Evaluation of Deep Species Distribution Models using Environment and Co-occurrences
This work addresses species distribution modeling for ecological research, but it is incremental as it builds on prior methods and datasets.
The paper tackled plant species distribution modeling by evaluating deep learning methods using environmental and co-occurrence data, finding that environmental models performed best and that combining both inputs led to significant performance gains.
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.