Artificial neural networks (ANN) are nonlinear models widely investigated in hydrology due to their properties of universal approximation and parsimony. Their performance during the training phase is very good, and their ability to generalize can be improved by using regularization methods such as early stopping and cross-validation. In our research, two kinds of generic models are implemented: the feed-forward model and the recurrent model.

CONTEXT: Expansion of bioenergy production is part of a global effort to reduce greenhouse gas emissions and mitigate climate change. Dedicated biomass crops will compete with other land uses as most high quality arable land is already used for agriculture, urban development, and biodiversity conservation. OBJECTIVE: First, we explore the trade-offs between converting land enrolled in the U.S. Conservation Reserve Program (CRP) to switchgrass for biofuel production or preserving it for biodiversity.

Protected areas remain the most commonly used tool for in situ conservation; however growth in the USA's system of public lands has stagnated while private land conservation continues to expand. Easements can provide a range of ecosystem services (ESs), but it is unknown whether conservation easements maintain ES capacities equivalent to public protected areas.

QUESTIONS: How has the vegetation of the major biomes (Grassland, Nama‐karoo, Albany Thicket, Azonal) of southeastern South Africa changed over the course of the 20th century? How do changes in climate and land‐use drivers relate to long‐term changes in vegetation? What are the implications of these findings for land degradation hypotheses and future climate change projections for the region? LOCATION: The biogeographically complex semi‐arid, Karoo Midlands region of the southeastern part of South Africa.

Stream water temperature (tₛ) is a critical water quality parameter for aquatic ecosystems. However, tₛrecords are sparse or nonexistent in many river systems. In this work, we present an empirical model to predict tₛat the site scale across the USA. The model, derived using data from 171 reference sites selected from the Geospatial Attributes of Gages for Evaluating Streamflow database, describes the linear relationship between monthly mean air temperature (tₐ) and tₛ.

Over the past few decades, groundwater has become an essential commodity owing to increased demand as a result of growing population, industrialization, urbanization and so on. The water supply situation is expected to become more severe in the future because of continued unsustainable water use and projected change in hydrometeorological parameters due to climate change.

The impacts of changes in water temperature and flow on selected water quality parameters, as one of the consequences of climate change, were studied in river catchments in the Czech Republic with little anthropogenic influence. The impact of climate change was manifested by an increase in stream temperature by 1.15°C over 28 years. The selected water quality parameters were dependent on flow, with up to 10-fold increases in the concentrations of ammonia, phosphorus and chlorophyll- a at minimum flow levels.

During the last few decades, land use changes have largely affected the global warming process through emissions of CO₂. However, C sequestration in terrestrial ecosystems could contribute to the decrease of atmospheric CO₂rates. Although Mediterranean areas show a high potential for C sequestration, only a few studies have been carried out in these systems. In this study, we propose a methodology to assess the impact of land use and land cover change dynamics on soil organic C stocks at different depths.

Karst rocky desertification (KRD) is a type of land degradation especially prominent in southwest China. This article analyzes the anthropogenic driving forces of KRD at two scales: rural locality and its macro socio‐economic circumstances. At the rural locality scale, the intensive human pressure on land because of a large and fast growing population and unsustainable land use are identified to be the reason for KRD. However, more radical driving forces lie in the farmers' disadvantages in social‐economic circumstances, which compel them to overuse rural land.

Information on the spatial distribution of soil salinity can be used as guidance in avoiding the continued degradation of land and water resources by better informing policy makers. However, most regional soil-salinity maps are produced through a conventional direct-linking method derived from historic observations. Such maps lack spatial details and are limited in describing the evolution of soil salinization in particular instances.

Land use changes are known to significantly affect the soil C balance by altering both C inputs and losses. Since the late 1990s, a large area of the Loess Plateau has undergone intensive land use changes during several ecological restoration projects to control soil erosion and combat land degradation, especially in the Grain for Green project. By using remote sensing techniques and the Yasso07 model, we simulated the dynamics of soil organic carbon (SOC) stocks in the Yangjuangou catchment of the Loess Plateau.

Dissolved organic carbon (DOC) concentrations in upland surface waters in many northern hemisphere industrialised regions are at their highest in living memory, provoking debate over their “naturalness”. Because of the implications for drinking water treatment and supply there is increasing interest in the potential for mitigation through local land management, and for forecasting the likely impact of environmental change. However, the dominant controls on DOC production remain unresolved, hindering the establishment of appropriate reference levels for specific locations.