Skip to Main content Skip to Navigation
Conference papers

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

Benjamin Deneu 1, 2 Maximilien Servajean 1 Christophe Botella 3, 2 Alexis Joly 2
2 ZENITH - Scientific Data Management
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This paper presents an evaluation of several approaches of plantsspecies 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 ob-tained the best performance of the GeoLifeCLEF 2018 challenge but on arevised dataset that fixes some of the issues of the previous one. We alsogo deeper in the analysis of co-occurrences information by evaluating anew model that jointly takes environmental variables and co-occurrencesas inputs of an end-to-end network. Results show that the environmentalmodels are the best performing methods and that there is a significantamount of complementary information between co-occurrences and envi-ronment. Indeed, the model learned on both inputs allows a significant performance gain compared to the environmental model alone.
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-02290310
Contributor : Benjamin Deneu <>
Submitted on : Wednesday, September 18, 2019 - 3:11:02 PM
Last modification on : Monday, November 30, 2020 - 6:42:01 PM
Long-term archiving on: : Sunday, February 9, 2020 - 12:17:22 AM

Identifiers

  • HAL Id : hal-02290310, version 1
  • ARXIV : 1909.08825

Collections

Citation

Benjamin Deneu, Maximilien Servajean, Christophe Botella, Alexis Joly. Evaluation of Deep Species Distribution Models using Environment and Co-occurrences. CLEF 2019 - Conference and Labs of the Evaluation Forum, Sep 2019, Lugano, Switzerland. ⟨hal-02290310⟩

Share

Metrics

Record views

145

Files downloads

623