Search

Freely-available satellite data streams and the ability to process these data on cloud-computing platforms such as Google Earth Engine have made frequent, large-scale landcover mapping at high resolution a real possibility. In this paper we apply these technologies, along with machine learning, to the mapping of peatlands–a landcover class that is critical for preserving biodiversity, helping to address climate change impacts, and providing ecosystem services, e.g., carbon storage–in the Boreal Forest Natural Region of Alberta, Canada. We outline a data-driven, scientific framework that: compiles large amounts of Earth observation data sets (radar, optical, and LiDAR); examines the extracted variables for suitability in peatland modelling; optimizes model parameterization; and finally, predicts peatland occurrence across a large boreal area (397, 958 km2) of Alberta at 10 m spatial resolution (equalling 3.9 billion pixels across Alberta). The resulting peatland occurrence model shows an accuracy of 87% and a kappa statistic of 0.57 when compared to our validation data set. Differentiating peatlands from mineral wetlands achieved an accuracy of 69% and kappa statistic of 0.37. This data-driven approach is applicable at large geopolitical scales (e.g., provincial, national) for wetland and landcover inventories that support long-term, responsible resource management. [ABSTRACT FROM AUTHOR]

Purple Loosestrife (Lythrum salicaria) is an invasive plant introduced into North America in the early 1800s. It has since spread into the prairie provinces of Canada (Manitoba, Saskatchewan, and Alberta). It invades wetland habitats, marshes, riparian areas, and natural areas, and it outcompetes native wetland vegetation. In this study we modelled the potential distribution of Purple Loosestrife in the Prairies, explored which suites of predictive variables produced the best ecological niche models, and explored two different approaches to the partitioning of data in evaluating models. We used a number of performance measures and expert evaluation to select our best models. The best model was developed using a suite of climate variables and growing degree-days as the predictive variables and by partitioning testing and training data using stratified random sampling. The model indicated that Purple Loosestrife has not yet reached its full potential distribution in the Prairies. The modelling techniques presented in this paper may be used to predict the potential distribution of other emerging invasive plants, and the results can be used to optimize early detection and surveillance strategies for Purple Loosestrife in areas of the Prairies. [ABSTRACT FROM AUTHOR]

The author discusses the fence lines crisscross in prairies of North America which continue to be erected to define property boundaries, protect drivers from collisions and control the distribution of domestic livestock. It outlines the negative effects of fences on animals including disruption of movement patterns, direct and indirect mortality and habitat fragmentation. The author also claims that barriers including fences are the reason for the collapse of a number of migratory systems.