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.
8,020
datasets available to search
ShareScore release 0.9.0
Dataset results
8,020 results for “pilots”
Appendix - Potential COVID-19 test fraud detection: Findings from a pilot study comparing conventional and statistical approaches
<p>The methods and results of the publication "COVID-19 test fraud detection: Findings from a pilot study comparing conventional and statistical approaches" are described in more detail in this appendix. The R-syntax for the calculation is provided, as well as a pseudo data set with which the syntax can also be tested.</p>
Steady-state operation dataset of an experimental Wet Cooling Tower pilot plant located at Plataforma Solar de Almería
<p>Repository that contains experimental data obtained from a Wet Cooling Tower (WCT) plant located at <a href="https://www.psa.es/es/index.php">Plataforma Solar de Almería</a>.</p> <p>For the article "Wet cooling tower performance prediction in CSP plants: A comparison between artificial neural networks and Poppe’s model", three experimental campaigns were used, quoting from the article:</p> <blockquote> <p>A total of 132 steady-state experimental points have been obtained thanks to the thorough experimentation conducted. These data cover a large variety of ambient conditions (different seasons, days and nights) and thermal loads (from 27 kW to 207 kW). </p> </blockquote> <p> </p> <p>See <code>README.md</code> for a more detailed description and instructions on how to use the data.</p> <h2><br>License</h2> <p><a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0. Attribution 4.0 International</a></p> <p>If the data is used as part of a scientific publication, please cite the source publication:</p> <div> <div>Serrano, Juan Miguel, Pedro Navarro, Javier Ruiz, Patricia Palenzuela, Manuel Lucas, and Lidia Roca. “Wet Cooling Tower Performance Prediction in CSP Plants: A Comparison between Artificial Neural Networks and Poppe’s Model.” <em>Energy</em> 303 (September 15, 2024): 131844. <a href="https://doi.org/10.1016/j.energy.2024.131844">https://doi.org/10.1016/j.energy.2024.131844</a>.</div> </div>
Dataset for algorithmic thinking skills assessment: Results from the virtual CAT pilot study in Swiss compulsory education
<p><strong>Overview</strong><br>This dataset was collected during a pilot study that evaluated the virtual Cross Array Task (CAT) platform as an assessment tool for algorithmic thinking (AT) skills among K-12 students in Swiss compulsory education.<br>As algorithmic thinking becomes increasingly vital in our digital age, this study bridges the gap between traditional assessments and the needs of today's learners by introducing a digital platform. The virtual CAT, a digital adaptation of an unplugged assessment activity, offers scalable, automated assessments with reduced human intervention.</p><p><strong>Study Context, Location and Participants</strong><br>To demonstrate the virtual CAT's effectiveness, we conducted a pilot study in March 2023.<br>The study was conducted in Switzerland, specifically within the Ticino canton.<br>The sample consisted of 31 students (21 girls and 10 boys) from a preschool class (ages 4-6) and two low secondary classes (1st grade, ages 11-12). </p><p><strong>Data Collection</strong><br>Data collection was integrated into a validation module of the app. <br>Sessions required manual input for details like date, canton, and school information. <br>Students' details, anonymised for privacy, encompassed their gender and date of birth. <br>Each interaction within the platform was meticulously logged, capturing operations like task confirmations, command updates, mode changes, and more.</p><p><strong>Data Features</strong><br>The dataset comprises the following files:</p><ul><li>ALGORITHMS.csv</li><li>CANTONS.csv</li><li>DF.csv</li><li>LOGS.csv</li><li>RESULTS.csv</li><li>SCHOOLS.csv</li><li>SESSIONS.csv</li><li>STUDENTS_SESSIONS.csv</li></ul><p>These files collectively provide insights into the algorithmic actions of the students, demographic details, session logs, results, and more.</p><p><strong>Usage & Ethics</strong><br>In the spirit of open science, this dataset is made available to the public after meticulous anonymisation to ensure all participants' privacy and ethical treatment. <br>Initial authorisations were secured from school administrators, teachers, and parents. <br>Detailed communication regarding the study's nature, data handling, and objectives was transparently shared with all stakeholders.</p><p> </p><p><strong>REFERENCES</strong></p><p><strong>[1]</strong> A. Piatti, G. Adorni, L. El-Hamamsy, L. Negrini, D. Assaf, L. Gambardella & F. Mondada. (2022). The CT-cube: A framework for the design and the assessment of computational thinking activities. Computers in Human Behavior Reports, 5, 100166. <a href="https://doi.org/10.1016/j.chbr.2021.100166">https://doi.org/10.1016/j.chbr.2021.100166</a></p><p><strong>[2]</strong> Adorni, G., & Piatti, S., & Karpenko, V. (2023). virtual CAT: An app for algorithmic thinking assessment within Swiss compulsory education. Zenodo Software. <a href="https://doi.org/10.5281/zenodo.10027851">https://doi.org/10.5281/zenodo.10027851</a> On GitHub: <a href="https://github.com/GiorgiaAuroraAdorni/virtual-CAT-app/">https://github.com/GiorgiaAuroraAdorni/virtual-CAT-app/</a></p><p><strong>[3]</strong> Adorni, G., & Karpenko, V. (2023). virtual CAT programming language interpreter. Zenodo Software. <a href="https://doi.org/10.5281/zenodo.10016535">https://doi.org/10.5281/zenodo.10016535</a> On GitHub: <a href="https://github.com/GiorgiaAuroraAdorni/virtual-CAT-programming-language-interpreter/">https://github.com/GiorgiaAuroraAdorni/virtual-CAT-programming-language-interpreter/</a></p><p><strong>[4]</strong> Adorni, G., & Karpenko, V. (2023). virtual CAT data infrastructure. Zenodo Software. <a href="https://doi.org/10.5281/zenodo.10015011">https://doi.org/10.5281/zenodo.10015011</a> On GitHub: <a href="https://github.com/GiorgiaAuroraAdorni/virtual-CAT-data-infrastructure">https://github.com/GiorgiaAuroraAdorni/virtual-CAT-data-infrastructure</a></p>
ALL-READY Questionnare on potential drivers and barriers to the adoption of innovation management, open science, and Intellectual Property Rights (IPR) among the members of the Pilot Network
<p><strong>Background & Summary</strong>: </p><p>The ALL-READY project unites a diverse consortium of Research Infrastructures (RI) and Living Labs, instrumental in developing new methodologies and technologies in agroecology. The project focuses on effective management of innovation, adherence to open science principles, and strategic application of Intellectual Property Rights (IPR). Task 6.4 of the project, which concentrates on Innovation and IPR Management, seeks to understand the dynamics influencing the adoption of these practices among its members. Recognizing the need for end-to-end data management, the project emphasizes standardized data collection and management while adhering to FAIR principles.</p><p><strong>Methods</strong>: </p><p>The questionnaire was developed by LifeWatch ERIC to capture data reflecting current practices and perceptions in agroecology. It included 26 questions divided into four sections, focusing on existing practices, potential drivers, and barriers in innovation management, open science, and IPR. The survey was disseminated via an online platform to the ALLREADY Pilot Network, ensuring a representative sample from diverse organizations. The data collection process was closely monitored, and the responses were analyzed using a mixed-methods approach to extract meaningful insights.</p><p><strong>Data Records of the ALLREADY Project Questionnaire</strong>: </p><p>The dataset, collected through an online survey platform, underwent a meticulous process of data preparation, download, formatting, and anonymization. It consists of one text file containing metadata (Readme.txt) and a single CSV file encompassing all questionnaire responses. The dataset provides a comprehensive view of innovation management, open science adoption, and IPR handling within the agroecology sector, particularly among the network of RIs and Living Labs involved in the project.</p><p><strong>Technical Validation of the ALLREADY Project Questionnaire</strong>: </p><p>Several critical steps were taken to ensure the accuracy, reliability, and overall quality of the data collected. This included development and testing of the questionnaire, rigorous monitoring of the data collection process, and thorough checks for data quality and completeness. The representativeness of the sample was analyzed specifically with respect to the Pilot Network rather than the broader population involved in agroecology. Strategies were employed to counter survey fatigue and maintain respondent engagement.</p><p><strong>Usage Notes for the ALLREADY Project Questionnaire</strong>: </p><p>The dataset's proper usage is vital for ensuring the validity and reproducibility of research. Researchers are advised to consider the nature of the data, the representativeness of the dataset, and its generalizability. The dataset allows for comprehensive analysis and integration of different sections, and analysts have the flexibility to handle open and write-in responses according to their research needs. Additional information to facilitate analysis is provided in a separate documentation file.</p><p> </p>
Artificial Intelligence for Quality Control of manufacturing operations: Macro-mechanical milling in the Pilot Line GAMHE 5.0.
<p>Quality is defined as the extent to which a product conforms to the design specifications and how it complies with the requirements of component functionality. For some industries, such as automotive and aeronautical, the quality of their parts is very important given the high requirements to which they are subject. However, difficulties arise from the fact that a measure of quality can only be evaluated ‘‘out-of-process”, resulting in losses because there is no alternative to removing defective parts from the production line. Therefore, it is necessary to apply Artificial Intelligence-based kits/solutions that provide in-process estimation to predict quality from some measured variables. </p> <p>The main goal of these datasets is to monitor the final quality of the manufactured components or parts by estimating surface roughness from vibration signals and cutting parameters information using Artificial Intelligence-based solutions. Surface roughness is an essential feature in quality control defined by the deviation in the direction of the normal vector of a real surface from its ideal form. Because the roughness measurement is an offline and post process procedure, being able to estimate this value online brings a series of benefits in terms of time and cost reduction in manufacturing lines, energy efficiency, unnecessary wear of tools and machines, etc. Once a part has been detected with a surface quality below what is desired, a series of corrective measures can be applied for the following operations, such as: reducing the feed rate percentage, increasing the percentage of spindle speed or reducing the axial depth per pass, etc.</p>
Artificial Intelligence for quality control in manufacturing operations: Micro-mechanical milling in the Pilot Line GAMHE 5.0
<p>Quality is defined as the extent to which a product conforms to the design specifications and how it complies with the requirements of component functionality. For some industries, such as automotive and aeronautical, the quality of of manufactured parts is very important due to the high requirements. However, difficulties arise from the fact that a measure of quality can only be evaluated ‘‘out-of-process”, resulting in losses because there is no alternative to removing defective parts from the production line. Therefore, it is necessary to incorporate AI-based kits/solutions that provide in-process estimation to predict quality from some measured variables.</p> <p>The main goal of these datasets is to enable monitoring of final quality of the manufactured components or parts by estimating surface roughness from vibration signals and cutting parameters information. Surface roughness is an essential feature in quality control defined by the deviation in the direction of the normal vector of a real surface from its ideal form. Because the roughness measurement is an offline and post process procedure, being able to estimate this value online brings a series of benefits in terms of time and cost reduction in manufacturing lines, energy efficiency, unnecessary wear of tools and machines, etc. Once a part has been detected with a surface quality below what is desired, a series of corrective measures can be applied for the following operations, such as: reducing the feed rate percentage, increasing the percentage of spindle speed or reducing the axial depth per pass, etc.</p> <p>Workstation 4 (WS4) of the GAMHE 5.0 pilot line is a Kern Evo high-precision machining centre, with a maximum spindle speed of 50 000 rpm and Blum laser system and is used to run micro-milling and micro-drilling operations. In this experimental dataset, five cutting parameters were considered in the processes: spindle speed, <em>n</em>; feed rate, <em>f</em>; and axial depth of cut, <em>a<sub>P</sub></em>. The radial depth of cut, <em>a<sub>e</sub></em>; was equal to the mill tool radius, <em>r</em>, in all of the slots.</p> <p>These experiments were micro-milling operations with 0.3 mm, 0.5 mm, 0.8 mm and 1 mm-diameter mills on a sintered tungsten-copper alloy (W78Cu22). The data collected for each micro milling operation was the rms and peak value of the vibrations in the three-machine axis. In addition, five cutting parameters were also collected: position in <em>X</em> of the last point of the sample, feed rate, spindle speed, tool radius and axial depth.</p>
EO-based area monitoring markers computed over the Lithuanian pilot region (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), the following EO-based monitoring marker maps were released over the two pilot regions, containing the results produced from a set of image analysis and machine learning techniques. The latest explores the benefits of Copernicus's multispectral high-resolution Sentinel-2 data acquired from 01-01-2021 until 26-07-2021 and provides tailored information on the needs of European paying agencies (e.g. CAPO and NPA), expressed with the following markers.</p> <ol> <li> <p><strong>Mowing marker:</strong> used to detect mowing events on meadow/grass like Features Of Interest (FOI)</p> </li> <li> <p><strong>Mean-NDVI marker:</strong> used to detect erroneous claims with no vegetation</p> </li> <li> <p><strong>Homogeneity marker:</strong> used to determine if a parcel geometry really consists of a single crop or if there are multiple things growing on the parcel</p> </li> <li> <p><strong>Bare soil marker:</strong> used to detect observation where bare soil is present on the feature of interest. This indicates agricultural activity on the FOI (plowing, harvest)</p> </li> <li> <p><strong>Similarity and distance markers:</strong> used to give additional context to the crop classification and to detect erroneous claims</p> </li> <li> <p><strong>Land marker:</strong> used to detect the land type and non-productive EFAs of the FOI</p> </li> <li> <p><strong>Crop-type marker:</strong> used to detect the specific crop growing on the FOI</p> </li> </ol> <p>This dataset is comprised of the two subsequent geopackage files, (i) the <em>"test_area_markers_summary.gpkg"</em> and (ii) <em>"crop_marker_summary_full_country.gpkg", which</em> were computed for the Lithuanian pilot region<em>. </em> Descriptions are given below.</p> <p><strong>Test area markers dataset: </strong>There is a total of 59995 FOIs in the test areas. Out of these, markers are computed on **54809** FOIs that contain more than 1 Sentinel-2 pixel.</p> <table> <caption><em><strong>Description of the information contained in the corresponding </strong></em><strong><em>"test area markers"</em> dataset</strong></caption> <thead> <tr> <th scope="col">Attribute Table name</th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>POLY_ID </td> <td>Reference ID of the polygon </td> </tr> <tr> <td>LABEL</td> <td>Declared crop group</td> </tr> <tr> <td>N_VALID_OBS</td> <td>Number of valid Sentinel-2 observations used for computing the markers</td> </tr> <tr> <td>HOMOGENEITY_PROBA</td> <td>The probability that the FOI is homogeneous</td> </tr> <tr> <td>N_MW_OBS_MAY_OCT</td> <td>Number of detected mowing observations between May and October</td> </tr> <tr> <td>N_BS_OBS_APR_OCT</td> <td>Number of detected mowing observations between April and October</td> </tr> <tr> <td>SIMILARITY_SCORE</td> <td>The normalised ([0, 100]) representation of the χ<sup>2</sup> value of the NDVI time-series difference between the target FOI and the neighbouring FOIs</td> </tr> <tr> <td>DISTANCE_SCORE</td> <td>The normalised ([0, 100]) representation of the Median Euclidean distance between the NDVI time-series of the target FOI and the neighbouring FOIs having assumed crop type declared</td> </tr> <tr> <td>MEAN_NDVI</td> <td>Μean NDVI value of all valid observations of the FOI</td> </tr> <tr> <td>PREDICTED_CROP</td> <td>Predicted crop group</td> </tr> <tr> <td>CROP_PREDICTION_SCORE</td> <td>The pseudo-probability of the crop group prediction</td> </tr> </tbody> </table> <p><strong>Crop marker full country dataset: </strong> There is a total of **1127455** FOIs for the full country GSAA dataset. Out of these, markers are computed on **1042671** FOIs that contain more than 1 Sentinel-2 pixel.</p> <table> <caption><em><strong>Description of the information contained in the corresponding </strong></em><strong><em>"crop marker full country"</em> dataset</strong></caption> <thead> <tr> <th scope="col">Attribute Table name</th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>POLY_ID</td> <td>Reference ID of the polygon</td> </tr> <tr> <td>LABEL</td> <td>Declared crop group</td> </tr> <tr> <td>PREDICTED_CROP</td> <td>Predicted crop group</td> </tr> <tr> <td>CROP_PREDICTION_SCORE</td> <td>The pseudo-probability of the crop group prediction </td> </tr> </tbody> </table>
EO-based area monitoring markers computed over the Cypriotic pilot region (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), the following EO-based monitoring marker maps were released over the two pilot regions, containing the results produced from a set of image analysis and machine learning techniques. The latest explores the benefits of Copernicus's multispectral high-resolution Sentinel-2 data acquired from 01-08-2020 until 05-10-2021 and provides tailored information on the needs of European paying agencies (e.g. CAPO and NPA), expressed with the following markers.</p> <ol> <li> <p><strong>Mowing marker:</strong> used to detect mowing events on meadow/grass like Features Of Interest (FOI)</p> </li> <li> <p><strong>Mean-NDVI marker:</strong> used to detect erroneous claims with no vegetation</p> </li> <li> <p><strong>Homogeneity marker:</strong> used to determine if a parcel geometry really consists of a single crop or if there are multiple things growing on the parcel</p> </li> <li> <p><strong>Bare soil marker:</strong> used to detect observation where bare soil is present on the feature of interest. This indicates agricultural activity on the FOI (plowing, harvest)</p> </li> <li> <p><strong>Similarity and distance markers:</strong> used to give additional context to the crop classification and to detect erroneous claims</p> </li> <li> <p><strong>Land marker:</strong> used to detect the land type and non-productive EFAs of the FOI</p> </li> <li> <p><strong>Crop-type marker:</strong> used to detect the specific crop growing on the FOI</p> </li> </ol> <p>This dataset is comprised of the geopackage file <em>"markers_summary.gpkg", which</em> was computed for the Cypriotic pilot region. Descriptions are given below.</p> <p><strong>Markers summary dataset</strong></p> <table> <caption><em><strong>Description of the information contained in the corresponding "markers summary" dataset</strong></em></caption> <thead> <tr> <th scope="col">Attribute name</th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>POLY_ID</td> <td>Reference ID of the polygon </td> </tr> <tr> <td>PLOT_ID_CROP</td> <td>The reference ID of the FOI </td> </tr> <tr> <td>PLOT_NAME</td> <td>The reference name of the FOI </td> </tr> <tr> <td>APPLICANT_NUMBER</td> <td>The ID of the FOI applicant</td> </tr> <tr> <td>LABEL</td> <td>Crop identifier column, based on `CROP_CODE` column in the GSAA dataset.</td> </tr> <tr> <td>CROP_DESC</td> <td>Crop name in Greek (Original crop name) </td> </tr> <tr> <td>CROP_ENG</td> <td>The English name of the crop on the FOI</td> </tr> <tr> <td>LAND_USE</td> <td> <p><strong>Land use types:</strong> 1-ARABLE LAND; 2-PERMANENT CROPS; 3-GRASSLAND (PERMANENT PASTURE); 5-AFFORESTED LAND (NON-AGRICULTURAL); 6-GREENHOUSE); 71-NON-ELIGIBLE (ABANDONED AT LEAST 2 YEARS);72 - NON-ELIGIBLE (FOREST/LOW WILD UNWANTED VEGETATION); 73NON-ELIGIBLE (NON PLANTED/BARREN/ROCKY); 81 - BUILT-UP (BUILDING/WAREHOUSE - MAN CONSTRUCTED); 82 - BUILT-UP (PARK/HOUSE YARD)</p> </td> </tr> <tr> <td>N_VALID_OBS</td> <td>Number of valid Sentinel-2 observations used for computing the markers</td> </tr> <tr> <td>HOMOGENEITY_PROBA</td> <td>The probability that the FOI is homogeneous</td> </tr> <tr> <td>MEAN_NDVI</td> <td>Mean NDVI value of all valid observations of the FOI</td> </tr> <tr> <td> N_MW_OBS_AUG20_OCT21</td> <td>Number of detected mowing observations between August 2020 and October 2021</td> </tr> <tr> <td>N_BS_OBS_AUG20_OCT21</td> <td>Number of detected mowing observations between August 2020 and October 2021</td> </tr> <tr> <td>BS_COUNT_MAR_START_MAR_END</td> <td>Number of bare-soil observations between March 1 2021 and April 1 2021</td> </tr> <tr> <td>BS_COUNT_MAR_START_APR_MID</td> <td>Number of bare-soil observations between March 1 2021 and April 15 2021</td> </tr> <tr> <td>BS_COUNT_MAR_APR</td> <td>Number of bare-soil observations between March 1 2021 and May 1 2021</td> </tr> <tr> <td>SIMILARITY_SCORE</td> <td>The normalised ([0, 100]) representation of the χ<sup>2</sup> value of the NDVI time-series difference between the target FOI and the neighboring FOIs</td> </tr> <tr> <td>DISTANCE_SCORE</td> <td>The normalised ([0, 100]) representation of the Median Euclidean distance between the NDVI time-series of the target FOI and the neighboring FOIs having assumed crop type declared</td> </tr> <tr> <td>PREDICTED_LAND_GROUP</td> <td>The FOI label as predicted by the land group model using crop groupings based on land use.</td> </tr> <tr> <td>LAND_GROUP_PREDICTION_SCORE</td> <td>The pseudoprobability of the crop-group prediction as assigned by the land-group model using crop groupings based on land use. A score close to 1 indicates that the model is very confident in the prediction a score close to 0 indicates that the model is not confident in the prediction.</td> </tr> <tr> <td>PREDICTED_CROP</td> <td>The FOI label as predicted by the crop group model using crop groupings proposed by CAPO.</td> </tr> <tr> <td>CROP_PREDICTION_SCORE</td> <td>The pseudoprobability of the crop-group prediction as it is assigned by the crop-group model using crop groupings proposed by PA. A score close to 1 indicates that the model is very confident in the prediction a score close to 0 indicates that the model is not confident in the prediction.</td> </tr> <tr> <td>PREDICTED_CROP_V39</td> <td>The FOI label as predicted by the crop group model using crop groupings to 39 groups.</td> </tr> <tr> <td>CROP_PREDICTION_SCORE_V39</td> <td>The pseudoprobability of the crop-group prediction as assigned by the crop-group model using crop groupings to 39 groups.</td> </tr> <tr> <td>PREDICTED_CROP_V41</td> <td>The FOI label as predicted by the crop group model using crop groupings to 41 groups</td> </tr> <tr> <td>CROP_PREDICTION_SCORE_V41</td> <td>The pseudoprobability of the crop-group prediction as assigned by the crop-group model using crop groupings to 41 groups.</td> </tr> </tbody> </table> <p><br> </p>
Super-resolution EO-based area monitoring markers computed over the Lithuanian pilot region (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), the following EO-based monitoring marker maps were released over defined pilot areas over the Lithuanian pilot country, enhanced by features raised from the Super-resolution models. It involved the implementation of matching marking and data fusion deep learning algorithms, which attempt to support the extraction of useful information from highly variable inputs. This will further allow the distinction of landscape features, which would otherwise not be available in initially acquired Sentinel-2 data. The use of VHR data (Copernicus Contributing Missions) in combination with drone imagery will enhance the super-resolution modelling capabilities, enabling the augmentation of the training dataset (spatio-temporal scale) and subsequently leading to increased model performance.<br> The goal was to enhance the outputs of the area monitoring markers and especially in the monitoring of small (i.e. 100m<sup>2</sup>), narrow and elongated parcels. </p> <p>For the needs of DIONE, the aforementioned data were explored and the following area-based monitoring markers were calculated from 01-01-2022 until 01-08-2022 providing tailored information for the needs of the National Paying Agency of Lithuania. </p> <ol> <li> <p><strong>Mowing marker:</strong> used to detect mowing events on meadow/grass like Features Of Interest (FOI)</p> </li> <li> <p><strong>Similarity and distance markers:</strong> used to give additional context to the crop classification and to detect erroneous claims</p> </li> <li> <p><strong>Crop-type marker:</strong> used to detect the specific crop growing on the FOI</p> </li> </ol> <p>This dataset is comprised of one geopackage file, the "S2SR-study-geopackage.gpkg"<em>, which</em> was computed for the Lithuanian pilot region<em>. </em>Descriptions are given below.</p> <p><strong>Super-resolution Markers dataset: </strong>Markers were computed for 16872 FOIs that contain less than 1 Sentinel-2 pixel, using signals from 2022-01-01 until 2022-08-01. </p> <table> <caption><strong>Description of the information contained in the corresponding "Super-Resolution markers" dataset</strong></caption> <thead> <tr> <th scope="col">Attribute name </th> <th scope="col">Description </th> </tr> </thead> <tbody> <tr> <td>CROP_LABEL</td> <td>Reference ID of the polygon </td> </tr> <tr> <td>POLY_ID </td> <td>Declared crop group</td> </tr> <tr> <td>crop_group_prediction_1_classification</td> <td>The FOI label as predicted by the crop group (v2) model</td> </tr> <tr> <td>crop_group_prediction_1_classification_score</td> <td>The pseudoprobability of the crop-group (v1) prediction. A score close to 1 indicates that the model is very confident in the prediction</td> </tr> <tr> <td>crop_group_prediction_2_classification</td> <td>The FOI label as predicted by the crop group (v2) model</td> </tr> <tr> <td>crop_group_prediction_2_classification_score</td> <td>The pseudoprobability of the crop-group (v2) prediction. A score close to 1 indicates that the model is very confident in the prediction</td> </tr> <tr> <td>distance_classification</td> <td>Most similar crops according to the distance marker</td> </tr> <tr> <td>distance_classification_score</td> <td>Distance marker score of a FOI when compared to nearby FOIs with the same claim. A value close to 100 indicates that a FOI is not similar to other FOIs with the same claim.</td> </tr> <tr> <td>mowing_event_count</td> <td>Number of detected mowing events in the observation period</td> </tr> <tr> <td>similarity_classification</td> <td>Most similar crops according to similarity marker</td> </tr> <tr> <td>similarity_classification_score</td> <td>Similarity marker score of a FOI when compared to nearby FOIs with the same claim. A value close to 100 indicates that a FOI is not similar to other FOIs with the same claim</td> </tr> </tbody> </table>
EO-based area monitoring markers computed over the Cypriotic pilot region (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), the following EO-based monitoring marker maps were released over the two pilot regions, containing the results produced from a set of image analysis and machine learning techniques. The latest explores the benefits of Copernicus's multispectral high-resolution Sentinel-2 data acquired from 01-08-2021 until 03-09-2022 and provides tailored information on the needs of European paying agencies (e.g. CAPO and NPA), expressed with the following markers.</p> <ol> <li> <p><strong>Mowing marker:</strong> used to detect mowing events on meadow/grass like Features Of Interest (FOI)</p> </li> <li> <p><strong>Mean-NDVI marker:</strong> used to detect erroneous claims with no vegetation</p> </li> <li> <p><strong>Homogeneity marker:</strong> used to determine if a parcel geometry consists of a single crop or if multiple things are growing on the parcel</p> </li> <li> <p><strong>Bare soil marker:</strong> used to detect observation where bare soil is present on the feature of interest. This indicates agricultural activity on the FOI (plowing, harvest)</p> </li> <li> <p><strong>Similarity and distance markers:</strong> used to give additional context to the crop classification and to detect erroneous claims</p> </li> <li> <p><strong>Land marker:</strong> used to detect the land type and non-productive EFAs of the FOI</p> </li> <li> <p><strong>Crop-type marker:</strong> used to detect the specific crop growing on the FOI</p> </li> </ol> <p>This dataset is comprised of the geopackage file <em>"markers_summary.gpkg", </em>which was computed for the Cypriotic pilot region. Descriptions are given below.</p> <p><strong>Markers summary dataset</strong></p> <table> <caption><strong>Description of the information contained in the corresponding "markers summary" dataset</strong></caption> <thead> <tr> <th scope="col">Attribute name</th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td> POLY_ID </td> <td>Unique polygon identifier</td> </tr> <tr> <td>OBS_ALL</td> <td>Number of all available observations</td> </tr> <tr> <td>OBS_VALID</td> <td>Number of all valid observations</td> </tr> <tr> <td>CROP_CODE</td> <td>Crop identifier</td> </tr> <tr> <td>N_PIXEL</td> <td>Number of S2 pixels within FOI</td> </tr> <tr> <td>PLOTIDCROP</td> <td>PLOT_ID_CROP</td> </tr> <tr> <td>BS_APR_END</td> <td>Number of bare-soil observations between 2022-03-01 and 2022-04-30 </td> </tr> <tr> <td>BS_FEB_JUN</td> <td>Number of bare-soil observations between 2022-02-01 and 2022-06-30</td> </tr> <tr> <td>BS_JAN_APR</td> <td>Number of bare-soil observations between 2022-01-01 and 2022-04-30</td> </tr> <tr> <td>BS_JAN_MAR</td> <td>Number of bare-soil observations between 2022-01-01 and 2022-03-31</td> </tr> <tr> <td>BS_OCT_DEC</td> <td>Number of bare-soil observations between 2021-10-01 and 2021-12-31</td> </tr> <tr> <td>BS_OCT_SEP</td> <td>Number of bare-soil observations between 2021-10-01 and 2022-09-30</td> </tr> <tr> <td>P_CROP</td> <td>The FOI label as predicted by the crop group model</td> </tr> <tr> <td>CR_P_SCORE</td> <td>The pseudoprobability of the crop-group prediction. A score close to 1 indicates that the model is very confident in the prediction</td> </tr> <tr> <td>D_GROUP</td> <td>Declared crop group</td> </tr> <tr> <td>DIST_CROP</td> <td>Most similar crop according to the distance marker</td> </tr> <tr> <td>DIST_SC00</td> <td>Distance marker score of a most similar crop</td> </tr> <tr> <td>DIST_SCORE</td> <td>Distance marker score of a FOI when compared to nearby FOIs with the same claim. A value close to 100 indicates that a FOI is not similar to other FOIs with the same claim.</td> </tr> <tr> <td>HOM_CLASS</td> <td>Homogeneous/Heterogeneous</td> </tr> <tr> <td>HOM_SCORE</td> <td>Homogeneity probability assigned by the homogeneity marker</td> </tr> <tr> <td>P_LAND_GR</td> <td>The FOI label as predicted by the land group model using crop groupings based on land use</td> </tr> <tr> <td>LGRP_SCORE</td> <td>The pseudoprobability of the crop-group prediction. A score close to 1 indicates that the model is very confident in the prediction.</td> </tr> <tr> <td>D_LAND</td> <td>Declared land group</td> </tr> <tr> <td>M_NDVI_A_J</td> <td>Mean NDVI value in interval 2022-04-01 till 2022-07-31</td> </tr> <tr> <td>M_NDVI_F_M</td> <td>Mean NDVI value in interval 2022-02-01 till 2022-03-31</td> </tr> <tr> <td>M_NDVI_J_A</td> <td>Mean NDVI value in interval 2022-01-01 till 2022-04-30 </td> </tr> <tr> <td>MW_FEB_JUN</td> <td>Number of mowing events between 2022-02-01 and 2022-06-30</td> </tr> <tr> <td>MW_OCT_SEP</td> <td>Number of mowing events between 2021-10-01 and 2022-09-30</td> </tr> <tr> <td>MW_ALL</td> <td>Number of mowing events in the observation period</td> </tr> <tr> <td>SIM_CROP</td> <td>Most similar crop according to similarity marker</td> </tr> <tr> <td>SIM_SC00</td> <td>Similarity marker score of a most similar crop</td> </tr> <tr> <td>SIM_SCORE</td> <td>Similarity marker score of a FOI when compared to nearby FOIs with the same claim. A value close to 100 indicates that a FOI is not similar to other FOIs with the same claim.</td> </tr> </tbody> </table> <p> </p>
Non productive EFAs detection over the Lithuanian pilot region (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), the Super-Resolved Sentinel-2 data were further used to identify small-sized areas that can be characterised of great importance in terms of environmental sustainability, which in the Common Agricultural Policy (CAP) are denoted as Ecological Focus Area (EFA). EFAs are characterised as a portion of farmland area that has to be designed for environmental purposes. For the needs of DIONE, the EFAs regions were identified with the Sentinel-2 & Very High Resolution (VHR) data to be acquired from 01-08-2020 until 31-05-2021 providing tailored information for the needs of the Lithuanian Paying Agency (e.g. NPA).</p> <p><strong>Further Details of the provided EFAs dataset</strong></p> <p>There are only three EFA types present in the dataset given by NPA:</p> <ul> <li><strong>mg0:</strong> Tree group, forest</li> <li><strong>gr0:</strong> Ditch, the canal from 1 m wide</li> <li><strong>ku0:</strong> Pond with coastal vegetation</li> </ul> <p>Due to the nature of the data, the majority of EFA polygons do not contain at least one full Sentinel-2 pixel. To circumvent this issue, the 2.5m resolution output of the multi-temporal SR model is used to produce EFA signals. Using 2.5m resolution, around 20% of FOIs belonging to the <em>"Ditch, canal from 1m wide"</em> class do not contain one full super-resolved pixel at 2.5m resolution. Out of "34157" EFA polygons in the sample area, we have signals for "32732" of them. The majority are missing due to pixelization (~1000 EFA FOIs fully contain less than 1 SR pixel), others are missing due to having no cloud-free observation during the observation period.</p> <p><strong>Details for the model </strong><strong>deployed</strong></p> <p>To classify EFAs an LSTM model is used (same as for crop type classification). The model is trained as a binary classifier using:</p> <ul> <li>LSTM FOIs inside the test area as positive examples</li> <li>Agricultural parcels inside the test area as negative examples</li> </ul> <p>Five models are trained using a 5-fold split to ensure that the results are predicted on data the model has not seen.</p> <p><strong>Results</strong></p> <table> <caption><strong>Overall performance of the models</strong></caption> <thead> <tr> <th scope="col">Accuracy = 91.1</th> </tr> </thead> <tbody> <tr> <td> </td> <td><strong>Precision </strong></td> <td><strong>Recall</strong></td> <td><strong> F1 </strong></td> <td><strong>Count</strong></td> </tr> <tr> <td><strong>EFA</strong></td> <td>92.3 </td> <td>93.2</td> <td>92.8</td> <td>32732</td> </tr> <tr> <td><strong>NOT EFA</strong></td> <td>89.2</td> <td>87.9</td> <td>88.6</td> <td>21005</td> </tr> </tbody> </table> <p>In reality, we are only interested to detect wrongly / fraudulently claimed EFAs - meaning FOIs that are claimed as EFAs and are in reality some kind of agricultural land. The model is less confident in predicting EFAs as EFAs for the <em>"Ditch/Canal"</em> group. This is probably due to the fact that these polygons are long and narrow and the most susceptible to registration errors and shifts which we know are present in the SR data from which the signals were produced.</p> <p>This dataset is comprised of one geopackage file, the <em>"efas-w-results-v0-binary.gpkg", which</em> was computed for the Lithuanian pilot region<em>. </em>Descriptions are given below.</p> <ul> <li><strong>classification</strong>: Whether the model thinks the FOI is an EFA (`EFA`) or not (`NOT_EFA`)</li> <li><strong>classification_score:</strong> the pseudoprobability of the EFA prediction as assigned by the crop-group model <ul> <li> a score close to 1 indicates that the model is very confident in the prediction</li> <li> a score close to 0 indicates that the model is not confident in the prediction</li> </ul> </li> </ul>
EO-based area monitoring markers computed over the Lithuanian pilot region (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), the following EO-based monitoring marker maps were released over the two pilot regions, containing the results produced from a set of image analysis and machine learning techniques. The latest explores the benefits of Copernicus's multispectral high-resolution Sentinel-2 data acquired from 01-01-2022 until 04-07-2021 and provides tailored information for the needs of European paying agencies (e.g. CAPO and NPA), expressed with the following markers.</p> <ol> <li> <p><strong>Mowing marker:</strong> used to detect mowing events on meadow/grass like Features Of Interest (FOI)</p> </li> <li> <p><strong>Mean-NDVI marker:</strong> used to detect erroneous claims with no vegetation</p> </li> <li> <p><strong>Homogeneity marker:</strong> used to determine if a parcel geometry consists of a single crop or if multiple things are growing on the parcel</p> </li> <li> <p><strong>Bare soil marker:</strong> used to detect observation where bare soil is present on the feature of interest. This indicates agricultural activity on the FOI (plowing, harvest)</p> </li> <li> <p><strong>Similarity and distance markers:</strong> used to give additional context to the crop classification and to detect erroneous claims</p> </li> <li> <p><strong>Land marker:</strong> used to detect the land type and non-productive EFAs of the FOI</p> </li> <li> <p><strong>Crop-type marker:</strong> used to detect the specific crop growing on the FOI</p> </li> </ol> <p>This dataset is comprised of one geopackage file, the <em>"markers_summary.gpkg", which</em> was computed for the Lithuanian pilot region<em>. </em>Descriptions are given below.</p> <p><strong>Markers summary dataset: </strong>There is a total of **1074460** FOIs for the complete country GSAA dataset. Out of these, markers are computed on **996028** FOIs that contain more than 1 Sentinel-2 pixel.</p> <table> <caption><strong>Description of the information contained in the corresponding "markers summary" dataset</strong></caption> <thead> <tr> <th scope="col">Attribute name </th> <th scope="col">Description </th> </tr> </thead> <tbody> <tr> <td>POLY_ID </td> <td>Reference ID of the polygon</td> </tr> <tr> <td>CROP_LABEL</td> <td>Declared crop group</td> </tr> <tr> <td>S2_all_observations_count</td> <td>Count of all observations </td> </tr> <tr> <td>S2_valid_observations_count</td> <td>Count of all valid observations</td> </tr> <tr> <td>S2_pixel_count</td> <td>Number of S2 pixels within FOI</td> </tr> <tr> <td>declared_as</td> <td>Declared crop group (v1)</td> </tr> <tr> <td>classification_score</td> <td>The pseudoprobability of the crop-group (v1) prediction. A score close to 1 indicates that the model is very confident in the prediction</td> </tr> <tr> <td>classification </td> <td>The FOI label as predicted by the crop group (v1) model</td> </tr> <tr> <td>crop_declared_as_2</td> <td>Declared crop group (v2)</td> </tr> <tr> <td>crop_classification_score_2</td> <td>The pseudoprobability of the crop-group (v2) prediction. A score close to 1 indicates that the model is very confident in the prediction</td> </tr> <tr> <td>crop_classification_2</td> <td>The FOI label as predicted by the crop group (v2) model</td> </tr> <tr> <td>mowing_event_count</td> <td>Number of mowing events detected</td> </tr> </tbody> </table>
Non productive EFAs detection over the Cypriotic pilot region (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), the Super-Resolved Sentinel-2 data were further used to identify small-sized areas that can be characterised of great importance in terms of environmental sustainability, which in the Common Agricultural Policy (CAP) are denoted as Ecological Focus Area (EFA). EFAs are characterised as a portion of farmland area that has to be designed for environmental purposes. For the needs of DIONE, the EFAs regions were identified with the Sentinel-2 & Very High Resolution (VHR) data to be acquired from 01-08-2020 until 25-06-2021 providing tailored information for the needs of the Cypriotic Paying Agency (e.g. CAPO).</p> <p><strong>Further Details of the provided EFAs dataset</strong></p> <p>The EFA polygons were downloaded from the EFA endpoints provided by CAPO.</p> <p>There are three EFA types present in the dataset:</p> <ul> <li><strong>Points: </strong>Trees</li> <li><strong>Lines</strong>: Ditches</li> <li><strong>Polygons</strong>: Productive EFAs - The current layer will not be exploited in the content of the DIONE project, as it is predominately focused on the detection of *non-productive (stable)* EFA elements.</li> </ul> <p>The points and lines had to be buffered to an extent of 5m so that the signals could be downloaded. Because the elements considered are very small and they would not fit into one full Sentinel-2 pixel, signals were downloaded from the 2.5m resolution output of the multi-temporal Super Resolution model. The observation period for EFAs detection is from 01-08-2020 until 25-06-2021. Results are provided for 52691 point polygons and 454 line polygons located in the test area.</p> <p><strong>Details for the model </strong><strong>deployed</strong></p> <p>To classify EFAs an LSTM model is used. The model is trained as a binary classifier using:</p> <ul> <li>Signals from EFA (buffered point and line geometries) FOIs inside the test area as positive examples</li> <li>Signals from agricultural parcels inside the test area as negative examples</li> </ul> <p>Five models are trained using a 5-fold split to ensure that the results are predicted on data the model has not seen.</p> <p><strong>Results</strong></p> <table> <caption><strong>Overall performance of the models</strong></caption> <thead> <tr> <th scope="col">Accuracy = 82.9</th> </tr> </thead> <tbody> <tr> <td> </td> <td><strong>Precision </strong></td> <td><strong>Recall</strong></td> <td><strong> F1 </strong></td> <td><strong>Count</strong></td> </tr> <tr> <td><strong>EFA</strong></td> <td>84.9</td> <td>92.9</td> <td>88.7</td> <td>53008</td> </tr> <tr> <td><strong>NOT EFA</strong></td> <td>74.9</td> <td>56.4</td> <td>64.3</td> <td>19992</td> </tr> </tbody> </table> <p>In reality, we are only interested in one side of the confusion matrix. We want to detect wrongly / fraudulently claimed EFAs - meaning FOIs that are claimed as EFAs and are in reality some kind of agricultural land. In these cases, 93% of the claimed EFAs were confirmed to be EFAs and for 7% of the EFA FOIs, the model disagrees.</p> <p>This dataset is comprised of one geopackage file, the <em>"efas_summary.gpkg", which</em> was computed for the Cypriotic pilot region<em>. </em>Descriptions are given below.</p> <ul> <li> <p><strong>classification: </strong>Whether the model thinks the FOI is an EFA (`EFA`) or not (`NOT_EFA`)</p> </li> <li> <p><strong>classification_score:</strong><strong> </strong>The pseudoprobability of the EFA prediction as assigned by the crop-group mode</p> <ul> <li> <p>a score close to 1 indicates that the model is very confident in the prediction</p> </li> <li> <p>a score close to 0.5 indicates that the model is not confident in the prediction</p> </li> </ul> </li> </ul>
Soil Organic Carbon Content estimations over the Lithuanian pilot area (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), Soil Organic Carbon Content (SOC) estimations have been released as outputs of novel machine learning algorithms which combined the point measurements (i.e. soil properties detected by the Soil Scanning Systems) with temporal EO multispectral imagery and other ancillary variables, enabling end-users, and for the DIONE case, the national paying agency of Lithuania (National Paying Agency - NPA) to mine meaningful information about overall soil health and the effects applied agricultural practices.<br> The dataset is delivered in a single-banded GeoTIFF file (DIONE_SOC_estimations_LT_2022.tif- EPSG:4326) containing the SOC content (SOC %) labelled as Band 1.</p>
Soil Organic Carbon Content estimations over the Cypriot pilot area (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), Soil Organic Carbon Content (SOC) estimations have been released as outputs of novel machine learning algorithms which combined the point measurements (i.e. soil properties detected by the Soil Scanning Systems) with temporal EO multispectral imagery and other ancillary variables, enabling end-users, and for the DIONE case, the national paying agency of Cyprus (Cyprus Agricultural Payments Organisation - CAPO) to mine meaningful information about overall soil health and the effects applied agricultural practices.<br> The dataset is delivered in a single-banded GeoTIFF file (DIONE_SOC_estimations_CY_2022.tif- EPSG:4326) containing the SOC content (SOC %) labelled as Band 1.<br> </p>
Soil properties as point estimations over the Lithuanian pilot area (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), VNIR topsoil reflectance was captured with DIONE’s Soil Scanning System and transformed through Machine Learning modelling to a set of soil properties that are meaningful for the assessment of soil health. The captured reflectance measurements correspond to locations distributed within the pilot areas of Lithuania and are indicated after the analysis of EO multispectral imagery, aiming to create a collection of point locations that well represent the soil characteristics of the area, and provide valuable information about soil condition through the estimations of the following soil properties:</p> <ul> <li>Sand %</li> <li>Clay %</li> <li>Silt %</li> <li>Electrical Conductivity (mS/m)</li> <li>pH</li> <li>Calcium carbonate %</li> <li>Soil Organic Carbon %</li> </ul> <p>The dataset is delivered in a shapefile format (DIONE_LT_point_estimations_2022_WP4.shp - EPSG:4326 - WGS 84) containing the following fields:</p> <table> <caption><strong>Description of the information contained in the corresponding "LT points estimations" dataset</strong></caption> <thead> <tr> <th scope="col">Field </th> <th scope="col">Type </th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>Sample ID</td> <td>String </td> <td>Unique ID</td> </tr> <tr> <td>Lat</td> <td>Real </td> <td>Latitude </td> </tr> <tr> <td>Lon</td> <td>Real </td> <td>Longitude</td> </tr> <tr> <td>Sand </td> <td>Real </td> <td>Sand fraction</td> </tr> <tr> <td>Clay</td> <td>Real </td> <td>Clay fraction</td> </tr> <tr> <td>Silt</td> <td>Real </td> <td>Silt fraction</td> </tr> <tr> <td>EC </td> <td>Real </td> <td>Electrical Conductivity</td> </tr> <tr> <td>ph_H<sub>2</sub>0</td> <td>Real </td> <td>ph</td> </tr> <tr> <td>CaCO<sub>3</sub></td> <td>Real </td> <td>Calcium Carbonate</td> </tr> <tr> <td>SOC </td> <td>Real </td> <td>Soil Organic Carbon</td> </tr> </tbody> </table>
Soil properties as point estimations over the Cypriot pilot area (2022)
<p>In the context of the EU-funded project DIONE (No. 870378), VNIR topsoil reflectance was captured with DIONE’s Soil Scanning System and transformed through Machine Learning modelling to a set of soil properties that are meaningful for the assessment of soil health. The captured reflectance measurements correspond to locations distributed within the pilot areas of Cyprus and are indicated after the analysis of EO multispectral imagery, aiming to create a collection of point locations that well represent the soil characteristics of the area, and provide valuable information about soil condition through the estimations of the following soil properties:</p> <ul> <li>Sand %</li> <li>Clay %</li> <li>Silt %</li> <li>Electrical Conductivity (mS/m)</li> <li>pH</li> <li>Calcium carbonate %</li> <li>Soil Organic Carbon %</li> </ul> <p>The dataset is delivered in a shapefile format (DIONE_CY_point_estimations_2022_WP4.shp - EPSG:4326 - WGS 84) containing the following fields:</p> <table> <caption><strong>Description of the information contained in the corresponding "CY points estimations" dataset</strong></caption> <thead> <tr> <th scope="col">Field </th> <th scope="col">Type </th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>Sample_ID</td> <td>String</td> <td>Unique ID</td> </tr> <tr> <td>Lat</td> <td>Real</td> <td>Latitude </td> </tr> <tr> <td>Lon</td> <td>Real</td> <td>Longitude</td> </tr> <tr> <td>Sand</td> <td>Real</td> <td>Sand fraction</td> </tr> <tr> <td>Clay</td> <td>Real</td> <td>Clay fraction</td> </tr> <tr> <td>Silt</td> <td>Real</td> <td>Silt fraction</td> </tr> <tr> <td>EC</td> <td>Real</td> <td>Electrical Conductivity</td> </tr> <tr> <td>ph_H<sub>2</sub>0</td> <td>Real</td> <td>pH</td> </tr> <tr> <td>CaCO<sub>3</sub></td> <td>Real</td> <td>Calcium Carbonate</td> </tr> <tr> <td>SOC</td> <td>Real</td> <td>Soil Organic Carbon</td> </tr> </tbody> </table> <p> </p>
Soil Organic Carbon Content estimations over the Cypriot pilot area (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), Soil Organic Carbon Content (SOC) estimations have been released as outputs of novel machine learning algorithms which combined the point measurements (i.e. soil properties detected by the Soil Scanning Systems) with temporal EO multispectral imagery and other ancillary variables, enabling end-users, and for the DIONE case, the national paying agency of Cyprus (Cyprus Agricultural Payments Organisation - CAPO) to mine meaningful information about overall soil health and the effects applied agricultural practices at a parcel level.</p> <p>The dataset is delivered in a shapefile format (DIONE_SOC_estimations_CY_2021.shp - EPSG: 4326) containing the SOC content (SOC %) labeled as SOC.</p>
Soil properties as point estimations over the Lithuanian pilot area (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), VNIR topsoil reflectance was captured with DIONE’s Soil Scanning System and transformed through Machine Learning modelling to a set of soil properties that are meaningful for the assessment of soil health. The captured reflectance measurements correspond to locations distributed within the pilot areas of Lithuania and are indicated after the analysis of EO multispectral imagery, aiming to create a collection of point locations that well represent the soil characteristics of the area, and provide valuable information about soil condition through the estimations of the following soil properties:</p> <ul> <li>Sand %</li> <li>Clay %</li> <li>Silt %</li> <li>Electrical Conductivity (mS/m)</li> <li>pH</li> <li>Calcium carbonate %</li> <li>Soil Organic Carbon %</li> </ul> <p>The dataset is delivered in a shapefile format (DIONE_LT_point_estimations_2021.shp - EPSG:4326 - WGS 84) containing the following fields:</p> <table> <caption><br> <strong>Description of the information contained in the corresponding "LTH points estimations" dataset</strong></caption> <thead> <tr> <th scope="col">Field</th> <th scope="col">Type</th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>Sample_ID</td> <td>String</td> <td>Unique ID</td> </tr> <tr> <td>lat</td> <td>Real</td> <td>Latitude </td> </tr> <tr> <td>lon</td> <td>Real</td> <td>Longitude</td> </tr> <tr> <td>Sand</td> <td>Real</td> <td>Sand fraction</td> </tr> <tr> <td>Clay</td> <td>Real</td> <td>Clay fraction</td> </tr> <tr> <td>Silt</td> <td>Real</td> <td>Silt fraction</td> </tr> <tr> <td>EC</td> <td>Real</td> <td>Electrical Conductivity</td> </tr> <tr> <td>pH_H20</td> <td>Real</td> <td>pH</td> </tr> <tr> <td>CaCO3</td> <td>Real</td> <td>Calcium Carbonate </td> </tr> <tr> <td>SOC</td> <td>Real</td> <td>Soil Organic Carbon</td> </tr> </tbody> </table> <p><br> </p>
Soil properties as point estimations over the Cypriot pilot area (2021)
<p>In the context of the EU-funded project DIONE (No. 870378), VNIR topsoil reflectance was captured with DIONE’s Soil Scanning System and transformed through Machine Learning modelling to a set of soil properties that are meaningful for the assessment of soil health. The captured reflectance measurements correspond to locations distributed within the pilot areas of Cyprus and are indicated after the analysis of EO multispectral imagery, aiming to create a collection of point locations that well represent the soil characteristics of the area, and provide valuable information about soil condition through the estimations of the following soil properties:</p> <ul> <li>Sand %</li> <li>Clay %</li> <li>Silt %</li> <li>Electrical Conductivity (mS/m)</li> <li>pH</li> <li>Calcium carbonate %</li> <li>Soil Organic Carbon %</li> </ul> <p>The dataset is delivered in a shapefile format (DIONE_CY_point_estimations_2021.shp - EPSG:4326 - WGS 84) containing the following fields:</p> <table> <caption><strong>Description of the information contained in the corresponding "CY points estimations" dataset</strong></caption> <thead> <tr> <th scope="col">Field</th> <th scope="col">Type</th> <th scope="col">Description</th> </tr> </thead> <tbody> <tr> <td>Sample_ID</td> <td>String</td> <td>Unique ID</td> </tr> <tr> <td>lat</td> <td>Real</td> <td>Latitude </td> </tr> <tr> <td>lon</td> <td>Real </td> <td>Longitude</td> </tr> <tr> <td>Sand</td> <td>Real</td> <td>Sand fraction</td> </tr> <tr> <td>Clay</td> <td>Real</td> <td>Clay fraction</td> </tr> <tr> <td>Silt</td> <td>Real</td> <td>Silt fraction</td> </tr> <tr> <td>EC</td> <td>Real</td> <td>Electrical Conductivity</td> </tr> <tr> <td>pH_H20</td> <td>Real</td> <td>pH</td> </tr> <tr> <td>CaCO3</td> <td>Real</td> <td>Calcium Carbonate </td> </tr> <tr> <td>SOC</td> <td>Real</td> <td>Soil Organic Carbon</td> </tr> </tbody> </table> <p> </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.