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.
9
datasets available to search
ShareScore release 0.9.0
Dataset results
9 results for “Land-cover mapping”
Land-cover mapping of the central Arizona region based on 2015 National Agriculture Imagery Program (NAIP) imagery
Detailed land-cover mapping is essential for a range of research issues addressed by sustainability science, especially for questions posed of urban areas, such as those of the Central Arizona-Phoenix Long-Term Ecological Research (CAP LTER) program. This project provides a 1-meter land-cover mapping of the CAP LTER study area (greater Phoenix metropolitan area and surrounding Sonoran desert). The mapping is generated primarily using 2015 National Agriculture Imagery Program (NAIP) four-band data, with auxiliary GIS data used to improve accuracy. Auxiliary data include the 2015 cadastral parcel data, the 2014 USGS LiDAR data (1-meter), the 2014 Microsoft/OpenStreetMap Building Footprint data, the 2015 Street TIGER/Line, and a previous (2010) NAIP-based land-cover map of the study area (https://portal.edirepository.org/nis/mapbrowse?scope=knb-lter-cap&identifier=623). Among auxiliary data, building footprints and LiDAR data significantly improved the boundary detection of above-ground objects. Post-classification, manual editing was applied to minimize classification errors. As a result, the land-cover map achieves an overall accuracy of 94 per cent. The map contains eight land cover classes, including: (1) building, (2) asphalt, (3) bare soil and concrete, (4) tree and shrub, (5) grass, (6) water, (7) active cropland, and (8) fallow. When compared to the aforementioned, previous (2010) NAIP-based land-cover map for the study area, buildings and tree canopies are classified more accurately in this 2015 land-cover map.
A comparison among three ways to assemble wall-to-wall land-cover maps from distribution models of vegetation types
<p>Dataset accompanying manuscript <em>"A comparison among three ways to assemble wall-to-wall land-cover maps from distribution models of vegetation types". </em>Datasets contain a wall-to-wall map of vegetation types covering the study area of terrestrial Norway, produced using three methods for assembling individual predictions from Distribution models (<em>probability-based method</em>, <em>performance-based method</em> and <em>prevalence-based method</em>). </p>
SinoLC-1: the first 1-meter resolution national-scale land-cover map of China created with the deep learning framework and open-access data (User guide V2.4)
<p>The<strong> User Guide V2.4 </strong>of the SinoLC-1 land-cover product. The SinoLC-1 was created by the Low-to-High Network (L2HNet), which can be found at: <strong><a href="https://doi.org/10.1016/j.isprsjprs.2022.08.008">L2HNet</a></strong>. A more detailed description of the data can be found in the<strong> <a href="https://doi.org/10.5194/essd-15-4749-2023">paper</a>.</strong> More related work can be found at my <strong><a href="https://lizhuohong.github.io/lzh/">homepage</a>.</strong></p> <p><a href="https://zenodo.org/search?q=parent.id%3A7707461&f=allversions%3Atrue&l=list&p=1&s=10&sort=version"><strong>Click to check all the data versions and download the data (点击查看/下载所有数据版本)</strong></a></p> <p><strong>NOTE: If you have any data needs, questions, or technical issues, contact us at </strong><a href="http://ashelee@whu.edu.cn"><strong>ashelee@whu.edu.cn</strong></a><strong> (Zhuohong Li, 李卓鸿).</strong></p> <p>The land-cover mapping method with Python code is open-access at <a href="https://github.com/LiZhuoHong/Paraformer/"><strong>Code link</strong></a>. You can now update the high-resolution land-cover map by yourself with the code! The updated method is accepted by CVPR 2024 (<strong><a href="https://arxiv.org/abs/2403.02746">Paper link</a></strong>).</p> <p><strong>我们的最新制图算法被计算机视觉顶会CVPR2024接收(<a href="https://arxiv.org/abs/2403.02746">Paper link</a>),代码开源在:<a href="https://github.com/LiZhuoHong/Paraformer/">Code link</a>,您可以利用该代码高效地更新自己数据集的高分土地覆盖图。</strong></p> <p><strong>Citation format of the paper:</strong><br>Li, Z., He, W., Cheng, M., Hu, J., Yang, G., and Zhang, H.: SinoLC-1: the first 1 m resolution national-scale land-cover map of China created with a deep learning framework and open-access data, Earth Syst. Sci. Data, 15, 4749–4780, 2023. </p> <p>Li, Z., Zhang, H., Lu, F., Xue, R., Yang, G. and Zhang, L.: Breaking the resolution barrier: A low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels, <em>ISPRS Journal of Photogrammetry and Remote Sensing</em>. <em>192</em>, pp.244-267, 2022.</p> <p><strong>BibTex format of the paper:</strong></p> <blockquote> <pre>@article{li2023sinolc, title={SinoLC-1: the first 1 m resolution national-scale land-cover map of China created with a deep learning framework and open-access data}, author={Li, Zhuohong and He, Wei and Cheng, Mofan and Hu, Jingxin and Yang, Guangyi and Zhang, Hongyan}, journal={Earth System Science Data}, volume={15}, number={11}, pages={4749--4780}, year={2023}, publisher={Copernicus Publications G{\"o}ttingen, Germany} }</pre> <pre>@article{li2022breaking, title={Breaking the resolution barrier: A low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels}, author={Li, Zhuohong and Zhang, Hongyan and Lu, Fangxiao and Xue, Ruoyao and Yang, Guangyi and Zhang, Liangpei}, journal={ISPRS Journal of Photogrammetry and Remote Sensing}, volume={192}, pages={244--267}, year={2022}, publisher={Elsevier} }</pre> </blockquote>
Global potential invasion maps of traded birds under climate and land-cover change
<p>Biological invasions rank among the top five threatening factors affecting biodiversity, but ongoing changes in climate and land cover might exacerbate risks. We used species distribution models for 609 traded bird species on the CITES list to examine the combined effects of projected climate change and land-cover change worldwide on the potential range expansion of bird species with commercial value as pets. The maps of potential invasion (may be inferred as the invasion risk) have been provided in the main manuscript and here, the potential invasion dataset for the current and future times is provided including the species distribution maps, all as GeoTiff files. The maps for the future time are provided for different future years and over a range of climate scenarios (SSP245, SSP370, and SSP585).</p>
CRLC: Cross-resolution national-scale land-cover mapping based on noisy label learning: a case study of China
<p><strong>CRLC are the 10-meter resolution land cover maps for China in 2020 achieved by a deep classification network.</strong></p> <p><strong>The maps include eight land cover classes:</strong></p> <p>1: Cropland</p> <p>2: Forest</p> <p>3: Grass/shrubland</p> <p>5: Wetland</p> <p>6: Water bodies</p> <p>8: Impervious</p> <p>9: Bareland</p> <p>10: Snow/ice</p> <p> </p> <p><strong>Reference:</strong></p> <pre>@article{liu2023cross, title={Cross-resolution national-scale land-cover mapping based on noisy label learning: A case study of China}, author={Liu, Yinhe and Zhong, Yanfei and Ma, Ailong and Zhao, Ji and Zhang, Liangpei}, journal={International Journal of Applied Earth Observation and Geoinformation}, volume={118}, pages={103265}, year={2023}, publisher={Elsevier} }</pre>
Global potential invasion maps of traded birds under climate and land-cover change
Open the record for dataset details and reuse information.
Input dataset for gap filling and land-cover mapping using eumap Library - 2000 to 2020
<p>Benchmark dataset containing slope, elevation, Landsat temporal composites and night light raster layers, and the training samples (<a href="https://land.copernicus.eu/imagery-in-situ/lucas">LUCAS</a> and <a href="https://land.copernicus.eu/pan-european/corine-land-cover">CORINE</a> samples compilation) to map the land-cover in different areas of the European Union-EU.</p> <p>The slope and elevation refers to <a href="https://zenodo.org/record/4057883#.X3MJ0Nkmz0q">Digital Terrain Model for Continental Europe</a>, and the night light images are from <a href="https://ladsweb.modaps.eosdis.nasa.gov/missions-and-measurements/products/VNP46A1/">VNP46A1 product (VIIRS/NPP Daily Gridded Day Night Band 500m)</a>. The temporal composites were based on <a href="https://glad.geog.umd.edu/ard/glad-landsat-ard">GLAD Landsat ARD</a>, considering the 4 seasons and 3 percentiles per season (25, 50 and 75), for 6 spectral (blue, green, red, NIR, SWIR1, SWIR2) and 1 thermal band, resulting at end in 88 Landsat composites per year. The images for each season were selected using the same calendar dates for all period:</p> <ul> <li>Winter: December 2 of previous year until March 20 of current year</li> <li>Spring: March 21 until June 24 of current year</li> <li>Summer: June 25 until September 12 of current year</li> <li>Fall: September 13 until December 1 of current year</li> </ul> <p>The temporal composites were generated to <a href="https://roda.sentinel-hub.com/sentinel-s2-l2a/readme.html">Sentinel-2 L2A</a> for 2018, 2019 and 2020, using the same approach (4 seasons x 3 percentiles x 6 spectral bands).</p> <p>The benchmark areas were selected according to the EU tiling system, which consists of 7,042 regular tiles with 30 x 30 km. The dataset uses the ETRS89-extended / LAEA Europe as spatial reference system (<a href="https://epsg.io/3035">EPSG:3035</a>), and all the raster layers have 1,000 x 1,000 pixels and 30m of spatial resolution.</p> <p>For all the EU the training samples will have 32 land-cover classes, varying according to the benchmark area:</p> <ul> <li>111: Urban fabric</li> <li>122: Road and rail networks and associated land</li> <li>123: Port areas</li> <li>124: Airports</li> <li>131: Mineral extraction sites</li> <li>132: Dump sites</li> <li>133: Construction sites</li> <li>141: Green urban areas</li> <li>211: Non-irrigated arable land</li> <li>212: Permanently irrigated arable land</li> <li>213: Rice fields</li> <li>221: Vineyards</li> <li>222: Fruit trees and berry plantations</li> <li>223: Olive groves</li> <li>231: Pastures</li> <li>311: Broad-leaved forest</li> <li>312: Coniferous forest</li> <li>321: Natural grasslands</li> <li>322: Moors and heathland</li> <li>323: Sclerophyllous vegetation</li> <li>324: Transitional woodland-shrub</li> <li>331: Beaches, dunes, sands</li> <li>332: Bare rocks</li> <li>333: Sparsely vegetated areas</li> <li>334: Burnt areas</li> <li>335: Glaciers and perpetual snow</li> <li>411: Inland wetlands</li> <li>421: Maritime wetlands</li> <li>511: Water courses</li> <li>512: Water bodies</li> <li>521: Coastal lagoons</li> <li>522: Estuaries</li> <li>523: Sea and ocean</li> </ul> <p>The gap filling validation data was generated by creating a mask of all nodata pixels (gaps) for each temporal composite, and then transposing that mask. All valid pixels covered by the transposed nodata mask are considered validation pixels. This method was chosen to retain the diversity of spatiotemporal nodata patterns that occur in the data. Each gap filling validation file contains 3 directory:</p> <ul> <li>raw: original temporal composite</li> <li>validation: transposed data</li> <li>filled_tmwm8: the best gap filling method that was tested</li> </ul> <p>See the <a href="https://gitlab.com/geoharmonizer_inea/eumap">eumap library</a> for more information about the gapfiling approach and land-cover mapping using this dataset.</p>
Mapping the páramo land cover in the Northern Andes: Figure S4 Expert land-cover classification of the Andean páramo and distribution according to three groups: natural vegetation, natural abiotic and anthropogenic, and 12 classes
<p>The Andean páramo is a biodiverse and vulnerable tropical high-mountain region, whose spatio-ecological patterns remain understudied. The lack of general characterization of its overall extent, land-cover classes, and treeline spatial features hinders our capacity to understand its responses to human impacts and predict future land-system changes. To address this knowledge gap, we classified the land-cover of the páramo in the northern Andes. Moreover, we estimated 1) the páramo's total extent and distribution among countries, 2) the relative extent of 12 of its main land-cover classes, categorized into <i>natural vegetation, natural abiotic</i> and <i>anthropogenic </i>groups, and 3) the preliminary position and anthropogenic influence of its bordering treeline. Relying on Landsat 8 imagery, we performed hybrid manual-automated classifications using the Maximum Likelihood and Random Forest algorithms. The two resulting <i>final classifications</i> were manually checked for errors compared to Google Earth and VegPáramo data, and used to produce the <i>expert classification</i>. Finally, we delimited the treeline based on regional forest connectivity, and applied it to the expert classification to evaluate páramo elevations, surface areas and land-cover classes above the treeline. The páramo extent was estimated at 24,301 km<sup>2</sup>, distributed between Ecuador (47%), Colombia (43%), Venezuela (8%) and Peru (2%). Natural vegetation, especially shrublands, rosette plant communities and grasslands were dominant (altogether, 65%), whereas classes reflecting intense land-use covered 12% overall. The average treeline reached 3546 m and was bordered uphill at 16% with anthropogenic land-cover classes. The páramo's extent is smaller than previously suggested. It remains a (semi-) natural region, yet crop and pasture expansion towards high elevations is a critical concern for long-term sustainability. Future research can build on our findings to predict land-system changes and assess priority areas for conservation. We recommend for future research to focus on remnant forest patches and treeline connectivity in priority.</p>
Mapping the páramo land cover in the Northern Andes: Figure S4 Expert land-cover classification of the Andean páramo and distribution according to three groups: natural vegetation, natural abiotic and anthropogenic, and 12 classes
Open the record for dataset details and reuse information.
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.