In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives,two aspects of feature extraction were explored. Based on clustering and decision tree alg...In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives,two aspects of feature extraction were explored. Based on clustering and decision tree algorithm,spectral absorption index (SAI),continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of different targets,and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA),minimum noise fraction (MNF),grouping PCA,and derivate spectral analysis,the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM,and SVM outperforms traditional SAM and MLC classifiers for OMIS data.展开更多
Formaldehyde(HCHO)is a high-yield product of the oxidation of volatile organic compounds(VOCs)released by anthropogenic activities,fires,and vegetations.Hence,we examined the spatiotemporal variation trends in HCHO co...Formaldehyde(HCHO)is a high-yield product of the oxidation of volatile organic compounds(VOCs)released by anthropogenic activities,fires,and vegetations.Hence,we examined the spatiotemporal variation trends in HCHO columns observed using the Ozone Monitoring Instrument(OMI)during 2005–2021 across the Fenwei Plain(FWP)and analysed the source and variability of HCHO using multi-source data,such as thermal anomalies.The spatial distribution of the annualmean HCHO in the FWP increased from northwest to southeast during 2005–2021,and the high-value aggregation areas contracted and gradually clustered,forming a belt-shaped distribution area from Xi’an to Baoji,north of the Qinling Mountains.The annual mean HCHO concentration generally showed a two-step increase over the 17 years.Fires showed a single-peak trend in March and a double-peak M-shaped trend in March and October,whereas urban thermal anomalies(UTAs)showed an inverted U-shaped trend over 17 years,with peaks occurring in May.The HCHO peaks are mainly caused by the alternating contributions of fires and UTAs.The fires and UTAs(predominantly industrial heat sources)played a role in controlling the background level of HCHO in the FWP.Precipitation and temperature were also important influencing variables for seasonal variations,and the influence of plant sources on HCHO concentrations had significant regional characteristics and contributions.In addition,the FWP has poor dispersion conditions and is an aggregated area for the long-range transport of air pollutants.展开更多
基金Projects 40401038 and 40871195 supported by the National Natural Science Foundation of ChinaNCET-06-0476 by the Program for New Century Excellent Talents in University20070290516 by the Specialized Research Fund for the Doctoral Program of Higher Education
文摘In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives,two aspects of feature extraction were explored. Based on clustering and decision tree algorithm,spectral absorption index (SAI),continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of different targets,and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA),minimum noise fraction (MNF),grouping PCA,and derivate spectral analysis,the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM,and SVM outperforms traditional SAM and MLC classifiers for OMIS data.
基金supported by the National Natural Science Foundation of China(No.41571062)the Fundamental Research Funds for the Central Universities(No.2021TS014)the Natural Science Basic Research Plan in Shaanxi Province of China(No.2023-JC-YB-259).
文摘Formaldehyde(HCHO)is a high-yield product of the oxidation of volatile organic compounds(VOCs)released by anthropogenic activities,fires,and vegetations.Hence,we examined the spatiotemporal variation trends in HCHO columns observed using the Ozone Monitoring Instrument(OMI)during 2005–2021 across the Fenwei Plain(FWP)and analysed the source and variability of HCHO using multi-source data,such as thermal anomalies.The spatial distribution of the annualmean HCHO in the FWP increased from northwest to southeast during 2005–2021,and the high-value aggregation areas contracted and gradually clustered,forming a belt-shaped distribution area from Xi’an to Baoji,north of the Qinling Mountains.The annual mean HCHO concentration generally showed a two-step increase over the 17 years.Fires showed a single-peak trend in March and a double-peak M-shaped trend in March and October,whereas urban thermal anomalies(UTAs)showed an inverted U-shaped trend over 17 years,with peaks occurring in May.The HCHO peaks are mainly caused by the alternating contributions of fires and UTAs.The fires and UTAs(predominantly industrial heat sources)played a role in controlling the background level of HCHO in the FWP.Precipitation and temperature were also important influencing variables for seasonal variations,and the influence of plant sources on HCHO concentrations had significant regional characteristics and contributions.In addition,the FWP has poor dispersion conditions and is an aggregated area for the long-range transport of air pollutants.
