RESUMO
We use a combination of proxy records from a high-resolution analysis of sediments from Searsville Lake and adjacent Upper Lake Marsh and historical records to document over one and a half centuries of vegetation and socio-ecological change-relating to logging, agricultural land use change, dam construction, chemical applications, recreation, and other drivers-on the San Francisco Peninsula. A relatively open vegetation with minimal oak (Quercus) and coast redwood (Sequoia sempervirens) in the late 1850s reflects widespread logging and grazing during the nineteenth century. Forest and woodland expansion occurred in the early twentieth century, with forests composed of coast redwood and oak, among other taxa, as both logging and grazing declined. Invasive species include those associated with pasturage (Rume x, Plantago), landscape disturbance (Urtica, Amaranthaceae), planting for wood production and wind barriers (Eucalyptus), and agriculture. Agricultural species, including wheat, rye, and corn, were more common in the early twentieth century than subsequently. Wetland and aquatic pollen and fungal spores document a complex hydrological history, often associated with fluctuating water levels, application of algaecides, raising of Searsville Dam, and construction of a levee. By pairing the paleoecological and historical records of both lakes, we have been able to reconstruct the previously undocumented impacts of socio-ecological influences on this drainage, all of which overprinted known climate changes. Recognizing the ecological manifestations of these impacts puts into perspective the extent to which people have interacted with and transformed the environment in the transition into the Anthropocene. Supplementary Information: The online version contains supplementary material available at 10.1007/s10113-023-02056-9.
RESUMO
PURPOSE: To assess whether octree representation and octree-based convolutional neural networks (CNNs) improve segmentation accuracy of three-dimensional images. MATERIALS AND METHODS: Cardiac CT angiographic examinations from 100 patients (mean age, 67 years ± 17 [standard deviation]; 60 men) performed between June 2012 and June 2018 with semantic segmentations of the left ventricular (LV) and left atrial (LA) blood pools at the end-diastolic and end-systolic cardiac phases were retrospectively evaluated. Image quality (root mean square error [RMSE]) and segmentation fidelity (global Dice and border Dice coefficients) metrics of the octree representation were compared with spatial downsampling for a range of memory footprints. Fivefold cross-validation was used to train an octree-based CNN and CNNs with spatial downsampling at four levels of image compression or spatial downsampling. The semantic segmentation performance of octree-based CNN (OctNet) was compared with the performance of U-Nets with spatial downsampling. RESULTS: Octrees provided high image and segmentation fidelity (median RMSE, 1.34 HU; LV Dice coefficient, 0.970; LV border Dice coefficient, 0.843) with a reduced memory footprint (87.5% reduction). Spatial downsampling to the same memory footprint had lower data fidelity (median RMSE, 12.96 HU; LV Dice coefficient, 0.852; LV border Dice coefficient, 0.310). OctNet segmentation improved the border segmentation Dice coefficient (LV, 0.612; LA, 0.636) compared with the highest performance among U-Nets with spatial downsampling (Dice coefficients: LV, 0.579; LA, 0.592). CONCLUSION: Octree-based representations can reduce the memory footprint and improve segmentation border accuracy.Keywords CT, Cardiac, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms© RSNA, 2021.