基于GF-1与Landsat8 OLI影像的作物种植结构提取——以新疆阿克苏地区为例

作物种植结构监测和估产是精准农业遥感应用的重点领域,其研究对于指导作物种植结构和制定农业政策具有重要意义。本文以新疆阿克苏地区为研究区,以2016年多时相Landsat8 OLI和GF-1影像为数据源,基于物候信息、时相特征、积温和光谱特征确定农作物识别关键时期和特征参数,构建决策树分类模型,开展作物种植结构监测研究。结果表明:多源与多时相遥感数据可以反映不同农作物的季相特征,研究中所构建的决策树分类模型能够在大区域范围内高精度地实现作物分类,总体精度达83%,Kappa系数为0.77。与统计数据对比,棉花面积精度在85%以上,玉米为81%,小麦为80%以上,水稻达80%以上。因此,利用Landsat 8和GF-1影像在大区域提取农作种植结构是可行的,为今后遥感在农业上的应用提供一个广阔前景。     

基于多时相影像植被指数变化特征的作物遥感分类

高分一号GF1/WFV遥感影像具有较高的时间和空间分辨率,利用多时相影像开展农作物分类调查具有明显优势。以安徽省颍上县为研究区域,利用2017年5月至9月共6景多时相GF-1/WFV卫星遥感影像数据对主要农作物的分类识别提取。首先,通过分析研究区主要农作物的典型植被指数NDVI、EVI和WDRVI时序变化特征,明析了不同作物在各时相对不同VI的响应特征;其次,基于作物在不同时相的敏感VI变化响应,构建了决策树分层分类模型,成功提取了研究区玉米、水稻、大豆和甘薯四种主要作物种植空间分布情况。结果表明:总体精度达到90.9%,Kappa系数为0.895。同时,采用最大似然法、支持向量机对研究区作物进行分类,通过分类效果对比发现,最大似然法最差,支持向量机次之,决策树分类方法最佳。研究表明:利用多时相时间序列的遥感影像数据,结合作物植被指数特征,采用决策树分类方法可以有效提高作物分类的精度。     

基于高时空分辨率遥感数据协同的作物种植结构调查

[目的]充分发掘遥感影像的空间、时间和光谱等特征谱信息,探索地块基元支持下的多源遥感数据作物种植信息自动识别方法,为作物种植结构信息的快速、精细化调查提供借鉴.[方法]以广西扶绥县为研究区,通过对高空间分辨率影像的多尺度分割和对象廓线编辑,提取精细农田地块信息;以地块为基元获取覆盖作物生育期内的时序光谱特征;基于时序光谱及其变化定义与作物长势状况相关的描述参量,形成静态光谱与动态过程特征结合的多维特征空间,结合作物的物候节律特征构建作物种植信息提取模型,实现主要农作物种植结构信息的提取.[结果]依据上述方法绘制出广西扶绥县甘蔗、水稻和其他作物农田及草地、林地、水体、城镇建设用地等的精细地块图,其中,提取广西扶绥县甘蔗和水稻作物的总面积分别为82420.01和6806.67 ha,作物提取的总体分类精度为86.8%,Kappa系数为0.84.[结论]提取的广西扶绥县作物种植结构的成果满足使用精度要求,可为精准农业补贴投放、农业灾害定损等政策制定提供依据,而技术方法对于作物种植结构信息的快速、精细化调查具有借鉴意义.     

农作物种植面积遥感提取研究进展

介绍了农作物种植面积遥感提取方面的研究进展,新算法包括：选择多时相数据、多源遥感数据;GIS辅助等手段,并指出采用中分辨率与低分辨率数据相结合的测量方法是获取作物种植面积的主要趋势之一。     

遥感在作物分类中的应用

在提取作物种植分类信息方面,多时相和多光谱特征信息综合应用十分重要。环境与灾害监测预报小卫星影像具有较高的时间、空间分辨率,采用时间序列分析的方法提取作物种植分类信息优势显著。本研究以宁夏平罗地区作物为研究对象,利用HJ-CCD数据提取主要农作物分类信息,采用非监督分类、最大似然分类、决策树分类3种算法挖掘数据。研究表明,通过构建的时间序列HJ卫星遥感影像,结合作物的光谱和典型植被指数时序变化特征,能够有效进行农作物分类。     

基于Segformer网络的地块尺度作物种植结构精细化识别与分类

防止耕地“非粮化”、稳定粮食生产是中国粮食安全的基石。为实现地块破碎化地区作物类型及种植结构精细化识别和分类,本研究以江苏省泰兴市为研究区,基于高分辨率遥感影像和多尺度融合特征显著的Segformer语义分割模型,实现地块尺度的耕地信息精细化提取;同时结合多源遥感数据构建主要植被类型归一化植被指数(NDVI)时序曲线及植被生长关键时间节点的光谱反射特征,开展地块尺度的作物种植结构分类。结果表明：基于Segformer模型的分割方法可有效识别耕地,F1系数达92.4%;基于主要植被类型多时相NDVI时序特征及植被生长关键时间节点光谱反射特征的作物种植结构分类方法能够实现地块尺度的种植结构分类,总体分类精度达82.38%。因此,本研究建立的方法可有效实现地块尺度耕地信息的精细化提取及种植结构识别和分类,为耕地保护提供技术支持。     

多源遥感数据协同的地块级农作物精细提取

【目的】 针对云南省大理市耕地地块不规整、破碎且农作物空间种植结构复杂的特点,结合多源数据在时间和空间分辨率的优势,达到准确地提取农作物信息的目的。【方法】 协同BJ-2数据和Sentinal-2数据进行农作物精细信息提取。首先,利用空间分辨率较高的BJ-2数据进行面向对象的图像分割,获得农作物地块信息;其次,在农作物物候规律分析的基础上,通过标准差分析获得关键时相,利用相应时间分辨率较高的Sentinal-2数据获取农作物地类信息,实现基于地块的小春农作物的快速精细提取。【结果】 采用实地调查地块真值与提取地类生成混淆矩阵进行精度验证,总体精度和Kappa系数分别为87.4%和0.83。其中,连片种植的农作物如蚕豆和马铃薯提取精度较高,地块细碎且内部种植结构复杂的作物提取精度略低。【结论】 多源遥感数据协同的农作物提取方法,通过高分辨率影像上获得的对象分析单元能很好地对单一地块中的农作物空间特征进行统计分析,很大程度上弥补了中分辨率影像由于分辨率偏低所导致的混合像元处错分的不足;不仅能从耕地地块级别获得农作物种植结构,更直观地反映农作物种植,能有效提升农作物提取的精细化程度,有利于精细化的农作物种植结构管理。     

多时相高分一号影像在丘陵地区大宗农作物提取中的应用

【目的】基于多时相的高分一号(GF-1)影像,利用面向地块对象分类法提取广西崇左市江州区大宗农作物种植面积,为南方多云雨丘陵地区提取作物信息提供参考。【方法】以2 m分辨率的GF-1影像为数据源,采用人机交互的方式准确识别地表覆盖的地块信息,基于对多时相GF-1影像进行云影检测,并处理生成影像的光谱、归一化植被指数(NDVI)、亮度等特征,采用面向地块对象的分类方法提取甘蔗、水稻和香蕉的作物信息。【结果】根据混淆矩阵评价分类的结果可知,提取大宗农作物的总体精度为90.08%,Kappa系数达0.85,满足农业成果应用的精度要求。【结论】利用有效影像数据,结合地块数据完成作物信息提取,该技术方法能够准确提取丘陵地区大宗农作物信息,为解决南方多云雨丘陵地区提取作物信息难题提供了有效途径。     

农作物种植面积提取精度提高技术研究

随着遥感技术的快速发展,应用遥感影像特别是中高分辨率卫星影像进行农业工作成为遥感技术和农业工程发展的必然趋势,利用2011年RapidEye数据模拟中高分辨率卫星数据进行农作物种植面积提取精度提高技术研究,选取黑龙江省肇东市为研究区域,通过对中高分辨率卫星农作物提取结果进行系数扣除,对比分析三种扣除系数对肇东市水稻、玉米和大豆提高精度的效果,达到提高农作物提取精度的效果。结果表明:在种植结构相对单一区,利用地面样方扣除系数,精度提高显著;在复杂种植结构种植区,利用多尺度扣除系数精度提高显著。     

农作物空间格局遥感监测研究进展

遥感技术因其高时效、宽范围和低成本等优点正被广泛应用于对地观测活动中,为大区域尺度掌握农作物空间格局提供了新的科学技术手段。本文系统总结了近10年来国内外农作物空间格局遥感监测在理论、方法、实践应用等方面取得的新进展,指出了亟待解决的问题,并对今后的发展方向进行了展望。研究认为,农作物种植面积遥感监测主要根据遥感传感器记录的不同农作物光谱特征的差异,进行不同农作物种植面积的识别,方法主要包括:基于光谱特征、基于作物物候特征和基于多源数据的农作物遥感识别方法。遥感技术应用于农作物复种模式监测主要根据时间序列植被指数描述的作物季节活动过程,利用不同的拟合方法得到作物生长曲线,实现作物复种模式有效监测。农作物种植方式遥感监测是更高层次的遥感应用,主要利用时间序列遥感数据,根据作物植被指数的变化规律区分不同作物生育周期,判断不同复种模式下作物的种植顺序和方式。在未来相当长的一段时间内,建立农作物空间格局遥感监测的理论和技术体系、发展和改进遥感影像分类方法、优化时间序列遥感数据平滑技术和提高信息提取的自动化与流程化将是农作物空间格局遥感监测需要重点解决的几个关键问题。     

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.     

Perspective of Chinese GF-1 high-resolution satellite data in agricultural remote sensing monitoring

High-resolution satellite data have been playing an important role in agricultural remote sensing monitoring. However,the major data sources of high-resolution images are not owned by China. The cost of large scale use of high resolution imagery data becomes prohibitive. In pace of the launch of the Chinese "High Resolution Earth Observation Systems",China is able to receive superb high-resolution remotely sensed images(GF series) that equalizes or even surpasses foreign similar satellites in respect of spatial resolution,scanning width and revisit period. This paper provides a perspective of using high resolution remote sensing data from satellite GF-1 for agriculture monitoring. It also assesses the applicability of GF-1 data for agricultural monitoring,and identifies potential applications from regional to national scales. GF-1's high resolution(i.e.,2 m/8 m),high revisit cycle(i.e.,4 days),and its visible and near-infrared(VNIR) spectral bands enable a continuous,efficient and effective agricultural dynamics monitoring. Thus,it has gradually substituted the foreign data sources for mapping crop planting areas,monitoring crop growth,estimating crop yield,monitoring natural disasters,and supporting precision and facility agriculture in China agricultural remote sensing monitoring system(CHARMS). However,it is still at the initial stage of GF-1 data application in agricultural remote sensing monitoring. Advanced algorithms for estimating agronomic parameters and soil quality with GF-1 data need to be further investigated,especially for improving the performance of remote sensing monitoring in the fragmented landscapes. In addition,the thematic product series in terms of land cover,crop allocation,crop growth and production are required to be developed in association with other data sources at multiple spatial scales. Despite the advantages,the issues such as low spectrum resolution and image distortion associated with high spatial resolution and wide swath width,might pose challenges for GF-1 data applications and need to be addressed in future agricultural monitoring.     

Mapping regional cropping patterns by using GF-1 WFV sensor data

The successful launched Gaofen satellite no. 1 wide field-of-view(GF-1 WFV) camera is characterized by its high spatial resolution and may provide some potential for regional crop mapping. This study,taking the Bei'an City,Northeast China as the study area,aims to investigate the potential of GF-1 WFV images for crop identification and explore how to fully use its spectral,textural and temporal information to improve classification accuracy. In doing so,an object-based and Random Forest(RF) algorithm was used for crop mapping. The results showed that classification based on an optimized single temporal GF-1 image can achieve an overall accuracy of about 83%,and the addition of textural features can improve the accuracy by 8.14%. Moreover,the multi-temporal GF-1 data can produce a classification map of crops with an overall accuracy of 93.08% and the introduction of textural variables into multi-temporal GF-1 data can only increase the accuracy by about 1%,which suggests the importance of temporal information of GF-1 for crop mapping in comparison with single temporal data. By comparing classification results of GF-1 data with different feature inputs,it is concluded that GF-1 WFV data in general can meet the mapping efficiency and accuracy requirements of regional crop. But given the unique spectral characteristics of the GF-1 WFV imagery,the use of textual and temporal information is needed to yield a satisfactory accuracy.     

From statistics to grids: A two-level model to simulate crop pattern dynamics

Crop planting patterns are an important component of agricultural land systems. These patterns have been significantly changed due to the combined impacts of climatic changes and socioeconomic developments. However, the extent of these changes and their possible impacts on the environment, terrestrial landscapes and rural livelihoods are largely unknown due to the lack of spatially explicit datasets including crop planting patterns. To fill this gap, this study proposes a new method for spatializing statistical data to generate multitemporal crop planting pattern datasets. This method features a two-level model that combines a land-use simulation and a crop pattern simulation. The output of the first level is the spatial distribution of the cropland, which is then used as the input for the second level, which allocates crop censuses to individual gridded cells according to certain rules. The method was tested using data from 2000 to 2019 from Heilongjiang Province, China, and was validated using remote sensing images. The results show that this method has high accuracy for crop area spatialization. Spatial crop pattern datasets over a given time period can be important supplementary information for remote sensing and thus support a wide range of application in agricultural land systems.     

基于遥感技术的土壤质地空间预测方法研究进展

土壤质地影响土壤持水持肥性和透气性，进而驱动一系列与土壤有关的物理化学过程，结合高效快速的遥感技术预测土壤质地空间分布，对土壤质量评价与农业生产规划具有重要的理论和实践意义。本文从遥感预测土壤质地的数据、方法和模型的应用出发，介绍了用于土壤质地遥感预测的雷达、地形和植被指数等辅助数据，提出了光谱响应、特征波长选择和遥感解译这三种基于遥感特征预测土壤质地空间分布的方法，梳理了统计学、地统计学和机器学习这三类模型与遥感结合对土壤质地空间预测的应用效果，总结了几种典型方法的优缺点与适用情况，并分析了遥感预测土壤质地的应用条件和精度验证方法，最后提出未来研究需侧重于深入提取各种遥感光谱特征、利用遥感技术获取多类型环境变量和开发土壤物理属性与数据驱动机器学习特征相结合的多算法混合模型，旨在为开展不同区域尺度下土壤质地空间预测研究提供依据与技术支撑。     

农作物遥感识别中的多源数据融合研究进展

农作物遥感识别是地理学和生态学研究的前沿和热点,多源数据在农作遥感识别中日益发挥重要作用。笔者从多源数据融合的角度,归纳了2000年后多源数据在农作物遥感识别中应用的总体概况,系统梳理并提炼了当前多源数据融合的主要融合技术和融合模式。围绕与多源数据融合和农作物遥感识别相关的关键词,在Google学术、ISI Web of Knowledge和中国知网中对2000-2014年间国内外发表的论文进行检索,并统计不同传感器的使用频率及结合方式。研究表明,以提高空间分辨率为目标的多源数据融合和以提高时间分辨率为目标的多源数据融合技术是当前的两种主要方式,可以在一定程度上实现时空尺度的扩展。前者的融合技术包括图像融合、正态模糊分布神经网络模型、成分替换、半经验数据模型融合及多分辨率小波分解等,可以提升遥感数据的空间分解力和清晰度,较好弱化混合像元产生的影响,但农作物光谱信息有一定程度的丢失或扭曲,农作物空间分布局部细节信息与纹理特征依然会缺失;后者的融合技术形式灵活多样,可分为同源数据联合扩展时序的时空优化技术和异源数据联合扩展时序的时空优化技术,其可以有效排除短时间段内农作物生育期交叉,但易受不同遥感数据源间光谱反射率或植被指数转换模型及光谱波段设置差异的影响。在融合模式方面,根据数据类型分为光学数据的融合、光学数据与微波数据的融合以及遥感与非遥感数据的融合,以实现卫星资源优势互补为宗旨,充分挖掘不同类型农作物在遥感数据上呈现的光谱、时间和空间特征差异信息。同样,农作物遥感识别研究中的多源遥感数据融合也存在诸多挑战,在未来一段时间内,完善不同传感器之间的合作、更深层次挖掘融合信息以及多尺度长时间序列的中高分辨率农作物空间分布数据集的需求是多源数据融合的农作物遥感识别研究的重点发展方向和亟待解决的问题。研究结果有助于更好地理解多源遥感数据融合的技术和模式,为摸清多源数据融合在农作物识别中总体进展提供支撑,同时也为其他多源数据融合研究提供借鉴。     

一年一季农作物遥感分类的时效性分析

【目的】基于遥感影像的作物分类研究是提取作物种植面积和长势分析及产量估测的基础,也是推动现代化农业快速发展的动力。研究结果可为农业等相关部门掌握农情,进行宏观调控提供依据。目前,农业遥感研究主要集中于中低分辨率遥感影像,影响植被信息提取的精度,应用高分辨率多时相遥感影像和选择最优分类方法可以提高植被信息提取精度。明确农作物遥感分类的时效性与最优分类方法,为快速、准确地获取作物空间分布数据和农情定量遥感监测提供依据。【方法】基于黑龙江省虎林市2014年5—10月覆盖完整生长期的20幅遥感影像,构建16 m分辨率NDVI时间序列曲线,建立决策树分类模型,通过分类影像进行系列阈值分割,并结合辅助背景数据及专家知识,成功提取虎林市土地利用覆被信息;利用20幅影像依次波段合成的方式进行作物分类,明确最优时相;将提取的耕地范围作为作物分类规则,并与未提取耕地范围的作物分类结果进行比较;同时通过最大似然法、马氏距离法、神经网络法、最小距离法、支持向量机、波谱角分类法、主成分分析法多种分类方法进行作物分类;利用农业保险投保地块数据进行精度验证。【结果】(1)7月初、7月末到8月初、9月末是研究区一年一季作物遥感分类的3个关键时相;(2)决策树分类方法在提取土地利用覆被信息的结果中精度最高,总体精度90.24%,Kappa系数0.87;(3)6月初与7月初2幅影像结合采用最大似然法对作物进行分类的总体精度高达94.01%,Kappa系数为0.79,6月初与7月初的影像结合,可以解决作物分类的时效性;(4)结合9月21日的影像,总体精度进一步提高,大豆分类精度明显提高,最终确定最大似然法为最优作物分类方法。【结论】通过遥感数据能实现在7月上旬对作物进行精准分类,拓展了遥感数据在农业领域的应用价值,对一年一季地区作物快速分类与农情定量遥感监测有重要意义。     

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.