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.     

Comparison of large-area land cover products with national forest inventories and CORINE land cover in the European Alps

Considerable efforts have recently resulted in the development of global land cover data at large spatial scales. The main objective of this study is a comparison of different AVHRR- and MODIS-based forest and land cover products at the scale of the European Alps: a large natural ecosystem that is exposed to both natural environmental threats and human impacts and exploitation. In a first test, the accuracy of land cover products in predicting the overall amount of forest across national boundaries was assessed using national forest inventory statistics. Both variants of forest class combinations resulted in a general overestimation of the forest area. The IGBP 2.0 cover performed best with an overall mean absolute error of 13% and a bias of 0%. In a second test, large-area land cover products were tested for accuracy in predicting 13 aggregated land cover types in a spatially explicit manner using CORINE land cover as reference dataset. Due to data inconsistencies, partly insufficient spatial resolution, steep terrain and land use heterogeneity of the European Alps, only partly satisfactory results were obtained.     

Area-based and location-based validation of classified image objects

Geographic object-based image analysis (GEOBIA) produces results that have both thematic and geometric properties. Classified objects not only belong to particular classes but also have spatial properties such as location and shape. Therefore, any accuracy assessment where quantification of area is required must (but often does not) take into account both thematic and geometric properties of the classified objects. By using location-based and area-based measures to compare classified objects to corresponding reference objects, accuracy information for both thematic and geometric assessment is available. Our methods provide location-based and area-based measures with application to both a single-class feature detection and a multi-class object-based land cover analysis. In each case the classification was compared to a GIS layer of associated reference data using randomly selected sample areas. Error is able to be pin-pointed spatially on per-object, per class and per-sample area bases although there is no indication whether the errors exist in the classification product or the reference data. This work showcases the utility of the methods for assessing the accuracy of GEOBIA derived classifications provided the reference data is accurate and of comparable scale.     

土地覆盖变化信息自适应抽样策略及其精度评估

提出了一种面向土地覆盖变化信息局域精度评估的自适应型抽样策略。结合待研究地图的土地覆盖变化信息局部特征（如土地覆盖变化类别、斑块大小、异质性和优势度）,探讨与土地覆盖变化信息精度显著相关的协变量,以预测精度的标准误差作为判断标准,识别需要提高精度预测结果可靠性的区域,以自适应地和逐步定位的方式进行样本采集。基于武汉地区的精度评价结果,自适应的抽取增加100个训练样本使得预测精度的确定系数提高了50.66%,而简单随机抽取的增加样本使得预测精度的确定系数提高了17.22%。试验表明,自适应型抽样策略能显著提高土地覆盖变化信息局域精度预测的抽样效益,减少预测精度的不确定性。模型选择的结果表明,土地覆盖变化类别和优势度指数是最优的协变量组合。     

Urban land cover thematic disaggregation,employing datasets from multiple sources and RandomForests modeling

Urban land cover mapping has lately attracted a vast amount of attention as it closely relates to a broad scope of scientific and management applications. Late methodological and technological advancements facilitate the development of datasets with improved accuracy. However, thematic resolution of urban land cover has received much less attention so far, a fact that hampers the produced datasets utility. This paper seeks to provide insights towards the improvement of thematic resolution of urban land cover classification. We integrate existing, readily available and with acceptable accuracies datasets from multiple sources, with remote sensing techniques. The study site is Greece and the urban land cover is classified nationwide into five classes, using the RandomForests algorithm. Results allowed us to quantify, for the first time with a good accuracy, the proportion that is occupied by each different urban land cover class. The total area covered by urban land cover is 2280 km² (1.76% of total terrestrial area), the dominant class is discontinuous dense urban fabric (50.71% of urban land cover) and the least occurring class is discontinuous very low density urban fabric (2.06% of urban land cover).     

Comparison and relative quality assessment of the GLC2000, GLOBCOVER,MODIS and ECOCLIMAP land cover data sets at the African continental scale

Land cover dynamics at the African continental scale is of great importance for global change studies. Actually, four satellite-derived land cover maps of Africa now available, e.g. ECOCLIMAP, GLC2000, MODIS and GLOBCOVER, are based on images acquired in the 2000s. This study aims at stressing the compliances and the discrepancies between these four land cover classifications systems. Each of them used different mapping initiatives and relies on different mapping standards, which supports the present investigation. In order to do a relative comparison of the four maps, a preamble was to reconcile their thematic legends into more aggregated categories after a projection into the same spatial resolution. Results show that the agreement between the four land cover products is between 56 and 69%. While all these land cover datasets show a reasonable agreement in terms of surface types and spatial distribution patterns, mapping of heterogeneous landscapes in the four products is not very successful. Land cover products based on remote sensing imagery can indeed significantly be improved by using smarter algorithms, better timing of image acquisition, improved class definitions. Either will help to improve the accuracy of future land cover maps at the African continental scale. Data producers may use the areas of spatial agreement for training area selection while users might need to verify the information in the areas of disagreement using additional data sources.     

Land cover mapping in the Upper Shire River catchment in Malawi using Landsat satellite data

Land cover mapping forms a reference base for resource managers in their decision-making processes to guide rural/urban growth and management of natural resources. The aim of this study was to map land cover dynamics within the Upper Shire River catchment, Malawi. The article promotes innovation of automated land cover mapping based on remote sensing information to generate data products that are both appropriate to, and usable within different scientific applications in developing countries such as Malawi. To determine land cover dynamics, 1989 and 2002 Landsat images were used. Image bands were combined in transformations and indices with physical meaning; together with spatial data, to enhance classification accuracy. A maximum likelihood classification for each image was computed for identification of land cover variables. The results showed that the combination of spatial and digital data enhanced classification accuracy and the ability to categorise land cover features, which are relatively inhomogeneous.     

中分辨率遥感图像土地利用与覆被分类的方法及精度评价

利用TM、SPOT及CBERS-1等中分辨率卫星图像,对土地覆被的专家系统分类方法、居民地的决策树提取方法以及水体的迭代混合提取方法进行了试验,其总体精度达到87.89%,与常用的监督分类方法相比精度可提高7.86%.专家系统分类的结果叠合居民地、水体等易于混分专题信息,可以形成精度较高的土地利用与覆被分类结果。     

Application of multidate satellite imagery for land use planning and management in the drought prone areas of Karnataka

Based on visual interpretation of Multidate Landsat Imagery, the spatial distribution of land use/land cover over 45,000 sq.km, spread over the three drought prone districts of Bijapur, Belgaum and Dharwar in NW Karnataka, has been mapped. The land use/land cover is classified into five Level-I and twelve Level-II classes. The pattern of change in land use/land cover during the period October, 1980 and January, 1982 has been one of decline in all the land use classes (except for agricultural use, which is more due to seasonal change) which highlight the land use/land cover changes in the drought prone area. An optimum land use plan requires that all the cropland should be zoned for cultivation while marginal lands like scrub land and mixed barren land (from the view point of cultivation) should be zoned for pasture/grazing and animal husbandary. There is a case for flexibility here, depending upon the pressure of population on land. The accuracy level of the ‘information base’ of the thematic map(s) obtained from Landsat imagery is 94 percent.     

GIDS空间插值法估算云下地表温度

选用陆面区域温度最佳空间插值法—梯度距离平方反比法(GIDS),为近似估算云下地表温度提供了可能。实验选取暖季南京江宁地区ETM+影像和ASTERGDEMV1高程数据,探索分析GIDS估算云下地表温度的可行性和可信性。对14种空间大小云覆盖区实验研究表明:利用GIDS插值估算云下地表温度具有可行性,且估算误差随着云覆盖区范围增大而增加,其最大MAE<0.9℃,最大RMSE<1.2℃,并在云覆盖区小于100×100像元时,最大MAE<0.8℃、RMSE<1℃;插值精度与最近邻无云像元典型代表性、区域内空间复杂度和地表覆盖类型均有关,存在不稳定性和动态性;云下NDVI均方差与MAE、RMSE有着一致变化趋势,借助NDVI均方差指示云下地表空间异质性及NDVI–LST负相关性,可对插值结果进行可信性评判,以避免插值结果盲目应用,推进和提升地表温度产品应用价值。     

国家基本资源与环境遥感数据库集成中的面积汇总技术

主要论述了在遥感和地理信息系统技术支持下的自然资源宏观调查中数据汇总各主要方面的技术问题。对于以卫星影像为主要信息源进行的资源调查工作 ,文中分析了结果数据中的误差来源并详细说明了其面积平差技术及面积校正方案的抽样原理和方法。     

国家基本资源与环境爱感数据库集成中的面积汇总技术

主要论述了在遥感和地理信息系统技术支持下的自然资源宏观调查中数据汇总各主要方向的技术问题。对于以卫星影像为主要信息源进行的资源调查工作,文中分析了结果数据中的误差来源并详细说明了其面积平差技术及面积校正方案的抽样原理和方法．     

Increasing the detail of European land use/cover data by combining heterogeneous data sets

ABSTRACT

Data on land use and land cover (LULC) are a vital input for policy-relevant research, such as modelling of the human population, socioeconomic activities, transportation, environment, and their interactions. In Europe, CORINE Land Cover has been the only data set covering the entire continent consistently, but with rather limited spatial detail. Other data sets have provided much better detail, but either have covered only a fraction of Europe (e.g. Urban Atlas) or have been thematically restricted (e.g. Copernicus High Resolution Layers). In this study, we processed and combined diverse LULC data to create a harmonised, ready-to-use map covering 41 countries. By doing so, we increased the spatial detail (from 25 to one hectare) and the thematic detail (by seven additional LULC classes) compared to the CORINE Land Cover. Importantly, we decomposed the class ‘Industrial and commercial units’ into ‘Production facilities’, ‘Commercial/service facilities’ and ‘Public facilities’ using machine learning to exploit a large database of points of interest. The overall accuracy of this thematic breakdown was 74%, despite the confusion between the production and commercial land uses, often attributable to noisy training data or mixed land uses. Lessons learnt from this exercise are discussed, and further research direction is proposed.     

对新疆塔里木河流域土地盐渍化进行专题信息提取的应用研究

对新疆塔里木河流域进行土地盐渍化专题信息提取,建立该地区土地盐渍化分类系统,提高土地盐渍化分类精度。结果表明:所采用的土地盐渍化专题信息提取方法是可行的,对于生态环境监测的土地利用/覆盖、土壤沙漠化等问题均适用。对于建立生态环境监测系统有非常实用的价值。     

Tree cover mapping based on Sentinel-2 images demonstrate high thematic accuracy in Europe

The spatial and temporal distribution of trees has a large impact on human health and the environment through contributions to important climate mechanisms as well as commercial, recreational and social activities in society. A range of tree mapping methodologies has been presented in the literature, but tree cover estimates still differ widely between the individual datasets, and comparisons of the thematic accuracy of the resulting tree maps are rather scarce. The Copernicus Sentinel-2 satellites, which were launched in 2015 and 2017, have a combination of high spatial and temporal resolution. Given that this is a new satellite, a substantial amount of research on development of tree mapping algorithms as well as accuracy assessment of said algorithms have to be done in the years to come. To contribute to this process, a tree map produced through unsupervised classification was created for six Sentinel-2 tiles. The agreement between the tree map and the corresponding national forest inventory, as a function of the band combination chosen, was analysed and the thematic accuracy was assessed for two out of the six tiles. The results show that the highest agreement between the present tree map and the national forest inventory was found for bands 2, 3, 6 and 12. The present tree map has a relative difference in tree cover between 8% and 79% compared to previous estimates, but results are characterised by large scatter. Lastly, it is shown that the overall thematic accuracy of the present map is up to 90%, with the user’s accuracy ranging from 34.85% to 92.10%, and the producer’s accuracy ranging from 23.80% to 97.60% for the various thematic classes. This demonstrates that tree maps with high thematic accuracy can be produced from Sentinel-2. In the future the thematic accuracy can be increased even more through the use of temporal averaging in the mapping procedure, which will enable an accurate estimate of the European tree cover.     

Approaches for Linking People,Place, and Environment for Human Dimensions Research

Abstract

Much of the human dimensions of environmental change research emphasize the mapping and modeling of land use and land cover patterns over space and time, and the linkages between people, place, and environment as proximate and distal forces of landscape dynamics. Spatial digital technologies, framed within a GIScience (GISc) context, figure prominently in the characterization of land use and land cover through remote sensing technologies, and in the assessment of social and demographic factors and local and regional site and situation considerations achieved through global positioning systems, data visualizations, and spatial and statistical analyses. Here, we describe some fundamental approaches for linking data across thematic domains, essential for the study of human‐environment interactions. The goal is to generate compatible data sets that extend across social, biophysical, and geographical domains so that the causes and consequences of land use and land cover dynamics might be explored within a spatially‐explicit context.     

Assessing land use/cover changes: a nationwide multidate spatial database for Mexico

A nationwide multidate GIS database was generated in order to carry out the quantification and spatial characterization of land use/cover changes (LUCC) in Mexico. Existing cartography on land use/cover at a 1:250,000 scale was revised to select compatible inputs regarding the scale, the classification scheme and the mapping method. Digital maps from three different dates (the late 1970s, 1993 and 2000) were revised, evaluated, corrected and integrated into a GIS database. In order to improve the reliability of the database, an attempt was made to assess the accuracy of the digitalisation procedure and to detect and correct unlikely changes due to thematic errors in the maps. Digital maps were overlaid in order to generate LUCC maps, transition matrices and to calculate rates of conversion. Based upon this database, rates of deforestation between 1976 and 2000 were evaluated as 0.25 and 0.76% per year for temperate and tropical forests, respectively.     

A spatial–temporal Hopfield neural network approach for super-resolution land cover mapping with multi-temporal different resolution remotely sensed images

The mixed pixel problem affects the extraction of land cover information from remotely sensed images. Super-resolution mapping (SRM) can produce land cover maps with a finer spatial resolution than the remotely sensed images, and reduce the mixed pixel problem to some extent. Traditional SRMs solely adopt a single coarse-resolution image as input. Uncertainty always exists in resultant fine-resolution land cover maps, due to the lack of information about detailed land cover spatial patterns. The development of remote sensing technology has enabled the storage of a great amount of fine spatial resolution remotely sensed images. These data can provide fine-resolution land cover spatial information and are promising in reducing the SRM uncertainty. This paper presents a spatial–temporal Hopfield neural network (STHNN) based SRM, by employing both a current coarse-resolution image and a previous fine-resolution land cover map as input. STHNN considers the spatial information, as well as the temporal information of sub-pixel pairs by distinguishing the unchanged, decreased and increased land cover fractions in each coarse-resolution pixel, and uses different rules in labeling these sub-pixels. The proposed STHNN method was tested using synthetic images with different class fraction errors and real Landsat images, by comparing with pixel-based classification method and several popular SRM methods including pixel-swapping algorithm, Hopfield neural network based method and sub-pixel land cover change mapping method. Results show that STHNN outperforms pixel-based classification method, pixel-swapping algorithm and Hopfield neural network based model in most cases. The weight parameters of different STHNN spatial constraints, temporal constraints and fraction constraint have important functions in the STHNN performance. The heterogeneity degree of the previous map and the fraction images errors affect the STHNN accuracy, and can be served as guidances of selecting the optimal STHNN weight parameters.     

基于直方变差图的土地覆盖数据集多尺度精度评价

针对目前精度评价尺度单一的问题,提出基于直方变差图的多尺度精度评价方法,分别在像元尺度和亚像元尺度进行土地覆盖数据集精度评价。在像元尺度利用驻点作为采样工具直接评价数据集精度;亚像元尺度上,则利用非严格定义的驻点和驻点直方变差图对不同面积和空间结构的优势类进行精度评价。并以浙江北部典型区域为实验区,Landsat TM/ETM+为参考数据,对UMD、IGBP DISCover、MOD12Q1-2001、GLC2000、GlobCover2009等5种大尺度土地覆盖数据集进行多尺度精度评价实验。结果表明,多尺度精度评价方法能够全面地评价土地覆盖数据集的精度,提供更加丰富的多尺度精度信息。像元尺度精度评价可在一定程度上消除由于参考数据与数据集间的空间匹配造成的误差,评价结果更加客观;亚像元尺度精度评价能有效反映亚像元尺度优势地物面积及空间结构与精度的关系。