Evaluating the influences of harvesting activity and eutrophication on loss of aquatic vegetations in Taihu Lake,China

A rapid degradation of aquatic vegetations in Taihu Lake has roused a wide attention in recent years. Giving large-scale harvesting activity on aquatic vegetation since 2012, whether water eutrophication or the human harvest activity induced the degradation remains controversial and unclear. In this study, based on Landsat and HJ-CCD data acquired from 1984 to 2016 and a 12-year field observation (2005–2016) of water quality, a method was proposed to quantitatively assess impacts of harvesting activity and water quality change on degradations of both floating-leaved aquatic vegetation (FAV) and submerged aquatic vegetation (SAV) in Taihu Lake. First, areas of FAV and SAV covers from 1984 to 2016 in Taihu Lake were mapped using the satellite data, and then the mapped areas were modified to those on a reference date by using phenological curves of FAV and SAV covers. Next, correlations between water quality data and FAV and SAV covers were analyzed by using Pearson correlation analysis based on the data before implementing the human harvesting activity (i.e., before 2012), and multiple general linear models were established based on the selected water quality variables with p-value <0.01 for estimating covers of FAV and SAV from 2012 to 2016. Finally, based on the predicted areas of FAV and SAV covers by the models and the modified areas mapped from satellite data, the influences of water eutrophication and the human harvesting activity on the degradation of FAV and SAV covers were quantitatively assessed. The results indicated that (1) FAV cover exhibited a significant increase from 1984 to 2011 and then a rapid decrease, while SAV cover increased significantly before 2003 and then obviously declined; (2) water level (WL) and total nitrogen (TN) showed significantly negative correlations with FAV and SAV covers, while secchi disk depth (SDD) and SDD/WL had significantly positive correlations with FAV and SAV covers; (3) the human harvesting activity made a major contribution to the loss of FAV cover, and the degradation of SAV cover was mainly due to an increased lake eutrophication and deteriorated underwater light environment. The findings derived from this study could offer a guidance for Taihu Lake ecological restoration and effective management.     

A soft-classification-based chlorophyll-a estimation method using MERIS data in the highly turbid and eutrophic Taihu Lake

Soft-classification-based methods for estimating chlorophyll-a concentration (C_chla) by satellite remote sensing have shown great potential in turbid coastal and inland waters. However, one of the most important water color sensors, the MEdium Resolution Imaging Spectrometer (MERIS), has not been applied to the study of turbid or eutrophic lakes. In this study, we developed a new soft-classification-based C_chla estimation method using MERIS data for the highly turbid and eutrophic Taihu Lake. We first developed a decision tree to classify Taihu Lake into three optical water types (OWTs) using MERIS reflectance data, which were quasi-synchronous (±3 h) with in situ measured C_chla data from 91 sample stations. Secondly, we used MERIS reflectance and in situ measured C_chla data in each OWT to calibrate the optimal C_chla estimation model for each OWT. We then developed a soft-classification-based C_chla estimation method, which blends the C_chla estimation results in each OWT by a weighted average, where the weight for each MERIS spectra in each OWT is the reciprocal value of the spectral angle distance between the MERIS spectra and the centroid spectra of the OWT. Finally, the soft-classification based C_chla estimation algorithm was validated and compared with no-classification and hard-classification-based methods by the leave-one-out cross-validation (LOOCV) method. The soft-classification-based method exhibited the best performance, with a correlation coefficient (R²), average relative error (ARE), and root-mean-square error (RMSE) of 0.81, 33.8%, and 7.0 μg/L, respectively. Furthermore, the soft-classification-based method displayed smooth values at the edges of OWT boundaries, which resolved the main problem with the hard-classification-based method. The seasonal and annual variations of C_chla were computed in Taihu Lake from 2003 to 2011, and agreed with the results of previous studies, further indicating the stability of the algorithm. We therefore propose that the soft-classification-based method can be effectively used in Taihu Lake, and that it has the potential for use in other optically-similar turbid and eutrophic lakes, and using spectrally-similar satellite sensors.     

基于光谱分类的太湖水体后向散射研究

由于时空变化而产生的水体后向散射系数参数化差异一直是影响水质参数遥感定量反演精度的一个重要因素。在对太湖遥感反射率光谱进行分类的基础上,针对影响太湖水体水色的不同主导因子,把太湖水体分为3种类型,分别利用半分析方法和光学闭合原理对后向散射系数进行模拟,在此基础上研究其光学特性及其与水体组分浓度的关系,最后针对3种不同主导类型的水体分别建立了后向散射系数参数化模型。将后向散射特性在不同时间和空间上的差异转化为水体不同主导因子在生物-光学上的差异,从而得到适用于太湖不同湖区及不同季节的后向散射系数参数化模型,为利用分析方法对太湖水质参数进行更为精确的遥感反演提供了基础。     

Individual tree crown approach for predicting site index in boreal forests using airborne laser scanning and hyperspectral data

Site productivity is essential information for sustainable forest management and site index (SI) is the most common quantitative measure of it. The SI is usually determined for individual tree species based on tree height and the age of the 100 largest trees per hectare according to stem diameter. The present study aimed to demonstrate and validate a methodology for the determination of SI using remotely sensed data, in particular fused airborne laser scanning (ALS) and airborne hyperspectral data in a forest site in Norway. The applied approach was based on individual tree crown (ITC) delineation: tree species, tree height, diameter at breast height (DBH), and age were modelled and predicted at ITC level using 10-fold cross validation. Four dominant ITCs per 400 m² plot were selected as input to predict SI at plot level for Norway spruce (Picea abies (L.) Karst.) and Scots pine (Pinus sylvestris L.). We applied an experimental setup with different subsets of dominant ITCs with different combinations of attributes (predicted or field-derived) for SI predictions. The results revealed that the selection of the dominant ITCs based on the largest DBH independent of tree species, predicted the SI with similar accuracy as ITCs matched with field-derived dominant trees (RMSE: 27.6% vs 23.3%). The SI accuracies were at the same level when dominant species were determined from the remotely sensed or field data (RMSE: 27.6% vs 27.8%). However, when the predicted tree age was used the SI accuracy decreased compared to field-derived age (RMSE: 27.6% vs 7.6%). In general, SI was overpredicted for both tree species in the mature forest, while there was an underprediction in the young forest. In conclusion, the proposed approach for SI determination based on ITC delineation and a combination of ALS and hyperspectral data is an efficient and stable procedure, which has the potential to predict SI in forest areas at various spatial scales and additionally to improve existing SI maps in Norway.     

Mediterranean forest species mapping using classification of Hyperion imagery

Regional operational forest species mapping is an active research topic that aims to provide the systematic and updatable information necessary for understanding and monitoring the rapidly changing forest environment. In this study, we investigated the potential of satellite hyperspectral imagery in regional forest species mapping by employing a pixel-based and an object-based nearest neighbour classifier in two different Mediterranean study areas. The overall thematic accuracy of the produced maps was assessed using reference data collected in the field and ranged between 0.72 and 0.83. No approach was found to be superior for the study areas. The McNemar test showed no statistically significant difference at the 95% confidence level in the classification accuracies achieved by the two approaches. Both pixel- and object-based approaches provide useful maps, suggesting that regional forest species mapping from space has much potential.     

Developing a semi-analytical algorithm to estimate particulate organic carbon (POC) levels in inland eutrophic turbid water based on MERIS images: A case study of Lake Taihu

Particulate organic carbon (POC) plays an important role in the carbon cycle in water due to its biological pump process. In the open ocean, algorithms can accurately estimate the surface POC concentration. However, no suitable POC-estimation algorithm based on MERIS bands is available for inland turbid eutrophic water. A total of 228 field samples were collected from Lake Taihu in different seasons between 2013 and 2015. At each site, the optical parameters and water quality were analyzed. Using in situ data, it was found that POC-estimation algorithms developed for the open ocean and coastal waters using remote sensing reflectance were not suitable for inland turbid eutrophic water. The organic suspended matter (OSM) concentration was found to be the best indicator of the POC concentration, and POC has an exponential relationship with the OSM concentration. Through an analysis of the POC concentration and optical parameters, it was found that the absorption peak of total suspended matter (TSM) at 665 nm was the optimum parameter to estimate POC. As a result, MERIS band 7, MERIS band 10 and MERIS band 12 were used to derive the absorption coefficient of TSM at 665 nm, and then, a semi-analytical algorithm was used to estimate the POC concentration for inland turbid eutrophic water. An accuracy assessment showed that the developed semi-analytical algorithm could be successfully applied with a MAPE of 31.82% and RMSE of 2.68 mg/L. The developed algorithm was successfully applied to a MERIS image, and two full-resolution MERIS images, acquired on August 13, 2010, and December 7, 2010, were used to map the POC spatial distribution in Lake Taihu in summer and winter.     

结合多分类器的遥感数据专题分类方法研究

采用标准的多分类器结合方法进行遥感图像的分类研究。首先介绍了标准的多分类器结合的算法,然后以Landsat-TM多光谱遥感数据的土地覆被分类为例,分别给出了抽象级上相同训练特征的多分类器结合、抽象级上不同训练特征的多分类器结合和测量级上的多分类器结合进行土地覆被分类的方法,并进行了实例研究。参与分类器结合的单个分类器包括最大似然分类器,最小距离分类器,马氏距离分类器,K-NN分类器,多层感知器神经网络分类器。分类器的分类精度用总体精度、用户精度、生产者精度、kappa系数和条件kappa系数评价。结果表明,每一种多分类器结合的分类方法都能够比较显著地提高总体分类精度。文章最后对不同多分类器结合方式的优缺点进行了分析。     

Evaluating techniques for mapping island vegetation from unmanned aerial vehicle (UAV) images: Pixel classification,visual interpretation and machine learning approaches

We evaluate three approaches to mapping vegetation using images collected by an unmanned aerial vehicle (UAV) to monitor rehabilitation activities in the Five Islands Nature Reserve, Wollongong (Australia). Between April 2017 and July 2018, four aerial surveys of Big Island were undertaken to map changes to island vegetation following helicopter herbicide sprays to eradicate weeds, including the creeper Coastal Morning Glory (Ipomoea cairica) and Kikuyu Grass (Cenchrus clandestinus). The spraying was followed by a large scale planting campaign to introduce native plants, such as tussocks of Spiny-headed Mat-rush (Lomandra longifolia). Three approaches to mapping vegetation were evaluated, including: (i) a pixel-based image classification algorithm applied to the composite spectral wavebands of the images collected, (ii) manual digitisation of vegetation directly from images based on visual interpretation, and (iii) the application of a machine learning algorithm, LeNet, based on a deep learning convolutional neural network (CNN) for detecting planted Lomandra tussocks. The uncertainty of each approach was assessed via comparison against an independently collected field dataset. Each of the vegetation mapping approaches had a comparable accuracy; for a selected weed management and planting area, the overall accuracies were 82 %, 91 % and 85 % respectively for the pixel based image classification, the visual interpretation / digitisation and the CNN machine learning algorithm. At the scale of the whole island, statistically significant differences in the performance of the three approaches to mapping Lomandra plants were detected via ANOVA. The manual digitisation took a longer time to perform than others. The three approaches resulted in markedly different vegetation maps characterised by different digital data formats, which offered fundamentally different types of information on vegetation character. We draw attention to the need to consider how different digital map products will be used for vegetation management (e.g. monitoring the health individual species or a broader profile of the community). Where individual plants are to be monitored over time, a feature-based approach that represents plants as vector points is appropriate. The CNN approach emerged as a promising technique in this regard as it leveraged spatial information from the UAV images within the architecture of the learning framework by enforcing a local connectivity pattern between neurons of adjacent layers to incorporate the spatial relationships between features that comprised the shape of the Lomandra tussocks detected.     

Tree species classification using UAS-based digital aerial photogrammetry point clouds and multispectral imageries in subtropical natural forests

Tree species composition of forest stand is an important indicator of forest inventory attributes for assessing ecosystem health, understanding successional processes, and digitally displaying forest biodiversity. In this study, we acquired high spatial resolution multispectral and RGB imagery over a subtropical natural forest in southwest China using a fixed-wing UAV system. Digital aerial photogrammetric (DAP) technique was used to generate multi-spectral and RGB derived point clouds, upon which individual tree crown (ITC) delineation algorithms and a machine learning classifier were used to identify dominant tree species. To do so, the structure-from-motion method was used to generate RGB imagery-based DAP point clouds. Then, three ITC delineation algorithms (i.e., point cloud segmentation (PCS), image-based multiresolution segmentation (IMRS), and advanced multiresolution segmentation (AMRS)) were used and assessed for ITC detection. Finally, tree-level metrics (i.e., multispectral, texture and point cloud metrics) were used as metrics in the random forest classifier used to classify eight dominant tree species. Results indicated that the accuracy of the AMRS ITC segmentation was highest (F₁-score = 82.5 %), followed by the segmentation using PCS (F₁-score = 79.6 %), the IMRS exhibited the lowest accuracy (F₁-score = 78.6 %); forest types classification (coniferous and deciduous) had a higher accuracy than the classification of all eight tree species, and the combination of spectral, texture and structural metrics had the highest classification accuracy (overall accuracy = 80.20 %). In the classification of both eight tree species and two forest types, the classification accuracies were lowest when only using spectral metrics, indicated that the texture metrics and point cloud structural metrics had a positive impact on the classification (the overall accuracy and kappa accuracy increased by 1.49–4.46 % and 2.86–6.84 %, respectively).     

鄱阳湖富营养化高光谱遥感监测模型初探

基于对光谱反射率与水质参数的相关分析,分别选取特征波长建立水质参数高光谱估测模型。结合修正营养状态指数,对湖泊的富营养化程度进行了监测和评价。结果表明:①总氮、总磷含量和透明度值的高光谱估测模型效果较理想;②单项指数评价水体富营养化水平其结果存在较大差异,综合考虑多个指标,计算营养指数的平均值,可以对富营养化程度进行正确的评价;③由于悬浮物浓度变化较大,掩盖了水体的叶绿素a信息,以致叶绿素a估测模型不具有通用性,为了完善叶绿素a浓度估测模型需要获得大范围、多季节的光谱数据,以便建立更有代表性和通用性的模型;④评价结果显示,鄱阳湖呈现轻度到中度富营养化状态,需要采取有力的保护措施防止进一步恶化。     

Classification of vegetation in an open landscape using full-waveform airborne laser scanner data

Airborne laser scanning (ALS) is increasingly being used for the mapping of vegetation, although the focus so far has been on woody vegetation, and ALS data have only rarely been used for the classification of grassland vegetation. In this study, we classified the vegetation of an open alkali landscape, characterized by two Natura 2000 habitat types: Pannonic salt steppes and salt marshes and Pannonic loess steppic grasslands. We generated 18 variables from an ALS dataset collected in the growing (leaf-on) season. Elevation is a key factor determining the patterns of vegetation types in the landscape, and hence 3 additional variables were based on a digital terrain model (DTM) generated from an ALS dataset collected in the dormant (leaf-off) season. We classified the vegetation into 24 classes based on these 21 variables, at a pixel size of 1 m. Two groups of variables with and without the DTM-based variables were used in a Random Forest classifier, to estimate the influence of elevation, on the accuracy of the classification. The resulting classes at Level 4, based on associations, were aggregated at three levels — Level 3 (11 classes), Level 2 (8 classes) and Level 1 (5 classes) — based on species pool, site conditions and structure, and the accuracies were assessed. The classes were also aggregated based on Natura 2000 habitat types to assess the accuracy of the classification, and its usefulness for the monitoring of habitat quality. The vegetation could be classified into dry grasslands, wetlands, weeds, woody species and man-made features, at Level 1, with an accuracy of 0.79 (Cohen’s kappa coefficient, κ). The accuracies at Levels 2–4 and the classification based on the Natura 2000 habitat types were κ: 0.76, 0.61, 0.51 and 0.69, respectively. Levels 1 and 2 provide suitable information for nature conservationists and land managers, while Levels 3 and 4 are especially useful for ecologists, geologists and soil scientists as they provide high resolution data on species distribution, vegetation patterns, soil properties and on their correlations. Including the DTM-based variables increased the accuracy (κ) from 0.73 to 0.79 for Level 1. These findings show that the structural and spectral attributes of ALS echoes can be used for the classification of open landscapes, especially those where vegetation is influenced by elevation, such as coastal salt marshes, sand dunes, karst or alluvial areas; in these cases, ALS has a distinct advantage over other remotely sensed data.     

Fuzzy Classification for Mapping Invasive Species from Multispectral Imagery

Vegetation maps are essential tools for planning and evaluation in nature conservation. To a large extend, management objectives can be defined in terms of vegetation attributes. Vegetation maps are frequently used in conservation planning and evaluation. Nowadays, remote sensing is one of the most important sources of vegetation cover classifications at different scales. In this paper, the usefulness of moderate resolution images for invasive species Cirsium arvense and Stachys byzanthina mapping at local scale is evaluated. A fuzzy classification approach is tested for improved discrimination of invasive species. The study was carried out in Vazroud rangelands located in the Mazandaran province of Iran. In this study among the analysed Z-score for uncertainty map creation is found that 0.9, 1.0 for TM image and 1.1 for IRS image in normalized are the best based on known attributes of the study area.     

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.     

Geospatial method for computing supplemental multi-decadal US coastal land use and land cover classification products,using Landsat data and C-CAP products

This paper discusses the development and implementation of a method that can be used with multi-decadal Landsat data for computing general coastal US land use and land cover (LULC) maps consisting of seven classes. With Mobile Bay, Alabama as the study region, the method that was applied to derive LULC products for nine dates across a 34-year time span. Classifications were computed and refined using decision rules in conjunction with unsupervised classification of Landsat data and Coastal Change and Analysis Program value-added products. Each classification’s overall accuracy was assessed by comparing stratified random locations to available high spatial resolution satellite and aerial imagery, field survey data and raw Landsat RGBs. Overall classification accuracies ranged from 83 to 91% with overall κ statistics ranging from 0.78 to 0.89. Accurate classifications were computed for all nine dates, yielding effective results regardless of season and Landsat sensor. This classification method provided useful map inputs for computing LULC change products.     

A comprehensive but efficient framework of proposing and validating feature parameters from airborne LiDAR data for tree species classification

Tree species information is crucial for digital forestry, and efficient techniques for classifying tree species are extensively demanded. To this end, airborne light detection and ranging (LiDAR) has been introduced. However, the literature review suggests that most of the previous airborne LiDAR-based studies were only based on limited kinds of tree signatures. To address this gap, this study proposed developing a novel modular framework for LiDAR-based tree species classification, by deriving feature parameters in a systematic way. Specifically, feature parameters of point-distribution (PD), laser pulse intensity (IN), crown-internal (CI) and tree-external (TE) structures were proposed and derived. With a support-vector-machine (SVM) classifier used, the classifications were conducted in a leave-one-out-for-cross-validation (LOOCV) mode. Based on the samples of four typical boreal tree species, i.e., Picea abies, Pinus sylvestris, Populus tremula and Quercus robur, tests showed that the accuracies of the classifications based on the acquired PD-, IN-, CI- and TE-categorized feature parameters as well as the integration of their individual optimal parameters are 65.00%, 80.00%, 82.50%, 85.00% and 92.50%, respectively. These results indicate that the procedures proposed in this study can be used as a comprehensive but efficient framework of proposing and validating feature parameters from airborne LiDAR data for tree species classification.     

基于多尺度特征融合和支持向量机的高分辨率遥感影像分类

相对传统的中低分辨率遥感数据而言,高空间分辨率遥感影像同一地物内部丰富的细节得到表征,空间信息更加丰富,地物的尺寸、形状以及相邻地物的关系得到更好的反映,但其光谱统计特性不如中低分辨率影像稳定,类内光谱差异较大,而传统分类方法仅依据像元的光谱值,因此在高分辨率影像分类中,传统方法往往不能获得好的结果。在此背景下,提出了一种多尺度空间特征融合的分类方法,旨在利用不同尺度的空间邻域特征弥补传统方法的不足。其基本过程是：首先针对不同尺度特点,用小波变换压缩空间邻域特征,并结合支持向量机得到不同尺度下的分类结果,然后根据尺度选择因子为每个像元选择最佳的类别。文中QuickBird和IKONOS影像实验证明该算法能有效提高高分辨率影像解译的精度。     

Employing airborne multispectral digital imagery to map Brazilian pepper infestation in South Texas

A study was conducted in south Texas to determine the feasibility of using airborne multispectral digital imagery for differentiating the invasive plant Brazilian pepper (Schinus terebinthifolius) from other cover types. Imagery obtained in the visible, near-infrared, and mid-infrared regions of the light spectrum and a supervised classification approach were employed to develop thematic maps of two areas infested with Brazilian pepper. Map accuracies ranged from 84.2 to 100% for the Brazilian pepper class. Findings support using airborne multispectral digital imagery as a tool for separating Brazilian pepper from associated land cover types and further encourage exploration of airborne multispectral digital imagery and image processing techniques for developing maps of Brazilian pepper infestation in Texas and abroad.     

Tracing high time-resolution fluctuations in dissolved organic carbon using satellite and buoy observations: Case study in Lake Taihu,China

Field measurements of dissolved organic carbon (DOC) concentration and remote-sensing reflectance were conducted to develop a regional, empirical red-blue algorithm to retrieve surface DOC from Geostationary Ocean Color Imager (GOCI) data for Lake Taihu, China. The auxiliary data (in-situ observations of the optical properties and water quality, buoy measurements of hydrodynamic data and water chemical parameters) were used to investigate the spatial and temporal variations in DOC. GOCI was shown to be capable of successfully obtaining hourly variations in DOC, with a root mean square error percentage (RMSP) of 17.29% (RMSE = 0.69 mg/L) for the match-up data. The GOCI-derived DOC in Lake Taihu confirms that the highest DOC concentration is in northwest Lake Taihu, followed by Meiliang Bay, Gonghu Bay and northeast Lake Taihu. Hourly DOC variation is significant and presents a different trend for each lake segment due to the variety of influencing factors. Discharge of DOC from surrounding rivers is an important factor to the variation of DOC in northeast Lake Taihu. However, organic products of algae will be the primary contributor to DOC when algal bloom occurred. During the period of algal bloom, high DOC levels in Lake Taihu can lead to hypoxia when coupled with high temperatures and low disturbance.     

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.