A large number of mathematical models have been developed for supporting optimization of land-use allocation; however, few of them simultaneously consider land suitability (e.g., physical features and spatial information) and various uncertainties existing in many factors (e.g., land availabilities, land demands, land-use patterns, and ecological requirements). This paper incorporates geographic information system (GIS) technology into interval-probabilistic programming (IPP) for land-use planning management (IPP-LUPM).

Areal interpolation is used to transfer attribute data between geographically incongruous zonal systems. Remotely sensed land cover data are widely used in intelligent areal interpolation methods to solve this problem. This article examines the usefulness of different publicly available remotely sensed land cover data sets as ancillary data used in conjunction with different areal interpolation methods.

This paper contributes to the discussion on current issues in methodologies of mapping land cover in the agro-silvo-pastoral landscapes of the Mediterranean. These landscapes, characterized by intermixed land use and indefinite boundaries, require particular attention in applying the patch-corridor-matrix model when classifying patches and their delineation. In a case study area in southeast Portugal, mainly characterized by agro-silvo pastoral systems, the land cover for 1990 has been mapped.

In this thesis we demonstrate some methods to integrate biophysical data with socio-economic variables with applications in agricultural land use analysis. Part of Nizamabad District of Andhra Pradesh State in India is considered for developing and testing the methods developed. First the study area is stratified as a pre-field work exercise for a focused land use analysis.

Direct applications of remote sensing thermal infrared (TIR) data in landscape ecological research are rare due to limitations in the sensors, calibration, and difficulty in interpretation. Currently there is a general lack of methodology for examining the relationship between land surface temperatures (LST) derived from TIR data and landscape patterns extracted from optical sensors. A separation of landscapes into values directly related to their scale and signature is a key step.

The Queensland Koala Phascolarctos cinereus and possum harvests were regulated from 1906-1927 and 1906-1936, respectively. Before that, there was an uncontrolled harvest. Historical data from the harvest period were analysed to gain information on P. cinereus and possum (mainly Trichosurus vulpecula) population ecology and status. P. cinereusi> numbers peaked in southern Queensland around the turn of the century or in the first decade of the 20th century.

Although the designation of greenbelts around cities has been a common practice for several decades, some greenbelts have not been successfully protected from development. To explore the forces driving the construction of greenbelts, this paper examines how past land use and land cover decisions and current socioeconomic factors have affected the development of the artificial greenbelt zone in China’s Shanghai metropolitan area. Using aerial photographs from 1994, 2005, and 2010, we find that the area of afforested greenbelt was generally related to past land use/cover decisions.

We used boosted regression trees (BRT) to model stream biological condition as measured by benthic macroinvertebrate taxonomic completeness, the ratio of observed to expected (O/E) taxa. Models were developed with and without exclusion of rare taxa at a site. BRT models are robust, requiring few assumptions compared with traditional modeling techniques such as multiple linear regression.

The economic value of pasture improvement in a farming system in a Mediterranean-type environment is assessed using farm modelling. Bioeconomic modelling combined with sensitivity analysis is used to explore how new annual legume species may impact on farm profit and land use. If introduced on all suitable soils the new pastures lead to a 26% increase in farm profit with an additional 12% of farm area being switched into pasture to support more livestock. However, stocking rates decline slightly, the enterprise mix becomes less diversified and several rotational changes are required.

This article presents a sufficient comparison of two types of advanced non-parametric classifiers implemented in remote sensing for land cover classification. A SPOT-5 HRG image of Yanqing County, Beijing, China, was used, in which agriculture and forest dominate land use. Artificial neural networks (ANNs), including the adaptive backpropagation (ABP) algorithm, Levenberg–Marquardt (LM) algorithm, Quasi-Newton (QN) algorithm and radial basis function (RBF) were carefully tested.

The Large-scale Biosphere-Atmosphere Experiment in Amazonia (LBA) is a multinational, interdisciplinary research program led by Brazil. Ecological studies in LBA focus on how tropical forest conversion, regrowth, and selective logging influence carbon storage, nutrient dynamics, trace gas fluxes, and the prospect for sustainable land use in the Amazon region. Early results from ecological studies within LBA emphasize the variability within the vast Amazon region and the profound effects that land-use and land-cover changes are having on that landscape.