Geoportal

Details

.

General

Meta data ID	{BC3B728B-0433-4C6B-9F00-A7C3952A67F5}
Last modified	2021-12-20T09:31:23

Dataset creators

Contact person

First name	Lauri
Last name	Kuismanen
Email	Lauri.Kuismanen(at)syke.fi
Organisation	Finnish Environment Institute Syke

Dataset creators

First name	Elina A.
Last name	Virtanen
Organisation	Finnish Environment Institute Syke

Project

Project name	SEAmBOTH - Seamless Maps and Management of the Bothnian Bay
Project funder	Interreg Nord, Swedish Agency for Marine and Water Management, and the Regional Council of Lapland

Description

Basic information

Dataset title	Species distribution models developed in the SEAmBOTH project
Theme	Biology and Ecology
Description	The SEAmBOTH (https://seamboth.wordpress.com/) ecological models were based on biological inventory data and environmental layers, developed for the SEAmBOTH study area. Some environmental data were derived from other data sources, developed, for example, for the use of other projects, such as the Finnish Inventory Programme for the Underwater Marine Diversity (VELMU). Currently, the model layers included in the data package only cover the Finnish side of the study area (northernmost Bothnian Bay). Used environmental variables included: seafloor substrates (rock, boulders, mud, sand and mobile/unstable sediments), chlorophyll-a, depth, nutrients, salinity, surface exposure, seafloor fetch, shallow areas (satellite-derived) and turbidity (satellite-derived). The ecological models were developed utilizing a machine learning method, generalized boosting machine and additional functions from boosted regression trees (see details from the SEAmBOTH final report: https://seamboth.files.wordpress.com/2020/06/seamboth_finalreport.pdf). Datasets were split into model training and testing with a ratio of 70/30, and for models with too little data for training/test separation, the full dataset was used in the modelling with 10-fold cross-validation. Independent test evaluations were not calculated for those models. For species with too little data for modelling, a linear, inverse distance model of 100 m was calculated. Error distribution of “Bernoulli” was used for the binomial species presence-absence data (1/0). Modelling performances relied on how well models capture true/false presences/absences (sensitivity/specificity). Modelling parameters were dependent on the ecological preferences of species and varied between generalists and specialist species. Tree complexities changed between 3-5, learning rates between 0.005-0.01 and bag fractions from 0.7-0.9 depending on species in question. Results of models are shown in a separate .csv file.
Language (dataset)	English
Keyword	species distribution model
Keyword	Zonation
Keyword	biodiversity

Data processing steps

Data processing steps	sampling
Description	Environmental predictor variables included in the models developed for the SEAmBTOH project (more detailed descriptions and sources in the final report) were based on geological, physical, and chemical parameters, either from national monitoring sites or utilising remote sensing. Used environmental variables included: seafloor substrates (rock, boulders, mud, sand and mobile/unstable sediments), chlorophyll-a, depth, nutrients, salinity, surface exposure, seafloor fetch, shallow areas (satellite-derived) and turbidity (satellite-derived). Biological and geological mapping were performed in the study area, the northernmost Bothnian Bay, by the project partners. Geological mapping of the study area included surveying pilot areas, and modelling for the larger part of the study area. The biological mapping followed the methodology developed and used by the The Finnish Inventory Programme for Underwater Marine Diversity (VELMU). Further, already existing data recorded in the VELMU programme, as well as data products/layers developed for the use of the VELMU programme, were utilised in the development of the models.
Additional information (URL)	https://seamboth.files.wordpress.com/2020/06/seamboth_finalreport.pdf

Data processing steps

Data processing steps	processing
Description	The ecological models were developed utilizing a machine learning method, generalized boosting machine and additional functions from boosted regression trees (see details from the SEAmBOTH final report). Datasets were split into model training and testing with a ratio of 70/30, and for models with too little data for training/test separation, the full dataset was used in the modelling with 10-fold cross-validation. Independent test evaluations were not calculated for those models. For species with too little data for modelling, a linear, inverse distance model of 100 m was calculated. A "Bernoulli" error distribution was used for the binomial species presence-absence data (1/0).
Additional information (URL)	https://seamboth.files.wordpress.com/2020/06/seamboth_finalreport.pdf

Data processing steps

Data processing steps	quality control
Description	Modelling performances relied on how well models capture true/false presences/absences (sensitivity/specificity). Modelling parameters were dependent on the ecological preferences of species and varied between generalists and specialist species. Tree complexities changed between 3-5, learning rates between 0.005-0.01 and bag fractions from 0.7-0.9 depending on species in question. Results of models are shown in a separate .csv file, which is included in the accompanied data package.
Additional information (URL)	https://seamboth.files.wordpress.com/2020/06/seamboth_finalreport.pdf

Material time period

Start date	2004-01-01
End date	2019-12-31

Area

West Bounding Longitude	20.5752
East Bounding Longitude	25.9738
South Bounding Latitude	64.644
North Bounding Latitude	66.0062

Distribution

???catalog.gxe.sykeResearch.pidTitle

Action (default: None)	publishDoi
Reserved DOI	10.48488/gmvr-7n64
Published DOI	10.48488/gmvr-7n64

Contact person

First name	Lauri
Last name	Kuismanen
Email	Lauri.Kuismanen(at)syke.fi
Organisation	Finnish Environment Institute Syke

Resources

Resource content description	The data package contains 89 files: 88 raster files in .tif format, describing the species distribution models for the Finnish side of the study area, as well as 1 .csv file describing model performances (full models; encompassing Swedish side of the study area, in addition to the Finnish side).
Web-address (URL)	http://tiw01.env.fi/tutkimusdata/BC3B728B-0433-4C6B-9F00-A7C3952A67F5/SEAmBOTH_models_Finnish_side.zip

Reference publications

Reference

Bergdahl L., Gipson A., Haapamäki J., Heikkinen M., Holmes A., Kaskela A., Keskinen E., Kotilainen A,, Koponen S., Kovanen T., Kågesten G., Kratzer S., Nurmi M., Philipson P., Puro-Tahvanainen A., Saarnio S., Slagbrand P., Virtanen E. (2020). Seamless Maps and Management of the Bothnian Bay SEAmBOTH - Final report. pp. 149 . URL: https://seamboth.files.wordpress.com/2020/06/seamboth_finalreport.pdf

The license for open SYKE's open datasets is Creative Commons Attribution 4.0 International.

The data described here can be freely used to all purposes, provided that the source of the data is mentioned.

The citation for the dataset as given above.

Further information on the license:
https://creativecommons.org/licenses/by/4.0/legalcode (English)
https://creativecommons.org/licenses/by/4.0/legalcode.fi (Finnish)

/geoportal/rest/document?f=html&id=%7BBC3B728B-0433-4C6B-9F00-A7C3952A67F5%7D