Dennis C. Duro

TL;DR: In this paper, pixel-based and object-based image analysis approaches for classifying broad land cover classes over agricultural landscapes are compared using three supervised machine learning algorithms: decision tree (DT), random forest (RF), and the support vector machine (SVM).

TL;DR: In this paper, the authors tested for consistent relationships between landscape heterogeneity and biodiversity in farmland, with a view to developing simple rules for landscape management that could increase biodiversity within farmland, and found that mean crop field size had the strongest overall effect on biodiversity measures in crop fields, and this effect was consistently negative.

TL;DR: A variety of definitions have been proposed each with varying levels of complexity and scope as mentioned in this paper, but none of them are simple operational definitions, and therefore they often elude simple operational definition.

TL;DR: The MOBIA approach outlined in this study achieved consistently high overall classification accuracies using the RF algorithm in all models examined, both before and after feature reduction; feature selection of a large data set with little expense to the overall classification accuracy; and increased interpretability of classification models due to the feature selection process and the use of variable importance scores generated by theRF algorithm.

TL;DR: The application of WQG to the CCME WQI was found to be a good tool to assess absolute water quality as it relates to national water quality guidelines for the protection of aquatic life, but had more limited use when evaluating spatial changes in water quality downstream of point source discharges.