大兴安岭森林火烈度遥感估测方法研究
|
摘要
作为森林生态系统重要组成部分的森林火灾,以从地表火到林冠火的多种形态影响着森林生态系统的树种组成、年龄结构和空间格局。它既毁灭了大量的林木,同时又对人类的生命财产以及生态环境造成了巨大的危害,影响着全球碳循环,是人类面临的最重要的自然灾害之一。我国森林火灾也非常严重,仅大兴安岭2003-2009年间,就发生森林火灾649次,过火面积75.2万公顷。本论文研究森林火灾火烈度的遥感估测方法,有助于定量评价森林火灾所造成的林木损失和林火对森林生态系统健康状况所造成的影响,从而为灾后是否进行植被恢复和选择何种森林生态系统恢复模式提供科学数据。同时对于正确估算森林火灾所造成的碳排放的多少及其对生态环境恶化的贡献大小提供技术方法与数据支持。
论文选择大兴安岭南瓮河林场2006年过火区为研究区域,应用森林资源清查资料、地面实地调查资料和火烧前后两期Landsat5TM遥感数据,研究分析了基于归一化燃烧比(NBR)与燃烧比差值(dNBR)的非线与非线性模型估测火烈度的精度,并用先进的数学建模方法偏最小二乘回归、神经网络、支持向量机等进行多变量森林火烈度估测比较,为了简化模型,也比较了变量投影重要性(VIP)、正交信号修正法(OSC)与平均影响值(MIV)筛选模型的效率问题。取得了以下初步成果：
目前遥感数据的应用中,存在3种对数据的处理形式：DN值、辐亮度与大气层表观反射率。利用3种形式对数据处理后提取NBR估测火烈度,得到的3个线性回归模型精度相差不多,R2从0.67-0.69。大气层表观反射率是最接近地物真实反射率的指标,是生物物理参数定量遥感的基础,因此本文的所有分析都是基于大气层表观反射率。
利用单变量估测火烈度,以二次多项式模型的精度最高。在国外研究中表现较好的两个非线性模型在本文的研究中没有得到有效结果。进一步用混淆矩阵对结果的评价表明,用3种模型(线性、多项式、指数)进行火烈度估测的总体精度并不高,估测正确率还不到65%,说明还需要探索别的遥感因子和新的方法来估测火烈度。
根据相关研究,选择20个遥感因子建立多变量估测火烈度模型：即支持向量分类机、广义回归神经网络和偏最小二乘模型,评价模型估测精度采用4-折交叉验证的方法。支持向量分类机的精度最高,最高估测准确率达到了85%。不同核函数的支持向量分类机的估测精度不同,径向基核函数的支持向量分类机的精度最高。当惩罚参数C取16,核函数参数gama取0.25时,径向基核函数支持向量分类机模型的精度最好。同支持向量分类机相比,广义回归神经网络模型估测火烈度的精度要逊色一点。模型除受神经网络自带的径向基传播速度参数(spread)影响以外,不同的建模数据处理方式对模型的预报精度也有影响,按[-1,1]标准化方式对建模数据进行标准化所建立的模型精度最高,当spread为0.9时模型估测精度达到80%。用偏最小二乘回归方法估测火烈度的精度最低,最高准确预报率仅有65%。使偏最小二乘回归模型预报精度最高的数据标准化方式是[0,1]标准化方式。除了偏最小二乘回归模型,多变量模型的预报精度都要比单变量多项式模型的精度高,说明单变量模型不足以概括地而火烈度的丰富信息。
变量过多会导致解释与应用的困难,论文采用和比较3种变量选择方法进行模型简化。利用变量投影重要性(VIP)方法选择出10个对模型有显著影响的变量,而正交信号修正法(OSC)与平均影响值法(MW)各选出了3个,它们互有重叠。两次采用VIP方法后选出的变量所建模型预报平均正确率为61.01%,最高预报正确率为70%,均高于全变量模型。OSC方法选出的3个变量是近红外与中红外原始波段以及它们的组合变量,所建立的PLS模型使得平均与最高正确预报率均有所提高。MIV方法选出的变量所建立的GRNN模型与全变量GRNN的预报精度相当,比另两种方法所选变量建立的PLS模型精度要高,但是MIV所选变量建立的PLS模型精度很底,说明MIV方法对神经网络模型有依赖性。也说明GRNN模型有较好的鲁棒性,能正确挖掘变量间的线性与非线性关系,而PLS回归模型只变量间的线性相关关系敏感。
总之,森林火烈度可以通过遥感数据进行估测,多变量模型由于充分利用卫星平台的多光谱信息而优于单变量模型,其中支持向量机、神经网络与偏最小二乘回归模型都是多变量模型中不错的选择,不仅节约灾后实地调查的时间和劳动强度,也将为全面正确评估森林火灾损失提供准确的实时基础数据。
Forest fire, as an important part of forest ecosystem, has an critical effect on species composition, age structure and spatial pattern of forest ecosystem with a variety of forms from surface fire to canopy fire. It destroyed a large amount of trees, caused tremendous harm to human life, property and the environment at the same time. Its affecting on the global carbon cycle is one of the most serious natural disasters faced by the mankind. Forest fire is also very severe in China. Merely in Da Hinggan Mountains district,649forest fires occurred from2003to2009, with a burned area of752,000hectares. Remote sensing estimation of burn severity was studied in this paper, which would contribute to the quantitative evaluation of tree losses caused by forest fires and impact of forest fires on forest ecosystem health, so that to provide scientific basis for post-disaster vegetation recovery and selection on proper forest ecosystem recovery mode. At the same time, it would provide technical methods and supportive data for the correct estimation of carbon emissions caused by forest fire and its contribution to ecological deterioration.
Burned district of2006in South Urn River forestry center of Da Hinggan Mountains was selected as the study area. With the application of forest resource inventory data, the ground field survey data and Landsat5TM remote sensing data of the area before and after the fire, the accuracy of fire intensity estimation from non-linear and linear model based on the normalized burn ratio (NBR) and delta normalized burn ratio (dNBR) was tested. Multivariate comparison of burn severity was made through advanced mathematical modeling, partial least squares regression, neural networks and vector supporting machines. In order to simplify the model, the efficiency of the screening model was also compared, such as the importance of the variable projection (VIP), and orthogonal signal correction (OSC) and mean impact value (MIV). Preliminary results were as follow:
While using a single variable to estimate the burn severity, the accuracy of the quadratic polynomial model was the highest. The two nonlinear models performed better in abroad study did not get effective results. Further evaluation of the results by confusion matrix showed that the three models (linear, polynomial, exponential) didn't have a high accuracy in estimating the overall accuracy burn severity, with the estimation accuracy rate of less than65%. It reveals that other remote sensing factors and new methods also need to be explored to estimate the burn severity.
There are three kinds of data processing forms in applications of remote sensing data:DN value, radiant brightness and atmosphere apparent reflectance., three linear regression model, through using three kinds of data processing then extracting NBR to estimate burn severity, had similar accuracy, R2from0.67to0.69. But in inspection of the regression coefficients and constant term, there was a significant difference between every two of the three models. The atmosphere apparent reflectance is closest to the perpendicular incidence reflectivity of ground objects, and is the basic of quantitative remote sensing of biophysical parameters foundation.
Building multivariable model to estimate burn severity was based on20remote sensing factors. A4-fold cross-validation method was used for evaluation model estimation accuracy. Vector supporting machine had the highest accuracy, with the highest estimation accuracy rate of85%. The estimation accuracy of different kernel function vector supporting machine was different, and the accuracy of the RBF kernel function vector supporting machine was the highest. When the penalty parameter C was16and the kernel function parameter gama was0.25, RBF kernel function vector supporting classifier machine had the highest accuracy. The generalized regression neural network model to estimate the accuracy of fire intensity was inferior while comparing with the vector supporting classifier machine. In addition to the effect from neural network that came with radial velocity of propagation parameters(spread), model accuracy was also impacted by different modeling approach. And modeling data standardization by [-1,1] standardized way gave the model the highest accuracy, model estimation accuracy was80%when the spread was0.9. Estimating the accuracy of burn severity with partial least squares regression method had the minimum accuracy, with a maximum accuracy of forecasting is only65%. The standardizing way to make partial least squares regression model predict with the highest accurate data was [0,1] standardizing way.
10variables were selected by VIP method, while3were selected by both the OSC and MIV with each having overlaps. Average accuracy rate of61.01percent were worked out from two selected variables with VIP method, and the highest prediction accuracy was70%which was higher than the full-variable model. The three variables selected by the OSC method was the original band of near-infrared and mid-infrared as well as variables of their combination. The established PLS model increased the average and the highest correct prediction rate. GRNN model established with variables selected by the MIV method and all variables GRNN had a same prediction accuracy, which was higher than the PLS model accuracy established by the other two methods selected variables. But PLS model established with variables selected by MIV had a low accuracy, indicating MIV method as quite depending on the model. It also revealed that GRNN model was robust, and could excavate linear and nonlinear relationships between the variables correctly. While at the same time, the PLS regression model was only sensitive to the linear relationship between the variables.
In short, forest fire intensity can be estimated by remote sensing data, especially, multi-variable models perform better than single variable model, and vector supporting machines, neural networks and partial least squares regression model are all good choices of multi- variable models. They do not only save investigating time and labor intensity of post-disaster field surveys, but also provide accurate real-time basic data for comprehensive assessment of the correct loss of forest fire.
论文选择大兴安岭南瓮河林场2006年过火区为研究区域,应用森林资源清查资料、地面实地调查资料和火烧前后两期Landsat5TM遥感数据,研究分析了基于归一化燃烧比(NBR)与燃烧比差值(dNBR)的非线与非线性模型估测火烈度的精度,并用先进的数学建模方法偏最小二乘回归、神经网络、支持向量机等进行多变量森林火烈度估测比较,为了简化模型,也比较了变量投影重要性(VIP)、正交信号修正法(OSC)与平均影响值(MIV)筛选模型的效率问题。取得了以下初步成果：
目前遥感数据的应用中,存在3种对数据的处理形式：DN值、辐亮度与大气层表观反射率。利用3种形式对数据处理后提取NBR估测火烈度,得到的3个线性回归模型精度相差不多,R2从0.67-0.69。大气层表观反射率是最接近地物真实反射率的指标,是生物物理参数定量遥感的基础,因此本文的所有分析都是基于大气层表观反射率。
利用单变量估测火烈度,以二次多项式模型的精度最高。在国外研究中表现较好的两个非线性模型在本文的研究中没有得到有效结果。进一步用混淆矩阵对结果的评价表明,用3种模型(线性、多项式、指数)进行火烈度估测的总体精度并不高,估测正确率还不到65%,说明还需要探索别的遥感因子和新的方法来估测火烈度。
根据相关研究,选择20个遥感因子建立多变量估测火烈度模型：即支持向量分类机、广义回归神经网络和偏最小二乘模型,评价模型估测精度采用4-折交叉验证的方法。支持向量分类机的精度最高,最高估测准确率达到了85%。不同核函数的支持向量分类机的估测精度不同,径向基核函数的支持向量分类机的精度最高。当惩罚参数C取16,核函数参数gama取0.25时,径向基核函数支持向量分类机模型的精度最好。同支持向量分类机相比,广义回归神经网络模型估测火烈度的精度要逊色一点。模型除受神经网络自带的径向基传播速度参数(spread)影响以外,不同的建模数据处理方式对模型的预报精度也有影响,按[-1,1]标准化方式对建模数据进行标准化所建立的模型精度最高,当spread为0.9时模型估测精度达到80%。用偏最小二乘回归方法估测火烈度的精度最低,最高准确预报率仅有65%。使偏最小二乘回归模型预报精度最高的数据标准化方式是[0,1]标准化方式。除了偏最小二乘回归模型,多变量模型的预报精度都要比单变量多项式模型的精度高,说明单变量模型不足以概括地而火烈度的丰富信息。
变量过多会导致解释与应用的困难,论文采用和比较3种变量选择方法进行模型简化。利用变量投影重要性(VIP)方法选择出10个对模型有显著影响的变量,而正交信号修正法(OSC)与平均影响值法(MW)各选出了3个,它们互有重叠。两次采用VIP方法后选出的变量所建模型预报平均正确率为61.01%,最高预报正确率为70%,均高于全变量模型。OSC方法选出的3个变量是近红外与中红外原始波段以及它们的组合变量,所建立的PLS模型使得平均与最高正确预报率均有所提高。MIV方法选出的变量所建立的GRNN模型与全变量GRNN的预报精度相当,比另两种方法所选变量建立的PLS模型精度要高,但是MIV所选变量建立的PLS模型精度很底,说明MIV方法对神经网络模型有依赖性。也说明GRNN模型有较好的鲁棒性,能正确挖掘变量间的线性与非线性关系,而PLS回归模型只变量间的线性相关关系敏感。
总之,森林火烈度可以通过遥感数据进行估测,多变量模型由于充分利用卫星平台的多光谱信息而优于单变量模型,其中支持向量机、神经网络与偏最小二乘回归模型都是多变量模型中不错的选择,不仅节约灾后实地调查的时间和劳动强度,也将为全面正确评估森林火灾损失提供准确的实时基础数据。
Forest fire, as an important part of forest ecosystem, has an critical effect on species composition, age structure and spatial pattern of forest ecosystem with a variety of forms from surface fire to canopy fire. It destroyed a large amount of trees, caused tremendous harm to human life, property and the environment at the same time. Its affecting on the global carbon cycle is one of the most serious natural disasters faced by the mankind. Forest fire is also very severe in China. Merely in Da Hinggan Mountains district,649forest fires occurred from2003to2009, with a burned area of752,000hectares. Remote sensing estimation of burn severity was studied in this paper, which would contribute to the quantitative evaluation of tree losses caused by forest fires and impact of forest fires on forest ecosystem health, so that to provide scientific basis for post-disaster vegetation recovery and selection on proper forest ecosystem recovery mode. At the same time, it would provide technical methods and supportive data for the correct estimation of carbon emissions caused by forest fire and its contribution to ecological deterioration.
Burned district of2006in South Urn River forestry center of Da Hinggan Mountains was selected as the study area. With the application of forest resource inventory data, the ground field survey data and Landsat5TM remote sensing data of the area before and after the fire, the accuracy of fire intensity estimation from non-linear and linear model based on the normalized burn ratio (NBR) and delta normalized burn ratio (dNBR) was tested. Multivariate comparison of burn severity was made through advanced mathematical modeling, partial least squares regression, neural networks and vector supporting machines. In order to simplify the model, the efficiency of the screening model was also compared, such as the importance of the variable projection (VIP), and orthogonal signal correction (OSC) and mean impact value (MIV). Preliminary results were as follow:
While using a single variable to estimate the burn severity, the accuracy of the quadratic polynomial model was the highest. The two nonlinear models performed better in abroad study did not get effective results. Further evaluation of the results by confusion matrix showed that the three models (linear, polynomial, exponential) didn't have a high accuracy in estimating the overall accuracy burn severity, with the estimation accuracy rate of less than65%. It reveals that other remote sensing factors and new methods also need to be explored to estimate the burn severity.
There are three kinds of data processing forms in applications of remote sensing data:DN value, radiant brightness and atmosphere apparent reflectance., three linear regression model, through using three kinds of data processing then extracting NBR to estimate burn severity, had similar accuracy, R2from0.67to0.69. But in inspection of the regression coefficients and constant term, there was a significant difference between every two of the three models. The atmosphere apparent reflectance is closest to the perpendicular incidence reflectivity of ground objects, and is the basic of quantitative remote sensing of biophysical parameters foundation.
Building multivariable model to estimate burn severity was based on20remote sensing factors. A4-fold cross-validation method was used for evaluation model estimation accuracy. Vector supporting machine had the highest accuracy, with the highest estimation accuracy rate of85%. The estimation accuracy of different kernel function vector supporting machine was different, and the accuracy of the RBF kernel function vector supporting machine was the highest. When the penalty parameter C was16and the kernel function parameter gama was0.25, RBF kernel function vector supporting classifier machine had the highest accuracy. The generalized regression neural network model to estimate the accuracy of fire intensity was inferior while comparing with the vector supporting classifier machine. In addition to the effect from neural network that came with radial velocity of propagation parameters(spread), model accuracy was also impacted by different modeling approach. And modeling data standardization by [-1,1] standardized way gave the model the highest accuracy, model estimation accuracy was80%when the spread was0.9. Estimating the accuracy of burn severity with partial least squares regression method had the minimum accuracy, with a maximum accuracy of forecasting is only65%. The standardizing way to make partial least squares regression model predict with the highest accurate data was [0,1] standardizing way.
10variables were selected by VIP method, while3were selected by both the OSC and MIV with each having overlaps. Average accuracy rate of61.01percent were worked out from two selected variables with VIP method, and the highest prediction accuracy was70%which was higher than the full-variable model. The three variables selected by the OSC method was the original band of near-infrared and mid-infrared as well as variables of their combination. The established PLS model increased the average and the highest correct prediction rate. GRNN model established with variables selected by the MIV method and all variables GRNN had a same prediction accuracy, which was higher than the PLS model accuracy established by the other two methods selected variables. But PLS model established with variables selected by MIV had a low accuracy, indicating MIV method as quite depending on the model. It also revealed that GRNN model was robust, and could excavate linear and nonlinear relationships between the variables correctly. While at the same time, the PLS regression model was only sensitive to the linear relationship between the variables.
In short, forest fire intensity can be estimated by remote sensing data, especially, multi-variable models perform better than single variable model, and vector supporting machines, neural networks and partial least squares regression model are all good choices of multi- variable models. They do not only save investigating time and labor intensity of post-disaster field surveys, but also provide accurate real-time basic data for comprehensive assessment of the correct loss of forest fire.
引文
[1]胡海清.林火生态与管理.北京：中国林业出版社,2005.
[2]Morisette JT, Giglio L, Csiszar I, et al. Validation of MODIS active fire detection products derived from two algorithms. Earth Interact,2005,9:1-25.
[3]徐爱俊,李清泉,方陆明,等.基于GIS的森林火灾预测预报模型的研究与探讨.浙江林学院学报,2003,20(3)：285-288.
[4]孔繁花,李秀珍,王绪高,等.林火迹地森林恢复研究进展.生态学杂志,2003,22(2)：60-64.
[5]Lentile LB, Morgan P, Hudak AT, et al. Post-Fire burn severity and vegetation response following eight large wildfires across the western United States. Fire Ecology Special Issue, 2007,3(1):91-108.
[6]王明玉,任云卯,李涛,等.火烧迹地更新与恢复研究进展.世界林业研究,2008,21(6)：49-54.
[7]于文颖,周广胜,赵先丽,等.大兴安岭林区火灾特征及影响因子.气象与环境学报,2009,25(4)：1-5.
[8]Calkin D E, Hyde K D, Robichaud P R, et al. Assessing post-fire values-at-risk with a new calculation tool. General Technical Report RMRS-GTR-205, United States Department of Agriculture,2007.
[9]Hood SM, McHugh CW, et al. Evaluation of a post-fire tree mortality model for western USA conifers. International Journal of Wildland Fire,2007,16:679-689.
[10]贺红士,常禹,胡远满,等.森林可燃物及其管理的研究进展.植物生态学报,2010,34(6)：741-752.
[11]金森.遥感估测森林可燃物载量的研究进展.林业科学,2007,42(12)：63-67.
[12]McKinley RA, Chine EP, Werth LF. Operational fire fuels mapping with NOAA-AVHRR data. Pecora X Symposium Proceedings,1985,295-304.
[13]Elvidge CD. Thermal infrared reflectance of dry plant materials:2.5-20.0 micrometers. Remote Sensing of Environment,1988,26:265-285.
[14]Keane RE, Brugan R, Van Wagtendonk J. Mapping wildland fuels for fire management across multiple scales:integrating remote sensing, GIS, and biophysical modeling. International Journal of Wildland Fire,2001,10:301-319.
[15]Kasischke ES, Melack JM, Dobson MC. The use of imaging Radars for ecological applications-a review. Remote Sensing of Environment,1997,59(2):141-156.
[16]DeWasseige C, Defourny P. Retrieval of tropical forest structure characteristics from bi-directional reflectance of SPOT images. Remote Sensing of Environment,2002,83:362- 375.
[17]赵宪文.中国热带林遥感探索：分类方法与调查方案.林业科学研究,1995,8(4)：373-379.
[18]郭志华,彭少麟,王伯荪.利用GIS和RS估算广东植被利用率.生态学报,2000(6)：903-909.
[19]Scott K, Oswald B, Farrish K, et al. Fuel loading prediction models developed from aerial photographs of the Sangre de Cristo and Jemez mountains of New Mexico, USA. International Journal of Wildland Fire,2002,11:85-90.
[20]Brandis K, Jacobson C. Estimation of vegetative fuel loads using Landsat TM imagery in New South Wales, Australia. International Journal of Wildland Fire,2003,12(2):185-194.
[21]王强.基于遥感图像估测森林可燃物的研究.东北林业大学硕士学位论文,2005.
[22]胡海清,魏云敏.利用TM遥感影像和林分因子估测森林可燃物载量.东北林业大学学报,2007,35(6)：18-20.
[23]Koetz B, Morsdorf F, Linden S. Multi-source land cover classification for forest fire management based on imaging spectrometry and LiDAR data. Forest Ecology and Management,2008,256(3):263-271.
[24]Arroyo LA, Pascual C, Manzanera JA. Fire models and methods to map fuel types:The role of remote sensing. Forest Ecology Management,2008,256(6):1239-1252.
[25]Jaiswal RK, Mukherjee S, Raju KD, et al. Forest fire risk zone mapping from satellite imagery and GIS. International Journal of Applied Earth Observation and Geoinformation, 2002,4:1-10.
[26]Chuvieco E, Cocero D, Riano D, et al. Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating. Remote Sensing of Environment,2004,92:322-331.
[27]Xu D, Dai LM, Shao GF, et al. Forest fire risk zone mapping from satellite images and GIS for Baihe Forestry Bureau, Jilin, China. Journal of Forestry Research,2005,16:169-174.
[28]郑海青,张春桂,陈家金,等.利用NOAA卫星遥感监测福建省森林火险.福建林学院学报,2003,23(2)：114-118.
[29]尹海伟,孔繁花,李秀珍.基于GIS的大兴安岭森林火险区划.应用生态学报,2005,16(5)：833-837
[30]祝必琴,张丽霞,彭家武,等.基于RS和GIS的庐山森林火险区划研究.江西农业大学学报,2009,31(3)：441-448
[31]赵明文,张广英,王付华.卫星遥感资料在森林火灾监测中的应用.黑龙江气象,2005,(1)：35-40.
[32]刘祖军,刘建,余坤勇,等.基于RS和GIS的森林火险区划.福建农林大学学报(自然科学版),2008,37(6)：606-609.
[33]陈晓玲,赵红梅,田礼桥.环境遥感模型与应用.武汉：武汉大学出版社,2008.
[34]Flasse SP, Ceccato P. A contextual algorithm for AVHRR fire detection. International Journal of Remote Sensing,1996,17(2):419-424.
[35]Kaufinan YJ, Justice C, Flynn LP, et al. Potential monitoring global fires from EOS-MODIS. Journal of Geophysical Research,1998,103:32215-32238.
[36]Li Z, Cihlar J, Fraser R H, et al. Remote sensing of Canadian boreal forest fires:hotspots, burned area, and smoke plumes. IEEE transaction on Geosciences and Remote Sensing, 1999,4:2241-2243.
[37]卿清涛.NOAA/AVHRR遥感监测森林火灾的准确性研究.四川气象.2004,4：30-32.
[38]Morisette JT, Giglio L, Csiszar I, et al. Validation of MODIS Active Fire Detection Products Derived from Two Algorithms. Earth Interact.2005,9:1-25.
[39]姚余君,卢统春,金森.用NOAA/AVHRR确定热点/火点的主要算法介绍.森林防火,2006,4：26-27.
[40]郭朝辉,亓雪勇,龚亚丽,等.环境减灾卫星影像森林火灾监测技术方法研究.遥感信息,201 0,(4)：85-89.
[41]Barbosa PM, Pereira JMC, Gregoire JM. Compositing criteria for burned area assessment using multitemporal low resolution satellite data. Remote Sensing of Environment,1998, 65:38-49.
[42]Giglio L, Van der Werf G, Randerson J, et al. Global estimation of burned area using MODIS active fire observations. Atmospheric Chemistry and Physics Discussions,2005,5: 11091-11141.
[43]覃先林,李增元,易浩若,等.基于ENVISAT-MERIS数据的过火区制图方法研究.遥感技术与应用,2008,23(1)：1-7.
[44]郑伟,李亚君,刘诚,等.基于多源卫星遥感数据的森林过火区面积估算方法.林业科学,2011,47(8)：192-195.
[45]Bigler C, Kulakowski D, Veblen T. Multiple disturbance interactions and drought influence fire severity in rocky mountain subalpine forests. Ecology,2005,86:3018-3029.
[46]Koutsias N, Kareris M, Chuvieco E. The use of intensity-hue-saturation transformation of Landsat-5 thematic mapper data for burned land mapping. Photogrammetric Engineering & Remote Sensing,2000,66(7):829-839.
[47]戴昌达.卫星监测森林火灾及灾后林木恢复变化.世界导弹与航天,1996,(6)：1-4.
[48]梁凤仙,顾钟炜.遥感技术在大兴安岭火烧迹地森林冻土环境变化调查中的应用.冰川冻土,1993,15(1):27-33.
[49]解伏菊,肖笃宁,李秀珍.基于NDVI的不同火烧强度下大兴安岭林火迹地森林景观恢复.生态学杂志,2005,24(4)：368-372.
[50]刘广菊,胡海清,张海林,等.火频度和火强度对植物群落结构稳定性的影响.东北 林业大学学报,2008,36(7)：32-33.
[51]Patterson M, Yool SR. Mapping fire-induced vegetation mortality using Landsat Thematic Mapper data:a comparison of linear transformation techniques. Remote Sensing of Environment,1998,65:132-142.
[52]Van Wagtendonk JW, Root RR, Key CH. Comparison of AVIRIS and Landsat ETM+ detection capabilities for burn severity. Remote Sensing of Environment,2004,92:397-408.
[53]Allen JL, Sorbel B. Assessing the differenced Normalized Burn Ratio's ability to map burn severity in the boreal forest and tundra ecosystems of Alaska's national parks. International Journal of Wildland Fire,2008,17:463-475.
[54]Soverel NO, Perrakis DB, Coops NC. Estimating burn severity from Landsat dNBR and RdNBR indices across western Canada. Remote Sensing of Environment,2010,114:1896-1909.
[55]Roy DP, Boschetti L, Trigg SN. Remote Sensing of Fire Severity:Assessing the Performance of the Normalized Burn Ratio. IEEE Geoscience and Remote Sensing Letters, 2006,3(1):112-116.
[56]Miller JD, Thode AE. Quantifying burn severity in a heterogeneous landscape with a relative version of the delta Normalized Burn Ratio (dNBR). Remote Sensing of Environment,2007,109:66-80.
[57]赵宪文.森林火灾遥感监测评价——理论及技术应用.北京：中国林业出版社,1995,pp.132-140.
[58]Conard SG, Sukhinin AI, Stocks BJ, et al. Determining effects of area burned and fire severity on carbon cycling and emissions in Siberia. Climatic Change,2002,55:197-211.
[59]Veraverbeke S, Lhermitte S, Verstraeten WW, et al. The temporal dimension of differenced Normalized Burn Ratio (dNBR) fire/burn severity studies:The case of the large 2007 Peloponnese wildfires in Greece. Remote Sensing of Environment,2010,114:2548-2563.
[60]池宏康,周广胜,许振柱,等.表观反射率及其在植被遥感中的应用.植物生态学报,2005,29(1)：74-80.
[61]Brumby SP, Harvey NR, Bloch JJ, et al. Evolving forest fire burn severity classification algorithm. Proceedings of SPIE,2001,4381:236-245.
[62]Epting J, Verbyla D, Sorbel B. Evaluation of remotely sensed indices for assessing burn severity in interior Alaska using Landsat TM and ETM+. Remote Sensing of Environment, 2005,96:328-339.
[63]French NHF, Kasischke ES, Hall RJ, et al. Using Landsat data to assess fire and burn severity in the North American boreal forest region:an overview and summary of results. International Journal of Wildland Fire,2008,17:443-462.
[64]Carreiras JMB, Pereira JMC, Pereira JS. Estimation of tree canopy cover in evergreen oak woodlands using remote sensing. Forest Ecology and Management,2006,223:45-53.
[65]White J, Ryan K, Key C, et al. Remote Sensing of Forest Fire Severity and Vegetation Recovery. International Journal of Wildland Fire,1996,6:125-125.
[66]Hall RJ, Freeburn JT, Groot WJ, et al. Remote sensing of burn severity:Experience from western Canada boreal fires. International Journal of Wildland Fire,2008,17:476-489.
[67]Key CH, Benson NC. Landscape assessment-Sampling and analysismethods. In Lutes D. (Ed.), FIREMON:Fire effects and Inventory Monitoring System. Ogden, UT:USDA Fores Service, Rocky Mountain Research Station,2005.
[68]Foody GM. Status of land cover classification accuracy assessment. Remote Sensing of Environment,2002,80(1):185-201.
[69]Foody GM. Assessing the accuracy of land cover change with imperfect ground reference data. Remote Sensing of Environment,2010,114(10):2271-2285.
[70]赵英时.遥感应用分析原理与方法.北京：科学出版社,2002.
[71]Huang C, Wylie B, Yang L, et al. Derivation of a tasseled cap transformation based on landsat 7 at satellite reflectance. International Journal of Remote Sensing,2002,23(8): 1741-1748.
[72]Hernandez-Stefanoni J, Ponce-Hernandez R. Mapping the spatial variability of plant diversity in a tropical forest:comparison of spatial interpolation methods. Environmental Monitoring and Assessment,2006,117(1):307-334.
[73]Hudak A, Morgan P, Bobbitt M, et al. The relationship of multispectral satellite imagery to immediate fire effects. Fire Ecology,2007,3 (1):64-90.
[74]LeMay V, Maedel J, Coops NC. Estimating stand structural details using nearest neighbor analyses to link ground data, forest cover maps, and Landsat imagery. Remote Sensing of Environment,2008,112:2578-2591.
[75]Browne MW. Cross-validation methods. Journal of Mathematical Psychology,2000,44(1): 108-132.
[76]李崇贵,赵宪文.森林郁闭度定量估测遥感比值波段的选择.林业科学,2005,41(4)：72-77.
[77]杜晓明,蔡体久,琚存勇.采用偏最小二乘回归方法估测森林郁闭度.应用生态学报,2008,19(2)：273-277.
[78]琚存勇,邸雪颖,蔡体久.变量筛选方法对郁闭度遥感估测模型的影响比较.林业科学,2007,43(12)：33-38.
[79]苏高利,邓芳萍.关于支持向量回归机的模型选择.科技通报,2006,22(2)：154-158.
[80]邓乃扬,田英杰.支持向量机——理论、算法与拓展.北京：科学出版社,2009.
[81]Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In:the International Joint Conference on Articial Intelligence, Lawrence Erlbaum Associates LTD,1995, pp.1134-1145.
[82]Lewis SA, Lentile L, Hudak AT, et al. Mapping ground cover using hyperspectral remote sensing after the 2003 Simi and Old wildfires in southern California. Fire Ecology,2007, 3(1):109-128.
[83]陈永义,俞小鼎,高学浩,等.处理非线性分类和回归问题的一种新方法(Ⅰ)——支持向量机方法简介.应用气象学报,2004,15(3)：345-354.
[84]祁亨年.支持向量机及其应用研究综述.计算机工程,2004,30(10)：6-9.
[85]Chih-Chung Chang, Chih-Jen Lin. LIBSVM:a library for support vector machines,2001. Software available at http://www.csie.ntu.edu.tw/-cjlin/libsvm.
[86]Faruto, liyang. LIBSVM-farutoUltimateVersion:a toolbox with implements for support vector machines based on libsvm,2009. Software available at http://www.ilovematlab.cn.
[87]史峰,王小川,郁磊,李洋.MATLAB神经网络30个案例分析.北京：北京航空航天大学出版社,2010.
[88]周昊,郑立刚,樊建人,等.广义回归神经网络在煤灰熔点预测中的应用.浙江大学学报(工学版),2004,38(11)：1479-1482.
[89]孙焱鑫,王纪华,李保国,等.基于BP和GRNN神经网络的冬小麦冠层叶绿素高光谱反演建模研究.遥感技术与应用,2007,22(4)：492-496.
[90]段松杰,张晓光,张闯志.基于广义回归神经网络的传感器非线性误差校正.传感器与微系统,2008,27(12)：14-16.
[91]琚存勇,蔡体久.鄂尔多斯草地生物量估测的GRNN模型实现.北京林业大学学报,2008,30(S 1)：296-299.
[92]Lei Chengliang, Ju Cunyong, Cai Tijiu, et al. Proper selection of the training data set for ANN model deriving valid relationships. Nature Resource & Ecology Environment,2012, (2):31-36
[93]李崇贵,石强,赵宪文,等.用岭估计研究以RS和GIS为基础的森林郁闭度估测.林业科学,2001,37(5)：24-30.
[94]琚存勇,蔡体久.用泛化改进的BP神经网络估测森林蓄积量.林业科学,42(12)：59-62.
[95]Naesset E, Bollandsas OM, Gobakken T. Comparing regression methods in estimation of biophysical properties of forest stands from two different inventories using laser scanner data. Remote Sensing of Environment,2005,94:541-553.
[96]竞霞,黄文江,琚存勇,等.基于PLS算法的棉花黄萎病高空间分辨率遥感监测.农业工程学报,2010,26(8)：229-235.
[97]蒋红卫,夏结来.偏最小二乘回归及其应用.第四军医大学学报,2003,24(3)：280-283.
[98]Hansen PM, Schjoerring JK. Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sensing of Environment,2003,86:542-553.
[99]Farifteh J, Van der Meer F, Atzberger C, et al. Quantitative analysis of salt-affected soil reflectance spectra:A comparison of two adaptive methods (PLSR and ANN). Remote Sensing of Environment,2007,110:59-78.
[100]Cai TJ, Ju CY, Yang XH. Comparison of ridge regression and partial least squares regression for estimating above-ground biomass with Landsat images and terrain data in Mu Us sandy land, China. Arid Land Research and Management,2009,23(3):248-261.
[101]Ju C, Cai T, Yang X. Topography-based modeling to estimate percent vegetation cover in semi-arid Mu Us sandy land, China. Computers and Electronics in Agriculture,2008,64: 133-139.
[102]王惠文,吴载斌,孟洁.偏最小二乘回归的线性与非线性方法.北京：国防工业出版社,2006.
[103]曾涛,琚存勇,蔡体久,等.利用变量投影重要性准则筛选郁闭度估测参数.北京林业大学学报,2010,32(6)：37-41.
[104]George E I. The variable selection problem. Journal of the American Statistical Association,2000,95:1304-1308.
[105]Lucic B, Trinajstic N, Sild S, et al. A new efficient approach for variable selection based on multiregression:Prediction of gas chromatographic retention times and response factors. Journal of chemical information and computer sciences,1999,39:610-621.
[106]方开泰,金辉,陈庆云.实用回归分析.北京：科学出版社,1988.
[107]何晓群.多元回归分析.北京：中国人民大学出版社,2008.
[108]吴琼,原忠虎,王晓宁.基于偏最小二乘回归分析综述.沈阳大学学报,2007,19(2)：33-35.
[109]Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction of near-infrared spectra. Chemometrics and Intelligent Laboratory Systems,1998,44:175-185.
[110]Sjoblom J, Svensson O, Josefson M, et al. An evaluation of orthogonal signal correction applied to calibration transfer of near infrared spectra. Chemometrics and Intelligent Laboratory Systems,1998,44:229-244.
[111]Fearn T. On orthogonal signal correction. Chemometrics and Intelligent Laboratory Systems,2000,50:47-52.
[112]Hoskuldsson A. Variable and subset selection in PLS regression. Chemometrics and Intelligent Laboratory Systems,2001,55:23-38.
[113]褚小立,袁洪福,陆婉珍.近红外分析中光谱预处理及波长选择方法进展与应用.化学进展,2004,16(4)：528-542.
[114]Jakubauskas ME, Price KP. Empirical relationships between structural and spectral factors of Yellowstone lodgepole pine forests. Photogrammetric engineering and remote sensing,1997,63:1375-1381.
[115]Dombi GW, Nandi P, Saxe JM, et al. Prediction of rib fracture injury outcome by an artificial neural network. The Journal of trauma,1995,39:915-921.
[116]黄成钢,金如锋,邱宏,等.我国某地区痢疾发病率与气象因素的关系及其预测模型.现代预防医学,2009,36(7)：1207-1210.
[117]吴洪丽,蒋永辉.软件可靠性影响因素权重分析.计算机工程与应用,2010,46(33)：58-63.
[118]王紫微,叶奇旺.基于神经网络MIV值分析的肿瘤基因信息提取.数学的实践与认识,2011,41(14)：47-59.
[119]李继泉,赵宪文,朱剑.用SPOT燃料对大兴安岭特大火灾林为行为研究及对阿穆尔林业局蓄积损失估计.林业科学研究,1988,1(6)：598～606.
[2]Morisette JT, Giglio L, Csiszar I, et al. Validation of MODIS active fire detection products derived from two algorithms. Earth Interact,2005,9:1-25.
[3]徐爱俊,李清泉,方陆明,等.基于GIS的森林火灾预测预报模型的研究与探讨.浙江林学院学报,2003,20(3)：285-288.
[4]孔繁花,李秀珍,王绪高,等.林火迹地森林恢复研究进展.生态学杂志,2003,22(2)：60-64.
[5]Lentile LB, Morgan P, Hudak AT, et al. Post-Fire burn severity and vegetation response following eight large wildfires across the western United States. Fire Ecology Special Issue, 2007,3(1):91-108.
[6]王明玉,任云卯,李涛,等.火烧迹地更新与恢复研究进展.世界林业研究,2008,21(6)：49-54.
[7]于文颖,周广胜,赵先丽,等.大兴安岭林区火灾特征及影响因子.气象与环境学报,2009,25(4)：1-5.
[8]Calkin D E, Hyde K D, Robichaud P R, et al. Assessing post-fire values-at-risk with a new calculation tool. General Technical Report RMRS-GTR-205, United States Department of Agriculture,2007.
[9]Hood SM, McHugh CW, et al. Evaluation of a post-fire tree mortality model for western USA conifers. International Journal of Wildland Fire,2007,16:679-689.
[10]贺红士,常禹,胡远满,等.森林可燃物及其管理的研究进展.植物生态学报,2010,34(6)：741-752.
[11]金森.遥感估测森林可燃物载量的研究进展.林业科学,2007,42(12)：63-67.
[12]McKinley RA, Chine EP, Werth LF. Operational fire fuels mapping with NOAA-AVHRR data. Pecora X Symposium Proceedings,1985,295-304.
[13]Elvidge CD. Thermal infrared reflectance of dry plant materials:2.5-20.0 micrometers. Remote Sensing of Environment,1988,26:265-285.
[14]Keane RE, Brugan R, Van Wagtendonk J. Mapping wildland fuels for fire management across multiple scales:integrating remote sensing, GIS, and biophysical modeling. International Journal of Wildland Fire,2001,10:301-319.
[15]Kasischke ES, Melack JM, Dobson MC. The use of imaging Radars for ecological applications-a review. Remote Sensing of Environment,1997,59(2):141-156.
[16]DeWasseige C, Defourny P. Retrieval of tropical forest structure characteristics from bi-directional reflectance of SPOT images. Remote Sensing of Environment,2002,83:362- 375.
[17]赵宪文.中国热带林遥感探索：分类方法与调查方案.林业科学研究,1995,8(4)：373-379.
[18]郭志华,彭少麟,王伯荪.利用GIS和RS估算广东植被利用率.生态学报,2000(6)：903-909.
[19]Scott K, Oswald B, Farrish K, et al. Fuel loading prediction models developed from aerial photographs of the Sangre de Cristo and Jemez mountains of New Mexico, USA. International Journal of Wildland Fire,2002,11:85-90.
[20]Brandis K, Jacobson C. Estimation of vegetative fuel loads using Landsat TM imagery in New South Wales, Australia. International Journal of Wildland Fire,2003,12(2):185-194.
[21]王强.基于遥感图像估测森林可燃物的研究.东北林业大学硕士学位论文,2005.
[22]胡海清,魏云敏.利用TM遥感影像和林分因子估测森林可燃物载量.东北林业大学学报,2007,35(6)：18-20.
[23]Koetz B, Morsdorf F, Linden S. Multi-source land cover classification for forest fire management based on imaging spectrometry and LiDAR data. Forest Ecology and Management,2008,256(3):263-271.
[24]Arroyo LA, Pascual C, Manzanera JA. Fire models and methods to map fuel types:The role of remote sensing. Forest Ecology Management,2008,256(6):1239-1252.
[25]Jaiswal RK, Mukherjee S, Raju KD, et al. Forest fire risk zone mapping from satellite imagery and GIS. International Journal of Applied Earth Observation and Geoinformation, 2002,4:1-10.
[26]Chuvieco E, Cocero D, Riano D, et al. Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating. Remote Sensing of Environment,2004,92:322-331.
[27]Xu D, Dai LM, Shao GF, et al. Forest fire risk zone mapping from satellite images and GIS for Baihe Forestry Bureau, Jilin, China. Journal of Forestry Research,2005,16:169-174.
[28]郑海青,张春桂,陈家金,等.利用NOAA卫星遥感监测福建省森林火险.福建林学院学报,2003,23(2)：114-118.
[29]尹海伟,孔繁花,李秀珍.基于GIS的大兴安岭森林火险区划.应用生态学报,2005,16(5)：833-837
[30]祝必琴,张丽霞,彭家武,等.基于RS和GIS的庐山森林火险区划研究.江西农业大学学报,2009,31(3)：441-448
[31]赵明文,张广英,王付华.卫星遥感资料在森林火灾监测中的应用.黑龙江气象,2005,(1)：35-40.
[32]刘祖军,刘建,余坤勇,等.基于RS和GIS的森林火险区划.福建农林大学学报(自然科学版),2008,37(6)：606-609.
[33]陈晓玲,赵红梅,田礼桥.环境遥感模型与应用.武汉：武汉大学出版社,2008.
[34]Flasse SP, Ceccato P. A contextual algorithm for AVHRR fire detection. International Journal of Remote Sensing,1996,17(2):419-424.
[35]Kaufinan YJ, Justice C, Flynn LP, et al. Potential monitoring global fires from EOS-MODIS. Journal of Geophysical Research,1998,103:32215-32238.
[36]Li Z, Cihlar J, Fraser R H, et al. Remote sensing of Canadian boreal forest fires:hotspots, burned area, and smoke plumes. IEEE transaction on Geosciences and Remote Sensing, 1999,4:2241-2243.
[37]卿清涛.NOAA/AVHRR遥感监测森林火灾的准确性研究.四川气象.2004,4：30-32.
[38]Morisette JT, Giglio L, Csiszar I, et al. Validation of MODIS Active Fire Detection Products Derived from Two Algorithms. Earth Interact.2005,9:1-25.
[39]姚余君,卢统春,金森.用NOAA/AVHRR确定热点/火点的主要算法介绍.森林防火,2006,4：26-27.
[40]郭朝辉,亓雪勇,龚亚丽,等.环境减灾卫星影像森林火灾监测技术方法研究.遥感信息,201 0,(4)：85-89.
[41]Barbosa PM, Pereira JMC, Gregoire JM. Compositing criteria for burned area assessment using multitemporal low resolution satellite data. Remote Sensing of Environment,1998, 65:38-49.
[42]Giglio L, Van der Werf G, Randerson J, et al. Global estimation of burned area using MODIS active fire observations. Atmospheric Chemistry and Physics Discussions,2005,5: 11091-11141.
[43]覃先林,李增元,易浩若,等.基于ENVISAT-MERIS数据的过火区制图方法研究.遥感技术与应用,2008,23(1)：1-7.
[44]郑伟,李亚君,刘诚,等.基于多源卫星遥感数据的森林过火区面积估算方法.林业科学,2011,47(8)：192-195.
[45]Bigler C, Kulakowski D, Veblen T. Multiple disturbance interactions and drought influence fire severity in rocky mountain subalpine forests. Ecology,2005,86:3018-3029.
[46]Koutsias N, Kareris M, Chuvieco E. The use of intensity-hue-saturation transformation of Landsat-5 thematic mapper data for burned land mapping. Photogrammetric Engineering & Remote Sensing,2000,66(7):829-839.
[47]戴昌达.卫星监测森林火灾及灾后林木恢复变化.世界导弹与航天,1996,(6)：1-4.
[48]梁凤仙,顾钟炜.遥感技术在大兴安岭火烧迹地森林冻土环境变化调查中的应用.冰川冻土,1993,15(1):27-33.
[49]解伏菊,肖笃宁,李秀珍.基于NDVI的不同火烧强度下大兴安岭林火迹地森林景观恢复.生态学杂志,2005,24(4)：368-372.
[50]刘广菊,胡海清,张海林,等.火频度和火强度对植物群落结构稳定性的影响.东北 林业大学学报,2008,36(7)：32-33.
[51]Patterson M, Yool SR. Mapping fire-induced vegetation mortality using Landsat Thematic Mapper data:a comparison of linear transformation techniques. Remote Sensing of Environment,1998,65:132-142.
[52]Van Wagtendonk JW, Root RR, Key CH. Comparison of AVIRIS and Landsat ETM+ detection capabilities for burn severity. Remote Sensing of Environment,2004,92:397-408.
[53]Allen JL, Sorbel B. Assessing the differenced Normalized Burn Ratio's ability to map burn severity in the boreal forest and tundra ecosystems of Alaska's national parks. International Journal of Wildland Fire,2008,17:463-475.
[54]Soverel NO, Perrakis DB, Coops NC. Estimating burn severity from Landsat dNBR and RdNBR indices across western Canada. Remote Sensing of Environment,2010,114:1896-1909.
[55]Roy DP, Boschetti L, Trigg SN. Remote Sensing of Fire Severity:Assessing the Performance of the Normalized Burn Ratio. IEEE Geoscience and Remote Sensing Letters, 2006,3(1):112-116.
[56]Miller JD, Thode AE. Quantifying burn severity in a heterogeneous landscape with a relative version of the delta Normalized Burn Ratio (dNBR). Remote Sensing of Environment,2007,109:66-80.
[57]赵宪文.森林火灾遥感监测评价——理论及技术应用.北京：中国林业出版社,1995,pp.132-140.
[58]Conard SG, Sukhinin AI, Stocks BJ, et al. Determining effects of area burned and fire severity on carbon cycling and emissions in Siberia. Climatic Change,2002,55:197-211.
[59]Veraverbeke S, Lhermitte S, Verstraeten WW, et al. The temporal dimension of differenced Normalized Burn Ratio (dNBR) fire/burn severity studies:The case of the large 2007 Peloponnese wildfires in Greece. Remote Sensing of Environment,2010,114:2548-2563.
[60]池宏康,周广胜,许振柱,等.表观反射率及其在植被遥感中的应用.植物生态学报,2005,29(1)：74-80.
[61]Brumby SP, Harvey NR, Bloch JJ, et al. Evolving forest fire burn severity classification algorithm. Proceedings of SPIE,2001,4381:236-245.
[62]Epting J, Verbyla D, Sorbel B. Evaluation of remotely sensed indices for assessing burn severity in interior Alaska using Landsat TM and ETM+. Remote Sensing of Environment, 2005,96:328-339.
[63]French NHF, Kasischke ES, Hall RJ, et al. Using Landsat data to assess fire and burn severity in the North American boreal forest region:an overview and summary of results. International Journal of Wildland Fire,2008,17:443-462.
[64]Carreiras JMB, Pereira JMC, Pereira JS. Estimation of tree canopy cover in evergreen oak woodlands using remote sensing. Forest Ecology and Management,2006,223:45-53.
[65]White J, Ryan K, Key C, et al. Remote Sensing of Forest Fire Severity and Vegetation Recovery. International Journal of Wildland Fire,1996,6:125-125.
[66]Hall RJ, Freeburn JT, Groot WJ, et al. Remote sensing of burn severity:Experience from western Canada boreal fires. International Journal of Wildland Fire,2008,17:476-489.
[67]Key CH, Benson NC. Landscape assessment-Sampling and analysismethods. In Lutes D. (Ed.), FIREMON:Fire effects and Inventory Monitoring System. Ogden, UT:USDA Fores Service, Rocky Mountain Research Station,2005.
[68]Foody GM. Status of land cover classification accuracy assessment. Remote Sensing of Environment,2002,80(1):185-201.
[69]Foody GM. Assessing the accuracy of land cover change with imperfect ground reference data. Remote Sensing of Environment,2010,114(10):2271-2285.
[70]赵英时.遥感应用分析原理与方法.北京：科学出版社,2002.
[71]Huang C, Wylie B, Yang L, et al. Derivation of a tasseled cap transformation based on landsat 7 at satellite reflectance. International Journal of Remote Sensing,2002,23(8): 1741-1748.
[72]Hernandez-Stefanoni J, Ponce-Hernandez R. Mapping the spatial variability of plant diversity in a tropical forest:comparison of spatial interpolation methods. Environmental Monitoring and Assessment,2006,117(1):307-334.
[73]Hudak A, Morgan P, Bobbitt M, et al. The relationship of multispectral satellite imagery to immediate fire effects. Fire Ecology,2007,3 (1):64-90.
[74]LeMay V, Maedel J, Coops NC. Estimating stand structural details using nearest neighbor analyses to link ground data, forest cover maps, and Landsat imagery. Remote Sensing of Environment,2008,112:2578-2591.
[75]Browne MW. Cross-validation methods. Journal of Mathematical Psychology,2000,44(1): 108-132.
[76]李崇贵,赵宪文.森林郁闭度定量估测遥感比值波段的选择.林业科学,2005,41(4)：72-77.
[77]杜晓明,蔡体久,琚存勇.采用偏最小二乘回归方法估测森林郁闭度.应用生态学报,2008,19(2)：273-277.
[78]琚存勇,邸雪颖,蔡体久.变量筛选方法对郁闭度遥感估测模型的影响比较.林业科学,2007,43(12)：33-38.
[79]苏高利,邓芳萍.关于支持向量回归机的模型选择.科技通报,2006,22(2)：154-158.
[80]邓乃扬,田英杰.支持向量机——理论、算法与拓展.北京：科学出版社,2009.
[81]Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In:the International Joint Conference on Articial Intelligence, Lawrence Erlbaum Associates LTD,1995, pp.1134-1145.
[82]Lewis SA, Lentile L, Hudak AT, et al. Mapping ground cover using hyperspectral remote sensing after the 2003 Simi and Old wildfires in southern California. Fire Ecology,2007, 3(1):109-128.
[83]陈永义,俞小鼎,高学浩,等.处理非线性分类和回归问题的一种新方法(Ⅰ)——支持向量机方法简介.应用气象学报,2004,15(3)：345-354.
[84]祁亨年.支持向量机及其应用研究综述.计算机工程,2004,30(10)：6-9.
[85]Chih-Chung Chang, Chih-Jen Lin. LIBSVM:a library for support vector machines,2001. Software available at http://www.csie.ntu.edu.tw/-cjlin/libsvm.
[86]Faruto, liyang. LIBSVM-farutoUltimateVersion:a toolbox with implements for support vector machines based on libsvm,2009. Software available at http://www.ilovematlab.cn.
[87]史峰,王小川,郁磊,李洋.MATLAB神经网络30个案例分析.北京：北京航空航天大学出版社,2010.
[88]周昊,郑立刚,樊建人,等.广义回归神经网络在煤灰熔点预测中的应用.浙江大学学报(工学版),2004,38(11)：1479-1482.
[89]孙焱鑫,王纪华,李保国,等.基于BP和GRNN神经网络的冬小麦冠层叶绿素高光谱反演建模研究.遥感技术与应用,2007,22(4)：492-496.
[90]段松杰,张晓光,张闯志.基于广义回归神经网络的传感器非线性误差校正.传感器与微系统,2008,27(12)：14-16.
[91]琚存勇,蔡体久.鄂尔多斯草地生物量估测的GRNN模型实现.北京林业大学学报,2008,30(S 1)：296-299.
[92]Lei Chengliang, Ju Cunyong, Cai Tijiu, et al. Proper selection of the training data set for ANN model deriving valid relationships. Nature Resource & Ecology Environment,2012, (2):31-36
[93]李崇贵,石强,赵宪文,等.用岭估计研究以RS和GIS为基础的森林郁闭度估测.林业科学,2001,37(5)：24-30.
[94]琚存勇,蔡体久.用泛化改进的BP神经网络估测森林蓄积量.林业科学,42(12)：59-62.
[95]Naesset E, Bollandsas OM, Gobakken T. Comparing regression methods in estimation of biophysical properties of forest stands from two different inventories using laser scanner data. Remote Sensing of Environment,2005,94:541-553.
[96]竞霞,黄文江,琚存勇,等.基于PLS算法的棉花黄萎病高空间分辨率遥感监测.农业工程学报,2010,26(8)：229-235.
[97]蒋红卫,夏结来.偏最小二乘回归及其应用.第四军医大学学报,2003,24(3)：280-283.
[98]Hansen PM, Schjoerring JK. Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sensing of Environment,2003,86:542-553.
[99]Farifteh J, Van der Meer F, Atzberger C, et al. Quantitative analysis of salt-affected soil reflectance spectra:A comparison of two adaptive methods (PLSR and ANN). Remote Sensing of Environment,2007,110:59-78.
[100]Cai TJ, Ju CY, Yang XH. Comparison of ridge regression and partial least squares regression for estimating above-ground biomass with Landsat images and terrain data in Mu Us sandy land, China. Arid Land Research and Management,2009,23(3):248-261.
[101]Ju C, Cai T, Yang X. Topography-based modeling to estimate percent vegetation cover in semi-arid Mu Us sandy land, China. Computers and Electronics in Agriculture,2008,64: 133-139.
[102]王惠文,吴载斌,孟洁.偏最小二乘回归的线性与非线性方法.北京：国防工业出版社,2006.
[103]曾涛,琚存勇,蔡体久,等.利用变量投影重要性准则筛选郁闭度估测参数.北京林业大学学报,2010,32(6)：37-41.
[104]George E I. The variable selection problem. Journal of the American Statistical Association,2000,95:1304-1308.
[105]Lucic B, Trinajstic N, Sild S, et al. A new efficient approach for variable selection based on multiregression:Prediction of gas chromatographic retention times and response factors. Journal of chemical information and computer sciences,1999,39:610-621.
[106]方开泰,金辉,陈庆云.实用回归分析.北京：科学出版社,1988.
[107]何晓群.多元回归分析.北京：中国人民大学出版社,2008.
[108]吴琼,原忠虎,王晓宁.基于偏最小二乘回归分析综述.沈阳大学学报,2007,19(2)：33-35.
[109]Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction of near-infrared spectra. Chemometrics and Intelligent Laboratory Systems,1998,44:175-185.
[110]Sjoblom J, Svensson O, Josefson M, et al. An evaluation of orthogonal signal correction applied to calibration transfer of near infrared spectra. Chemometrics and Intelligent Laboratory Systems,1998,44:229-244.
[111]Fearn T. On orthogonal signal correction. Chemometrics and Intelligent Laboratory Systems,2000,50:47-52.
[112]Hoskuldsson A. Variable and subset selection in PLS regression. Chemometrics and Intelligent Laboratory Systems,2001,55:23-38.
[113]褚小立,袁洪福,陆婉珍.近红外分析中光谱预处理及波长选择方法进展与应用.化学进展,2004,16(4)：528-542.
[114]Jakubauskas ME, Price KP. Empirical relationships between structural and spectral factors of Yellowstone lodgepole pine forests. Photogrammetric engineering and remote sensing,1997,63:1375-1381.
[115]Dombi GW, Nandi P, Saxe JM, et al. Prediction of rib fracture injury outcome by an artificial neural network. The Journal of trauma,1995,39:915-921.
[116]黄成钢,金如锋,邱宏,等.我国某地区痢疾发病率与气象因素的关系及其预测模型.现代预防医学,2009,36(7)：1207-1210.
[117]吴洪丽,蒋永辉.软件可靠性影响因素权重分析.计算机工程与应用,2010,46(33)：58-63.
[118]王紫微,叶奇旺.基于神经网络MIV值分析的肿瘤基因信息提取.数学的实践与认识,2011,41(14)：47-59.
[119]李继泉,赵宪文,朱剑.用SPOT燃料对大兴安岭特大火灾林为行为研究及对阿穆尔林业局蓄积损失估计.林业科学研究,1988,1(6)：598～606.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |