Land cover classification of the North China Plain using MODIS_EVI time series

Moderate Resolution Imaging Spectroradiometer (MODIS) data have played an important role in global environmental and resource research. However, its low spatial resolution has been an impediment to researchers pursuing more accurate classification results. In this research, the high temporal resolution of MODIS was employed to improve the accuracy of land cover classification of the North China Plain using MODIS_EVI time series from 2003. Harmonic Analysis of Time Series (HANTS) was performed on the MODIS_EVI image time series to reduce cloud and other noise effects. The improved MODIS_EVI time series was then classified into 100 clusters by the Iterative Self-Organizing Data Analysis Technique (ISODATA). To distinguish ambiguous land cover classes, a decision tree was built on five phenological features derived from EVI profiles, Land Surface Temperature (LST) and topographic slope. The overall accuracy of the final land cover map was 75.5%, indicating the promise of using MODIS EVI time series and decision trees for broad area land cover classification.     

全球地图第一版中国土地覆盖产品的生成

介绍了全球地图第一版中国土地覆盖分类产品的遥感数据源、数据处理方法及结果,详细介绍了非监督聚类和决策树分类相结合的区域级土地覆盖分类方法及处理步骤,并以2003年全年的MODIS/TERRA16d合成产品MOD43B4为主要遥感数据源,采用先进行影像聚类,然后以聚类结果为处理单元进行多时相多特征决策树分类,得到了覆盖全国、约1km分辨率的土地覆盖分类结果。采用室内精度评定和外业验证两种方法对分类结果进行了检验,生成的中国土地覆盖分类产品的精度为89.14%。     

Exploring improvement of impervious surface estimation at national scale through integration of nighttime light and Proba-V data

Directly mapping impervious surface area (ISA) at national and global scales using nighttime light data is a challenge due to the complexity of land surface components and the impacts of unbalanced economic conditions. Previous research mainly used the coarse spatial resolution Defense Meteorological Satellite Program’s Operational Linescan System (DMSP OLS) and Moderate Resolution Imaging Spectroradiometer (MODIS), normalized difference vegetation index (NDVI) data for ISA mapping; the improved spatial resolution and data quality in the Suomi National Polar-orbiting Partnership, Visible Infrared Imaging Radiometer Suite’s Day/Night Band (VIIRS DNB) and in Proba-V data provide a new opportunity to accurately map ISA distribution at the national scale, which has not been explored yet. This research aimed to develop a new index – modified impervious surface index (MISI) – based on VIIRS DNB and Proba-V data to improve ISA estimation and to compare the results with those from the combination of VIIRS DNB and MODIS NDVI data. Landsat data were used to develop ISA data for the typical sites for use as reference data. Regression analysis was used to establish the ISA estimation model in which the dependent variable was from the Landsat data and the independent variable was from the MISI, as well as the previously used Large-scale Impervious Surface Index (LISI). The results indicate that the major error is from the very small or very large proportion of ISA in a unit; improvement of spatial resolution through use of higher spatial resolution nighttime light data (e.g., VIIRS DNB) or NDVI (e.g., Proba-V NDVI) data is an effective approach to improve ISA estimation. Although different indices for the combination of nighttime light and NDVI data have been used, the MISI is especially valuable for reducing the estimation errors for the regions with a small or large ISA proportion.     

基于MODIS数据的环北京地区土地资源监测研究

本文基于MODIS 16天合成的NDVI时间序列数据及其他辅助数据,首先用PCA方法对NDVI时间序列数据进行信息增强与压缩处理,结合LST数据、DEM数据及降雨温度数据,利用模糊K-均值非监督分类法,进行环北京地区的土地覆盖分类,得到土地资源现状情况。然后利用变化矢量(CVA)分析方法对环北京地区的土地利用及植被覆盖的多年变化状况进行了分析。结果表明,MODIS数据能很好的应用于大范围的土地资源监测中,并能得到较好的结果。     

Land cover mapping applications with MODIS: a literature review

Abstract

Land use/land cover monitoring and mapping is crucial to efficient management of the land and its resources. Since the late 1980s increased attention has been paid to the use of coarse resolution optical data. The Moderate Resolution Imaging Spectroradiometer (MODIS) has features, which make it particularly suitable to earth characterization purposes. MODIS has 10 products dedicated mainly to land cover characterization and provides three kinds of data: angular, spectral and temporal. MODIS data also includes information about the data quality through the ‘Quality Assessment’ product. In this paper, we review how MODIS data are used to map land cover including the preferred MODIS products, the preprocessing and classification approaches, the accuracy assessment, and the results obtained.     

Comparative assessment of thematic accuracy of GLC maps for specific applications using existing reference data

Inputs to various applications and models, current global land cover (GLC) maps are based on different data sources and methods. Therefore, comparing GLC maps is challenging. Statistical comparison of GLC maps is further complicated by the lack of a reference dataset that is suitable for validating multiple maps. This study utilizes the existing Globcover-2005 reference dataset to compare thematic accuracies of three GLC maps for the year 2005 (Globcover, LC-CCI and MODIS). We translated and reinterpreted the LCCS (land cover classification system) classifier information of the reference dataset into the different map legends. The three maps were evaluated for a variety of applications, i.e., general circulation models, dynamic global vegetation models, agriculture assessments, carbon estimation and biodiversity assessments, using weighted accuracy assessment. Based on the impact of land cover confusions on the overall weighted accuracy of the GLC maps, we identified map improvement priorities. Overall accuracies were 70.8 ± 1.4%, 71.4 ± 1.3%, and 61.3 ± 1.5% for LC-CCI, MODIS, and Globcover, respectively. Weighted accuracy assessments produced increased overall accuracies (80–93%) since not all class confusion errors are important for specific applications. As a common denominator for all applications, the classes mixed trees, shrubs, grasses, and cropland were identified as improvement priorities. The results demonstrate the necessity of accounting for dissimilarities in the importance of map classification errors for different user application. To determine the fitness of use of GLC maps, accuracy of GLC maps should be assessed per application; there is no single-figure accuracy estimate expressing map fitness for all purposes.     

Measures of spatio-temporal accuracy for time series land cover data

Remote sensing is a useful tool for monitoring changes in land cover over time. The accuracy of such time-series analyses has hitherto only been assessed using confusion matrices. The matrix allows global measures of user, producer and overall accuracies to be generated, but lacks consideration of any spatial aspects of accuracy. It is well known that land cover errors are typically spatially auto-correlated and can have a distinct spatial distribution. As yet little work has considered the temporal dimension and investigated the persistence or errors in both geographic and temporal dimensions. Spatio-temporal errors can have a profound impact on both change detection and on environmental monitoring and modelling activities using land cover data. This study investigated methods for describing the spatio-temporal characteristics of classification accuracy. Annual thematic maps were created using a random forest classification of MODIS data over the Jakarta metropolitan areas for the period of 2001–2013. A logistic geographically weighted model was used to estimate annual spatial measures of user, producer and overall accuracies. A principal component analysis was then used to extract summaries of the multi-temporal accuracy. The results showed how the spatial distribution of user and producer accuracy varied over space and time, and overall spatial variance was confirmed by the principal component analysis. The results indicated that areas of homogeneous land cover were mapped with relatively high accuracy and low variability, and areas of mixed land cover with the opposite characteristics. A multi-temporal spatial approach to accuracy is shown to provide more informative measures of accuracy, allowing map producers and users to evaluate time series thematic maps more comprehensively than a standard confusion matrix approach. The need to identify suitable properties for a temporal kernel are discussed.     

New urban map of Eurasia using MODIS and multi-source geospatial data

Urban areas are of paramount significance to both the individuals and communities at local and regional scales. However, the rapid growth of urban areas exerts effects on climate, biodiversity, hydrology, and natural ecosystems worldwide. Therefore, regular and up-to-date information related to urban extent is necessary to monitor the impacts of urban areas at local, regional, and potentially global scales. This study presents a new urban map of Eurasia at 500 m resolution using multi-source geospatial data, including Moderate Resolution Imaging Spectroradiometer (MODIS) data of 2013, population density of 2012, the Defense Meteorological Satellite Program’s Operational Linescan System (DMSP-OLS) nighttime lights of 2012, and constructed Impervious Surface Area (ISA) data of 2010. The Eurasian urban map was created using the threshold method for these data, combined with references of fine resolution Landsat and Google Earth imagery. The resultant map was compared with nine global urban maps and was validated using random sampling method. Results of the accuracy assessment showed high overall accuracy of the new urban map of 94%. This urban map is one product of the 20 land cover classes of the next version of Global Land Cover by National Mapping Organizations.     

Global mapping of urban built-up areas of year 2014 by combining MODIS multispectral data with VIIRS nighttime light data

An improved methodology for the extraction and mapping of urban built-up areas at a global scale is presented in this study. The Moderate Resolution Imaging Spectroradiometer (MODIS)-based multispectral data were combined with the Visible Infrared Imager Radiometer Suite (VIIRS)-based nighttime light (NTL) data for robust extraction and mapping of urban built-up areas. The MODIS-based newly proposed Urban Built-up Index (UBI) was combined with NTL data, and the resulting Enhanced UBI (EUBI) was used as a single master image for global extraction of urban built-up areas. Due to higher variation of the EUBI with respect to geographical regions, a region-specific threshold approach was used to extract urban built-up areas. This research provided 500-m-resolution global urban built-up map of year 2014. The resulted map was compared with three existing moderate-resolution global maps and one high-resolution map in the United States. The comparative analysis demonstrated finer details of the urban built-up cover estimated by the resultant map.     

Primitives as building blocks for constructing land cover maps

Land cover maps play an integral role in environmental management. However, countries and institutes encounter many challenges with producing timely, efficient, and temporally harmonized updates to their land cover maps. To address these issues we present a modular Regional Land Cover Monitoring System (RLCMS) architecture that is easily customized to create land cover products using primitive map layers. Primitive map layers are a suite of biophysical and end member maps, with land cover primitives representing the raw information needed to make decisions in a dichotomous key for land cover classification. We present best practices to create and assemble primitives from optical satellite using computing technologies, decision tree logic and Monte Carlo simulations to integrate their uncertainties. The concept is presented in the context of a regional land cover map based on a shared regional typology with 18 land cover classes agreed on by stakeholders from Cambodia, Laos PDR, Myanmar, Thailand, and Vietnam. We created annual map and uncertainty layers for the period 2000–2017. We found an overall accuracy of 94% when taking uncertainties into account. RLCMS produces consistent time series products using free long term historical Landsat and MODIS data. The customizable architecture can include a variety of sensors and machine learning algorithms to create primitives and the best suited smoothing can be applied on a primitive level. The system is transferable to all regions around the globe because of its use of publicly available global data (Landsat and MODIS) and easily adaptable architecture that allows for the incorporation of a customizable assembly logic to map different land cover typologies based on the user's landscape monitoring objectives     

Forest cover classification using Landsat ETM+ data and time series MODIS NDVI data

Forest cover plays a key role in climate change by influencing the carbon stocks, the hydrological cycle and the energy balance. Forest cover information can be determined from fine-resolution data, such as Landsat Enhanced Thematic Mapper Plus (ETM+). However, forest cover classification with fine-resolution data usually uses only one temporal data because successive data acquirement is difficult. It may achieve mis-classification result without involving vegetation growth information, because different vegetation types may have the similar spectral features in the fine-resolution data. To overcome these issues, a forest cover classification method using Landsat ETM+ data appending with time series Moderate-resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) data was proposed. The objective was to investigate the potential of temporal features extracted from coarse-resolution time series vegetation index data on improving the forest cover classification accuracy using fine-resolution remote sensing data. This method firstly fused Landsat ETM+ NDVI and MODIS NDVI data to obtain time series fine-resolution NDVI data, and then the temporal features were extracted from the fused NDVI data. Finally, temporal features combined with Landsat ETM+ spectral data was used to improve forest cover classification accuracy using supervised classifier. The study in North China region confirmed that time series NDVI features had significant effects on improving forest cover classification accuracy of fine resolution remote sensing data. The NDVI features extracted from time series fused NDVI data could improve the overall classification accuracy approximately 5% from 88.99% to 93.88% compared to only using single Landsat ETM+ data.     

Satellite Data Classification Using Open Source Support

In this study we explored the potential of open source data mining software support to classify freely available Landsat image. The study identified several major classes that can be distinguished using Landsat data of 30 m spatial resolution. Decision tree classification (DTC) using Waikato environment for knowledge analysis (WEKA), open source software is used to prepare land use land cover (LULC) map and the result is compared with supervised (maximum likelihood classifier – MLC) and unsupervised (Iterative self-organizing data analysis technique - ISODATA clustering) classification techniques. The accuracy assessment indicates highest accuracy of the map prepared using DTC with overall accuracy (OA) 92 % (kappa = 0.90) followed by MLC with OA 88 % (kappa = 0.84) and ISODATA OA 76 % (kappa = 0.69). Results indicate that data set with a good definition of training sites can produce LULC map having good overall accuracy using decision tree. The paper demonstrates utility of open source system for information extraction and importance of DTC algorithm.     

Production of global land cover data – GLCNMO

Abstract

Global land cover is one of the fundamental contents of Digital Earth. The Global Mapping project coordinated by the International Steering Committee for Global Mapping has produced a 1-km global land cover dataset – Global Land Cover by National Mapping Organizations. It has 20 land cover classes defined using the Land Cover Classification System. Of them, 14 classes were derived using supervised classification. The remaining six were classified independently: urban, tree open, mangrove, wetland, snow/ice, and water. Primary source data of this land cover mapping were eight periods of 16-day composite 7-band 1-km MODIS data of 2003. Training data for supervised classification were collected using Landsat images, MODIS NDVI seasonal change patterns, Google Earth, Virtual Earth, existing regional maps, and expert's comments. The overall accuracy is 76.5% and the overall accuracy with the weight of the mapped area coverage is 81.2%. The data are available from the Global Mapping project website (http://www.iscgm.org/). The MODIS data used, land cover training data, and a list of existing regional maps are also available from the CEReS website. This mapping attempt demonstrates that training/validation data accumulation from different mapping projects must be promoted to support future global land cover mapping.     

Classifying historical remotely sensed imagery using a tempo-spatial feature evolution (T-SFE) model

Large and growing archives of orbital imagery of the earth’s surface collected over the past 40 years provide an important resource for documenting past and current land cover and environmental changes. However uses of these data are limited by the lack of coincident ground information with which either to establish discrete land cover classes or to assess the accuracy of their identification. Herein is proposed an easy-to-use model, the Tempo-Spatial Feature Evolution (T-SFE) model, designed to improve land cover classification using historical remotely sensed data and ground cover maps obtained at later times. This model intersects (1) a map of spectral classes (S-classes) of an initial time derived from the standard unsupervised ISODATA classifier with (2) a reference map of ground cover types (G-types) of a subsequent time to generate (3) a target map of overlaid patches of S-classes and G-types. This model employs the rules of Count Majority Evaluation, and Subtotal Area Evaluation that are formulated on the basis of spatial feature evolution over time to quantify spatial evolutions between the S-classes and G-types on the target map. This model then applies these quantities to assign G-types to S-classes to classify the historical images. The model is illustrated with the classification of grassland vegetation types for a basin in Inner Mongolia using 1985 Landsat TM data and 2004 vegetation map. The classification accuracy was assessed through two tests: a small set of ground sampling data in 1985, and an extracted vegetation map from the national vegetation cover data (NVCD) over the study area in 1988. Our results show that a 1985 image classification was achieved using this method with an overall accuracy of 80.6%. However, the classification accuracy depends on a proper calibration of several parameters used in the model.     

Application of Earth Remote Sensing and GIS in Mapping Land Cover Patterns in Kinangop Division, Kenya

<正>Land cover is a fundamental variable that links many facets of the natural environment and a key driver of global environmental change.Alterations in its status can have significant ramifications at local,regional and global levels.Hence,it is imperative to map land cover at a range of spatial and temporal scales with a view to understanding the inherent patterns for effective characterization,prediction and management of the potential environmental impacts.This paper presents the results of an effort to map land cover patterns in Kinangop division,Kenya,using geospatial tools.This is a geographic locality that has experienced rapid land use transformations since Kenya's independence culminating in uncontrolled land cover changes and loss of biodiversity.The changes in land use/cover constrain the natural resource base and presuppose availability of quantitative and spatially explicit land cover data for understanding the inherent patterns and facilitating specific and multi-purpose land use planning and management.As such,the study had two objectives viz.(i) mapping the spatial patterns of land cover in Kinangop using remote sensing and GIS and;(ii) evaluating the quality of the resultant land cover map.ASTER satellite imagery acquired in January 23,2007 was procured and field data gathered between September l0 and October 16,2007.The latter were used for training the maximum likelihood classifier and validating the resultant land cover map.The land cover classification yielded 5 classes,overall accuracy of 83.5%and kappa statistic of 0.79,which conforms to the acceptable standards of land cover mapping. This qualifies its application in environmental decision-making and manifests the utility of geospatial techniques in mapping land resources.     

MTSAT-2静止气象卫星中国区域雪盖监测

利用MTSAT-2静止气象卫星数据开展了中国区域的雪盖监测研究,结合MODIS雪盖产品及站点雪深观测数据对判识结果进行对比分析和验证。首先,根据MTSAT-2静止气象卫星数据特点,进行角度效应校正及多时相数据合成,以减少云对图像的影响;其次,根据多个雪盖判识因子建立中国区域雪盖判识算法;最后,对比分析2011年1月份MTSAT-2和MODIS雪盖判识结果,并使用站点观测数据进行精度验证。研究表明:(1)MTSAT-2雪盖判识受云影响比例约30%,MODIS雪盖产品受云影响比例约60%,MTSAT-2去云效果明显。(2)无云情况下,MTSAT-2雪盖判识和MODIS雪盖产品判识精度均高于92%;有云覆盖时,MTSAT-2判识精度约65%,优于MODIS雪盖产品35%的判识精度。(3)MTSAT-2静止气象卫星在保持高积雪判识精度的前提下,可以更有效减少云对雪盖判识影响,实时获取更多地表真实信息。该研究对中国区域雪盖信息准确监测、气候变化研究以及防灾减灾等具有重要意义。     

Fusion of HJ1B and ALOS PALSAR data for land cover classification using machine learning methods

Image classification from remote sensing is becoming increasingly urgent for monitoring environmental changes. Exploring effective algorithms to increase classification accuracy is critical. This paper explores the use of multispectral HJ1B and ALOS (Advanced Land Observing Satellite) PALSAR L-band (Phased Array type L-band Synthetic Aperture Radar) for land cover classification using learning-based algorithms. Pixel-based and object-based image analysis approaches for classifying HJ1B data and the HJ1B and ALOS/PALSAR fused-images were compared using two machine learning algorithms, support vector machine (SVM) and random forest (RF), to test which algorithm can achieve the best classification accuracy in arid and semiarid regions. The overall accuracies of the pixel-based (Fused data: 79.0%; HJ1B data: 81.46%) and object-based classifications (Fused data: 80.0%; HJ1B data: 76.9%) were relatively close when using the SVM classifier. The pixel-based classification achieved a high overall accuracy (85.5%) using the RF algorithm for classifying the fused data, whereas the RF classifier using the object-based image analysis produced a lower overall accuracy (70.2%). The study demonstrates that the pixel-based classification utilized fewer variables and performed relatively better than the object-based classification using HJ1B imagery and the fused data. Generally, the integration of the HJ1B and ALOS/PALSAR imagery can improve the overall accuracy of 5.7% using the pixel-based image analysis and RF classifier.     

GEE环境下联合Sentinel主被动遥感数据的国家公园土地覆盖分类

国家公园的土地覆盖分类对于掌握自然资源现状、查明存在的生态安全威胁并快速应对具有基础性数据支撑作用。基于谷歌地球引擎（Google Earth Engine,GEE）平台,结合哨兵（Sentinel）主被动遥感数据及其导出的光谱指数、纹理特征和地形特征,分别采用基于像元的随机森林（random forest,RF）算法和面向对象的简单非迭代聚类（simple noniterative clustering,SNIC）+RF算法实现了钱江源国家公园异质性景观的土地覆盖（耕地、森林、草地、水体、人造地表和裸地）分类。地面实验表明,在多种输入数据组合中,基于像元和面向对象方法分类获得的最高总体精度分别为92.37%和93.98%。合成孔径雷达（synthetic aperture radar,SAR）数据的纳入能够提高基于像元方法的分类精度,但在面向对象方法中未能体现精度提升效果。通过SNIC+RF算法生成的土地覆盖分类图完整性更好,所需特征数量较少,并且算法能够在GEE环境下快速执行,适用于国家公园管理实践。     

Quantifying deforestation in the Brazilian Amazon using Advanced Land Observing Satellite Phased Array L-band Synthetic Aperture Radar (ALOS PALSAR) and Shuttle Imaging Radar (SIR)-C data

The study examined the capability of dual-polarization SAR data for forest cover mapping and change assessment in the Brazilian Amazon Forest regions. Shuttle Imaging Radar (SIR)-C and Advanced Land Observing Satellite Phased Array L-band Synthetic Aperture Radar (ALOS PALSAR) data were analysed to map and quantify deforestation. The images were classified using hybrid classifier, where each land cover was grouped in various spectral sub-classes interpreted on the imagery and later merged together to generate the desired land cover classes. The classification accuracy for forest was reasonably high (>90%). The technique applied in this study can be extended for operational mapping and monitoring of deforestation in the tropics, particularly for those regions which are often covered by cloud.     

Land cover dynamics monitoring with Landsat data in Kunming,China: a cost-effective sampling and modelling scheme using Google Earth imagery and random forests

Changes in forest composition impact ecological services, and are considered important factors driving global climate change. A hybrid sampling method along with a modelling approach to map current and past land cover in Kunming, China is reported. MODIS land cover (2001–2011) data-sets were used to detect pixels with no apparent change. Around 3000 ‘no change points’ were systematically selected and sampled using Google Earth’s high-resolution imagery. Thirty-five per cent of these points were verified and used for training and validation. We used Random forests to classify multi-temporal Landsat imagery. Results show that forest cover has had a net decrease of 14385?ha (1.3% of forest area), which was primary converted to shrublands (11%), urban and barren land (2.7%) and agriculture (2.5%). Our validation indicates an overall accuracy (Kappa) of 82%. Our methodology can be used to consistently map the dynamics of land cover change in similar areas with minimum costs.