Using artificial neural networks to predict future dryland responses to human and climate disturbances.

摘要: Land degradation and sediment remobilisation in dryland environments is considered to be a significant global environmental problem. Given the potential for currently stabilised dune systems reactivate under climate change increased anthropogenic pressures, identifying role of external disturbances driving geomorphic response vitally important. We developed novel approach, using artificial neural networks (ANNs) applied time series historical reactivation-deposition events from Nebraska Sandhills, determine relationship between historic periods sand deposition semi-arid grasslands climatic conditions, land use pressures wildfire occurrence. show that both vegetation growth re-deposition episodes can accurately estimated. Sensitivity testing individual factors shows localised forcings (overgrazing wildfire) have statistically impact when held at present-day conditions. However, dominant effect climate-induced drought. Our approach has great estimating future landscape sensitivity scenarios across wide range potentially fragile environments.