Seagrass and hydrographic data for the Mediterranean Sea.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31453288", "kind": "science-record", "revision": 4, "content_hash": "sha256:fa8b30200a7515dc3c3c6b19b1440b9c4e622afcb93a45eab55d1c991f039c84", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T21:22:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Seagrass and hydrographic data for the Mediterranean Sea.", "doi": "10.1016/j.dib.2019.104286", "pmid": "31453288", "authors": ["Dimitrios Effrosynidis", "Avi Arampatzis", "Georgios Sylaios"], "journal": "Data in brief", "year": 2019, "abstract": "The dataset includes 1,771 locations of major seagrass families (Cymodoceaceae, Zosteraceae, Posidoniaceae, Hydrocharitaceae, Ruppiaceae), which are further divided into the species they include, as well as 1,284 locations of seagrass absence (algorithmically produced), in the Mediterranean Sea. For each location, 217 biological, chemical, physics, and human related parameters are available, which were merged from other publicly available data sources. As the most comprehensive dataset for seagrass in the Mediterranean to date, it is suitable for data analysis and machine learning. For more insight, please see \"Seagrass Detection in the Mediterranean: A Supervised Learning Approach\" (Effrosynidis et al., 2018). The dataset is available on Mendeley Data (Effrosynidis, 2019).", "claims": [{"id": "claim-method", "statement": "Finally, we display the Spearman's rank between the variables of the dataset as it is a standard first step for machine learning engineers to check for the correlation between variables (Fig. 3).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31453288", "locator": "sections[7] \"Dataset analysis\" paragraph 5", "quote": "Finally, we display the Spearman's rank between the variables of the dataset as it is a standard first step for machine learning engineers to check for the correlation between variables (Fig. 3)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data are publicly available on Mendeley Data (https://data.mendeley.com/datasets/8nmh5grxp8/1) [2]", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31453288", "locator": "sections[1] \"p\" paragraph 1", "quote": "All data are publicly available on Mendeley Data (https://data.mendeley.com/datasets/8nmh5grxp8/1) [2]"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:31453288"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31453288", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104286", "sha256": "sha256:a3781da0d96f4222fe4254ba80d37b6b93aacd48eb941b22eb21ae8910d0554f", "bytes": 18993, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104286", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6700390", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:31453288:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ce7578508d45a4bced1235162f389f51a97a14d4ce5329f87e5bb66131daa148", "bytes": 1299, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications table", "structure": {"pmcid": "PMC6700390", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications table", "rows": [["Subject area", "Biology"], ["More specific subject area", "Marine Ecology"], ["Type of data", "Table, figures"], ["How data was acquired", "Several datasets from sources such as UNEP-WCMC global biodiversity standardized database, Copernicus Marine Environmental Service, European Marine Observation and Data Network, and Hydrosheds were aggregated using Python."], ["Data format", "Raw, processed, and analyzed."], ["Experimental factors", "The data consists of in-situ observations and the variables were aggregated from several databases."], ["Experimental features", "For each observation, 217 environmental variables are presented"], ["Data source location", "Mediterranean Sea (from −5.60° to 36.29° E in longitude and 30.18° to 45.97° N in latitude)."], ["Data accessibility", "All data are publicly available on Mendeley Data (https://data.mendeley.com/datasets/8nmh5grxp8/1) [2]"], ["Related research article", "Effrosynidis D., Arampatzis A., & Sylaios, G. (2018). Seagrass Detection in the Mediterranean: A Supervised Learning Approach. Ecological Informatics 2018, 48, 158–170, https://doi.org/10.1016/j.ecoinf.2018.09.004[1]."]], "row_count": 10, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31453288:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:93ece038f1d05887dbb3b6a50706bf1d3fb193bc194e926e5eead798b5b7ac4a", "bytes": 633, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6700390", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the data•This dataset can be used in machine learning classification tasks to classify an unknown location having seagrass or not, and if it has, in which seagrass family it belongs to.•This dataset can also help in finding which variables are most important when classifying seagrasses and under which conditions each seagrass family favors.•Provided data can be used to resolve conditions related to seagrass presence and absence and the differences between them."]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31453288:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1491ffbf8dfa3dd06f562f44d394810636190df0f0a69a1fe5716476f7a5a6a4", "bytes": 790, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "Seagrass families’ presence in dataset. The last column shows how the species of the initial dataset can be grouped to form the families.", "structure": {"pmcid": "PMC6700390", "section_index": 2, "section_title": "Data", "row_count": 6, "column_count": 4}, "table": {"label": "Table 1", "caption": "Seagrass families’ presence in dataset. The last column shows how the species of the initial dataset can be grouped to form the families.", "rows": [["Seagrass Family", "Instances", "Percentage", "Species of this Family"], ["Cymodoceaceae", "1,337", "75.49%", "Cymodocea nodosa, Cymodoceaceae Cymodocea nodosa"], ["Zosteraceae", "187", "10.56%", "Zostera noltii, Zostera marina, Zosteraceae Zostera noltii, Zosteraceae Zostera marina"], ["Posidoniaceae", "125", "7.07%", "Posidoniaceae Posidonia oceanica"], ["Hydrocharitaceae", "94", "5.30%", "Halophila stipulacea, Hydrocharitaceae Halophila stipulacea"], ["Ruppiaceae", "28", "1.58%", "Ruppia maritima, Ruppia cirrhosa"]], "row_count": 6, "column_count": 4, "numeric_cells": 10, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:31453288:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cbecdef4b7e8d87601ec39f40f23708bf501eb60ca7aeb049cf85f3613bdb4c7", "bytes": 938, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#tbl2", "version": null, "note": "Seagrass families’ Hydrographic Variables selected to be collected from publicly available databases for each seagrass data point.", "structure": {"pmcid": "PMC6700390", "section_index": 2, "section_title": "Data", "row_count": 14, "column_count": 4}, "table": {"label": "Table 2", "caption": "Seagrass families’ Hydrographic Variables selected to be collected from publicly available databases for each seagrass data point.", "rows": [["Name", "Type", "Layers", "Variables"], ["Bathymetry", "Static", "–", "1"], ["Temperature", "Temporal", "2 (surface, bottom)", "38"], ["Salinity", "Temporal", "2 (surface, bottom)", "38"], ["Chlorophyll-α", "Temporal", "1 (surface)", "19"], ["Nitrate", "Temporal", "2 (surface, bottom)", "38"], ["Phosphate", "Temporal", "2 (surface, bottom)", "38"], ["Secchi Disk Depth", "Temporal", "1 (surface)", "19"], ["Wave Height", "Temporal", "1 (surface)", "19"], ["Distance from nearest City", "Static", "–", "2"], ["Distance from nearest River Mouth", "Static", "–", "2"], ["Distance from nearest Port", "Static", "–", "1"], ["Distance to Coast", "Static", "–", "1"], ["Substrate", "Static", "–", "1"]], "row_count": 14, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[2]/table-wrap[2]#tbl2"}}, {"id": "asset:table:pmid:31453288:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:57c098bf4c5c531f34655892b01ab92371a58eda90342be247fa124d79096e1b", "bytes": 749, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#tbl3", "version": null, "note": "CMEMS products and spatial resolution for the temporally-changing hydrographic and water quality variables.", "structure": {"pmcid": "PMC6700390", "section_index": 5, "section_title": "Dataset creation", "row_count": 7, "column_count": 3}, "table": {"label": "Table 3", "caption": "CMEMS products and spatial resolution for the temporally-changing hydrographic and water quality variables.", "rows": [["Parameter", "CMEMS Product", "Resolution"], ["Chlorophyll-a", "MEDSEA REANALYSIS_BIO_006_008", "0.063° × 0.063°"], ["Nutrients", "MEDSEA REANALYSIS_BIO_006_008", "0.063° × 0.063°"], ["Salinity", "MEDSEA REANALYSIS_PHYS_006_004", "0.063° × 0.063°"], ["Secchi Disk depth", "OCEANCOLOUR_GLO_OPTICS_L4_REP_OBSERVATIONS_009_081", "1 km × 1 km"], ["Significant wave height", "MEDSEA_HINDCAST_WAV_006_012", "0.042° × 0.042°"], ["Water Temperature", "MEDSEA REANALYSIS_PHYS_006_004", "0.063° × 0.063°"]], "row_count": 7, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[5]/table-wrap[1]#tbl3"}}, {"id": "asset:table:pmid:31453288:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:282cd6ab97c0095614a8685aebed4e90da89ef58c3d08d28292e4b70cde293f7", "bytes": 544, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#tbl4", "version": null, "note": "Substrate Types at final seagrass database points (data from EMODnet database).", "structure": {"pmcid": "PMC6700390", "section_index": 7, "section_title": "Dataset analysis", "row_count": 12, "column_count": 2}, "table": {"label": "Table 4", "caption": "Substrate Types at final seagrass database points (data from EMODnet database).", "rows": [["Substrate Type", "Count"], ["Unknown", "663"], ["Sand", "550"], ["Fine mud", "503"], ["Posidonia oceanica meadows", "401"], ["Seabed Sandy mud", "287"], ["Coarse and mixed sediment", "275"], ["Muddy sand", "189"], ["Dead mattes of Posidonia oceanica", "101"], ["Cymodocea nodosa meadows", "47"], ["Seabed", "34"], ["SeabedSeabed", "5"]], "row_count": 12, "column_count": 2, "numeric_cells": 11, "header_rows": 1, "locator": "section[7]/table-wrap[1]#tbl4"}}, {"id": "asset:table:pmid:31453288:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aeb89ab900788e9525792b881f9eb3b1bcdee03b1cce4792dee83f8a0f4164a8", "bytes": 793, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#tbl5", "version": null, "note": "Statistics for static variables.", "structure": {"pmcid": "PMC6700390", "section_index": 7, "section_title": "Dataset analysis", "row_count": 6, "column_count": 8}, "table": {"label": "Table 5", "caption": "Statistics for static variables.", "rows": [["", "Bathymetry (m)", "Distance to Major Cities (degrees)", "Distance to Complete Cities (degrees)", "Distance to Port (degrees)", "Distance to Major River (degrees)", "Distance to Complete River (degrees)", "Distance to Coast (degrees)"], ["Mean", "−52.52", "0.6843", "0.0416", "0.2564", "2.0753", "6.6912e-02", "0.0149"], ["Std", "123.99", "0.4162", "0.0457", "0.2183", "1.6058", "8.6419e-02", "0.0248"], ["Min", "−2416.80", "0.0037", "0.000015", "0.00034", "0.0207", "8.2400e-11", "0"], ["Median", "−17.46", "0.6604", "0.0314", "0.19463", "1.5440", "4.1886e-02", "0.0076"], ["Max", "0", "2.7394", "1.0354", "1.25", "9.8424", "7.1247e+00", "1.0068"]], "row_count": 6, "column_count": 8, "numeric_cells": 35, "header_rows": 1, "locator": "section[7]/table-wrap[2]#tbl5"}}, {"id": "asset:table:pmid:31453288:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:260a1c75513ab621814dfcfc1ecd8510c6476d4e9c8489b3094f51033292bd57", "bytes": 692, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[3]#tbl6", "version": null, "note": "Spatial Statistics for temporally-changing variables (Annual average values at the sea surface).", "structure": {"pmcid": "PMC6700390", "section_index": 7, "section_title": "Dataset analysis", "row_count": 6, "column_count": 8}, "table": {"label": "Table 6", "caption": "Spatial Statistics for temporally-changing variables (Annual average values at the sea surface).", "rows": [["", "Temperature (degC)", "Salinity", "Chlorophyll-α (mg/m3)", "Nitrate (mmol/m3)", "Phosphate (mmol/m3)", "Secchi Disk Depth (m)", "Wave Height (m)"], ["Mean", "19.64", "38.15", "0.21", "0.79", "0.01", "17.05", "0.63"], ["Std", "1.41", "0.99", "0.22", "2.55", "0.01", "5.91", "0.25"], ["Min", "16.31", "25.92", "0.00", "0.00", "0.00", "1.82", "0.12"], ["Median", "19.88", "38.11", "0.13", "0.20", "0.01", "17.78", "0.60"], ["Max", "23.50", "39.60", "2.27", "38.76", "0.46", "38.74", "1.78"]], "row_count": 6, "column_count": 8, "numeric_cells": 35, "header_rows": 1, "locator": "section[7]/table-wrap[3]#tbl6"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Finally, we display the Spearman's rank between the variables of the dataset as it is a standard first step for machine learning engineers to check for the correlation between variables (Fig. 3)."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["All data are publicly available on Mendeley Data (https://data.mendeley.com/datasets/8nmh5grxp8/1) [2]"], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["spearman_rho"], "assets": ["source:pmid:31453288", "asset:table:pmid:31453288:1", "asset:table:pmid:31453288:2", "asset:table:pmid:31453288:3", "asset:table:pmid:31453288:4", "asset:table:pmid:31453288:5", "asset:table:pmid:31453288:6", "asset:table:pmid:31453288:7", "asset:table:pmid:31453288:8"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 14798, "completion_tokens": 2838, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:31453288", "type": "paper", "label": "pmid:31453288"}, {"id": "source:pmid:31453288", "type": "manuscript", "label": "PMID 31453288 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31453288", "type": "paper", "label": "pmid:31453288"}, {"id": "source:pmid:31453288", "type": "manuscript", "label": "PMID 31453288 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31453288", "type": "extraction", "used": ["source:pmid:31453288"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:31453288", "parent_hash": "sha256:9a3a39d88a969c3406a3abc903b0565fe1c3415e833cba3f3e8cfc392d30d8db", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Finally, we display the Spearman's rank between the variables of the dataset as it is a standard first step for machine learning engineers to check for the correlation between variables (Fig. 3)."], "order_basis": "analysis_only", "id": "assay:1"}]}