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.
109
datasets available to search
ShareScore release 0.9.0
Dataset results
109 results for “satellite image”
Supplementary data for: Comparison of optical flow derivation techniques for retrieving tropospheric winds from satellite image sequences
Open the record for dataset details and reuse information.
Irradiance measurements, satellite images, and clear-sky expectations for Spring 2014 in Tucson, AZ.
<p>This dataset contains the metadata and measurements from a number of irradiance sensors and rooftop solar power systems in addition to clear-sky expectations for those sensors. Irradiance derived from images from the GOES-W satellite are also included. The dataset covers April, May, and June 2014 over the Tucson, AZ, area. The data is in a number of formats including CSV, plain text, HDF5, and netCDF4. </p> <p> </p> <p>See the following for a description of the NREL calibrated GHI sensor:</p> <p>Andreas, A.; Wilcox, S.; (2010). Observed Atmospheric and Solar Information System (OASIS); Tucson, Arizona (Data); NREL Report No. DA-5500-56494. http://dx.doi.org/10.5439/1052226</p> <p> </p> <p>More information about the custom irradiance and rooftop PV sensors can be found in:</p> <p>A. T. Lorenzo, W. F. Holmgren, M. Leuthold, C. K. Kim, A. D. Cronin, and E. A. Betterton, “Short-term PV power forecasts based on a real-time irradiance monitoring network,” in <em>2014 IEEE 40th Photovoltaic Specialist Conference (PVSC)</em>, 2014, pp. 0075–0079.</p>
Deep Learning with Satellite Images Enables High-Resolution Income Estimation: a Case Study of Buenos Aires
<p>This repository contains the datasets required for replicating the results in Abbate et al (forthcoming). The datasets also include per capita income estimates at a 50x50 meter resolution for the years 2013, 2018, and 2022, using satellite images from the Metropolitan Area of Buenos Aires (Argentina) and 2010 census+survey data. The model, based on the EfficientnetV2 architecture, achieved high accuracy in predicting household incomes (R2=0.878), surpassing existing methods in spatial resolution and performance. </p> <p>Inside the Replication Package folder, the user can replicate the main results from the paper. This includes:</p> <ol> <li> <p><strong>Small Area Estimation (SAE) Replication:</strong></p> <ul> <li> <p><strong>Argentina Household Survey Data (EPH):</strong> Processed microdata for 2010, 2013, 2018, and 2022 (ARG_*_EPHC-S2_*.dta).</p> </li> <li> <p><strong>Argentina Census Microdata:</strong> Raw 2010 census microdata (censo2010_fullraw_p.dta).</p> </li> <li> <p><strong>Census Tract Map:</strong> Shapefile of 2010 census tracts (radios_eph_with_link.shp).</p> </li> <li> <p><strong>SAE Output:</strong> The final small_area_estimates.parquet file containing census tract-level population and estimated income, which serves as labels for the CNN model.</p> </li> </ul> </li> <li> <p><strong>CNN-based Income Prediction Replication (Paper Results):</strong></p> <ul> <li> <p><strong>CNN Model Income Predictions:</strong> Gridded 50x50m income estimates for Buenos Aires for 2013, 2018, and 2022 (income_estimates_*.shp).</p> </li> <li> <p><strong>Normalization Scalars:</strong> A CSV file (scalars_ln_pred_inc_mean_trimTrue.csv) to convert the model's log-scale outputs into real income values (2010 PPP-adjusted Argentinian pesos).</p> </li> <li> <p><strong>World Settlement Footprint (WSF):</strong> Satellite-based data (WSF2015_v2_-60_-36.tif) used to mask predictions in uninhabited areas.</p> </li> </ul> </li> </ol> <p>Key prediction datasets are published in shapefile format, while input data for SAE and other auxiliary files are in formats like .dta, .parquet, .csv, and .tif.</p> <p>Results can be replicated by connecting these datasets with the scripts available at the GitHub repo linked below.</p> <p>For researchers who wish to replicate the full analysis pipeline starting from the original source imagery, the data must be acquired commercially. The proprietary Pleiades and Pleiades NEO satellite imagery is owned by Airbus and can be purchased through their data portal: https://space-solutions.airbus.com/imagery/. To facilitate this process, we provide the unique product identifiers for each scene used in this study. These identifiers can be used to query the Airbus archive and purchase the exact scenes.</p> <ul> <li><strong>Pléiades</strong>: for 2013 imagery the IDs are DS_PHR1A_201302051411520_FR1_PX_W059S35_0807_03124, DS_PHR1A_201302071357305_FR1_PX_W059S35_0410_06105 and DS_PHR1A_201302071357509_FR1_PX_W059S35_0609_05426, and for 2018, DS_PHR1A_201803251356358_FR1_PX_W059S35_0909_03875, DS_PHR1A_201808021356574_FR1_PX_W059S35_0509_06938 and DS_PHR1A_201808021357186_FR1_PX_W059S35_0706_06104.</li> <li><strong>Pleiades NEO</strong>: for 2022 imagery the IDs used are 000047717_1_22_STD_A, 000047717_1_24_STD_A, 000047717_1_25_STD_A, 000047717_1_26_STD_A, 000058605_1_3_STD_A, 000058605_1_4_STD_A, 000058605_1_7_STD_A, and 000058608_1_2_STD_A.</li> </ul> <p><strong>Important Usage Note:</strong> Since the predictions for each 50x50m cell individually present some random variation, we recommend that the results are used by averaging out the estimations for each area of interest (e.g., municipalities, neighborhoods, sections, or census tracts) and not at an individual cell level. As detailed throughout the paper, the aggregated results, even in small areas such as census tracts, predict household incomes with precision.</p> <p>Furthermore, inside this repository, it is possible to access and use the model’s trained parameters to make predictions about different satellite images.</p> <p>Data can be visualized by accessing: <a href="https://ingresoamba.netlify.app">https://ingresoamba.netlify.app</a></p> <p> </p> <p> </p>
Satellite Image Maps and GIS File of the Masara, Maco, Davao de Oro Landslide
<p>These maps and GIS file provide visualizations of the landslide that occurred in Brgy. Masara, Maco, Davao de Oro, Philippines on 06 February 2024.<br><br>The PlanetScope Super Dove satellite image was acquired four (4) days after the landslide event (10 February 2024). Using the satellite image, the extents of the landslide were manually delineated using GIS software. We estimated that the larger landslide has a surface area of approximately 85,960 sq. m., while the smaller one measures approximately 759 sq. m. Unfortunately, some portions of the image near the landslide area are contaminated by cloud shadows, making it challenging to visualize and accurately map the extent of the landslide.<br><br>Also included is a high-resolution satellite image depicting Brgy. Masara before the occurrence of the landslide. The image was acquired sometime in November 2019. The manually delineated extent of the landslide area (from the PlanetScope image) is overlaid to easily visualize the impact of the landslide on the nearby community.<br><br>Credits:<br><br>* GIS analysis and map preparation: Jojene R. Santillan<br>* Imagery © 2024 Planet Labs Inc., Maxar<br><br>Access to the PlanetScope image was made possible by the Planet Education and Research Program.<br><br>****<br>Disclaimers:</p> <p>The maps and GIS files ("Products") shall be used for non-commercial, reference purposes only. They shall not be used as replacements to authoritative maps and information provided/issued by mandated government agencies.</p> <p>Accuracy and Limitations: The accuracies of the Products are dependent on the source datasets, and limitations of the software and algorithms used and implemented procedures. The Products are provided “as is” without any warranty of any kind, expressed or implied. CCGeo does not warrant that the Products will be complete, and meet the needs or expectations of the user, or that the operations or use of the maps and GIS files will be error-free.</p> <p><br>Limitation of Liability: CCGeo and Caraga State University will not be held liable for any incidental, consequential, special, exemplary, or indirect damages (including lost profits and lost data) arising from or relating to the use of the maps and GIS files.</p>
Conjugate observation data between DMSP satellites and all-sky imager of Chinese Yellow River station at Ny-Ålesund, Svalbard from January 2005 to December 2009
<p>Chinese Arctic Yellow River Station (YRS) locates at Ny-Ålesund, Svalbard with the geographic coordinates (78.92°N, 11.93°E) and the corrected geomagnetic latitude 76.24°. The relation between local time and universal time is MLT≈UT+3hr. In November 2003, a set of monochromatic auroral observation system was installed at YRS, which is consisted of three identical all-sky imageries (ASIs) with the filters at 427.8nm, 557.7nm and 630.0nm, respectively. DMSP (Defense Meteorological Satellite Program) satellites are a collection of polar-orbit weather satellites launched by the U.S. department of defense. This series of satellites is sun synchronous satellite, which takes about 101 minutes to orbit the earth, has an altitude of about 835-850km, an inclination of about 96°, and crosses the equatorial plane daily from south to north (ascending segment) and from north to south (descending segment) at a fixed time (DMSP F13 is at 05:45LT and 17:45LT, and F15 is at 09:30LT and 21:30LT). DMSP satellite is equipped with Special Sensor for Particle Flux (SSJ/4), which can measure the fluxes of downgoing electrons and ions with energies between from 30eV to 30keV in 19 energy steps (34, 49, 71, 101, 150, 218, 320, 460, 670, 960 eV, and 1.4, 2.1, 3.0, 4.4, 6.5, 9.5, 14.0, 20.5, 29.5 keV), with a time resolution of 1 second. According to the orbit of the DMSP satellites and the observation of the ASIs of YRS, we obtained the conjugate observation periods of the satellite flying over the ASI.</p> <p>During the period from January 2005 to December 2009, a total of 136 conjugate observation events were obtained. Moreover, according to the morphological characteristics of discrete aurora in the all-sky image, 136 events are classified according to four typical forms of dayside discrete auroras, namely 27 events of drapery dayside corona (DDC), 24 events of radial dayside corona (RDC), 37 events of hot-spot aurora (HSA), and 48 events of arc aurora (ARC). The event list of 136 events is recorded in the “asi&dmsp@YRS03-09-v2.xlsx” file. The EPS file gives the trajectory of the DMSP satellite crossing the ASI in each conjugate observation event, while the JPG files are the corresponding all-sky images.</p>
Training and validation data for artificial neural networks using three-dimensional partial convolutions to fill gaps in satellite image time series
<p>This dataset contains training and validation data for artificial neural networks using three-dimensional partial convolutions to fill gaps in satellite image time series. The data have been derived from Sentinel-5P total column carbon monoxide observations, using the offline processing stream.</p> <p><strong>Preprocessing</strong></p> <p>The following operations have been applied on the original S5P imagery:</p> <ol> <li>Images have been resampled to 0.1 by 0.1 degree spatial resolution</li> <li>Pixels with quality assessment value less than or equal to 0.5 have been set to NA</li> <li>Images have been aggregated by day of observation</li> <li>Images have been cropped to -60 to 60 degrees latitude</li> <li>Images have been devided into spatiotemporal blocks of size 128 x 128 pixels and 16 days</li> </ol> <p>Imagery has been recorded between 2021-01-01 and 2021-11-25. Notice that both the training and the validation blocks have been randomly sampled from all available blocks.</p> <p><br> <strong>Data Format and Naming Conventions</strong></p> <p>Input and output data blocks are stored as GeoTIFF files, where bands represent time. Notice the following file naming conventions:</p> <ul> <li>Files starting with <em>X</em> represent input measurements for training, where artificial gaps have been added.</li> <li>Files starting with <em>Y</em> represent true measurements without artificially added gaps (but still containing gaps in many cases).</li> <li>Binary masks of input data where all pixels with valid measurements are 1 and others 0 are stored in files whose name starts with <em>MASK</em></li> <li>Files starting with <em>VALMASK</em> contain a binary mask where only pixels that are available in Y but not in X are 1. The latter is used for validation on artificially removed pixels only.</li> </ul> <p>Numbers in filenames encode spatial and temporal block indexes.</p> <p>In addition, the dataset contains prediction of the validation blocks from different models in the `predictions` directory. The subfolders contain output from different models:</p> <ul> <li>mean refers to simple block-wise mean predictions.</li> <li>timeseries refers to simple linear time series interpolation.</li> <li>gapfill refers to the method proposed in [1].</li> <li>stmra refers to the method proposed in [2].</li> <li>STpconv refers to predictions passed on an artificial neural netowork with three-dimensional partial convolutions.</li> </ul> <p><strong>References</strong></p> <p>[1] Gerber, F., de Jong, R., Schaepman, M. E., Schaepman-Strub, G., & Furrer, R. (2018). Predicting missing values in spatio-temporal remote sensing data. IEEE Transactions on Geoscience and Remote Sensing, 56(5), 2841-2853.</p> <p>[2] Appel, M., & Pebesma, E. (2020). Spatiotemporal multi-resolution approximations for analyzing global environmental data. Spatial Statistics, 38, 100465.</p>
TCRIP-MIM: Rapid Intensification Prediction for Tropical Cyclone by Combining Memory In Memory Network with Sequential Satellite Images
<p>This is the official repository for the paper TCRIP-MIM: Rapid Intensification Prediction for Tropical Cyclone by Combining Memory In Memory Network with Sequential Satellite Images. We use the publicly available dataset from Taiwan University (Bai et al., 2019) as experimental data, consisting of four channels of TC satellite images with a temporal resolution of 3 hours, whose preprocessing method is also publicly available. We use infrared and passive microwave TC satellite image sequences for our experiments, each divided into 24-hour segments (8 infrared and 8 passive microwave satellite images, 16 in total), preprocessing and enhancing data as noted above, so there is no experimental error due to different data preprocessing methods. In this study, the 2003–2017 TC dataset from various global basins was divided into training (1097 TCs, 43528 events), validation (188 TCs, 7884 events), and test sets (94 TCs, 3196 events).</p>
Observations of low-latitude traveling ionospheric disturbances by a 630-nm airglow imager and the CHAMP satellite over Indonesia
<p>We report the first comparison of ground and satellite measurements of low-latitude traveling ionospheric disturbances (TIDs). Three TID events were simultaneously observed by a 630-nm airglow imager and the CHAMP satellite on April 30, 2006 (event 1), September 28, 2006 (event 2), and April 12, 2004 (event 3) at Kototabang, Indonesia (geographic coordinates: 0.2$^\circ$S, 100.3$^\circ$E, geomagnetic latitude: 10.6$^\circ$S). In 630-nm airglow images of all three events, there are clear southward-moving structures. Events 1 and 2 are a single pulse with horizontal scales of $\sim$500--1000 km. Event 3 shows five wave fronts with a horizontal scale size of 500--1000 km. All three TIDs are medium-scale TIDs. Horizontal wavelengths of both airglow intensity at an average emission altitude of 250 km and CHAMP neutral density variations measured at 400 km are estimated by fitting a sinusoidal function to the observed data. For events 1 and 3, estimated horizontal wavelengths are nearly equal, indicating both instruments are observing the same wave. For event 1, the CHAMP electron density mapped along the geomagnetic field line onto the airglow altitude does not show wave structure similar<br> to the airglow variation. For events 2 and 3, the relationship of electron density and airglow intensity is unclear. These results suggest that the cause of the observed TID is not caused by ionospheric plasma instability but by gravity waves in the thermosphere. According to these results, we conclude that the observed TIDs in all three cases are caused by gravity waves in the thermosphere.</p>
Satellite images (10x10 pixels) centered at Folsom, CA (lat=38.642N, lon=121.148W)
<p>Satellite images centered on Folsom, CA (lat=38.642N, lon=121.148W).</p> <p>This dataset includes images from GOES-15, which operated as GOES-West from 2011 until February 2019, when it was superseded by GOES-17.<br> The Earth-facing imager on GOES-15 has five spectral bands: one visible band centered at 0.63<span class="math-tex">\(\mu m\)</span> and four infrared bands centered at 3.9, 6.5, 10.7, and 13.3<span class="math-tex">\(\mu m \)</span>, respectively.</p> <p>This data includes measurements from the visible band (VIS), which has a spatial resolution of 1.0 km and a temporal resolution of one image every 30 minutes.</p> <p>Each image of 10 pixels x 10 pixels is flattened into a vector <span class="math-tex">\(\tilde{x}\)</span>. Each image is then normalized as</p> <p><span class="math-tex">\(x_i = \frac{ \tilde{x}_i-\text{avg}(\tilde{x})}{\sqrt{ \text{var}(\tilde{x})+10}}\)</span></p> <p>where <span class="math-tex">\(\tilde{x}\)</span> is the unprocessed 8 bit grayscale image vector, avg is the arithmetic mean value, and var is the variance.</p> <p>Each line in the csv file corresponds to a single image.<br> The first column is the image timestamp in UTC.<br> The values that follow the timestamp correspond to 100 normalized gray-scale values obtained using the algorithm described above.</p> <p> </p>
Random satellite images of buildings
<p>This dataset contains satellite images. In the center of each image there is a building, whose roof can be visually identified. </p> <p>More information can be found on project website <a href="https://github.com/NHERI-SimCenter/BRAILS">https://github.com/NHERI-SimCenter/BRAILS</a></p> <p>This material is based upon work supported by the NSF National Science Foundation under Grant No. 1612843.</p>
Images and plotting code : Stray light correction and enhancement of nocturnal low-light image of early-morning-orbiting Fengyun-3E satellite
<p>These are images to demonstrate the effectiveness of the algorithm and plotting code : Stray light correction and enhancement of nocturnal low-light image of early-morning-orbiting Fengyun-3E satellite. Readme.pdf will provide specific instructions about these folder compression packages.</p>
Brazilian highways dataset - satellite images
<p>The <strong>Brazilian Highways</strong> dataset was developed to meet the growing demand for data that represents the reality of Brazilian highways, particularly in vehicle detection in satellite images. This dataset contains images from eight Brazilian highways (SP 160, SP 150, BR 101, BR 116, SP 021, SP 041, SP 070, SP 280) high-quality RGB images. Each image includes detailed annotations in two main classes—light vehicles and heavy vehicles—with a ground sampling distance (GSD) of 0.074 m/pixel and 0.3 m/pixel, providing essential data for training deep learning models in computer vision. This dataset is available and offers an unprecedented and valuable resource for developing technologies adapted to the characteristics of the Brazilian fleet and highways.</p> <p>The dataset development was conducted under the guidance of <strong>Prof. Dr. André Luiz Cunha</strong>, with the active participation of researchers <strong>Luan André Contel</strong> and <strong>Crhistian Emilio Ribeiro</strong>. The project stands out for its relevance in the field of vehicle detection by satellite images through computer vision and deep learning techniques and its potential applications in urban planning and traffic management.</p> <p>Funded by the <strong>University of São Paulo (USP)</strong>, through the PUB scholarship program, the work represents a significant advance in the use of technologies for vehicle detection for innovative solutions in urban mobility. The initiative not only contributes to the academic development of those involved but also to technological progress in the area of intelligent transport systems.</p>
SD4EO: AI-based synthetic satellite Sentinel-2 images of cities and building coverture (RGB+NIR bands)
<p>This dataset has been created as part of the deliverables for ESA’s <a href="https://eo4society.esa.int/projects/sd4eo/">SD4EO project</a>. It consists of synthetic versions of Sentinel-2 images in urban areas. These images were synthetically generated using schematic representations from Open Street Maps as a guide to create AI-based conditioned diffusion model images in the visible and near-infrared spectrum, along with coverage masks for non-residential buildings and the set of residential buildings combined with the former.</p> <p>At least five synthetic variants were generated for each of the eleven cities:</p> <ul> <li>Paris (11 variants)</li> <li>Toulouse (9 variants)</li> <li>Poitiers (8 variants)</li> <li>Bordeaux (6 variants)</li> <li>Limoges (9 variants)</li> <li>Clermont-Ferrand (5 variants)</li> <li>Troyes (6 variants)</li> <li>Le Mans (14 variants)</li> <li>Angers (7 variants)</li> <li>Madrid (15 variants)</li> <li>Niort (6 variants)</li> </ul> <p>The file names within the ZIP archives follow a very simple schema:</p> <p>`assembled_` + city name + usage or band indicator + variant + PNG extension / NC extension</p> <p>Each of the four types of images has a different indicator or band:</p> <ul> <li>`_RGB_` for images encoding visible spectrum signals</li> <li>`_NIR_` for images generated for the near-infrared band</li> <li>`_full_allbuildingmask` for the coverage pixel mask of all building types in floating point</li> <li>`_full_nonresidentialmask` for the coverage pixel mask of non-residential buildings in floating point</li> <li>if we have no indicator, then it is a netCDF file with a labelled xarray that merges RGB+NIR as the original Sentinel-2 spectral bands in full original range</li> </ul> <p>NOTE: This 5th version corrects a minor bug in 3rd version of this dataset. If you want to access to version 4 (with non-already assembled patches), it is also available in the right side control version list.</p> <p>The SD4EO Project is funded by the ESA’s FutureEO programme under contract no. 4000142334/23/I-DT and supervised by ESA Φ-lab.</p>
PASTIS - Panoptic Segmentation of Satellite image TIme Series
<p>Public dataset for Panoptic segmentation of agricultural parcels from satellite image time series.</p> <p>See companion <a href="https://github.com/VSainteuf/pastis-benchmark">github repository </a> for more information.</p>
LBHL (~170 nm) UVI images of Polar satellite from December 1996 to January 1997
<p>The UVI aboard the Polar satellite can obtain the ultraviolet auroral intensity distribution in the northern hemisphere. In order to reduce the influence of dayglow on UVI image data, we only used LBHL (~170 nm) UVI images from December 1996 to January 1997, which have full aurora oval (the aurora oval region in the northern hemisphere during this period is in the polar night region, and the aurora image is weakly affected by dayglow and solar light). Each image has a pixel size of 200×228 and a spatial resolution of about 0.04° per pixel (UVI auroral images of Polar satellite taken at apogee have a pixel size of 40×40 km at 100 km above the ground), and the value of each pixel is converted to the value with auroral intensity, the unit is photons/cm<sup>2</sup>/s.</p> <p>These UVI data is save as the mat file of Matlab.</p>
Global daily Aerosol Optical Depth measurements from Moderate Resolution Imaging Spectroradiometer (MODIS) on NASA's Aqua and Terra satellites
<p>This repository contains input MODIS AOD data prepared for “Subways and Urban Air Polution” by Gendron-Carrier, Gonzalez-Navarro, Polloni and Turner (American Economic Journal: Applied Economics, <a href="https://doi.org/10.1257/app.20180168">https://doi.org/10.1257/app.20180168</a>). The main replication archive is available at <a href="https://doi.org/10.3886/E126401V1">https://doi.org/10.3886/E126401V1</a> .</p> <p>Description of input MODIS AOD data</p> <p>The Moderate Resolution Imaging Spectroradiometers aboard the Terra and Aqua earth-observing satellites provide daily measures of the aerosol optical depth of the atmosphere at a 3km spatial resolution everywhere in the world. Data is available in ‘granules’ which describe five minutes of satellite time. These granules are available, more or less continuously, from February 24, 2000 for the Terra satellite and from July 4, 2002 for Aqua. During September of 2018, we downloaded all available granules for Terra and Aqua until August 31, 2018 and subsequently consolidated them into daily rasters describing global AOD. In August 2020, we processed additional Terra data. This archive therefore contains daily rasters for Aqua (from 2002-07-04 to 2018-08-31) and Terra (from 2000-02-24 to 2020-07-31). We note that February 2005 data are missing for the Aqua satellite.</p> <p> </p> <p>We use source products MOD04_3K (<a href="https://doi.org/10.5067/MODIS/MOD04_L2.006">https://doi.org/10.5067/MODIS/MOD04_L2.006</a>) and MYD04_3K (<a href="https://doi.org/10.5067/MODIS/MYD04_L2.006">https://doi.org/10.5067/MODIS/MYD04_L2.006</a>). The product files are stored in Hierarchical Data Format (HDF) and we use the "Optical Depth Land And Ocean" layer, which is stored as a Scientific Data Set (SDS) within the HDF file, as our measure of aerosol optical depth. The "Optical Depth Land And Ocean" dataset contains only the AOD retrievals of high quality. We convert all HDF formatted granules to GIS compatible formats using the HDF-EOS To GeoTIFF Conversion Tool (HEG) provided by NASA’s Earth Observing System Program. We consolidate GeoTIFF granules into a global raster for each day using ArcGIS. First, we keep only AOD values that do contain information. The missing value is -9999 in AOD retrievals. Second, we create a raster catalog with all the granules for a given day and calculate the average AOD value using the Raster Catalog to Raster Dataset tool. The code used to accomplish this is included for reference purposes in “dofiles/old_work” of the main replication archive at <a href="https://doi.org/10.3886/E126401V1">https://doi.org/10.3886/E126401V1</a>.</p>
High spatial resolution satellite images for glacier outlines
<p>Two RapidEye satellite images acquired on Sep 13, 2013 and Sep 17, 2018. The two satellite images have a high spatial resolution of 5 m × 5 m and were used to derive the outlines of the Parlung No. 94 Glacier in years 2013 and 2018, respectively. The GaoFen-7 (GF-7) satellite image with a high spatial resolution of 3 m × 3 m acquired on Feb 26, 2021 was used to derive the outlines of the Dongkemadi Glacier in 2021</p>
SSUSI Images acquired by Ultraviolet Spectrographic Imager aboard DMSP satellite from October to December during 2004-2006
<p>SSUSI is a far ultraviolet scanning imaging spectrometer, which can detect 5 spectral bands of ultraviolet aurora (HI-Lyman α@121.6 nm、 OI@130.4nm、 OI@135.6 nm、 N2-LBHS@140-160 nm and N2-LBHL@160-180 nm) for synchronous scanning imaging observation, its mirror rotates perpendicular to the satellite orbit, and each scan produces an image of 16 ×156pixels. Due to the DMSP satellites need 20-30 minutes to fly over the polar regions, SSUSI can obtain an image covering 1/3 to 1/2 of the auroral oval with a spatial resolution of about 10 × 10 km for each polar flight.In order to reduce the influence of dayglow on SSUSI image data, we only use data from October to December 2004 to 2006 for the study of substorm detection (the aurora oval region in the northern hemisphere during this period is in the polar night region, and the aurora image is weakly affected by dayglow and solar light).<br> The zip file SSUSIdata_mat contains two folders, the plain folder contains the data without the westbound surge structure and the wts folder contains the files with the westbound surge structure.</p>
Satellite images and road-reference data for AI-based road mapping in Equatorial Asia
<p><span>1. </span><span>INTRODUCTION</span></p> <p><span>For the purposes of training AI-based models to identify (map) road features in rural/remote tropical regions on the basis of true-colour satellite imagery, and subsequently testing the accuracy of these AI-derived road maps, we produced a dataset of 8904 satellite image 'tiles' and their corresponding known road features across Equatorial Asia (Indonesia, Malaysia, Papua New Guinea).</span><span> </span></p> <p><span>2. </span><span>FURTHER INFORMATION</span></p> <p><span>The following is a summary of our data. Fuller details on these data and their underlying methodology are given in the corresponding article, under consideration by the journal Remote Sensing as of September 2023: </span></p> <p><span>Sloan, S., Talkhani, R.R., Huang, T., Engert, J., Laurance, W.F. (2023) Mapping remote roads using artificial intelligence and satellite imagery. Under consideration by Remote Sensing.</span></p> <p><span>Correspondence regarding these data can be directed to:</span></p> <p><span>Sean Sloan</span></p> <p>Department of Geography, Vancouver Island University, Nanaimo, B.C, Canada</p> <p><span><a href="mailto:sean.sloan@viu.ca"><span>sean.sloan@viu.ca</span></a></span>; </p> <p><span>Tao (Kevin) Huang</span></p> <p>College of Science and Engineering, James Cook University, Cairns, Queensland 4878, Australia</p> <p><a href="mailto:tao.huang1@jcu.edu.au">tao.huang1@jcu.edu.au</a><span> </span></p>
Satellite images and road-reference data for AI-based road mapping in Equatorial Asia
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.