Evaluation of Deep Species Distribution Models using Environment and Co-occurrences

TL;DR

This paper evaluates plant species distribution models using environmental data and co-occurrences, showing that combining both improves performance over environmental models alone.

Contribution

It re-evaluates a top-performing CNN model on a revised dataset and introduces a new end-to-end model that jointly uses environmental and co-occurrence data.

Findings

Environmental models perform best individually.

Combining co-occurrences with environmental data yields significant performance gains.

Co-occurrence information provides complementary insights to environmental data.

Abstract

This paper presents an evaluation of several approaches of plants species distribution modeling based on spatial, environmental and co-occurrences data using machine learning methods. In particular, we re-evaluate the environmental convolutional neural network model that obtained the best performance of the GeoLifeCLEF 2018 challenge but on a revised dataset that fixes some of the issues of the previous one. We also go deeper in the analysis of co-occurrences information by evaluating a new model that jointly takes environmental variables and co-occurrences as inputs of an end-to-end network. Results show that the environmental models are the best performing methods and that there is a significant amount of complementary information between co-occurrences and environment. Indeed, the model learned on both inputs allows a significant performance gain compared to the environmental model alone.