Producer's Accuracy Research Articles

Monitoring conterminous United States (CONUS) land cover change with Web-Enabled Landsat Data (WELD)

Forest cover loss and bare ground gain from 2006 to 2010 for the conterminous United States (CONUS) were quantified at a 30m spatial resolution using Web-Enabled Landsat Data available from the USGS Center for Earth Resources Observation and Science (EROS) (http://landsat.usgs.gov/WELD.php). The approach related multi-temporal WELD metrics and expert-derived training data for forest cover loss and bare ground gain through a decision tree classification algorithm. Forest cover loss was reported at state and ecoregional scales, and the identification of core forests' absent of change was made and verified using LiDAR data from the GLAS (Geoscience Laser Altimetry System) instrument. Bare ground gain correlated with population change for large metropolitan statistical areas (MSAs) outside of desert or semi-desert environments. GoogleEarth™ time-series images were used to validate the products. Mapped forest cover loss totaled 53,084km2 and was found to be depicted conservatively, with a user's accuracy of 78% and a producer's accuracy of 68%. Excluding errors of adjacency, user's and producer's accuracies rose to 93% and 89%, respectively. Mapped bare ground gain equaled 5974km2 and nearly matched the estimated area from the reference (GoogleEarth™) classification; however, user's (42%) and producer's (49%) accuracies were much less than those of the forest cover loss product. Excluding errors of adjacency, user's and producer's accuracies rose to 62% and 75%, respectively. Compared to recent 2001–2006 USGS National Land Cover Database validation data for forest loss (82% and 30% for respective user's and producer's accuracies) and urban gain (72% and 18% for respective user's and producer's accuracies), results using a single CONUS-scale model with WELD data are promising and point to the potential for national-scale operational mapping of key land cover transitions. However, validation results highlighted limitations, some of which can be addressed by improving training data, creating a more robust image feature space, adding contemporaneous Landsat 5 data to the inputs, and modifying definition sets to account for differences in temporal and spatial observational scales. The presented land cover extent and change data are available via the official WELD website (ftp://weldftp.cr.usgs.gov/CONUS_5Y_LandCover/ftp://weldftp.cr.usgs.gov/CONUS_5Y_LandCover/).

Robust Extraction of Urban Land Cover Information From HSR Multi-Spectral and LiDAR Data

This paper focuses on the description and demonstration of a simple, but effective object-based image analysis (OBIA) approach to extract urban land cover information from high spatial resolution (HSR) multi-spectral and light detection and ranging (LiDAR) data. Particular emphasis is put on the evaluation of the proposed method with regard to its generalization capabilities across varying situations. For this purpose, the experimental setup of this work includes three urban study areas featuring different physical structures, four sets of HSR optical and LiDAR input data, as well as statistical measures to enable the assessment of classification accuracies and methodological transferability. The results of this study highlight the great potential of the developed approach for accurate, robust and large-area mapping of urban environments. User's and producer's accuracies observed for all maps are almost consistently above 80%, in many cases even above 90%. Only few larger class-specific errors occur mainly due to the simple assumptions on which the method is based. The presented feature extraction workflow can therefore be used as a template or starting point in the framework of future urban land cover mapping efforts.

Satellite based calculation of spatially distributed crop water requirements for cotton and wheat cultivation in Fergana Valley, Uzbekistan

This study focuses on the generation of reliable data for improving land and water use in Central Asia. An object-based remote sensing classification is applied and combined with the CropWat model developed by the Food and Agriculture Organization (FAO) to determine crop distribution and water requirements for irrigation of cotton and winter-wheat in Fergana Valley, Uzbekistan. The crop classification is conducted on RapidEye and Landsat data acquired before the onset of the main summer irrigation phases in July using a random forest algorithm. The ClimWat database of FAO is utilized for calculating crop water requirements (CWR) and crop irrigation requirements (CIR).Classification reveals an overall accuracy of 86.2% and exceeds a producer's (user's) accuracy of 95% (89%) for both, cotton and wheat. In 2010, cotton and winter-wheat are planted on 66.7% of the agricultural area under investigation, whereas orchard areas amount to 15.5%. The CWR modelled for winter-wheat and cotton cultivation revealed 5443m3ha−1 and 9278m3ha−1, respectively. Subtracting effective precipitation leads to CIR of 4133m3ha−1 and 8813m3ha−1. Comparisons of CWR and CIR for the area dominating crops with the total of water officially allocated for irrigation underline the pressure on the water resources in the entire Syr Darya catchment and suggest modifications of the cropping system towards more winter crops. The early season crop maps can be used for water saving as they enable modifications of water allocation plans within the different irrigation subsystems of the valley. The method for mapping spatially distributed CWR and CIR can be transferred to other irrigated areas in Central Asia and beyond.

Combining airborne laser scanning data and optical satellite data for classification of alpine vegetation

Climate change and outdated vegetation maps are among the reasons for renewed interest in mapping sensitive alpine and subalpine vegetation. Satellite data combined with elevation derivatives have been shown to be useful for mapping alpine vegetation, however, there is room for improvement.The inclusion of airborne laser scanning data metrics has not been widely investigated for alpine vegetation. This study has combined SPOT 5 satellite data, elevation derivatives, and laser data metrics for a 25km×31km study area in Abisko, Sweden. Nine detailed vegetation classes defined by height, density and species composition in addition to snow/ice, water, and bare rock were classified using a supervised Random Forest classifier. Several of the classes consisted of shrub and grass species with a maximum height of 0.4m or less. Laser data metrics were calculated from the nDSM based on a 10m×10m grid, and after variable selection, the metrics used in the classification were the 95th and 99th height percentiles, a vertical canopy density metric, the mean and standard deviation of height, a vegetation ratio based on the raw laser data point cloud with a variable height threshold (from 0.1 to 1.0m with 0.1m intervals), and standard deviation of these vegetation ratios. The satellite data used in classification was all SPOT bands plus NDVI and NDII, while the elevation derivatives consisted of elevation, slope and the Saga Wetness Index. Overall accuracy when using the combination of laser data metrics, elevation derivatives and SPOT 5 data increased by 6% as compared to classification of SPOT and elevation derivatives only, and increased by 14.2% compared to SPOT 5 data alone. The classes which benefitted most from inclusion of laser data metrics were mountain birch and alpine willow. The producer's accuracy for willow increased from 18% (SPOT alone) to 41% (SPOT+elevation derivatives) and then to 55% (SPOT+elevation derivatives+laser data) when laser data were included, with the 95th height percentile and Saga Wetness Index contributing most to willow's improved classification. Addition of laser data metrics did not increase the classification accuracy of spectrally similar dry heath (<0.3m height) and mesic heath (0.3–1.0m height), which may have been a result of laser data penetration of sparse shrub canopy or laser data processing choices. The final results show that laser data metrics combined with satellite data and elevation derivatives contributed overall to a better classification of alpine and subalpine vegetation.

An Object-Based Approach for Urban Land Cover Classification: Integrating LiDAR Height and Intensity Data

Digital surface models (DSMs) derived from light detection and ranging (LiDAR) data have been increasingly integrated with high-resolution multispectral satellite/aerial imagery for urban land cover classification. Fewer studies, however, have investigated the usefulness of LiDAR intensity in aid of urban land cover classification, particularly in highly developed urban settings. In this letter, we use an object-based classification approach to investigate whether a combination of LiDAR height and intensity data can accurately map urban land cover. We further compare the approach to a method that uses multispectral imagery as the primary data source, but LiDAR DSM as ancillary data to aid in classification. The study site is a suburban area in Baltimore County, MD. The LiDAR data were acquired in March 2005, from which DSM and two intensity layers (first and last returns), with 1-m spatial resolution were generated, respectively. Four classes were included: 1) buildings; 2) pavement; 3) trees and shrubs; and 4) grass. Our results indicated that the object-based approach provided flexible and effective means to integrate LiDAR height and intensity data for urban land cover classification. A combination of the LiDAR height and intensity data proved to be effective for urban land cover classification. The overall accuracy of the classification was 90.7%, and the overall Kappa statistics equaled 0.872, with the user's and producer's accuracies ranging from 86.8% to 93.6%. The accuracy of the results were far better than those using multispectral imagery alone, and comparable to using DSM data in combination with high-resolution multispectral satellite/aerial imagery.

A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees

We developed a multiscale object-based classification method for detecting diseased trees (Japanese Oak Wilt and Japanese Pine Wilt) in high-resolution multispectral satellite imagery. The proposed method involved (1) a hybrid intensity–hue–saturation smoothing filter-based intensity modulation (IHS-SFIM) pansharpening approach to obtain more spatially and spectrally accurate image segments; (2) synthetically oversampling the training data of the ‘Diseased tree’ class using the Synthetic Minority Over-sampling Technique (SMOTE); and (3) using a multiscale object-based image classification approach. Using the proposed method, we were able to map diseased trees in the study area with a user's accuracy of 96.6% and a producer's accuracy of 92.5%. For comparison, the diseased trees were mapped at a user's accuracy of 84.0% and a producer's accuracy of 70.1% when IHS pansharpening was used alone and a single-scale classification approach was implemented without oversampling the ‘Diseased tree’ class.

Impact of training and validation sample selection on classification accuracy and accuracy assessment when using reference polygons in object-based classification

Reference polygons are homogenous areas that aim to provide the best available assessment of ground condition that the user can identify. Delineation of such polygons provides a convenient and efficient approach for researchers to identify training and validation data for supervised classification. However, the spatial dependence of training and validation data should be taken into account when the two data sets are obtained from a common set of reference polygons. We investigate the effect on classification accuracy and the accuracy estimates derived from the validation data when training and validation data are obtained from four selection schemes. The four schemes are composed of two sampling designs (simple random and systematic) and two methods for splitting sample points between training and validation (validation points in separate polygons from training points and validation points and training points split within the same polygons). A supervised object-based classification of the study region was repeated 30 times for each selection scheme. The selection scheme did not impact classification accuracy, but estimates of overall (OA), user's (UA), and producer's (PA) accuracies produced from the validation data overestimated accuracy for the study region by about 10%. The degree of overestimation was slightly greater when the validation sample points were allowed to be in the same polygons as the training data points. These results suggest that accuracy estimates derived from splitting training and validation within a limited set of reference polygons should be regarded with suspicion. To be fully confident in the validity of the accuracy estimates, additional validation sample points selected from the region outside the reference polygons may be needed to augment the validation sample selected from the reference polygons.

Using Volunteered Data in Land Cover Map Validation: Mapping West African Forests

Accuracy assessment should be a fundamental part of a programme that maps land cover from remotely sensed imagery but this activity is often constrained by the lack of high quality ground reference data. Here, two sources of volunteered data are used to illustrate the potential of amateur or neogeographical activity in map validation. Ground based photographs acquired from an internet-based collaborative project and interpreted by a set of four further volunteers provided the reference data to support evaluation of the Globcover map's representation of tropical forest in West Africa. Although the results highlight some concerns with volunteered data, notably the low levels of inter-volunteer agreement they also show that such imperfect data may be used to derive credible estimates on accuracy from both a site and non-site specific perspective. Specifically, the estimates of the producer's accuracy of forest and of forest extent derived from the free and volunteered data using a latent class model were of comparable magnitude to those derived in a formal validation by experts; the estimate of forest extent was within 1.38-9.08% of reference estimates while the difference in estimated producer's accuracy from that derived in an authoritative assessment of map accuracy was 2.82% and 0.34% for the forest and non-forest classes respectively.

Optical and radar data integration for land use and land cover mapping in the Brazilian Amazon

This study aims to evaluate different methods of integrating optical and multipolarized radar data for land use and land cover (LULC) mapping in an agricultural frontier region in the Central Brazilian Amazon, which requires continuous monitoring due to the increasing human intervention. The evaluation is performed using different sets of fused and combined data. This article also proposes to apply the principal component (PC) technique to the multipolarized synthetic aperture radar (SAR), prior to the optical and radar data PC fusion process, aiming at the use of all available polarized information in the fusion process. Although the fused images improve the visual interpretation of the land use classes, the best results are achieved with the simple combination of the Advanced Land Observing Satellite (ALOS)/phased array L-Band SAR (PALSAR) with the LANDSAT5/Thematic Mapper (TM) images. Radar information is found to be particularly useful for improving the user accuracies (UAs) of Soybean with 40 days after seeding (an increase of about 55%), Dirty Pasture (22%), Degraded Forest and Regeneration (5%), and the producer accuracies (PAs) of Clean Pasture (39%), Fallow Agriculture (16%), Degraded Forest and Regeneration (3%), and Primary Forest (2%). Information from the HH (horizontal transmit and horizontal receive) polarization contributes more than that from HV (horizontal transmit and vertical receive) polarization to discriminate the classes, although the use of both polarizations produces results that are statistically better than those obtained with a single polarization.

Using a remotely sensed optimized Disturbance Index to detect insect defoliation in the Apostle Islands, Wisconsin, USA

The Disturbance Index (DI) proposed by Healey et al. (2005) has been used successfully to locate and monitor disturbances by various researchers and in many locations. Here, a modification of the DI is presented that adapts it to local conditions by weighting each of its input components to maximize the difference between disturbed and undisturbed forest canopy. The weights reduce the effects of background variation while emphasizing the variation caused by disturbance. The weighted DI was applied to the severe insect defoliation of 2006 in the Apostle Island National Lakeshore with promising results. A supervised maximum likelihood thematic map based on the unweighted DI was 59% accurate and one based on the weighted DI was 62%. A classification with only two classes, defoliated and not defoliated, was also more accurate when based upon the weighted DI (77% verses 69%). In nearly all instances, the user's and producer's accuracies were significantly higher for the weighted DI image, suggesting that weighting the DI to fit local conditions is a superior approach, at least for small-area studies.

Toward near real-time monitoring of forest disturbance by fusion of MODIS and Landsat data

Timely and accurate monitoring of forest disturbance is essential to help us understand how the Earth system is changing. MODIS (Moderate Resolution Imaging Spectroradiometer) imagery and subsequent MODIS products provide near-daily global coverage and have transformed the ways we study and monitor the Earth. To monitor forest disturbance, it is necessary to be able to compare observations of the same place from different times, but this is a challenging task using MODIS data as observations from different days have varying view angles and pixel sizes, and cover slightly different areas. In this paper, we propose a method to fuse MODIS and Landsat data in a way that allows for near real-time monitoring of forest disturbance. The method is based on using Landsat time-series images to predict the next MODIS image, which forms a stable basis for comparison with new MODIS acquisitions. The predicted MODIS images represent what the surface should look like assuming no disturbance, and the difference in the spectral signatures between predicted and observed MODIS images becomes the “signal” used for detecting forest disturbance. The method was able to detect subpixel forest disturbance with a producer's accuracy of 81% and a user's accuracy of 90%. Patches of forest disturbance as small as 5 to 7ha in size were detected on a daily basis. The encouraging results indicate that the presented fusion method holds promise for improving monitoring of forest disturbance in near real-time.

Tree Species Classification in Boreal Forests With Hyperspectral Data

Tree species mapping in forest areas is an important topic in forest inventory. In recent years, several studies have been carried out using different types of hyperspectral sensors under various forest conditions. The aim of this work was to evaluate the potential of two high spectral and spatial resolution hyperspectral sensors (HySpex-VNIR 1600 and HySpex-SWIR 320i), operating at different wavelengths, for tree species classification of boreal forests. To address this objective, many experiments were carried out, taking into consideration: 1) three classifiers (support vector machines (SVM), random forest (RF), and Gaussian maximum likelihood); 2) two spatial resolutions (1.5 m and 0.4 m pixel sizes); 3) two subsets of spectral bands (all and a selection); and 4) two spatial levels (pixel and tree levels). The study area is characterized by the presence of four classes 1) Norway spruce, 2) Scots pine, together with 3) scattered Birch and 4) other broadleaves. Our results showed that: 1) the HySpex VNIR 1600 sensor is effective in boreal tree species classification with kappa accuracies over 0.8 (with Pine and Spruce reaching producer's accuracies higher than 95%); 2) the role of the HySpex-SWIR 320i is limited, and its bands alone are able to properly separate only Pine and Spruce species; 3) the spatial resolution has a strong effect on the classification accuracy (an overall decrease of more than 20% between 0.4 m and 1.5 m spatial resolution); and 4) there is no significant difference between SVM or RF classifiers.

Full polarimetric PALSAR-based land cover monitoring in Cambodia for implementation of REDD policies

Forest cover monitoring plays an important role in the implementation of climate change mitigation policies such as Kyoto protocol and Reducing Emissions from Deforestation and Forest Degradation (REDD). In this study, we have monitored land cover using the PALSAR (Phased Array type L-band Synthetic Aperture Radar) full polarimetric data based on incoherent target decomposition. Supervised classification technique has been applied on Cloude–Pottier decomposition, Freeman–Durden three component, and Yamaguchi four component decomposition for accurate mapping of different types of land cover classes. Based on confusion matrix derived from the predicted and defined pixels, the evergreen and sparsely deciduous forests have shown high producer's accuracy by Freeman–Durden three component and Yamaguchi four component classifications. The overall accuracy of Maximum Likelihood Classification by Yamaguchi four component is 94.1% with 0.93 kappa coefficient as compared to the 90.3% with 0.88 kappa coefficient by Freeman–Durden three component and 89.7% with 0.88 kappa coefficient by Cloude–Pottier decomposition. High accuracy of classification in a forested area using full polarimetric PALSAR data may have been because of high penetration of L-band SAR. The content of this study could be useful for the forest cover mapping during cloudy days needed for proper implementation of REDD policies in Cambodia.

Mapping deciduous rubber plantations through integration of PALSAR and multi-temporal Landsat imagery

Due to increasing global demand for natural rubber products, rubber (Hevea brasiliensis) plantation expansion has occurred in many regions where it was originally considered unsuitable. However, accurate maps of rubber plantations are not available, which substantially constrain our understanding of the environmental and socioeconomic impacts of rubber plantation expansion. In this study we developed a simple algorithm for accurate mapping of rubber plantations in northern tropical regions, by combining a forest map derived from microwave data and unique phenological characteristics of rubber trees observed from multi-temporal Landsat imagery. Phenology of rubber trees and natural evergreen forests in Hainan Island, China, was evaluated using eighteen Landsat TM/ETM+ images between 2007 and 2012. Temporal profiles of the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Land Surface Water Index (LSWI), and near-infrared (NIR) reflectance for rubber trees and natural forest were constructed. The results showed that rubber plantations are distinguishable from natural evergreen forests in two phenological phases: 1) during the defoliation (leaf-off) phase in late February–March, vegetation index (NDVI, EVI, LSWI) values were lower in rubber plantations than in natural evergreen forests; and 2) during the foliation (new leaf emergence) phase in late March–April, rubber plantations had similar NDVI and LSWI values but higher EVI and NIR reflectance values than in natural forests. Therefore, it is possible to delineate rubber plantations within forested landscapes using one to two optical images acquired in the defoliation and/or foliation period. The mapping technique was developed and applied in the Danzhou Region of Hainan. Phased Array type L-band Synthetic Aperture Radar (PALSAR) 50-m Orthorectified Mosaic images were used to generate a forest cover map and further integrated with the phenological information of rubber plantations extracted from Landsat TM images during the foliation phase. The resultant map of rubber plantations has high accuracy (both producer's and user's accuracy is 96%). This simple and integrated algorithm has the potential to improve mapping of rubber plantations at the regional scale. This study also shows the value of time series Landsat images and emphasizes imagery selection at appropriate phenological phase for land cover classification, especially for delineating deciduous vegetation.

Cloud and cloud shadow screening across Queensland, Australia: An automated method for Landsat TM/ETM + time series

The 20+ year collection and moderate resolution of Landsat Thematic Mapper (TM) imagery and Enhanced Thematic Mapper (ETM+) imagery provide a crucial data source for analysing land surface change over time for a range of applications. In Queensland, Australia, a number of government policies, natural resource management programmes and research activities are reliant on large-area, multi-temporal land cover monitoring applications based on Landsat satellite imagery. However, clouds and associated cloud shadows frequently obstruct the view of the land surface. The restriction of analyses to cloud-free imagery will reduce the opportunities to sample the land surface and limit the analysis of trends in reflectance over time. This study presents a new automated method to screen cloud and cloud shadow and is intended for application to entire time series of Landsat imagery rather than single images processed in near- real time. The method uses a hierarchical approach and takes advantage of spectral, temporal, and contextual information. Outliers are located relative to the time series of land surface reflectance by smoothing time series information using minimum and median filters which are then used in multi-temporal image differencing. Seeded region grow and morphological dilation (pixel buffering) filters are then applied to map a larger spatial extent of the cloud/cloud shadow. Spectral and contextual rules were developed empirically using calibration and validation data derived from six Landsat WRS Path/Rows (number of images=60) with varying climatic and land surface characteristics across the state of Queensland, Australia. The validation demonstrates that cloud contaminated pixels were accurately classified with producer's, user's and overall accuracies of 98, 87 and 97%, respectively. The ability to detect cloud shadow was less accurate, in comparison, with producer's, user's and overall accuracies of 90, 62 and 97%, respectively. The pixel buffer was found to be the largest source of commission error for cloud and cloud shadow in the final classifications. However, for many applications removing additional cloud/shadow at the expense of higher commission errors may be desirable. The performance of the method was also compared with the published Fmask (Function of mask) method. This demonstrated a moderate improvement in the detection of cloud (producer's accuracies: time series 98% and Fmask 90%; and an equivalent user's accuracy of 87%), and a significant improvement in the detection of cloud shadow (producer's accuracies: time series 90% and Fmask 78%; user's accuracies: time series 62% and Fmask 50%). Importantly, the results indicate that this automated method is robust and that temporal information can improve the detection of cloud and cloud shadow, although shadow detection above cropping areas is limited. The calibration/validation of the method has been restricted to Queensland, Australia. With further development there is potential for this method or one using a similar framework to have wider application in other landscapes.

Incorporating the uncertainty of linguistic-scale reference data to assess accuracy of land-cover maps using fuzzy intervals

The reference classifications that serve as the fundamental basis of accuracy assessment of land-cover maps are subject to uncertainty. A fuzzy interval approach is proposed in which linguistic-scale labels assigned to each land-cover class at each sample observation are converted to fuzzy intervals. These fuzzy intervals are then used to produce a fuzzy confusion matrix from which fuzzy thematic accuracy measures analogous to overall, user's, and producer's accuracy are produced. An advantage of this methodology is that it employs a practical and relatively simple reference labelling protocol (the linguistic scale) that accounts for reference database uncertainty and information on the percentage of the pixel covered by a land-cover class incorporating this uncertainty in fuzzy accuracy measures, providing an analysis that is readily interpretable because of similarity to the familiar confusion matrix approach. The fuzzy accuracy measures can be defuzzified to provide simplified accuracy measures analogous to the thematic accuracy measures derived from traditional (i.e. crisp classification) confusion matrices. The proposed methodology is illustrated using a case study in which the accuracy assessment of a land-cover map for Continental Portugal derived from Medium Resolution Imaging Spectrometer (MERIS) images is made.

Mapeamento de fragmentos florestais com monodominância de aroeira a partir da classificação supervisionada de imagens Rapideye

A espécie florestal Myracrodruon urundeuva (Fr. All.) figura desde 1992 na lista de espécies da flora brasileira ameaçadas de extinção e, contudo, manifesta comportamento monodominante em algumas regiões do Estado de Minas Gerais, sobretudo na região do Médio Rio Doce. Este trabalho teve por objetivo comparar métodos de classificação supervisionada de imagens Rapideye para mapeamento de fragmentos florestais monodominados por Myracrodruon urundeuva em Tumiritinga, MG. Foram avaliadas a classificação pelo algoritmo da Maximaverossimilhança (Maxver) e a classificação por Redes Neurais Artificiais (RNA). Foram testadas 19 combinações envolvendo diferentes bandas, componentes principais e o índice de vegetação da diferença normalizada para a classificação da imagem Rapideye. O treinamento da rede foi realizado variando-se a taxa de aprendizado, o número de interações e o número de neurônios na camada interna. A avaliação dos mapas temáticos produzidos foi realizada através dos índices Kappa e Kappa condicional para a classe de uso do solo "aroeira" e pela análise das Matrizes de Confusão. O método que apresentou melhor desempenho foi a classificação de todas as bandas da imagem Rapideye pelo algoritmo Maxver, apresentando coeficientes Kappa 80 e Kappa condicional 90. O mapa temático gerado teve exatidão do usuário igual a 93% e exatidão do produtor igual a 90%, sendo as maiores confusões do classificador para a classe Aroeira Monodominante acometidas entre as classes Mata Nativa e Pasto Manejado. Da imagem temática produzida, extraiu-se a informação de que 22% do Município de Tumiritinga se encontrava sob ocupação da aroeira em monodominância. A análise do uso e cobertura do solo no município não retrata, na região de estudo, o quadro anunciado de espécie ameaçada de extinção, no qual M. urundeuva se encontra.

Classification of California agriculture using quad polarization radar data and Landsat Thematic Mapper data

This study evaluated the accuracy of classifying California agriculture using spaceborne quad polarization radar from the Japanese ALOS PALSAR system and optical Landsat Thematic Mapper (TM) data. In addition, the study analyzed the utility of radar texture and sensor fusion techniques. The original radar had an overall accuracy of 74% but with individual crop producer's accuracies ranging from 100% for almonds to 49% for alfalfa. Landsat provided a much higher overall classification accuracy of 91%. The merger of Landsat with radar texture increased overall accuracy to 97%, indicating the advantages of sensor integration.

Mapping the distribution of the main host for plague in a complex landscape in Kazakhstan: An object-based approach using SPOT-5 XS, Landsat 7 ETM+, SRTM and multiple Random Forests

Plague is a zoonotic infectious disease present in great gerbil populations in Kazakhstan. Infectious disease dynamics are influenced by the spatial distribution of the carriers (hosts) of the disease. The great gerbil, the main host in our study area, lives in burrows, which can be recognized on high resolution satellite imagery. In this study, using earth observation data at various spatial scales, we map the spatial distribution of burrows in a semi-desert landscape.The study area consists of various landscape types. To evaluate whether identification of burrows by classification is possible in these landscape types, the study area was subdivided into eight landscape units, on the basis of Landsat 7 ETM+ derived Tasselled Cap Greenness and Brightness, and SRTM derived standard deviation in elevation.In the field, 904 burrows were mapped. Using two segmented 2.5m resolution SPOT-5 XS satellite scenes, reference object sets were created. Random Forests were built for both SPOT scenes and used to classify the images. Additionally, a stratified classification was carried out, by building separate Random Forests per landscape unit.Burrows were successfully classified in all landscape units. In the ‘steppe on floodplain’ areas, classification worked best: producer's and user's accuracy in those areas reached 88% and 100%, respectively. In the ‘floodplain’ areas with a more heterogeneous vegetation cover, classification worked least well; there, accuracies were 86 and 58% respectively. Stratified classification improved the results in all landscape units where comparison was possible (four), increasing kappa coefficients by 13, 10, 9 and 1%, respectively.In this study, an innovative stratification method using high- and medium resolution imagery was applied in order to map host distribution on a large spatial scale. The burrow maps we developed will help to detect changes in the distribution of great gerbil populations and, moreover, serve as a unique empirical data set which can be used as input for epidemiological plague models. This is an important step in understanding the dynamics of plague.

Using control data to determine the reliability of volunteered geographic information about land cover

There is much interest in using volunteered geographic information (VGI) in formal scientific analyses. This analysis uses VGI describing land cover that was captured using a web-based interface, linked to Google Earth. A number of control points, for which the land cover had been determined by experts allowed measures of the reliability of each volunteer in relation to each land cover class to be calculated. Geographically weighted kernels were used to estimate surfaces of volunteered land cover information accuracy and then to develop spatially distributed correspondences between the volunteer land cover class and land cover from 3 contemporary global datasets (GLC-2000, GlobCover and MODIS v.5). Specifically, a geographically weighted approach calculated local confusion matrices (correspondences) at each location in a central African study area and generated spatial distributions of user's, producer's, portmanteau, and partial portmanteau accuracies. These were used to evaluate the global datasets and to infer which of them was 'best’ at describing Tree cover at each location in the study area. The resulting maps show where specific global datasets are recommended for analyses requiring Tree cover information. The methods presented in this research suggest that some of the concerns about the quality of VGI can be addressed through careful data collection, the use of control points to evaluate volunteer performance and spatially explicit analyses. A research agenda for the use and analysis of VGI about land cover is outlined.