Dear colleagues,
Transmitting Science has opened registration for the online course
"Evaluating and validating species distribution models with R".
To promote interaction the course in a small group (maximum 18
participants). This course is designed for PhD students, postdocs, and
researchers interested evaluating species distribution models; some
familiarity with building species distribution models is recommended.
Dates: May 6th and 8th, 2025, from 10:00 to 14:00 (Madrid time zone).
Course webpage:
https://www.transmittingscience.com/courses/ecology/evaluating-and-validating-species-distribution-models-with-r/
[1]
COURSE OVERVIEW
Species distribution models are commonly evaluated with metrics such as
the area under the receiver operating characteristic (ROC) curve (AUC),
the true skill statistic (TSS), Cohen's kappa, sensitivity, specificity,
or the overall classification accuracy or correct classification rate.
These metrics assess discrimination and/or classification capacity,
i.e., the ability of the model to distinguish and classify localities
with and without presence records. However, this is only one limited
aspect of model performance. Other aspects, such as calibration or
reliability (i.e., how predicted presence probabilities relate to
observed occurrence frequencies), are also very important, albeit often
overlooked, aspects of model performance. In addition, common
discrimination metrics are often deceivingly high for rare species and
naturally lower for generalist species, which do not clearly
discriminate "good" from "bad" habitat.
Model quality should thus be assessed with a comprehensive set of
evaluation measures, appropriate for species with different ecological
and biogeographical traits.
In this short course, we will use R to compute a wide range of model
evaluation metrics, encompassing discrimination, classification,
explanatory power and calibration. We will also see different ways to
validate models outside their training area, including spatial block
cross-validation.
The course will be highly interactive and will include both theoretical
and practical sessions. Participants are encouraged to bring their own
models with observed and predicted values, though they can also work
with example models that will be provided.
If you have any questions, do not hesitate to write to
cour...@transmittingscience.com or to me.
Best wishes
Sole
--
Soledad De Esteban-Trivigno, PhD
Director
Transmitting Science
www.transmittingscience.com
Twitter @SoleDeEsteban
Orcid: https://orcid.org/0000-0002-2049-0890
Under the provisions of current regulations on the protection of
personal data, Regulation (EU) 2016/679 of 27 April 2016 (GDPR), we
inform you that personal data and email address, collected from the data
subject will be used by TRANSMITTING SCIENCE SL to manage communications
through email and properly manage the professional relationship with
you. The data are obtained based on a contractual relationship or the
legitimate interest of the Responsible, likewise the data will be kept
as long as there is a mutual interest for it. The data will not be
communicated to third parties, except for legal obligations. We inform
you that you can request detailed information on the processing as well
as exercise your rights of access, rectification, portability and
deletion of your data and those of limitation and opposition to its
treatment by contacting Calle Gardenia, 2 Urb. Can Claramunt de Piera
CP: 08784 (Barcelona) or sending an email to
i...@transmittingscience.com or
http://transmittingscience.com/additional-terms. If you consider that
the processing does not comply with current legislation, you can
complain with the supervisory authority at www. aepd.es .
Confidentiality. - The content of this communication, as well as that of
all the attached documentation, is confidential and is addressed to the
addressee. If you are not the recipient, we request that you indicate
this to us and do not communicate its contents to third parties,
proceeding to its destruction.
Disclaimer of liability. - The sending of this communication does not
imply any obligation on the part of the sender to control the absence of
viruses, worms, Trojan horses and/or any other harmful computer program,
and it corresponds to the recipient to have the necessary hardware and
software tools to guarantee both the security of its information system
and the detection and elimination of harmful computer programs.
TRANSMITTING SCIENCE SL shall not be liable.
Links:
------
[1]
https://www.transmittingscience.com/courses/ecology/evaluating-and-validating-species-distribution-models-with-r/
To unsubscribe from this list please go to
https://community.esa.org/confirm/?u=RhPWqPxFwODKvbkiT32nkIqRrsiSgulp
