This letter evaluates the effectiveness of a new kernel-based extreme learning machine (ELM) algorithm for a land cover classification using both multi- and hyperspectral remote-sensing data. The results are compared with the most widely used algorithms – support vector machines (SVMs). The results are compared in terms of the ease of use (in terms of the number of user-defined parameters), classification accuracy and computation cost.

This study examined the effect of two different forest fires 19 and 23 years ago on the Mediterranean island of Thasos. An object-based classification scheme was developed to map the major land-cover types using multi-temporal Système Pour l’Observation de la Terre (SPOT) and European Remote-Sensing (ERS) (C-band VV) images covering the time period from 1993 to 2007. The developed scheme mapped the post-fire land-cover types accurately: 0.84 Kappa coefficient and 90.5% overall accuracy.

The remote sensing community has recently adopted land-cover map updating methodologies using spectral image differencing, change masking and concatenation procedures to monitor land change accurately and consistently. Unfortunately, map updating requires costly, time-consuming manual image interpretation to achieve accurate spectral threshold placement for land-change masking. The purpose of this study is to minimize time and costs associated with manual image interpretation of change thresholds by developing a new, semi-automated method using support vector machines (SVM).

In this study, we show the novel applications of model-based scattering power decomposition analyses in synthetic aperture radar (SAR) polarimetry for man-made target detection on the sea surface. Model-based decomposition technique is primarily used for land-cover classification mainly because microwave scattering from land is composed of various scattering mechanisms.

Land cover distribution is one of the factors that influence fire behaviour and its consequences in the landscape. The relation between land cover type and fire was investigated at a broad scale, in order to analyse land cover differences in fire proneness. The selection ratio for nine different land cover categories was calculated for the fire perimeters mapped in Southern Europe between 2000 and 2008. The results obtained were then compared per country and region. The fire proneness of topographic classes and its potential association with land cover types were also assessed.

Soil erosion caused by low vegetation cover associated with agricultural land use in the catchment is blamed for the eutrophication of Lake Victoria. Above-ground biomass as an indicator of vegetation cover and biodiversity was assessed using the Normalized Difference Vegetation Index, estimation of tree density and biomass with the aim of assessing the extent to which vegetation covers the soil surface. Tree density is significantly different between agricultural and semi-natural systems with an average of 96 and 90 trees ha⁻¹ observed in Rakai and Mayuge respectively.

Climate change is affecting biodiversity worldwide inducing species to either “move, adapt or die”. In this paper we propose a conceptual framework for analysing range shifts, namely a catalogue of the possible patterns of change in the distribution of a species along elevational or other environmental gradients and an improved quantitative methodology to identify and objectively describe these patterns.

In this paper we analyse the extent of fire-induced forest degradation in Mato Grosso State, Brazil. We utilise a sample based approach used in a previous pan-tropical deforestation survey to derive information on land cover and burned areas in the two major biomes of Mato Grosso: Amazon and Cerrado. Land cover and burned area are mapped for three years (2000–2005–2010) over 77 sample sites (10000ha each) distributed systematically throughout the state which covers 90.337 Mha.

We examined macrophyte–environment relationships in shallow lakes located within the Prairie Parkland and Laurentian Mixed Forest provinces of Minnesota. Environmental variables included land cover within lake watersheds, and within-lake, water and sediment characteristics. CCA indicated that sediment fraction smaller than 63μm (f

A comparison between half-hourly and daily measured and computed evapotranspiration (ET) using three models of different complexity, namely, the Priestley–Taylor (P-T), the reference Penman–Monteith (P-M) and the Common Land Model (CLM), was conducted using three AmeriFlux sites under different land cover and climate conditions (i.e. arid grassland, temperate forest and subhumid cropland).

Dense multi-temporal stacks of Landsat imagery have most commonly been exploited to identify land cover and land use changes (LCLUC) based on detection of abrupt changes in continuous value spectral indices. In this study, a discrete classification approach to LCLUC identification based on stable training sites is tested on a nine-date, 4-year Landsat-7 ETM + time sequence for a study area in Ghana that is prone to cloud cover.