Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
2
datasets available to search
ShareScore release 0.9.0
Dataset results
2 results for “metropolitan region of São Paulo”
Tree cover for the year 2010 of the Metropolitan Region of São Paulo, Brazil
<p><strong>Dataset description</strong></p> <p>The tree cover dataset for the year 2010 of the Metropolitan Region of São Paulo (Brazil) was produced using 71 orthorectified RGB aerial photographs taken in 2010 at 1 m spatial resolution. This aerial photographs were made available by the EMPLASA (Empresa Paulista de Planejamento Metropolitano S.A) and can be visualized on the following Brazilian government website http://datageo.ambiente.sp.gov.br/app/# in the directory /Base Imagem/Portal de imagens - DigitalGlobe/Ortofotos do Estado de São Paulo - 2010 / 2011 (EMPLASA). The map of the tree cover was produced using a state-of-the-art deep learning method for image segmentation called U-net. The U-net method was originally developed by Ronneberger et al. (2015) for medical imagery and first applied to remote sensing of vegetation by Wagner et al. (2019). To train the U-net algorithm to recognize and segment trees, a mask of tree cover was manually delineated in one of the images (image ID: SF-23-Y-C-VI-2-SO) resulting in 4015 polygons. The image for manual sampling was chosen because it presented all different types of São Paulo tree cover, that are, isolated trees, natural forests, natural degraded forests and eucalyptus plantations as well as a high diversity in the background classes, with different urban building types (high rise buildings, individual houses, slums and industrial buildings) and also other important classes for the city of São Paulo such as water reservoir, roads and highways. Clipping the image and the mask in 64 x 64 pixels resulted in a sample of 1608 images and their associated labelled mask to train the model. Among these images, 1296 contained trees or forest and 312 contained only background. 1286 images were used for the training and 322 for independent validation. The algorithm presents an excellent level of accuracy, with an overall accuracy of 96.4 % and a F1-score of 0.941 (precision = 0.945 and recall = 0.937). The main known limitations of the algorithm are (i) that it misses sometimes the segmentation of trees on the image borders, however it is largely corrected by the overlap between tiles and has been corrected since Version 2.0; (ii) due to the shade of some buildings or mountains, the image is too dark for the algorithm to recognize objects; and, (iii) in relatively few occasions, it segments some green vegetation or algae which are not trees but present a similar texture or colour.</p> <p>The dataset is distributed in 71 tiles (EPSG:32723, WGS 84 / UTM zone 23S) that are available in raster and shapefile format in the compressed file. The rasters contain one band with value 1 if the pixel is tree cover and 0 otherwise. The shapefiles contain only polygons and these polygons are the tree cover. The tree cover can represent individual trees, natural forests, natural degraded forests or eucalyptus plantation. The total size of the decompressed archives is 6.40 Go.</p> <p>When using this dataset, please cite the original data descriptor article : <strong><a href="https://doi.org/10.3390/data4040145">https://doi.org/10.3390/data4040145</a></strong></p> <p><strong>References</strong></p> <p>Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, CoRR, abs/1505.04597, http://arxiv.org/abs/1505.04597, 2015.</p> <p>Wagner, F. H., Sanchez, A., Tarabalka, Y., Lotte, R. G., Ferreira, M. P., Aidar, M. P. M., Gloor, E., Phillips, O. L., and Aragão, L. E. O. C.: Using the U-net convolutional network to map forest types and disturbance in the Atlantic rainforest with very high resolution images, Remote Sensing in Ecology and Conservation, https://doi.org/10.1002/rse2.111, https://zslpublications.onlinelibrary.wiley.com/doi/abs/10.1002/rse2.111, 2019.</p>
Climate characteristics and trends of extreme daily precipitation events associated with cold fronts in the metropolitan region of São Paulo, Brazil
<p>Data used in the paper "Climate characteristics and trends of extreme daily precipitation events associated with cold fronts in the metropolitan region of São Paulo, Brazil" from Theoretical and Applied Climatology</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.