Next Article in Journal
Retained Austenite Destabilization during Tempering of Low-Temperature Bainite
Previous Article in Journal
Floating Offshore Wind Farms in Italy beyond 2030 and beyond 2060: Preliminary Results of a Techno-Economic Assessment
Article

Species Distribution Modelling via Feature Engineering and Machine Learning for Pelagic Fishes in the Mediterranean Sea

1
Database & Information Retrieval research Unit, Democritus University of Thrace, 671 00 Xanthi, Greece
2
Laboratory of Ichthyology, School of Biology, Aristotle University of Thessaloniki, 541 24 Thessaloniki, Greece
3
Laboratory of Ecological Engineering & Technology, Department of Environmental Engineering, Democritus University of Thrace, 671 00 Xanthi, Greece
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(24), 8900; https://doi.org/10.3390/app10248900
Received: 21 October 2020 / Revised: 22 November 2020 / Accepted: 7 December 2020 / Published: 13 December 2020
(This article belongs to the Section Marine Science and Engineering)
In this work a fish species distribution model (SDM) was developed, by merging species occurrence data with environmental layers, with the scope to produce high resolution habitability maps for the whole Mediterranean Sea. The final model is capable to predict the probability of occurrence of each fish species at any location in the Mediterranean Sea. Eight pelagic, commercial fish species were selected for this study namely Engraulis encrasicolus, Sardina pilchardus, Sardinella aurita, Scomber colias, Scomber scombrus, Spicara smaris, Thunnus thynnus and Xiphias gladius. The SDM environmental predictors were obtained from the databases of Copernicus Marine Environmental Service (CMEMS) and the European Marine Observation and Data Network (EMODnet). The probabilities of fish occurrence data in low resolution and with several gaps were obtained from Aquamaps (FAO Fishbase). Data pre-processing involved feature engineering to construct 6830 features, representing the distribution of several mean-monthly environmental variables, covering a time-span of 10 years. Feature selection with the ensemble Reciprocal Ranking method was used to rank the features according to their relative importance. This technique increased model’s performance by 34%. Ten machine learning algorithms were then applied and tested based on their overall performance per species. The XGBoost algorithm performed better and was used as the final model. Feature categories were explored, with neighbor-based, extreme values, monthly and surface ones contributing most to the model. Environmental variables like salinity, temperature, distance to coast, dissolved oxygen and nitrate were found the strongest ones in predicting the probability of occurrence for the above eight species. View Full-Text
Keywords: species distribution models; fish species; feature extraction; feature selection; XGBoost; habitability maps species distribution models; fish species; feature extraction; feature selection; XGBoost; habitability maps
Show Figures

Figure 1

MDPI and ACS Style

Effrosynidis, D.; Tsikliras, A.; Arampatzis, A.; Sylaios, G. Species Distribution Modelling via Feature Engineering and Machine Learning for Pelagic Fishes in the Mediterranean Sea. Appl. Sci. 2020, 10, 8900. https://doi.org/10.3390/app10248900

AMA Style

Effrosynidis D, Tsikliras A, Arampatzis A, Sylaios G. Species Distribution Modelling via Feature Engineering and Machine Learning for Pelagic Fishes in the Mediterranean Sea. Applied Sciences. 2020; 10(24):8900. https://doi.org/10.3390/app10248900

Chicago/Turabian Style

Effrosynidis, Dimitrios, Athanassios Tsikliras, Avi Arampatzis, and Georgios Sylaios. 2020. "Species Distribution Modelling via Feature Engineering and Machine Learning for Pelagic Fishes in the Mediterranean Sea" Applied Sciences 10, no. 24: 8900. https://doi.org/10.3390/app10248900

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop