Remote sensing images can be used to delineate variations in the area of lakes and to assess the influence of environmental changes and human activities. However, because lakes are dynamic, results obtained from individual images acquired on a single date are not representative and do not accurately reflect ongoing changes. In this study, we used 8-day moderate resolution imaging spectroradiometer (MODIS) composite data from 2000 to 2010 to map water surface changes over 629 lakes in China.

It is necessary to estimate the area of afforestation and deforestation in New Zealand, since 1990, to meet reporting obligations under the Kyoto Protocol. We describe a method for national mapping of forest change that achieves high accuracy, but only requires moderate effort. A national coverage of satellite imagery is standardised, classified (automatically) for land cover, and then compared with an existing 1990 land-use map to identify polygons (>1ha) of possible forest change. Each one of these possible change polygons is checked by operators for actual or spurious change.

Native animals are affected differently by urbanization. Some species respond favorably and thrive in human-dominated landscapes, but others are extirpated. Raptors are often sensitive to changes in land cover and prey abundance. We therefore used a combination of broadcast surveys and incidental observations while spot-mapping to evaluate the influences of these two variables on the presence of raptors at 21 sites from 2004–2008 along an urban-to-wildland gradient in western Washington, U.S.A.

The coyote (Canis latrans) has dramatically expanded its range to include the cities and suburbs of the western US and those of the Eastern Seaboard. Highly adaptable, this newcomer’s success causes conflicts with residents, necessitating research to understand the distribution of coyotes in urban landscapes. Citizen science can be a powerful approach toward this aim.

Delmarva Bays are depressional wetlands that are elliptical in shape with sandy rims, and occur mainly in the central portion of the Delmarva Peninsula within the Mid- Atlantic United States. Situated in a region with abundant agriculture, Delmarva Bays and other wetlands may enhance water quality by reducing nutrient and sediment levels in local waters. A significant portion have been drained and converted from forested wetlands to agriculture.

Mass movements are major hazards that threaten natural and human environments. In Lebanon, the occurrence of mass movements increased by almost 60% between 1956 and 2008. Forest fire has emerged as an additional hazard: it destroyed over 25% of Lebanon’s forests in a period less than 40 years. This paper investigates the potential effect of forest fire on the occurrence of mass movements in the Damour and Nahr Ibrahim watersheds of Lebanon. Mass movement and forest fire inventory maps were produced through remote sensing using aerial and satellite images.

In much of the United States and elsewhere, urbanization continues to transform landscapes. In central Texas, anthropogenic conversion of land is due in part to a rapidly growing population in the Austin and San Antonio metro areas and the subsequent infrastructure and resources needed to support that growth. Protected natural areas adjacent to urbanized landscapes are often intended to mitigate the impact of land development by serving as wildlife habitat.

Forest productivity is strongly affected by seasonal weather patterns and by natural or anthropogenic disturbances. However weather effects on forest productivity are not currently represented in inventory-based models such as CBM-CFS3 used in national forest C accounting programs. To evaluate different approaches to modelling these effects, a model intercomparison was conducted among CBM-CFS3 and four process models (ecosys, CN-CLASS, Can-IBIS and 3PG) over a 2500ha landscape in the Oyster River (OR) area of British Columbia, Canada.

This research selected water soil erosion indicators (land cover, vegetation cover, slope) to assess the risk of soil erosion, ARCMAP GIS ver.9.0 environments and ERDAS ver.9.0 were used to manage and process satellite images and thematic tabular data. Landsat TM images in 2003 were used to produce land/cover maps of the study area based on visual interpreting method and derived vegetation cover maps, and the relief map at the scale of 1:50,000 to calculate the slope gradient maps.

Support vector machine (SVM) was applied for land-cover characterization using MODIS time-series data. Classification performance was examined with respect to training sample size, sample variability, and landscape homogeneity (purity). The results were compared to two conventional nonparametric image classification algorithms: multilayer perceptron neural networks (NN) and classification and regression trees (CART).

A novel approach to image radiometric normalization for change detection is presented. The approach referred to as stratified relative radiometric normalization (SRRN) uses a time-series of imagery to stratify the landscape for localized radiometric normalization. The goal is to improve the detection accuracy of abrupt land cover changes (human-induced, natural disaster, etc.) while decreasing false detection of natural vegetation changes that are not of interest. These vegetation changes may be associated with such phenomena as phenology, growth and stress (e.g.

The random forest (RF) classifier is a relatively new machine learning algorithm that can handle data sets with large numbers and types of variables. Multi-scale object-based image analysis (MOBIA) can generate dozens, and sometimes hundreds, of variables used to classify earth observation (EO) imagery. In this study, a MOBIA approach is used to classify the land cover in an area undergoing intensive agricultural development. The information derived from the elevation data and imagery from two EO satellites are classified using the RF algorithm.