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.
19
datasets available to search
ShareScore release 0.9.0
Dataset results
19 results for “Solar panels”
Hybrid Solar Panel Real Measurements in Switzerland
<h3>Measurements of a hybrid solar panel</h3> <p>Datasheet of the hybrid PV panel (<a title="Datasheet" href="https://cdn.enfsolar.com/Product/pdf/Crystalline/55adc587c2506.pdf" target="_blank" rel="noopener">Here</a>)</p> <p>These measurements have taken place in two places in Valais, Switzerland.</p> <p>One is "Granges" in longitude: 7.4649965° and latitude: 46.2647793° and the other is "Sion" in longitude: 7.364832° and latitude: 46.227372°.</p> <p> </p>
DeepStat WP5 Solar Panel Dataset
<p>The DeepSolaris/ DeepGeoStat dataset was developed in two projects with the same names, during the period 2017 - 2022. The dataset contains 20m x 20m cutouts from an aerial image of the Netherlands. Multiple annotators labeled each cutout for the presence or absence of solar panels. The dataset can be used to train machine or deep learning models on a solar panel classification task.</p> <p>The dataset contains cutouts from the 2018 high-resolution (DOP 10) aerial image of the Netherlands. Each cutout is 200x200 pixels which translates to a 20m x 20m grid. Cutouts were sampled from two nearby regions in the Netherlands:</p> <p>1. The region around the city of <em>Heerlen</em></p> <p>2. The region around the city of <em>Valkenburg</em></p> <p>Between both regions, a 100m strip was left free in which no cutouts were sampled. Both image subsets are therefore independent of each other.</p> <p>In total 26 annotators, annotated 63258 unique pictures with 200795 annotations; 34523 positive annotations indicating that the annotator saw a solar panel in the image, and 166272 negatives indicating that the annotator didn't see a solar panel in the image. More information can be found in the README.md in the archive.</p> <p>Python source code for training models on this dataset can be found here: <a href="https://gitlab.com/CBDS/deepgeostat-wp-5">https://gitlab.com/CBDS/deepgeostat-wp-5</a>.</p> <p>PyTorch weights for a trained model can be found here: <a href="https://zenodo.org/record/7547703#.Y8l0phPMLap">https://zenodo.org/record/7547703#.Y8l0phPMLap</a>.</p> <p>This research was conducted under:</p> <ul> <li>the ESS action 'Merging Geostatistics and Geospatial Information in Member States' (grant agreement no.: 08143.2017.001-2017.408),</li> <li>under the ESS topic B5674-2020-GEOS (project 101033951 2020-NL-GEOS-DEEP-GEO-STAT),</li> <li>an investment of [Statistics Netherlands](https://www.cbs.nl) for the development of Deep Learning models, practices, and methodology.</li> </ul> <p>The researchers want to furthermore thank everyone involved in helping to create and annotate this dataset.</p>
Mapping of solar panels and Fukushima Daiichi Nuclear Power Plant Accident-associated radioactive waste storage in 2022 and 2023, Fukushima, Japan
<p>The policy of reconstruction after the Fukushima Daiichi Nuclear Plant accident has led to a radical transformation of the landscapes of Fukushima Prefecture especially in two aspects (Asanuma-Brice et al., 2023). The first is related to an extensive decontamination policy which resulted in the removal of more than 13 million m<sup>3</sup> of contaminated soil (MOEJ, 2021). The second is the widespread installation of solar panels, which demonstrate the transition decided by the Prefecture and the inhabitants in terms of energy policy.</p> <p>A systematic mapping of these features was carried out from the satellite imagery of Google Map (2023) within the boundaries of Fukushima Prefecture. The objective was to highlight the evolution of specific land use features that are captured imprecisely by automatic detection mapping. We focused on the main visible change in the landscape in terms of land use since Fukushima Daiichi nuclear accident: contaminated waste disposal areas and solar panel fields. These zones were delineated allowing a calculation of the corresponding surface areas (m<sup>2</sup>).<strong> The dataset is composed of 4 shapefile layers: contaminated waste deposits in 2022 and 2023, solar panels in 2022 and 2023. For the year 2022 the last update was conducted in July 2022 and for the year 2023 the last update took place in March 2023.</strong></p> <p>As the land use is in constant and rapid transition (Asanuma-Brice, 2021), we considered as contaminated waste deposits, the permanent storage centers as well as the sites where there are still bags of contaminated waste in varying numbers, knowing that they will be removed and stored on other dedicated sites (Evrard et al., 2019). This choice was made to potentially identify, when the map was updated, the future uses of the land where this waste was stored temporarily.</p> <p>This dataset is part of a larger project that aims to provide the community with an interactive tool (https://mitatelab.cnrs.fr/mitate-labs-map-of-solar-panel-and-contaminated-wasted-land/) that makes available various types of information essential to the analysis of the reconstruction, such as: the delineation of the evacuated zone (which evolved throughout time), the delineation of the municipality boundaries affected by the reconstruction policy, the main services found in these localities, the location of the memorials of the disaster in the zone, as well as the geo-localization of the soil/sediment samples collected by other Mitate lab researchers in order to investigate the redistribution of radionuclides in the environment (Evrard et al., 2021).</p>
Pilot output of a hybrid micro-CPV solar panels with integrated micro-tracking and diffuse capture
<p>Dataset of power output of four final generation Insolight/Hiperion modules on the rooftop of the Instituto de Energía Solar - Universidad Politécnica de Madrid. These are micro CPV modules using integrated planar tracking and hybrid diffuse collection. The modules have a four terminal output: the "CPV" output corresponds to triple junction micro solar cells under ~100X concentration using integrated planar tracking and the "SI" output corresponds to an array of IBC silicon solar cells which ocupies the rest of hte backplane area and harvests light not captured by the concentrator. See References for more information</p><p><strong>Monitoring campaign:</strong></p><ul><li>Location: 40.453°N, -3.727°E. <a href="https://www.google.com/maps/place/40%C2%B027'11.6%22N+3%C2%B043'37.3%22W/@40.453215,-3.7275722,142m/data=!3m2!1e3!4b1!4m13!1m6!3m5!1s0x0:0xc636231f90c3bbeb!2sInstituto+de+Energ%C3%ADa+Solar!8m2!3d40.4531766!4d-3.7269107!3m5!1s0x0:0x0!7e2!8m2!3d40.4532142!4d-3.7270248">Instituto de Energía Solar</a>, Universidad Politécnica de Madrid. 28040 Madrid, Spain.</li><li>Starting date: 19 Oct 2022</li><li>End date: 1 Dec 2022</li></ul><p><strong>Measurement setup:</strong></p><ul><li>The four modules included in this data set were mounted on an 8 module pilot array.</li><li>The four modules have the following ID numbers: 195, 196, 197, and 198</li><li>The modules were mounted at a fixed mounting angle: Due South, Slope Angle = 30°</li><li>All modules were connected to two Enphase IQ7+ microinverters (one per output) to place them at MPPT.</li><li>CPV and SI voltages and currents wer measured with the Enphase monitoring gateway (Envoy)</li><li><strong>NOTE: Some shading on array in mornings due to time of year.</strong></li></ul><p><strong>Description of data file:</strong></p><ul><li><strong>Data files format:</strong> single comma-separated text file; headers in first row; all of the following parameters; order below is the same as order in file</li><li><strong>Measurement time</strong>: the vector of times represents the times at which the Insolight module firmware sampled the current values of the III-V and Si outputs (measured simultaneously).<ul><li>Date Time (dd/mmm/yyyy HH:MM:SS): time in local civil time (data set begins in CEST / UTC+2 but on 30-Oct-22 transitions to CET / UCT+1 with the end of central european summer time.</li></ul></li><li><strong>Measured meteorological data</strong>: these values are measured directly by the IES meteorological station with 1-minute resolution. They have been re-interpolated to match the measurement times.<ul><li>DNI (W/m2): direct normal irradiance as measured by a Normal Incidence Pyrheliometer from Eppley on a solar tracker. Spectral Range: 250-3000 nm. Field of view: 5°</li><li>DNI_Top (W/m2): equivalent direct normal irradiance as measured by a top component cell of a lattice-matched III-V triple-junction cell in the ICU-3J35 Triband Spectro-heliometer from Solar Added Value on a solar tracker. Spectral range: 300 - 680 nm. Field of view: 5.7º</li><li>DNI_Mid (W/m2): equivalent direct normal irradiance as measured by a middle component cell of a lattice-matched III-V triple-junction cell in the <a href="http://solaraddedvalue.com/en/category/products/spectro-heliometer/">ICU-3J35</a> Triband Spectro-heliometer from Solar Added Value on a solar tracker. Spectral range: 680 - 900 nm. Field of view: 5.7º</li><li>GNI (W/m2): global normal irradiance at the aperture plane as measured with a pyranometer on a solar tracker. Spectral range: 305 – 2800 nm.</li><li>T_Amb (°C): ambient temperature</li><li>Wind Speed (m/s): wind speed</li><li>Wind Dir. (m/s): wind direction</li></ul></li><li><strong>Processed meteorological data</strong>: these values are calculated from the above meteorological data and provided for convenience<ul><li>DII (W/m2): Direct Inclined (plane of array) Irradiance corresponding to the module slope angle has been calculated using the sun's known declination and hour angle from the time.</li><li>GII (W/m2): The Global Inclined (plane of array) Irradiance is calculated by first calculating the DII(41°), that is the DII corresponding to the G(41°) measurement, and finding the Diffuse Inclined Irradiance Diff(41°) = G(41°) – DII(41°). It is assumed that the Diffuse Inclined Irradiance at 41° and 30° is equal, so GII = DII + Diff(41°).</li><li>SMR_Top_Mid (n.d.): "Spectral Matching Ratio". This is the ratio between DNI_Top and DNI_Mid. A value of unity indicates a spectrum that is equivalent to AM1.5D with regards to the energy balance between top and middle subcells.</li></ul></li><li><strong>Measured module data:</strong> The MP voltage and current are provided for each output of each module. XXX indicates ID number of module. The power in watts may be found by multiplying these values<ul><li>V_CPV_XXX(V):</li><li>V_SI_XXXi (V)</li><li>I<i>_</i>CPV_XXX(A):</li><li>I<i>_</i>SI_XXXi (A)</li></ul></li></ul>
Solar panels and solar farms in the UK - geographic open data (UKPVGeo)
<p>We present the results of a major crowd-sourcing campaign to create open geographic data for over 260,000 solar PV installations across the UK, covering the vast majority of the capacity in the country. We focus in particular on capturing small-scale domestic solar PV, which accounts for a significant fraction of generation but was until now very poorly documented.</p> <p>The data we introduce will enable decarbonisation at national scales, through forecasting and management of generation, and also serves as a training dataset for machine vision detection of new PV.</p> <p>For a complete description please see <a href="https://www.nature.com/articles/s41597-020-00739-0">the research paper describing the dataset</a>. Please cite this paper in any academic use of the data.</p>
Dataset for Solar Panel Identification
<p>This small dataset consists of 3D meshes of buildings with and without solar panels. We used this to train a DL model to extract Solar Panels, but further data pre-processing steps needs to be followed to be able to use this dataset. For every other use, please check the dataset.</p> <p>These steps can be found here: https://arcg.is/Xu0nn0</p> <p> </p>
SD4EO: AI-based synthetic solar panel dataset on urban areas
<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 aerial images of urban areas that mimic certain regions inside Poitiers, Bordeaux and Toulouse.<br>The images have been synthetized with a generative diffusion model, conditioned with schematic maps, and later augmented to include solar panels in the most sunlighted portions of the building roofs.</p> <p>Each entry has 4 types of files:</p> <ul> <li>A PNG image containing the binary mask with pixel-by-pixel segmentation of areas where solar panels have been installed.</li> <li>A PNG image which shows a variant of the synthetic image, each featuring differently placed panels with white support structures.</li> <li>A TXT file containing the locations of axis-aligned bounding boxes in YOLOv8 format (also compatible with YOLOv5). These are included only if panels have been added to the image, with one file per panel variant, to facilitate YOLO training without needing to modify its Dataset class for file reading.</li> <li>An NPZ file storing the coordinates of the bounding boxes aligned with the solar panels (not with the axes), intended for use in more advanced object detection models like YOLOv8.1 or Mask R-CNN.</li> </ul> <p>The dataset includes 46,872 synthetic images, which have been further enhanced by adding solar panels in strategic locations. The complete dataset with metadata has been subdivided into 18 ZIP files (each containing a different subfolder), totalling 6.5GB. This division was made to avoid overloading the storage system. By distributing the 156,127 files across multiple folders, we prevent potential issues on users' computers related to exceeding the maximum number of inodes in the file system and/or the operating system.</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>
Outdoor monitoring of a hybrid micro-CPV solar panel with integrated micro-tracking and diffuse capture
<p>Dataset from the outdoor characterization of a B Series module from Insolight at the rooftop of the Instituto de Energía Solar - Universidad Politécnica de Madrid. These are measurements of a module of the same type as “<a href="zenodo.org/record/2667772">Outdoor monitoring data of an Insolight B-series module - CPV sub-module</a>” however, in the previous measurements the module was mounted on a two-axis tracker to benchmark its performance, while in these measurements, the module’s integrated planar micro tracking system was used. This data was presented at IEEE PVSC 46 in June 2019 in Chicago. <strong><a href="https://zenodo.org/record/3349781">See preprint of conference article</a>.</strong></p> <p><strong>Monitoring campaign:</strong></p> <ul> <li>Location: 40.453°N, -3.727°E. <a href="https://www.google.com/maps/place/40%C2%B027'11.6%22N+3%C2%B043'37.3%22W/@40.453215,-3.7275722,142m/data=!3m2!1e3!4b1!4m13!1m6!3m5!1s0x0:0xc636231f90c3bbeb!2sInstituto+de+Energ%C3%ADa+Solar!8m2!3d40.4531766!4d-3.7269107!3m5!1s0x0:0x0!7e2!8m2!3d40.4532142!4d-3.7270248">Instituto de Energía Solar</a>, Universidad Politécnica de Madrid. 28040 Madrid, Spain.</li> <li>Fixed Mounting Angle: Due South, Slope Angle = 30°</li> <li>Starting date: 30 May 2019</li> <li>End date: 14 June 2018</li> </ul> <p><strong>Description of data file:</strong></p> <ul> <li><strong>Data files format:</strong> single comma-separated text file; headers in first row; all of the following parameters; order below is the same as order in file</li> <li><strong>Measurement time</strong>: the vector of times represents the times at which the Insolight module firmware sampled the current values of the III-V and Si outputs (measured simultaneously). <ul> <li>Date Time (dd/mmm/yyyy HH:MM:SS): time in CEST / UTC+2</li> </ul> </li> <li><strong>Measured meteorological data</strong>: these values are measured directly by the IES meteorological station with 1-minute resolution. They have been re-interpolated to match the measurement times. <ul> <li>DNI (W/m2): direct normal irradiance as measured by a Normal Incidence Pyrheliometer from Eppley on a solar tracker. Spectral Range: 250-3000 nm. Field of view: 5°</li> <li>DNI_Top (W/m2): equivalent direct normal irradiance as measured by a top component cell of a lattice-matched III-V triple-junction cell in the ICU-3J35 Triband Spectro-heliometer from Solar Added Value on a solar tracker. Spectral range: 300 - 680 nm. Field of view: 5.7º</li> <li>DNI_Mid (W/m2): equivalent direct normal irradiance as measured by a middle component cell of a lattice-matched III-V triple-junction cell in the <a href="http://solaraddedvalue.com/en/category/products/spectro-heliometer/">ICU-3J35</a> Triband Spectro-heliometer from Solar Added Value on a solar tracker. Spectral range: 680 - 900 nm. Field of view: 5.7º</li> <li>GNI (W/m2): global normal irradiance at the aperture plane as measured with a pyranometer on a solar tracker. Spectral range: 305 – 2800 nm.</li> <li>G(41°) (W/m2): Global Inclined Irradiance as measured with a pyranometer mounted facing due south and at a slope angle of 41° (near to local latitude). Spectral range: 305 – 2800 nm.</li> <li>T_Amb (°C): ambient temperature </li> <li>Wind Speed (m/s): wind speed</li> <li>Wind Dir. (m/s): wind direction</li> </ul> </li> <li><strong>Processed meteorological data</strong>: these values are calculated from the above meteorological data and provided for convenience <ul> <li>DII (W/m2): Direct Inclined (plane of array) Irradiance corresponding to the module slope angle has been calculated using the sun’s known declination and hour angle from the time.</li> <li>GII (W/m2): The Global Inclined (plane of array) Irradiance is calculated by first calculating the DII(41°), that is the DII corresponding to the G(41°) measurement, and finding the Diffuse Inclined Irradiance Diff(41°) = G(41°) – DII(41°). It is assumed that the Diffuse Inclined Irradiance at 41° and 30° is equal, so GII = DII + Diff(41°).</li> <li>SMR_Top_Mid (n.d.): “Spectral Matching Ratio”. This is the ratio between DNI_Top and DNI_Mid. A value of unity indicates a spectrum that is equivalent to AM1.5D with regards to the energy balance between top and middle subcells.</li> </ul> </li> <li><strong>Measured module data:</strong> The module was placed in a short-ciruit condition and allowed to track using its integrated tracking system. The short circuit current was measured using shut resistors and integrated A/D channels. This hybrid module features both III-V micro cells (under concentration, with planar microtracking) and large area silicon solar cells (for diffuse capture). <ul> <li>ISC_measured_IIIV (A):</li> <li>ISC_measured_Si (A)</li> </ul> </li> <li><strong>Estimated module data:</strong> As is explained in the IEEE PVSC 46 manuscript (<a href="https://zenodo.org/record/3349781">see Preprint</a>) the following values are estimated using the previously listed measured data. <ul> <li>T_Backplane (°C)</li> <li>PMP_estimated_IIIV (W)</li> <li>PMP_estimated_Si (W)</li> </ul> </li> </ul>
Dataset for evaluating rooftop photovoltaic solar panels impact on urban temperature at city scale
<p>This dataset contains simulation outputs from the WRF/BEP+BEM v4.3.3 model, evaluating the impact of rooftop photovoltaic solar panels on urban temperatures in five cities: Kolkata, Austin, Sydney, Athens, and Brussels. The model uses one parent domain and two nested domains with resolutions of 18 km, 6 km, and 2 km, focusing on the 2 km resolution. Simulations cover the summer periods of each city, including panel surface temperature and urban state variables data. The dataset represents diverse climate types: tropical wet and dry (Kolkata), Mediterranean (Athens), moderate oceanic<em> </em>(Brussels), and subtropical humid (Sydney and Austin).</p>
DeepGeoStat WP5 Solar Panel Trained Network
<p>This dataset contains the weights of a convolutional neural network (CNN) trained to recognize the presence of solar panels on aerial photos. In particular, it contains the saved state of a ResNet50 CNN that has been trained on a dataset containing annotated high-resolution aerial images of two regions in the south of the Netherlands. Many photos in this dataset have been annotated multiple times, and the annotations are not always unanimous. The dataset of aerial images together with annotations can be downloaded from <a href="https://zenodo.org/record/7551799#.Y85W5pKZO3A">here</a>.</p> <p>The model for detecting whether solar panels are present in aerial photos has been developed under the DeepSolaris and DeepGeoStat projects. Corresponding Pytorch code can be found <a href="https://gitlab.com/CBDS/deepgeostat-wp-5">here</a>. The code also demonstrates how to load the saved state into a ResNet50 model, and use it for detecting solar panels on aerial photos.</p> <p>This research was conducted under:</p> <ul> <li>ESS action 'Merging Geostatistics and Geospatial Information in Member States' (grant agreement no.: 08143.2017.001-2017.408),</li> <li> ESS topic B5674-2020-GEOS (project 101033951 2020-NL-GEOS-DEEP-GEO-STAT),</li> <li>a research program of Statistics Netherlands (https://www.cbs.nl)</li> </ul>
Data from: Solar panels as novel nest sites for the European paper wasp Polistes dominula
Open the record for dataset details and reuse information.
Concentrated Hybrid Solar Panel Real Measurements in Switzerland
<h3>Measurements of concentrated hybrid solar panel</h3> <p>Datasheet of the hybrid PV panel (<a title="Datasheet" href="https://cdn.enfsolar.com/Product/pdf/Crystalline/55adc587c2506.pdf" target="_blank" rel="noopener">Here</a>)</p> <p>These measurements have taken place in Granges, Valais, Switzerland in longitude: 7.4649965° and latitude: 46.2647793° with three flat mirrors that concentrated the sun's reflection on one hybrid panel.</p> <p>The PV-T and each mirror length (L) : 1 m</p> <p>The distance between the mirrors (D) : 1.5 m</p> <p>The distance between the mirrors and PV-T (F) : 10 m</p>
GEOLAB Project FROSPER: FROst heaving soils-Solar Panel foundations interaction in cold European Regions: an experimental study
<p>The objective of the proposed project is to investigate the<strong> resilience of solar panels foundations in cold climates</strong>. The efficiency of solar panels is overall better in cold climates, when the direct sunlight is available, due to the lower temperature-induced dispersion. For this reason, large solar fields tend to be installed in cold regions, such as northern Europe or Canada. A solar field with <i>e.g.</i>, 10 MW, requires a great number of solar panels (~6000) whose foundations are generally<strong> steel piles</strong> driven into the soil down to a depth of 2÷5 m below the ground surface. In the cold regions, the shallow layers of soil are periodically subjected to <strong>freezing thus to the frost-heaving phenomena</strong>. The latter can increase the <strong>risk of uplift failure mechanism of the pile foundation</strong> compromising the exercise of the entire solar panel row.</p><p>This project aims to investigate the interaction between saturated soils and solar panel foundations under frozen conditions in <strong>scaled centrifuge models</strong>. The steel piles will be at first driven into the saturated soil sample, then a set of the <strong>freezing-thawing cycles</strong> will be reproduced in the centrifuge. <strong>Possible practical interventions to reduce the soil frost-heaving effects</strong> will also be explored, as the use of protective insulating mantel at the ground surface all around the head of the pile.</p><p>This project will represent a breakthrough in the understanding of the solar panel foundations behaviour, allowing a deeper insight into possible uplift failure mechanisms. The motivation of the study lies in the reduction of the costs and in the resilience improvement of critical infrastructures for the generation of energy in the EU territories. </p>
Global Photovoltaic Solar Panel Dataset from 2019 to 2022
<p>Using Google Earth imagery and 2019-2022 Sentinel-2 datasets, we developed a two-stage classification framework to obtain the annual global dataset of solar photovoltaic panels at 20-meter resolution from 2019 to 2022.</p> <p>To classify the global solar photovoltaic panels, we applied the global zoning method of IPCC AR6 WGI to define the main-zoning, and used 4 degree × 4 degree grids to create the sub-zoning. Then, we extracted the solar photovoltaic panels in each sub-zoning, and stored the result data in TIFF format.</p> <p>The number of each file corresponds to the ID in the attribute table of the sub-zoning-ID file, and users can download and use the corresponding file based on the sub-zoning-ID. After the ID, 2019, 2020, 2021, and 2022 respectively represent four years.</p> <p>The folder of the annual global PV dataset is named after the year, and each file is named as "sub zoning ID_year".</p>
SD4EO - Physically Based Rendering images of human settlements for solar panel detection
<p>This dataset contains part of the results of the SD4EO project, including images corresponding to the use case of solar panel detection on human settlements. The dataset contains images that have been simulated corresponding to low altitude aerial images. Each image in the dataset includes pixel-level labels for each element present in the image, ensuring perfect accuracy due to the synthetic nature of the images. This eliminates common errors in manual or semi-automatic labeling processes.</p> <p><strong>Image labeling</strong></p> <p><strong>(Open Street Map color code)</strong></p> <div> <table> <tbody> <tr> <td> <p><strong>Element</strong></p> </td> <td> <p><strong>R</strong></p> </td> <td> <p><strong>G</strong></p> </td> <td> <p><strong>B</strong></p> </td> </tr> <tr> <td> <p>Road</p> </td> <td> <p>255</p> </td> <td> <p>255</p> </td> <td> <p>255</p> </td> </tr> <tr> <td> <p>Building</p> </td> <td> <p>196</p> </td> <td> <p>182</p> </td> <td> <p>171</p> </td> </tr> <tr> <td> <p>Highway</p> </td> <td> <p>232</p> </td> <td> <p>146</p> </td> <td> <p>162</p> </td> </tr> <tr> <td> <p>Industrial zone</p> </td> <td> <p>234</p> </td> <td> <p>203</p> </td> <td> <p>228</p> </td> </tr> <tr> <td> <p>Parking</p> </td> <td> <p>238</p> </td> <td> <p>238</p> </td> <td> <p>238</p> </td> </tr> <tr> <td> <p>Railway</p> </td> <td> <p>112</p> </td> <td> <p>112</p> </td> <td> <p>112</p> </td> </tr> <tr> <td> <p>Residential zone</p> </td> <td> <p>224</p> </td> <td> <p>223</p> </td> <td> <p>223</p> </td> </tr> <tr> <td> <p>Vegetation</p> </td> <td> <p>174</p> </td> <td> <p>223</p> </td> <td> <p>163</p> </td> </tr> <tr> <td> <p>Water</p> </td> <td> <p>170</p> </td> <td> <p>211</p> </td> <td> <p>223</p> </td> </tr> </tbody> </table> </div> <p>For solar panels masks white color is used to mark the pixels corresponding to solar panels.</p> <p><br><strong>Image name convention</strong></p> <p>The name convention follows the next schema of fields, separated by the character “_”</p> <p>- ID number</p> <p>- Sub ID number</p> <p>- Meters per pixel resolution</p> <p>- Type of image: color, labels, solarpanels</p> <p><strong>Creation and funding</strong></p> <p>All the images have been generated using a tool developed in Unity. This tool will be soon available to enable the generation of new datasets.</p> <p>This research work has been funded by the European Space Agency (ESA) under the FutureEO program and the SD4EO project (Contract No.: 4000142334/23/I-DT), supervised by the ESA Φ-lab.</p> <p><strong>License and attribution</strong></p> <p>This dataset <span>is</span> licensed under a <a href="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a> (CC <span>BY</span> <span>4.0</span>).</p> <p><span>When using the images from this dataset, please attribute them as follows: "Synthetic images created by the research group ARTEC - IRTIC - University of Valencia".</span></p>
Custom Scripts For Solar Panel Identification
<p>These are custom scripts that are used for the Solar Panel Identification, adpated from the scripts provided by:<br>Lei, H., Akhtar, N., Shah, M., & Mian, A. (2023). Mesh Convolution With Continuous Filters for 3-D Surface Parsing. IEEE Transactions on Neural Networks and Learning Systems. IEEE.</p> <p> Git Repository: "https://github.com/EnyaHermite/PicassoPlus".</p>
Analysis and Optimizing Solar Panels for Offshore Remote Wellhead Platforms as a Sustainable and Renewable Energy Source
<p>Data set</p>
Energy and water co-benefits from covering canals with solar panels
Open the record for dataset details and reuse information.
FOREIGN EXPERIENCES ON USING BUILDINGS EQUIPPED WITH INTEGRATED SOLAR PANELS IN URBAN
<p><em><span>Respublikamizning iqtisodiyot tarmoqlarida va ijtimoiy sohada energiya samaradorligini oshirish va <a name="_Hlk178178817"></a>qayta tiqlanuvchi energiya manbalaridan foydalanishni kengaytirish bo`yicha keng ko`lamli ishlar amalga oshirilmoqda. Shuningdek, ushbu maqolaning maqsadi integratsiyalashuv jarayoni orqali qayta tiklanadigan energiya resurslarni birgalikda boshqarish va eksport qilish imkonini yaratadigan quyosh panelli qoplama tizimlarini joriy etishnidir. </span></em></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.