Predictive models are frequently used to define the most suitable areas for species protection or reintroduction. Land-cover variables can be used in different ways for distribution modelling. The surface area of a set of land-cover classes is often used, each land-cover presence/absence or the distance to them from any point of the study area can be preferred; multiple types of land-cover variables may be combined to produce a single model.

Land cover and land use changes in Kenya’s Rift Valley have altered the hydrologic response of the River Njoro watershed by changing the partitioning of excess rainfall into surface discharge and groundwater recharge. The watershed contributes a significant amount of water to Lake Nakuru National Park, an internationally recognized Ramsar site, as well as groundwater supplies for local communities and the city of Nakuru.

Phytodiversity is affected both by natural and anthropogenic factors and in Island ecosystems these impacts can devastate or reduce diversity, if the native vegetation is lost. In addition to rich species richness and diversity, Island systems are the sites of high endemism and any threat to these ecosystems will consequently lead to loss and extinction of species.

In any watershed, many factors influence land use/cover change (LUCC). The nonlinear relationships between these factors and LUCC are very complicated and make it difficult to build a model that is capable of accurately simulating the range of physical processes. The aim of this study was: (1) to simplify the structure of a simulation model and improve its simulation speed, and (2) evaluate the impact of land use/cover change on surface runoff and evapotranspiration.

In this work, a high resolution wind atlas for Nakhon Si Thammarat and Songkhla provinces in southern Thailand was developed using combined mesoscale, MC2, and microscale, MsMicro, modeling techniques. The model inputs consist of long-term statistical climate data, i.e. the NCEP/NCAR database, high resolution topography and land cover data. The 200 m resolution wind resource maps were validated with observed mean wind speeds from 10 met stations located along the coastlines of the territory studied.

Koa (Acacia koa) forests are found across broad environmental gradients in the Hawaiian Islands. Previous studies have identified important environmental factors controlling stand structure and productivity at the plot level, but these have not been applied at the landscape level because of small-scale spatial variability.

AIM: The rate of climate change might exceed the migration capacity of plants, particularly where habitats became fragmented by human land use. Except for some tree species, the extent to which habitat fragmentation decreases migration rates has nevertheless been little evaluated. Here, we compare simulated migration rates of understorey herbs, which comprise the big part of temperate forest plant diversity, under varying levels of fragmentation at a continental scale. LOCATION: Europe.

In this study, the Breaks for Additive Seasonal and Trend (BFAST), a recently introduced trend analysis technique, was employed for the detection of fire-induced changes in a Mediterranean ecosystem. BFAST enables the decomposition of time series into trend, seasonal and noise components, resulting in the detection of gradual and rapid land cover changes. Normalised Difference Vegetation Index (NDVI) time series derived from the MODIS and VEGETATION (VGT) standard products were analysed.

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).