The collocation technique has become a popular tool in oceanography and hydrology for estimating the error variances of different data sources such as in situ sensors, models and remote sensing products. It is also possible to determine calibration constants, for example to account for an off-set between the data sources. So far, the temporal autocorrelation structure of the errors has not been...

Soil is one of the most important natural resources covering a large area of the land surface. Soil plays a vital role in biosphere processes, such as energy balance, hydrology, biochemistry, and biological productivity. It supports plants that supply foods, fibers, drugs, and some other human needs. Conversely, desert regions include about one third of earth lands and these regions have increa...

Land use/cover change is a major global environmental change issue and projecting these changes is essential for the assessment of environmental impacts. In this study, a combined use of satellite remote sensing, geographic information systems (GIS), and markov chains stochastic modelling techniques were employed in analysing and projecting land use/cover changes. The results indicate that ther...

The aim of th is research is to produce an urban land cover map ready to be used for planning and management. To extract the reliable information from the selected remote sensing (RS) data, a knowledge-based method based on a rule-based approach is constructed. The result of the knowledge-based technique is compared with the result of a standard maximum likelihood classification (MLC) method an...

Snow cover depletion curves are required for several water management applications of snow hydrology and are often difficult to obtain automatically using optical remote sensing data owing to both frequent cloud cover and temporary snow cover. This study develops a methodology to produce accurate snow cover depletion curves automatically using high temporal resolution optical remote sensing dat...

Land cover characterization at a regional scale using spaceborne multi-angle remote sensing data is in its infancy. A data mining technique was employed to evaluate the degree to which the accuracy of land cover classification can be increased using multi-spectral, multi-temporal and multi-angle remote sensing data. The study area is around the Jornada Rangeland in New Mexico, USA with shrublan...

Land cover and vegetation classification systems are generally designed for ecological or land use applications that are independent of remote sensing considerations. As a result, the classes of interest are often poorly separable in the feature space provided by remotely sensed data. In many cases, ancillary data sources can provide useful information to help distinguish between inseparable cl...

From the past epoch, there have been great hard work and researches are undertaken for mounting land-cover classification in data mining. Whereas the essential uses of the remotely-sensed images is for mainly land-cover classification, for the purpose of applications like monitoring the forest and agricultural areas. Through remote sensing technology an extensive diversity of digital imagery is...

Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon fo...

1. Introduction The potential of remote sensing for the monitoring of the Earth environment and the detection of its temporal variations is well known. A variety of applications in the fields of flood monitoring, forest fire detection, landslide and subsidence, surface deformation and land cover variations were shown in the last ten years using space optical and radar data. However, the real-ti...