DOI: 10.14466/CefasDataHub.171

Description

Model agreement data for Environmental Niche Model (ENM) outputs for 19 vulnerable species under climate change until end of century around northwestern Europe. A model ensemble of 5 ENMs was used (MaxEnt, Generalised Linear Models, Support Vector Machine, Random Forest and Bayesian Additive Regression Trees), and projections were made under two different emission scenarios: RCP4.5 and RCP 8.5. The data shows model agreement (normalised to 1) for presence/absence decadal projections from 2020 to 2100. Only ENMs with an Area Under the Curve (AUC) score of at least 0.7 were considered. The data is based on the output of an ensemble of 5 Environmental Niche Modeling techniques: Maximum Entropy (MaxEnt), Generalised Linear Model (GLM), Support Vector Machine (SVM), Random Forest and Bayesian Additive Regression Trees (BART). Each model was trained to capture the environmental requirements of individual species, using the 10 year-average in the period 2005-2014 of the environmental variables: near-bed and sea surface temperature, near-bed and sea surface salinity, and their differences, sea surface chlorophyll concentrations, water depth and substrate properties.

Once the models were trained, they were used to study future habitat suitability for the 19 vulnerable marine species selected for this piece of work, in 10-year averages to the end of century. To produce maps of the suitable habitat, the model projections were converted to binary presence/absence data using the thresholds that optimized the True Skill Statistics (TSS) of each model. The data shows the model agreement, normalised to 1 ("1" denotes all ENMs agree an area is suitable, "0" denotes all ENMs agree an area is not suitable). The number of ENMs considered for each combination of species and emission scenario depends on model performance. A ENM model was considered if its Area Under the Curve (AUC) score of the Receiver Operator Characteristic (ROC) curve was at least 0.7. Model performance is listed in the file "Model performance.csv".

Model input data: Climate change projection data from Plymouth Marine Laboratory (PML) (as referenced in Marine Biology paper). Species presence records from online databases (Ocean Biodiversity Information System (OBIS), Global Biodiversity Information System (GBIF) (references provided in associated Marine Biology paper and modelinputdatareadme), and from additional data sources as described in the Marine Biology paper and modelinputdatareadme. Models were trained using the R software.

Study region: northeast Atlantic shelf. Latitudes between -17° and 9.25°; longitudes between 44° and 65°.

These datasets were produced for the study in the article "Climate change resilience of vulnerable marine species in northwest Europe" in Marine Biology.

Contributors

Couce, Elena / Pinnegar, John / Townhill, Bryony

Subject

Climate / Species / Biodiversity

Start Date

01/01/2005

End Date

31/12/2100

Year Published

2025

Version

1

Citation

Couce, Pinnegar & Townhill. (2025). Species distribution model agreement data for 19 vulnerable marine species under future climate change scenarios in northwest Europe from 2020 to 2100. Cefas, UK. V1. doi: https://doi.org/10.14466/CefasDataHub.171

Rights List

Open Government Licence

DOI

10.14466/CefasDataHub.171