Leaf chlorophyll content retrieval of wheat by simulated RapidEye,Sentinel-2 and EnMAP data

Leaf chlorophyll content(LCC) is an important physiological indicator of the actual health status of individual plants. An accurate estimation of LCC can therefore provide valuable information for precision field management. Red-edge information from hyperspectral data has been widely used to estimate crop LCC. However, after the advent of red-edge bands in satellite imagery, no systematic evaluation of the performance of satellite data has been conducted. Toward this end, we analyze herein the performance of winter wheat LCC retrieval of currant and forthcoming satellites(RapidEye, Sentinel-2 and EnMAP) and their new red-edge bands by using partial least squares regression(PLSR) and a vegetation-indexbased approach. These satellite spectral data were obtained by resampling ground-measured hyperspectral data under various field conditions and according to specific spectral response functions and spectral resolution. The results showed: 1) This study confirmed that RapidEye, Sentinel-2 and EnMAP data are suitable for winter wheat LCC retrieval. For the PLSR approach, Sentinel-2 data provided more accurate estimates of LCC(R2=0.755, 0.844, 0.805 for 2002, 2010, and 2002+2010) than do RapidEye data(R2=0.689, 0.710, 0.707 for 2002, 2010, and 2002+2010) and EnMAP data(R2=0.735, 0.867, 0.771 for 2002, 2010, and 2002+2010). For index-based approaches, the MERIS terrestrial chlorophyll index, which is a vegetation index with two red-edge bands, was the most sensitive and robust index for LCC for both the Sentinel-2 and EnMAP data(R2≥0.628), and the indices(NDRE1, SRRE1 and CIRE1) with a single red-edge band were the most sensitive and robust indices for the RapidEye data(R2≥0.420); 2) According to the analysis of the effect of the wavelength and number of used red-edge spectral bands on LCC retrieval, the short-wavelength red-edge bands(from 699 to 734 nm) provided more accurate predictions when using the PLSR approach, whereas the long-wavelength red-edge bands(740 to 783 nm) gave more accurate predictions when using the vegetation indice(VI) approach. In addition, the prediction accuracy of RapidEye, Sentinel-2 and EnMAP data was improved gradually because of more number of red-edge bands and higher spectral resolution; VI regression models that contain a single or multiple red-edge bands provided more accurate predictions of LCC than those without red-edge bands, but for normalized difference vegetation index(NDVI)-, simple ratio(SR)-and chlorophyll index(CI)-like index, two red-edge bands index didn't significantly improve the predictive accuracy of LCC than those indices with a single red-edge band. Although satellite data with higher spectral resolution and a greater number of red-edge bands marginally improve the accuracy of estimates of crop LCC, the level of this improvement remains insufficient because of higher spectral resolution, which results in a worse signal-to-noise ratio. The results of this study are helpful to accurately monitor LCC of winter wheat in large-area and provide some valuable advice for design of red-edge spectral bands of satellite sensor in future.     

基于随机森林法的农作物高光谱遥感识别

  目的  不同农作物种类光谱差异小,通过探测众多窄波段范围的细微差别,提取区分不同农作物的特征波段,是目前实现农作物高光谱遥感识别的重要途径。如何提取区分不同农作物的特征波段,进而实现农作物的精确识别是一个挑战。近来出现的随机森林方法在多变量目标的分类识别方法展现了优势,为解决这一难题提供了一个新手段。  方法  利用随机森林法与传统方法分析杭州地区8种典型农作物的反射光谱,提取特征波段并进行分类,对比不同方法的识别效果。  结果  不同作物的反射光谱及其一阶微分、二阶微分、倒数的对数、去包络线法所提取的特征波段只能区分部分作物;随机森林法无需对反射光谱预处理,直接对全波段反射光谱数据处理,不仅筛选出了区分不同作物的特征波段,且运用所选择的波段对作物进行随机森林分类的效果也是最优的。  结论  随机森林法选择的波段（550、2 490、370、770、560、380、540、530、570、350 nm）不仅能区分不同作物,还能反映农作物生化属性的不同,使得用于分类的波段及分类方法体现了不同作物间物化性质的不同,在展现高光谱遥感识别农作物优势的同时,也为大面积农作物遥感精细分类提供借鉴。     

Winter wheat identification by integrating spectral and temporal information derived from multi-resolution remote sensing data

Timely crop acreage and distribution information are the basic data which drive many agriculture related applications. For identifying crop types based on remote sensing, methods using only a single image type have significant limitations. Current research that integrates fine and coarser spatial resolution images, using techniques such as unmixing methods, regression models, and others, usually results in coarse resolution abundance without sufficient detail within pixels, and limited attention has been paid to the spatial relationship between the pixels from these two kinds of images. Here we propose a new solution to identify winter wheat by integrating spectral and temporal information derived from multi-resolution remote sensing data and determine the spatial distribution of sub-pixels within the coarse resolution pixels. Firstly, the membership of pixels which belong to winter wheat is calculated using a 25-m resolution resampled Landsat Thematic Mapper (TM) image based on the Bayesian equation. Then, the winter wheat abundance (acreage fraction in a pixel) is assessed by using a multiple regression model based on the unique temporal change features from moderate resolution imaging spectroradiometer (MODIS) time series data. Finally, winter wheat is identified by the proposed Abundance-Membership (AM) model based on the spatial relationship between the two types of pixels. Specifically, winter wheat is identified by comparing the spatially corresponding 10×10 membership pixels of each abundance pixel. In other words, this method takes advantage of the relative size of membership in a local space, rather than the absolute size in the entire study area. This method is tested in the major agricultural area of Yiluo Basin, China, and the results show that acreage accuracy (Aa) is 93.01% and sampling accuracy (As) is 91.40%. Confusion matrix shows that overall accuracy (OA) is 91.4% and the kappa coefficient (Kappa) is 0.755. These values are significantly improved compared to the traditional Maximum Likelihood classification (MLC) and Random Forest classification (RFC) which rely on spectral features. The results demonstrate that the identification accuracy can be improved by integrating spectral and temporal information. Since the identification of winter wheat is performed in the space corresponding to each MODIS pixel, the influence of differences of environmental conditions is greatly reduced. This advantage allows the proposed method to be effectively applied in other places.     

Using high spatial resolution satellite imagery for mapping powdery mildew at a regional scale

Efficient crop protection management requires timely detection of diseases. The rapid development of remote sensing technology provides a possibility of spatial continuous monitoring of crop diseases over a large area. In this study, to monitor powdery mildew in winter wheat in an area where a severe disease infection occurred, the capability of high resolution (6 m) multi-spectral satellite imagery, SPOT-6, in disease mapping was assessed and validated using field survey data. Based on a rigorous feature selection process, five disease sensitive spectral features: green band, red band, normalized difference vegetation index, triangular vegetation index, and atmospherically-resistant vegetation index were selected from a group of candidate spectral features/variables. A spectral correction was processed on the selected features to eliminate possible baseline effect across different regions. Then, the disease mapping method was developed based on a spectral angle mapping technique. By validating against a set of field survey data, an overall mapping accuracy of 78 % and kappa coefficient of 0.55 were achieved. Such a moderate but practically acceptable accuracy suggests that the high resolution multi-spectral satellite image data would be of great potential in crop disease monitoring.     

基于成像高光谱的苹果树叶片病害区域提取方法研究

【目的】对带病斑苹果树叶片的高光谱图像进行病斑提取,为作物病虫害的遥感监测提供支持。【方法】对带有病斑的苹果树叶片成像高光谱图像,从传统基于光谱特征和面向对象特征2个方向入手进行病斑提取。为减少高光谱图像波段之间的冗余,首先对高光谱图像采用PCA变换进行降维处理,利用降维之后的前11个波段,分别采用波谱角分类和面向对象分类的方法提取苹果树叶片病害区域。【结果】由于同物异谱和异物同谱现象的存在,波谱角分类算法在提取病斑时,对叶柄和叶脉产生了错误的分类,而且以像元为分类单位的波谱角分类,在分类结果图中存在椒盐噪声,而面向对象分类则避免了这一现象的发生。【结论】采用面向对象分类方法提取苹果叶片病斑的结果优于基于光谱特征的波谱角分类方法,其总体精度和Kappa系数分别为98.44%和0.97。     

作物环境胁迫高光谱遥感监测研究进展

作物环境胁迫频发不仅严重影响区域粮食生产和生态安全,还威胁社会经济稳定和可持续发展,高光谱遥感可实时、准确监测作物环境胁迫,与传统监测方法相比具有较大优势。首先阐述了高光谱遥感监测作物环境胁迫的理论基础,重点从基于光谱响应特征的直接监测、基于农学参数和生理信息反演的间接监测两方面,概述了高光谱遥感在监测作物病虫害、水分胁迫方面的研究进展。在此基础上,提出了目前该技术在作物环境胁迫监测应用领域的不足,如光谱响应特征的专属性认识不足、反演模型的精度及普适性较低、数据使用受到限制等,并讨论了高光谱遥感在作物环境胁迫监测方面的发展方向,旨在为农作物环境胁迫监测及预警提供参考。     

基于高光谱成像估测冬小麦不同生育时期水分状况

【目的】研究实时、快速估测冬小麦不同生育时期水分状况并构建模型,为冬小麦水分精准管理提供科学依据。【方法】以新疆典型滴灌冬小麦为研究对象,应用高光谱成像技术获取冬小麦冠层光谱信息,并对原始光谱反射率进行平滑和数据变换,利用一元线性回归(Simple linear regression,SLR)、主成分回归(Principal components regression,PCR)和偏最小二乘回归(Partial least squares regression,PLSR)3种建模方法,对冬小麦冠层原始光谱及变换光谱分别构建植株水分含量估测模型。【结果】冬小麦冠层原始光谱反射率与植株水分含量相关性不高,对原始光谱反射率进行数据变换可以显著增强与水分含量的相关性和相关波段数,其中倒数一阶微分变换与冬小麦植株水分含量的相关系数最大,为-0.893 0,但不同变换最优相关系数所对应的波段位置并不固定。PLSR方法的模型精度最高,对数变换的PLSR模型估测精度最高,模型$R_{p}^{2}$、RMSE_p、RPD值分别为0.880 8、3.251 2%、2.934 3;冬小麦不同生育时期估测模型精度存在差异,拔节期、抽穗期估测模型精度较低,灌浆中期最高,其估测模型$R_{p}^{2}$、RMSE_p、RPD值分别为0.904 8、1.381 1%、3.454 7。【结论】利用高光谱成像技术对估测冬小麦植株水分含量是可行的,在灌浆中期的估测效果最佳。     

基于Bi-LSTM模型的时间序列遥感作物分类研究

【目的】及时、准确地作物分类制图是农情监测的重要依据。本研究基于双向长短期记忆网络模型探究深度学习技术在时间序列遥感作物分类与早期识别中的应用潜力。【方法】本文以黄河三角洲地区为例,以哨兵2号全年可用卫星影像为数据源,构建年时间序列NDVI数据集;采用循环神经网络构架,搭建针对结构化时序数据的双向长短期记忆网络模型（bidirectional long short-term memory,Bi-LSTM）,开展遥感作物分类,并评估模型的泛化能力;通过输入不同长度时间序列遥感数据,探究满足一定制图精度条件下的作物最早可识别时间。【结果】作物年生长时序特征对于大多数作物遥感分类识别都具有较好的区分能力,基于年时间序列NDVI数据的Bi-LSTM模型作物分类总体准确率达90.9%,Kappa系数达到0.892。通过测试不同时间序列长度对作物分类的影响发现,对大多数作物来说,其分类精度随着数据时间序列长度增加而不断提高,冬小麦、水稻等作物在生长季早期即具有较为独特的分类特征,因而利用生长季早期的时间序列影像即可获得较高的制图精度,而棉花、春玉米等作物需要完整生长序列影像才能更好地保证分类精度。【结论】卫星影像时间序列蕴含的结构化特征信息可以有效地降低特定时段的作物光谱混淆;双向循环神经网络模型能够同时考虑前向和后向的时间状态信息,可以学习作物不同阶段的光谱变化特征,在水稻、棉花、春玉米等易混淆作物的识别上表现优异;模型能够有效地把握样本总体上的变化趋势,在农作物多分类任务中表现出较好的泛化能力和鲁棒性。本研究通过集成深度学习和遥感时间序列,为及时、快速的区域作物高精度制图提供了可行的思路。     

基于包络线法的不同树种叶片高光谱特征分析

高光谱遥感的出现使树种的精细识别成为可能,而高光谱数据具有波段多、数据量大、冗余度大等特点,利用高光谱遥感技术进行树种鉴别时,光谱特征的选择及提取是个非常重要的过程。选择了樟树Cinnamomum camphora,麻栎Quercus acutissima,马尾松Pinus massoniana和毛竹Phyllostachys pubescens 4个树种,利用包络线去除法对ASD高光谱仪实测的原始光谱数据处理,比较原始光谱和包络线去除曲线图,选择差异较大的波段用于识别不同树种,用欧氏距离法检验所选择的波段识别不同树种的效果。结果证明,利用波段较窄的高光谱数据能够挖掘出不同树种的光谱差异,实现不同树种的鉴别;包络线去除法能够有效解决高光谱数据冗余的问题,对4个树种叶片的高光谱进行波段选择,能够将有效波段减少到8个,为484 ~ 493,670 ~ 679,971 ~ 980,1 162 ~ 1 171,1 435 ~ 1 444,1 773 ~ 1 782,1 918 ~ 1 927和2455 ~ 2464 nm,并得到较理想的树种鉴别效果。图5表2参11     

利用高光谱技术估测小麦叶片氮量和土壤供氮水平

有效的监测作物氮素营养水平及土壤供氮能力可以为合理施用氮肥提供重要依据。本文以2 年3 点不同氮素水平下不同小麦品种的田间试验数据为基础,运用植被指数和偏最小二乘回归法,比较和分析小麦冠层光谱与叶片氮含量及土壤氮含量的关系。结果表明：小麦冠层光谱与叶片氮含量的相关性分析在可见光波段存在显著负相关,在近红外波段呈显著正相关,而与土壤氮含量的相关性呈相反趋势。基于光谱参数ND705 和GNDVI所建叶片氮含量估算模型的决定系数分别达到0.827 和0.826。基于光谱参数VOG2 所建土壤氮含量估算模型的决定系数达到0.646;与植被指数所建模型相比,综合350~1350 nm光谱波段反射率分别与小麦叶片氮含量、土壤氮含量建立偏最小二乘回归模型的预测精 度均有所提高,决定系数分别达到0.842 和0.654。本研究结果可为小麦氮素营养及土壤供氮水平的诊断监测与合理施肥管理提供了理论依据和技术支持。     

Evaluating high resolution SPOT 5 satellite imagery for crop identification

High resolution satellite imagery offers new opportunities for crop monitoring and assessment. A SPOT 5 image acquired in May 2006 with four spectral bands (green, red, near-infrared, and short-wave infrared) and 10-m pixel size covering intensively cropped areas in south Texas was evaluated for crop identification. Two images with pixel sizes of 20 m and 30 m were also generated from the original image to simulate coarser resolution satellite imagery. Two subset images covering a variety of crops with different growth stages were extracted from the satellite image and five supervised classification techniques, including minimum distance, Mahalanobis distance, maximum likelihood, spectral angle mapper (SAM), and support vector machine (SVM), were applied to the 10-m subset images and the two coarser resolution images to identify crop types. The effects of the short-wave infrared band and pixel size on classification results were also examined. Kappa analysis showed that maximum likelihood and SVM performed better than the other three classifiers, though there were no statistical differences between the two best classifiers. Accuracy assessment showed that the 10-m, four-band images based on maximum likelihood resulted in the best overall accuracy values of 91% and 87% for the two respective sites. The inclusion of the short-wave infrared band statistically significantly increased the overall accuracy from 82% to 91% for site 1 and from 75% to 87% for site 2. The increase in pixel size from 10 m to 20 m or 30 m did not significantly affect the classification accuracy for crop identification. These results indicate that SPOT 5 multispectral imagery in conjunction with maximum likelihood and SVM classification techniques can be used for identifying crop types and estimating crop areas.     

Using hyperspectral remote sensing techniques to monitor nitrogen,phosphorus, sulphur and potassium in wheat (Triticum aestivum L.)

In situ, non-destructive and real time mineral nutrient stress monitoring is an important aspect of precision farming for rational use of fertilizers. Studies have demonstrated the ability of remote sensing to monitor nitrogen (N) in many crops, phosphorus (P) and potassium (K) in very few crops and none so far to monitor sulphur (S). Specially designed (1) fertility gradient experiment and (2) test crop experiments were used to check the possibility of mineral N–P–S–K stress detection using airborne hyperspectral remote sensing. Leaf and canopy hyperspectral reflectance data and nutrient status at booting stage of the wheat crop were recorded. N–P–S–K sensitive wavelengths were identified using linear correlation analysis. Eight traditional vegetation indices (VIs) and three proposed (one for P and two for S) were evaluated for plant N–P–S–K predictability. A proposed VI (P_1080_1460) predicted P content with high and significant accuracy (correlation coefficient (r) 0.42 and root means square error (RMSE) 0.180 g m^?2). Performance of the proposed S VI (S_660_1080) for S concentration and content retrieval was similar whereas prediction accuracies were higher than traditional VIs. Prediction accuracy of linear regressive models improved when biomass-based nutrient contents were considered rather than concentrations. Reflectance in the SWIR region was found to monitor N–P–S–K status in plants in combination with reflectance at either visible (VIS) or near infrared (NIR) region. Newly developed and validated spectral algorithms specific to N, P, S and K can further be used for monitoring in a wheat crop in order to undertake site-specific management.     

基于无人机多光谱影像特征融合的小麦倒伏监测

【目的】小麦倒伏严重影响小麦光合及成熟进程,进而造成小麦减产及品质下降。为快速精确获取倒伏信息,评估无人机遥感监测小麦倒伏的能力,构建小麦倒伏监测模式,为灾情评估、保险理赔及灾后补救提供技术支持。【方法】利用近地无人机获取包含红、绿、蓝、红边和近红外5个多光谱波段图像,经过预处理飞行高度50 m的小麦冠层图像,得到分辨率为1.85(cm/像素)的数字正射影像图（DOM）和数字表面模型（DSM）,从中提取光谱特征、高度特征和光谱纹理共3类特征信息;采用支持向量机（SVM）和随机森林（RF）2种分类器对6种不同特征集组合进行倒伏分类比较,使用准确率（Acc）、精确率（Pre）、召回率（Re）和调和平均数（F1）以确定较优的特征组合和分类器;同时使用3种不同的特征集筛选方法（套索算法Lasso、随机森林递归算法RF-RFE和Boruta算法）对优化的特征子集进行综合评价,确立适宜的倒伏分类评价方法。【结果】单一特征的光谱和纹理及其组合对小麦倒伏的分类评价结果较差,“椒盐现象”严重,在此基础上融合DSM信息的分类精度显著提高。采用随机森林分类器对光谱特征、纹理特征和高度特征进行特征集组合,小麦...     

Airborne Hyperspectral Imagery and Yield Monitor Data for Mapping Cotton Yield Variability

Increased availability of hyperspectral imagery necessitates the evaluation of its potential for precision agriculture applications. This study examined airborne hyperspectral imagery for mapping cotton (Gossypium hirsutum L.) yield variability as compared with yield monitor data. Hyperspectral images were acquired using an airborne imaging system from two cotton fields during the 2001 growing season, and yield data were collected from the fields using a cotton yield monitor. The raw hyperspectral images contained 128 bands between 457 and 922 nm. The raw images were geometrically corrected, georeferenced and resampled to 1 m resolution, and then converted to reflectance. Aggregation functions were then applied to each of the 128 bands to reduce the cell resolution to 4 m (close to the cotton picker's cutting width) and 8 m. The yield data were also aggregated to the two grids. Correlation analysis showed that cotton yield was significantly related to the image data for all the bands except for a few bands in the transitional range from the red to the near-infrared region. Stepwise regression performed on the yield and hyperspectral data identified significant bands and band combinations for estimating yield variability for the two fields. Narrow band normalized difference vegetation indices derived from the significant bands provided better yield estimation than most of the individual bands. The stepwise regression models based on the significant narrow bands explained 61% and 69% of the variability in yield for the two fields, respectively. To demonstrate if narrow bands may be better for yield estimation than broad bands, the hyperspectral bands were aggregated into Landsat-7 ETM+ sensor's bandwidths. The stepwise regression models based on the four broad bands explained only 42% and 58% of the yield variability for the two fields, respectively. These results indicate that hyperspectral imagery may be a useful data source for mapping crop yield variability.     

植被重金属污染检测模型研究

利用高光谱遥感技术代替传统方法检测重金属污染,具有效率高、费用低、检测范围广等优点.但是高光谱影像的空间分辨率较低,为了提高精度需要提取影像的端元.鉴于纯净像元指数（Pixel Purity Index,PPI）法耗时长的缺点,提出一种基于高斯分布的波谱曲线概率法用于高光谱影像端元提取,并结合重金属胁迫下植被波谱响应变化建立了高光谱遥感影像的植被重金属污染检测模型.经过试验研究及分析,发现波谱曲线概率法端元提取的效果和精度与PPI相近,但是时间消耗明显减少.因此,建立的植被重金属污染检测模型可以用于高光谱遥感图像,具有一定的价值.     

基于水稻特征波段的决策树分类研究

以滁州市为例,结合水稻物候的特征波段,选用反映水稻物候期时相的TM数据,并基于多特征波段,构建CART决策树分类提取水稻种植面积。结果表明,植被指数、湿度因子、绿度因子、纹理特征等多特征参与CART决策树分类能够提高总体精度。基于光谱信息、植被指数和纹理特征的决策树分类的总精度比以最大似然法进行的监督分类方法提高了6.942 1百分点,Kappa系数提高了0.110 4。合理选用作物物候期数据及其遥感影像的特征波段能够有效降低分类误差,为地形复杂地区获取作物种植面积提新的方法。     

高分六号遥感数据在有林地识别中的应用

精准农业观测卫星-高分六号卫星(GF6)增加了4个特殊波段,更加有效地反映了植被特有的光谱特性,为植被应用研究提供更为详细的地物光谱信息。为了分析GF6数据在植被识别能力上的优越性,比较了GF6号新增波段(红边1、红边2、黄边、紫边波段)和高分数据传统波段对有林地识别精度的影响。结果表明:GF6新增波段对有林地快速识别的精度达到97.67%,Kappa系数为0.95,比GF数据4波段对有林地的识别精度提高了3.35%,Kappa系数提高了0.08。CART自适应特征和阈值选择决策树算法比人工决策树分类算法对有林地识别精度有显著增加,精度由88.81%提高到97.67%,Kappa系数由0.78提高到0.95。GF6数据新增特殊波段结合CART自适应特征和阈值决策树算法对有林地具有快速优越的识别能力。     

Mapping wheat nitrogen uptake from RapidEye vegetation indices

Mapping wheat nitrogen (N) uptake at 5 m spatial resolution could provide growers with new insights regarding nitrogen-use efficiency at the field scale. This study explored the use of spectral information from high resolution (5 × 5 m) RapidEye satellite data at peak leaf area index (LAI) to estimate end-of-season cumulative N uptake of wheat (Triticum spp.) in a heterogeneous, rainfed system. The primary objectives were to evaluate the usefulness of simple, widely used vegetation indices (VIs) from RapidEye as a tool to map crop N uptake over three growing seasons, farms and growing conditions, and to examine the usefulness of remotely sensed N uptake maps for precision agriculture applications. Data on harvested wheat N was collected at twelve plots over three seasons at four farms in the Palouse region of Northern Idaho and Eastern Washington. Seventeen commonly used spectral VIs were computed for images collected during ‘peak greenness’ (maximum LAI) to determine which VIs would be most appropriate for estimating wheat N uptake at harvest. The normalized difference red-edge index was the top performing VI, explaining 81 % of the variance in wheat N uptake with a regression slope of 1.06 and RMSE of 15.94 kg/ha. Model performance was strong across all farms over all three seasons regardless of crop variety, allowing the creation of high accuracy wheat N uptake maps. In conclusion, for this particular agro-ecosystem, mid-season VIs that incorporate the use of the NIR and red-edge bands are generally better predictors of end-of-season crop N uptake than VIs that do not include these bands, thereby further enabling their use in precision agriculture applications.     

冬小麦叶片光合特征高光谱遥感估算模型的比较研究

【目的】光合作用是农作物产量和品质形成的基础,农作物光合参数的准确定量遥感反演不仅能够了解农作物的生长发育和有机物累积状况,还能为基于遥感的生态系统过程模型提供参考。为快速准确的估算光合特征参量,本研究综合原始光谱、3种传统光谱变换技术和4种模拟方法构建冬小麦3种光合参数的高光谱反演模型,探讨高光谱反演冬小麦光合参数的可行性,对比不同类别光谱和模拟方法的适用性。【方法】本研究基于氮肥施用条件冬小麦气体交换和高光谱田间试验,获取不同叶位叶片的最大净光合速率（Amax）、PSⅡ有效光化学量子产量（Fv′/Fm′）、光化学猝灭系数（qP）和高光谱反射率,并对原始高光谱进行倒数、对数和一阶微分变换。根据3种光合参数和4种光谱的相关性分析结果,筛选显著性水平优于0.01的波段作为输入变量,采用偏最小二乘（PLS）、支持向量机（SVM）、多元线性回归（MLR）和人工神经网络（ANN）等方法建立冬小麦叶片光合参量反演模型,以建模和验证的决定系数（R ²）和均方根误差（RMSE）为依据,对不同模型的模拟精度进行比较分析。 【结果】（1）3种光合参数和4种光谱的相关性分析结果表明,原始、倒数和对数光谱对3种光合参数（Amax、Fv′/Fm′和qP）的敏感谱区均集中在400—750 nm波谱区间,一阶导数光谱对3个光合参数的敏感谱区为470—560、630—700和700—770 nm波谱区间。（2）Amax、Fv′/Fm′和qP的最优反演模型组合分别为基于倒数光谱的MLR模型、基于一阶导数光谱的MLR模型和基于原始光谱的MLR模型。模型的建模R ²分别为0.75、0.65和0.65,验证R ²分别为0.73、0.59和0.44,表明基于高光谱模拟Amax和Fv′/Fm′切实可行,模拟qP的有效性需要进一步验证。（3）不同变换的光谱表现能力不同,以PLS模拟Amax为例,光谱的表现能力顺序为原始光谱>倒数光谱>对数光谱>一阶导数光谱。（4）不同模型的估算能力也存在明显差异,以基于原始光谱的Amax模拟为例,不同模型的估算能力顺序为MLR>PLS>ANN>SVM。 【结论】通过对比分析4种光谱和4种模拟方法对3种冬小麦光合参数的高光谱反演结果发现,Amax和Fv′/Fm′可以很好通过高光谱进行模拟,而高光谱对qP解释能力偏低,有待进一步研究。高光谱信息对冬小麦光合参量具有较强的敏感性,同时受光谱类型和模拟方法的影响,可以用来监测冬小麦光合能力的动态变化,为把握农作物生长状况提供依据。     

C5.0决策树Hyperion影像森林类型精细分类方法

以吉林省白河林业局为中心研究区,利用星载高光谱Hyperion数据并结合其他辅助数据,综合利用影像光谱特征、纹理特征、地形特征、典型地类和主要森林类型外业调查样本数据,探究针对C5.0决策树算法的高光谱影像土地覆盖类型多层次信息提取与森林类型识别的有效方法。在分析典型地物光谱特征的基础上,优选8种纹理特征,引入主成分分量及与主要森林类型空间分布相关的敏感地形因子,采用分层分类的策略,根据光谱特征将地类划分层次,在层次间建立基于C5.0决策树算法的决策树模型,对研究区的地类进行细分。为便于对比,以相同的策略采用支持向量机（SVM）分类器进行分类。最后,结合野外采集样本并参考高分辨率影像,采用分层随机抽样的独立检验样本对森林类型精细识别结果进行精度验证。结果表明:C5.0决策树算法可综合利用高光谱影像的光谱、纹理及其他辅助数据,自动寻找出区分各类别的最佳特征变量及分割阈值,运算速度快,占用内存较小且无需人为参与,其分类精度达到优势树种级别,总体分类精度达81.9%,Kappa系数0.709 8。