Publications

Support vector machines (SVM) are attractive for the classification of remotely sensed data with some claims that the method is insensitive to the dimensionality of the data and, therefore, does not require a dimensionality-reduction analysis in preprocessing. Here, a series of classification analyses with two hyperspectral sensor data sets reveals that the accuracy of a classification by an SVM does vary as a function of the number of features used. Critically, it is shown that the accuracy of a classification may decline significantly (at 0.05 level of statistical significance) with the addition of features, particularly if a small training sample is used. This highlights a dependence of the accuracy of classification by an SVM on the dimensionality of the data and, therefore, the potential value of undertaking a feature-selection analysis prior to classification. Additionally, it is demonstrated that, even when a large training sample is available, feature selection may still be useful. For example, the accuracy derived from the use of a small number of features may be noninferior (at 0.05 level of significance) to that derived from the use of a larger feature set providing potential advantages in relation to issues such as data storage and computational processing costs. Feature selection may, therefore, be a valuable analysis to include in preprocessing operations for classification by an SVM.

Welcome to the first issue of Remote Sensing Letters. This is a peer-reviewed international journal committed to the rapid publication of short articles (up to 10 journal pages) that advance the sc...

The location of a pixel in feature space is a function of its thematic composition. The latter is central to an image classification analysis, notably as an input (e.g., training data for a supervised classifier) and/or an output (e.g., predicted class label). Whether as an input to or output from a classification, little if any information beyond a class label is typically available for a pixel. The Kohonen self-organising feature map (SOFM) neural network however offers a means to both cluster together spectrally similar pixels that can be allocated suitable class labels and indicate relative thematic similarity of the clusters generated. Here, the thematic composition of pixels allocated to clusters represented by individual SOFM output units was explored with two remotely sensed data sets. It is shown that much of the spectral information of the input image data is maintained in the production of the SOFM output. This output provides a topologically structured representation of the image data, allowing spectrally similar pixels to be grouped together and the similarity of different clusters to be assessed. In particular, it is shown that the thematic composition of both pure and mixed pixels can be characterised by a SOFM. The location of the output unit in the output layer of the SOFM associated with a pixel conveys information on its thematic composition. Pixels in spatially close output units are more similar spectrally and thematically than those in more distant units. This situation also enables specific sub-areas of interest in the SOFM output space and/or feature space to be identified. This may, for example, provide a means to target efforts in training data acquisition for supervised classification as the most useful training cases may have a tendency to lie within specific sub-areas of feature space.

The biomass and biomass dynamics of forests are major uncertainties in our understanding of tropical environments. Remote sensing is often the only practical means of acquiring information on forest biomass but has not always been used successfully. Here the conventional approaches to the estimation of forest biomass from remotely sensed data were evaluated relative to techniques based on the application of artificial neural networks. Together these approaches were used to estimate and map the biomass of tropical forests in north‐eastern Borneo from Landsat TM data. The neural networks were found to be particularly suited to the application. A basic multi‐layer perceptron network, for example, provided estimates of biomass that were strongly correlated with those measured in the field ( r = 0.80). Moreover, these estimates were more strongly correlated with biomass than those derived from 230 conventional vegetation indices, including the widely used normalized difference vegetation index (NDVI).

No abstract is provided for this article.

The potential of remotely sensed imagery as a source of information on industrially despoiled land cover was investigated. Emphasis was placed on issues relating to the separability and mapping of despoiled land cover from Landsat TM imagery for the production of estimates of despoiled land cover extent in administratively defined local districts. Spatial filtering was found to enhance the separability of despoiled land in the TM imagery. A land cover classification derived from Landsat TM imagery which had been preprocessed with an appropriate filter, was integrated with local district boundaries within a geographical information system and used to derive estimates of despoiled land cover extent. These initial estimates were adjusted using information on classification accuracy to derive a remotely sensed estimate of despoiled land cover extent in each local district. These were then evaluated against the estimates derived from a manually produced map of despoiled land cover. The results showed a high degree of correspondence between the remotely sensed and manually mapped estimates, with correlation coefficients of up to 0.93 observed (significant at the 99% level of confidence) and illustrate a potential operational role for remote sensing in identifying and monitoring despoiled land within administratively defined local authority areas.

The ground data used as a reference in the validation of land cover change products are often not an ideal gold standard but degraded by error. The effects of ground reference data error on the accuracy of land cover change detection and the accuracy of estimates of the extent of change were evaluated. Twelve data sets were simulated to allow the exploration of the impacts of a spectrum of ground data imperfections on the estimation of the producer's and user's accuracy of change as well as of change extent. Simulated data were used since this ensured that the actual properties of the data were known and to exclude effects due to other sources of ground reference data error; although the impacts of simulated reference data error on two real confusion matrices are also illustrated. The imperfections evaluated ranged from the inclusion of small amounts of known error into the ground reference data through to the extreme situation in which ground data were absent. The results show that even small amounts of error in the ground reference data can introduce large error into studies of land cover change by remote sensing and reinforce the desire to avoid the expression ground truth as this might imply that the data are a gold standard reference. The effect of reference data imperfections was dependent on the degree of association between the errors in the cross-tabulated data sets. For example, in the scenarios investigated, a 10% error in the reference data set introduced an underestimation of the producer's accuracy of 18.5% if the errors were independent but an over-estimation of the producer's accuracy of 12.3% if the errors were correlated. The magnitude of the mis-estimation of the producer's accuracy was also a function of the amount of change and greatest at low levels of change. The amount of land cover change estimated also varied greatly as a function of ground reference data error. Some possible methods to reduce or even remove the impacts of ground reference data error were illustrated. These ranged from simple algebraic means to estimate the actual values of accuracy and change extent if the imperfections were known through to a latent class analysis that allowed the assessment of classification accuracy and estimation of change extent without the use of ground reference data if the underlying model is defined appropriately.

Soft classification accuracy was negatively related to the degree of intra-class variation. Moreover, the utility of a single value prediction of the fractional cover of a class derived from a soft classification declined as level of intra-class variation increased and it may be preferable instead to derive a distribution of possible fractional covers. The distributional output may also help in the evaluation of change derived from the use of a post-classification comparison analysis.

No abstract is provided for this article.

In ecology, a number of studies have dealt with the prediction of species
\ndiversity over space and its changes over time based on a set of predictors
\nrelated to environmental variability, productivity, spatial constraints, and
\nclimate drivers. However, the observed diversity is a portion of the actual
\npool which is strictly related to abiotic conditions and evolutionary history
\nof species in the pool. In this study we aim to explicitly show uncertainty
\nof the prediction of species distribution at a global scale. This is in line
\nwith the “dark diversity” concept extended to a global spatial scale. We
\nwill not deal with problems in the detectability of species but with hidden
\npatterns in the probability of their distribution.
\nThus far, species distribution estimates based on field data sampling do
\nnot represent reality in a deterministic sense and are only estimates of
\npotential presence. Therefore, the use of “maps of ignorance” representing
\nthe bias or the uncertainty deriving from species distribution modeling,
\nalong with predictive maps, is strongly encouraged.
\nUncertainty can derive from a number of input data sources, such as the
\ndefinition or identification of a certain species, as well as location-based
\nerrors. The spatial distribution of uncertainty should explicitly be shown
\non maps to avoid ignoring overall accuracy or model errors.
\nWe propose methods mainly based on Bayesian logistic regression coupled
\nwith simulation-based Monte Carlo techniques and Cartograms applied to
\nEuropean and worldwide datasets for explicitly mapping uncertainty in
\nthe distribution of species in a Free and Open Source environment.

Three possible methods of combining soft classification outputs to increase soft classification accuracy were assessed. These methods were (i) an approach that selects the most accurate predictions on a class-specific basis, (ii) Dempster-Shafer theory of evidence and (iii) an approach which degrades the soft classification output into a set of ordered classes and then combines these through the use of a conventional ensemble approach. The potential of these approaches was assessed using coarse spatial resolution NOAA AVHRR imagery of Australia. The data were classified using two neural networks (a multi-layer perceptron and a radial basis function network) as well as a probabilistic classifier. All three approaches to combine the classifications were applied to combine the soft classification outputs and had been shown to increase classification accuracy. Relative to the most accurate individual classification, the increases in overall accuracy derived ranged from 2.73 to 4.45% and large increases in individual class accuracy were also observed. The results highlight that ensemble based approaches may be used to increase soft classification accuracy.

No abstract is provided for this article.

Stress cause crops to grow at less than their full potential and can cause reduction in yield; this is as a result of threats emanating from the causative factor(s) known as stressors. Field experiments were conducted in 2010 to compare the effects of two stress-inducing agents on the spectral reflectance of barley: (1) High concentration of Carbon dioxide in soil and (2) four different levels of concentration of herbicide application. Carbon dioxide concentrations up to 80% in soil were applied to experimental plots as part of a study of the potential effects of leakage from carbon capture and storage. In a separate set of plots, glyphogan herbicide (Makhteshim Agan, UK) containing 360g l -1 of glyphosate was applied at four different levels of concentration, at the rate of 0.15 , 0.3 , 0.6 and 1.2 l ha -1 in 200 l ha -1 of water. These rates are equivalent to 5, 10, 20 and 40% of the usual lethal dose for barley crop, diluted to give the normal rate of spray coverage. Thus 0.1, 0.2, 0.4, and 0.8 ml Glophogan in 80 ml of water was sprayed evenly over each of the four plots treatment levels. This was designed to provide a range of levels of stress to the barley crop. Plant stress effects were detected by spectral scanning between 350 and 2500 nm with an ASD Fieldspec FR spectroradiometer (ASD, Boulder, USA). Canopy reflectance spectra were used to locate the position and height of the inflection point of the red edge by derivative analysis and to investigate other peaks that may indicate stress in plants. Measurements of soil gas concentration, and chlorophyll content were carried out at various stages of the crop development to determine any variations as the experiments progressed.

Fuzzy classifications have been used to represent land cover when pixels may have multiple and partial class membership. A fuzzy classification can be derived by softening the output of a conventional “hard” classification. Thus, for example, the probabilities of class membership may be derived from a conventional probability-based classification and mapped to represent the land cover of a site. The accuracy of the representation provided by a fuzzy classification is, however, difficult to evaluate. Conventional measures of classification accuracy cannot be used since they are appropriate only for “hard” classifications. The accuracy of a classification may, however, be indicated by the way in which the probability of class membership is partitioned between the classes and this may be expressed by entropy measures. Here cross-entropy is proposed as a means of evaluating the accuracy of a fuzzy classification, by illustrating how closely a fuzzy classification represents land cover when multiple and partial class membership is a feature of both the remotely sensed and ground data sets. Cross-entropy is calculated from the probability distributions of class membership derived from the remotely sensed and ground data sets. The use of cross-entropy as an indicator of classification accuracy was investigated with reference to land cover classifications of two contrasting test sites. The results show that cross-entropy may be used to indicate the accuracy of the representation of land cover when the classification of the remotely sensed data and ground data are both fuzzy.