Till startsida
To content Read more about how we use cookies on gu.se

Modelling invertebrates

We compared the ability of selected modelling methods to predict distribution and abundance of 25 macrofauna species from coastal waters of Lithuania and the Archipelago Sea. Four methods were evaluated for predicting distribution (presences and absences), and three methods were evaluated for predicting abundance (biomass and cover). All measures of performance represent results of validation using external test datasets.

1. Methods for modelling macrofauna distribution

In general we found that classification accuracy of each method was on average good (AUC >0.8). Although there were small differences among techniques, RF had the highest average performance, followed by MaxEnt, GAM and MARS. See figure 1.

However, the range and variance of classification accuracy differed among the methods. The most consistent technique was RF, ranging from fair (AUC >0.7) to excellent (AUC >0.9) levels, while MaxEnt, GAM and MARS were slightly more variable.

In conclusion, the obtained results from PREHAB indicate that good to excellent mean classification accuracy by the four evaluated methods is highly probable, however MARS performed slightly worse than the other three methods.

Performance of models predicting macrofauna distributionFigure 1. Classification accuracy (AUC) of four methods for modelling macrofauna distribution. RF and MaxEnt provided the best models, but all approaches were useful. Dotted line represent level of relative good classification accuracy (AUC= 0.8); values above the line are considered as good and below it as poor. Grey dots=values; squares=means; whiskers =standard deviations.

2. Methods for modelling macrofauna abundance

All three evaluated methods for modelling the abundance of benthic invertebrates performed very similarly, with average values of NRMSE) ranging from 0.14 (RF) to 0.16 (MARS) between different models (see figure 2). Despite the lack of generally accepted guidelines, these levels of error should be considered relatively good accuracy of predictions. RF provided models with the smallest deviations and the most consistent results.

In conclusion, the obtained results from PREHAB indicate that relatively good prediction performance by the three evaluated methods is highly probable. RF model showed slightly better performance and consistency than the other two.

Performance of models predicting macrofauna abundanceFigure 2. Performance of three methods for modelling the abundance of benthic macrofauna. The prediction error expressed as root mean square error normalized by range (NRMSE) was the smallest and most consistent for RF. Grey dots=values; squares=means; whiskers=standard deviation.



© University of Gothenburg, Sweden Box 100, S-405 30 Gothenburg
Phone +46 31-786 0000, About the website

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?