199 research outputs found
Mapping the species richness and composition of tropical forests from remotely sensed data with neural networks
No full textThe understanding and management of biodiversity is often limited by a lack of data. Remote sensing has considerable potential as a source of data on biodiversity at spatial and temporal scales appropriate for biodiversity management. To-date, most remote sensing studies have focused on only one aspect of biodiversity, species richness, and have generally used conventional image analysis techniques that may not fully exploit the data's information content. Here, we report on a study that aimed to estimate biodiversity more fully from remotely sensed data with the aid of neural networks. Two neural network models, feedforward networks to estimate basic indices of biodiversity and Kohonen networks to provide information on species composition, were used. Biodiversity indices of species richness and evenness derived from the remotely sensed data were strongly correlated with those derived from field survey. For example, the predicted tree species richness was significantly correlated with that observed in the field (r=0.69, significant at the 95% level of confidence). In addition, there was a high degree of correspondence (?83%) between the partitioning of the outputs from Kohonen networks applied to tree species and remotely sensed data sets that indicated the potential to map species composition. Combining the outputs of the two sets of neural network based analyses enabled a map of biodiversity to be produce
Linking remote sensing, land cover and disease
No full textLand cover is a critical variable in epidemiology and can be characterized remotely. A framework is used to describe both the links between land cover and radiation recorded in a remotely sensed image, and the links between land cover and the disease carried by vectors. The framework is then used to explore the issues involved when moving from remotely sensed imagery to land cover and then to vector density/disease risk. This exploration highlights the role of land cover: the need to develop a sound knowledge of each link in the predictive sequence; the problematic mismatch between the spatial units of the remotely sensed and epidemiological data and the challenges and opportunities posed by adding a temporal mismatch between the remotely sensed and epidemiological data. The paper concludes with a call for both greater understanding of the physical components of the proposed framework and the utilization of optimized statistical tools as prerequisites to progress in this field
Local characterization of thematic classification accuracy through spatially constrained confusion matrices
No full textClassification accuracy statements derived from remote sensing are typically global measures. These provide a summary measure of the quality of the entire classification and are typically assumed to apply uniformly over the region represented. Classification accuracy may, however, vary across the region. A simple means of measuring and characterizing accuracy locally, which also facilitates the representation of the spatial variation in classification accuracy, is to constrain geographically the data used for accuracy assessment. The use of this approach is illustrated with a crop classification from Satellite pour l'Observation de la Terre (SPOT) High Resolution Visible (HRV) data. The global accuracy of the classification was estimated to be 84.0% but accuracy was found to vary locally from 53.33% to 100%. Moreover, accuracy varied from 0–100% over the region on a per-class basis. These variations in accuracy arose mainly as functions of the geographical distribution of the classes and highlight dangers in using a global measure of accuracy that masks spatial variation as a tool in classification evaluation. Local accuracy assessment can, therefore, be a useful analysis and, as the locational information is known, may be achieved at no substantial extra cost to the analysis
Review of Fischer, M.M. and Leung, Y. Geocomputational modelling: techniques and application
No full textSupervised image classification by MLP and RBF neural networks with and without an exhaustively defined set of classes
No full textThe absence of assumptions about the dataset to be classified is one of the major attractions of neural networks for supervised image classification applications. Classification by a neural network does, however, make assumptions about the classes. One key assumption typically made is that the set of classes has been defined exhaustively. If this assumption is unsatisfied, cases of an untrained class will be present and commissioned into the set of trained classes to the detriment of classification accuracy. This was observed in land cover classifications derived with multi-layer perceptron (MLP) and radial basis function (RBF) neural networks in which the presence of an untrained class resulted in a 12.5% decrease in the accuracy of crop classifications derived from airborne thematic mapper data. However, since the RBF network partitions feature space locally rather than globally as with the MLP, it was possible to reduce the commission of atypical cases into the set of trained classes through the setting of post-classification thresholds on the RBF network's outputs. As a result it was possible to identify and exclude some cases of untrained classes from a classification with a RBF network which resulted in an increase in classification accuracy
The role of soft classification techniques in the refinement of estimates of ground control point location
No full textMis-registration of data sets is one of the largest sources of error in many remote sensing studies. An initial contribution to this error arises through the mis-location of ground control points (GCPs) used to derive geometrical transformation equations. Here, it is proposed that a soft classification of land cover may be used to direct the estimation of GCP location. The soft classification provides an estimate of the class composition of each image pixel. The spatial distribution of a pixel's component land covers may then be modeled over the area it represents and used to reduce the error in estimating the location of a GCP that lies within this area. An example is provided in which the error in locating a set of GCPs was reduced by up to 35.7 percent when information from a soft classification was available to aid the estimation of their location at a sub-pixel scale
What is the difference between two maps? A remote senser's view
No full textIn remote sensing, thematic map comparison is often undertaken on a per-pixel basis and based upon measures of classification agreement. Here, the degree of agreement between two thematic maps, and so the difference between the pair, was evaluated through visual and quantitative analyses for two scenarios. Quantitative assessments were based on basic site-specific measures of agreement that are used widely in accuracy assessment (e.g. the overall percentage of pixels with the same class label in each of the two maps and the kappa coefficient of agreement) as well as an information theory based approach that allows the degree of mutual or shared information to be assessed even if different classification schemes have been used to produce the maps. The results indicated that in the first map comparison scenario, focused on labelling, there was a fair degree of correspondence between the maps but with an overall difference in information content of ~42%. In the second comparison scenario, focused on change in time, considerable change had occurred with a change in class label for ~42% of the pixels. It was also apparent that global assessments masked local scale changes
Progress reports, GIS: the accuracy of spatial data revisited
No full textThematic maps have a central and often unquestioned role in geographical information systems (GIS) (Woodcock and Gopal, 2000). They are one of the most common ways of representing spatial data and are unsurprisingly, therefore, a common input and output of analyses undertaken in GIS. They are, however, only a model or simplification and hence a flawed representation of reality. Consequently, it is important that the quality of thematic maps is evaluated and expressed in a meaningful way so that their suitability for use may be assessed. This is important not only in providing a guide to the quality of a map and its fitness for a particular purpose but also in understanding error and its likely implications, especially if allowed to propagate through analyses linking the thematic map to other data sets. Unfortunately, for many geospatial data sets there is commonly a lack of information on data quality and what exists is often poorly communicated (Johnston and Timlin, 2000). The quality of spatial data sets is a very broad issue that may relate to a variety of properties (Worboys, 1998) but with thematic maps the property of interest is typically map accuracy. The accuracy of spatial data sets has long been an important issue in GIS and has been the focus of considerable research, particularly since the influential book by Goodchild and Gopal (1989). As accuracy remains a major research topic and issue of concern to many researchers, it seems pertinent to revisit the topic of accuracy, especially that of thematic maps. For instance, it is apparent that considerable development is required in the methods of accuracy assessment (Scepan, 1999) particularly as the accuracy of thematic maps is one of the greatest limitations to many users (Guisan and Zimmermann, 2000)
- …
