Shaofang He, Qing Zhou, Fang Wang, Luming Shen, Jing Yang
{"title":"利用可见近红外高光谱成像的土壤分形特征建立土壤有机质估算模型","authors":"Shaofang He, Qing Zhou, Fang Wang, Luming Shen, Jing Yang","doi":"10.56530/spectroscopy.fz7077a2","DOIUrl":null,"url":null,"abstract":"To produce a fast, accurate estimation for soil organic matter (SOM) by soil hyperspectral methods, we developed a novel intelligent inversion model based on multiscale fractal features combined with principal component analysis (PCA) of hyperspectral data. First, we calculated the local generalized Hurst exponent of the spectral reflectivity by multiscale multifractal detrended fluctuation analysis (MMA) while determining the sensitive spectral bands. PCA was employed to access the maximum principal component features of the sensitive bands used as the model input. Finally, two intelligent algorithms, random forest (RF), and a support vector machine (SVM), were utilized for establishing the SOM estimation model. The soil hyperspectral data possesses the typical nature of long-range correlation, presenting distinct fractal structures at different scales and fluctuations. The sensitive bands were from 359 nm to 405 nm, and were not impacted by window fitting size. The accuracy of the models of MMA-based sensitive bands is superior to that of the original bands. The PCA processing brings additional model performance improvement. The MMA-based models combined with RF is recommended for SOM estimation.","PeriodicalId":21957,"journal":{"name":"Spectroscopy","volume":null,"pages":null},"PeriodicalIF":0.8000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Soil Organic Matter Estimation Modeling Using Fractal Feature of Soil for vis-NIR Hyperspectral Imaging\",\"authors\":\"Shaofang He, Qing Zhou, Fang Wang, Luming Shen, Jing Yang\",\"doi\":\"10.56530/spectroscopy.fz7077a2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To produce a fast, accurate estimation for soil organic matter (SOM) by soil hyperspectral methods, we developed a novel intelligent inversion model based on multiscale fractal features combined with principal component analysis (PCA) of hyperspectral data. First, we calculated the local generalized Hurst exponent of the spectral reflectivity by multiscale multifractal detrended fluctuation analysis (MMA) while determining the sensitive spectral bands. PCA was employed to access the maximum principal component features of the sensitive bands used as the model input. Finally, two intelligent algorithms, random forest (RF), and a support vector machine (SVM), were utilized for establishing the SOM estimation model. The soil hyperspectral data possesses the typical nature of long-range correlation, presenting distinct fractal structures at different scales and fluctuations. The sensitive bands were from 359 nm to 405 nm, and were not impacted by window fitting size. The accuracy of the models of MMA-based sensitive bands is superior to that of the original bands. The PCA processing brings additional model performance improvement. The MMA-based models combined with RF is recommended for SOM estimation.\",\"PeriodicalId\":21957,\"journal\":{\"name\":\"Spectroscopy\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2023-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Spectroscopy\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://doi.org/10.56530/spectroscopy.fz7077a2\",\"RegionNum\":4,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"SPECTROSCOPY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Spectroscopy","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.56530/spectroscopy.fz7077a2","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"SPECTROSCOPY","Score":null,"Total":0}
引用次数: 0
摘要
为了利用土壤高光谱方法快速、准确地估算土壤有机质(SOM),我们开发了一种基于多尺度分形特征并结合高光谱数据主成分分析(PCA)的新型智能反演模型。首先,我们通过多尺度多分形去趋势波动分析(MMA)计算了光谱反射率的局部广义赫斯特指数,同时确定了敏感光谱波段。采用 PCA 方法获取敏感波段的最大主成分特征作为模型输入。最后,利用随机森林(RF)和支持向量机(SVM)这两种智能算法建立 SOM 估算模型。土壤高光谱数据具有典型的长程相关性,在不同尺度和波动下呈现出不同的分形结构。敏感波段为 359 nm 至 405 nm,且不受窗口拟合大小的影响。基于 MMA 的敏感带模型的精度优于原始敏感带。PCA 处理进一步提高了模型的性能。建议将基于 MMA 的模型与射频相结合用于 SOM 估算。
Soil Organic Matter Estimation Modeling Using Fractal Feature of Soil for vis-NIR Hyperspectral Imaging
To produce a fast, accurate estimation for soil organic matter (SOM) by soil hyperspectral methods, we developed a novel intelligent inversion model based on multiscale fractal features combined with principal component analysis (PCA) of hyperspectral data. First, we calculated the local generalized Hurst exponent of the spectral reflectivity by multiscale multifractal detrended fluctuation analysis (MMA) while determining the sensitive spectral bands. PCA was employed to access the maximum principal component features of the sensitive bands used as the model input. Finally, two intelligent algorithms, random forest (RF), and a support vector machine (SVM), were utilized for establishing the SOM estimation model. The soil hyperspectral data possesses the typical nature of long-range correlation, presenting distinct fractal structures at different scales and fluctuations. The sensitive bands were from 359 nm to 405 nm, and were not impacted by window fitting size. The accuracy of the models of MMA-based sensitive bands is superior to that of the original bands. The PCA processing brings additional model performance improvement. The MMA-based models combined with RF is recommended for SOM estimation.
期刊介绍:
Spectroscopy welcomes manuscripts that describe techniques and applications of all forms of spectroscopy and that are of immediate interest to users in industry, academia, and government.