为3.658),黏壤土在0.6阶的模型最佳(R_C~2=0.942,R_P~2=0.944,RMSEP为0.554 g/kg,RPD为4.316);经最佳模型组合后的SVMDA-RF模型,砂质土和黏壤土的模型精度都有所提高,其中R_C~2=0.980,R_P~2=0.979,RMSEP为0.481 g/kg,RPD为7.004。研究成果可为快速评估荒漠土壤有机质含量提供依据。 |
英文摘要 | Aiming to explore the effect of fractional-order derivatives (FOD) combined with support vector machine discriminant analysis-random forest model (SVMDA-RF) on hyperspectral monitoring of desert soil organic matter content (SOM). The desert soil samples collected in the Sde Boker area of Israel were analyzed. These soil samples were through pretreatment, physical and chemical analysis, soil classification (divided into sandy soil (SS) and clay loam soil (CLS)), indoor spectral acquisition and spectral resampling (interval 10 nm). In order to avoid the influence of soil quality on the inversion model, the support vector machines discriminant analysis (SVMAD) was established based on the average reflectance of the spectrum. The spectral reflectance was processed by 0~2 order (interval 0.2) FOD. Then NDI was constructed by using the spectral data that through fractional order derivatives processing and the two-dimensional correlation between SOM and NDI was analyzed. In order to obtain all different FOD enhanced-NDI, the highest coefficient of determination (R~2) of 0-order NDI was used as the threshold (sand soil R~2>0.901, clay loam soil R~2>0.763). By using the different FOD enhanced-NDI to establish random forest (RF) models. All models based on different soils were compared and analyzed, the best models of different soils were combined to establish the SVMDA-RF model. The results showed that SVMDA based on spectral average reflectance, the classification rate of soil texture could reach 100%. Fractional order derivatives coupling normalized spectral index, which had ability to amplify SOM-related implicit information between bands, but it had different effects on different soils. For the paper, clay loam soil was superior to sandy soil, and two soils of the FOD-enhanced sensitive index peaked at 0.6-order, but the number of sensitive index of clay loam soil was much larger than that of sandy soil. In the sandy soil RF models, the model based on 1.2-order NDI was the best(R_C~2=0.962,R_P~2=0.920,RMSEP was 0.435 g/kg,and RPD was 3.658). In the loam RF models, the model based on 0.6-order NDI was the best (R_C~2=0.942,R_P~2=0.944,RMSEP was 0.554 g/kg,and RPD was 4.316). Combining the optimal models of the two soils to get the high-precision SVMDA-RF model, R_P~2=0.979,RMSEP was 0.481 g/kg,and RPD was 7.004. The model could provide effective support for quickly assessing the desert soil types and fertility. |
中文关键词 | 荒漠土壤 ; 有机质含量 ; 高光谱 ; 支持向量机分类 ; 分数阶微分 ; 随机森林 |
英文关键词 | desert soil soil organic matter hyperspectral support vector machines discriminant analysis fractional-order derivative random forest |
类型 | Article |
语种 | 中文 |
收录类别 | CSCD |
WOS研究方向 | Agriculture |
CSCD记录号 | CSCD:6711596 |
来源机构 | 西北农林科技大学 |
资源类型 | 期刊论文 |
条目标识符 | http://119.78.100.177/qdio/handle/2XILL650/336414 |
作者单位 | 张智韬, 西北农林科技大学水利与建筑工程学院;;西北农林科技大学, ;;旱区农业水土工程教育部重点实验室, 杨凌;;杨凌, 陕西;;陕西 712100;;712100, 中国.; 劳聪聪, 西北农林科技大学水利与建筑工程学院;;西北农林科技大学, ;;旱区农业水土工程教育部重点实验室, 杨凌;;杨凌, 陕西;;陕西 712100;;712100, 中国.; 王海峰, 西北农林科技大学水利与建筑工程学院;;西北农林科技大学, ;;旱区农业水土工程教育部重点实验室, 杨凌;;杨凌, 陕西;;陕西 712100;;712100, 中国.; 陈俊英, 西北农林科技大学水利与建筑工程学院;;西北农林科技大学, ;;旱区农业水土工程教育部重点实验室, 杨凌;;杨凌, 陕西;;陕西 712100;;712100, 中国.; 李宇, 西北农林科技大学水利与建筑工程学院;;西北农林科技大学, ;;旱区农业水土工程教育部重点实验室, 杨凌;;杨凌, 陕西;;陕西 712100;;712100, 中国. |
推荐引用方式 GB/T 7714 | 张智韬,劳聪聪,王海峰,等. 基于FOD和SVMDA-RF的土壤有机质含量高光谱预测[J]. 西北农林科技大学,2020,51(1):156-167. |
APA | 张智韬,劳聪聪,王海峰,Arnon Karnieli,陈俊英,&李宇.(2020).基于FOD和SVMDA-RF的土壤有机质含量高光谱预测.农业机械学报,51(1),156-167. |
MLA | 张智韬,et al."基于FOD和SVMDA-RF的土壤有机质含量高光谱预测".农业机械学报 51.1(2020):156-167. |
条目包含的文件 | 条目无相关文件。 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[张智韬]的文章 |
[劳聪聪]的文章 |
[王海峰]的文章 |
百度学术 |
百度学术中相似的文章 |
[张智韬]的文章 |
[劳聪聪]的文章 |
[王海峰]的文章 |
必应学术 |
必应学术中相似的文章 |
[张智韬]的文章 |
[劳聪聪]的文章 |
[王海峰]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。