Sign in

Olivier Gimenez 🦦

@oaggimenez.bsky.social
4.6K followers 3.7K following 119 posts

Scientist (he/him) @cnrs.bsky.social oliviergimenez.github.io Grown statistician • Improvised ecologist • Sociologist apprentice Statistical ecology • Bayesian statistics • Mammals #rstats

PostsRepliesMedia
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 03/08/2026
🦦💦 Très heureux de partager notre article "Médiation scientifique autour de la préservation des zones humides : le bassin versant du Lez (Montpellier, France) et la loutre d’Europe (Lutra lutra) comme cas d’étude" revue-set.fr/article/view...
Figure 1. Illustration de la valise pédagogique « La loutre se met à Lez ». En haut se trouve le logo, et en bas on retrouve quelques outils pédagogiques contenus dans la valise (voir aussi tableau 1).Figure 2. Illustration de l’exposition « Théâtre enchanté ». L’exposition est constituée de trente clichés (deux exemples photos e et f) au format bâche (photos a et b) et dibond (photos c et d). Les clichés sont de Yann Raulet.
175
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 05/03/2026
📘 Nouveau livre ! Introduction à la statistique bayésienne avec le logiciel R Découvrez pas à pas la statistique bayésienne et sa mise en œuvre dans R : théorème de Bayes, MCMC, priors, régression, GLM/GLMM et comparaison/validation de modèles. Aux éditions Quae 🙏 📷 Crédit photo : Yann Raulet
couverture du livre introduction à la statistique bayésienne avec R
35718
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 01/02/2026
📘 New book out soon ! I’m excited to share that 𝐁𝐚𝐲𝐞𝐬𝐢𝐚𝐧 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬 𝐨𝐟 𝐂𝐚𝐩𝐭𝐮𝐫𝐞-𝐑𝐞𝐜𝐚𝐩𝐭𝐮𝐫𝐞 𝐃𝐚𝐭𝐚 𝐰𝐢𝐭𝐡 𝐇𝐢𝐝𝐝𝐞𝐧 𝐌𝐚𝐫𝐤𝐨𝐯 𝐌𝐨𝐝𝐞𝐥𝐬: 𝐓𝐡𝐞𝐨𝐫𝐲 𝐚𝐧𝐝 𝐂𝐚𝐬𝐞 𝐒𝐭𝐮𝐝𝐢𝐞𝐬 𝐢𝐧 𝐑 𝐚𝐧𝐝 𝐍𝐈𝐌𝐁𝐋𝐄 is being published by Chapman & Hall / CRC Press Hope it’s useful to students, researchers, and practitioners #StatisticalEcology #NIMBLE
Book cover for https://oliviergimenez.github.io/banana-book/
28727
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 12/09/2025
🌿 Le Centre d’Écologie Fonctionnelle et Évolutive à Montpellier (lnkd.in/erpreW-F), recherche sa/son DU 😉 👉 lnkd.in/etM5tXEP 🌿 The Centre for Functional and Evolutionary Ecology in Montpellier (lnkd.in/e9JBQNai) is looking for its next director. Come and join us 😉 👉 lnkd.in/etM5tXEP
174
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 02/09/2025
🌿🤝 Excited to launch BRAM - Biodiversity, Research & Mediation in Montpellier! 🎯 This new consortium unites research, local authorities & biodiversity managers to co-create projects where science meets society. 🦦🌃 From species management to urban nature and ecological connectivity.
Anne Bancel & Jean-Christophe Avarre (IRD), Pierre-Edouard Guillain (OFB), Isabelle Touzart (Montpellier Méditerranée Métropole), Stéphane Jouault (ville de Montpellier), Philippe Augé (Montpellier university), Laurent Barbieri (CNRS)Group picture
191
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 10/07/2025
I talk to lots of junior colleagues about this stuff. They want a lot of different things. But mostly they want more senior academics to recognize and talk about these problems. It’s not like it’s a secret that there are replication and reliability problems at the highest levels of research. It’s that the most successful academics talk about it the least. Recognition would help not only with morale, but also with momentum to get things done.
153
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 23/06/2025
🚨 Candidatez à la thèse sur "Déterminants géographiques, sociaux et culturels des risques liés aux interactions entre humains et ragondins" 🥳 ➡️ Tous les détails ici lnkd.in/exsXZRHS 📩 Envoyez CV et lettre de motiv à avant ce vendredi 27 juin 🤯 ℹ️ A propos du projet LeptoNex : lnkd.in/e7rhyyBS
151
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 12/06/2025
Intermediate-levelworkshop Bayesian population analysis using NIMBLE and JAGS 🇨🇭
Intermediate-levelworkshop
Bayesian population analysis using
NIMBLE and JAGS

In the course we introduce many key models used in the analysis of distribution, abundance and
animal demography, as well as their spatial and temporal patterns, in a Bayesian analysis
framework. In concept, we follow the book "Bayesian population analysis using WinBUGS"
(Academic Press, 2012), which will be handed out for free. We introduce statistical inference and
computation, and use the programs R and NIMBLE (and occasionally JAGS) to fit and understand
some of the most widely used models for the analysis of animal and plant populations. Models
and topics include:
081
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 11/06/2025
Today is #InternationalLynxDay, and we've just had this paper published in @peercomjournal.bsky.social "Modelling Eurasian lynx populations in Western Europe: What prospects for the next 50 years?" led by Sarah Bauduin 🥳 peercommunityjournal.org/articles/10....
cover page of our new paper on "Modelling Eurasian lynx populations in
Western Europe: What prospects for the next 50 years?". The abstract is: "Persistence of populations may be uncertain for large carnivore species, especially for those established
in human-dominated landscapes. Here, we studied the Eurasian lynx in Western Europe established
in the Upper Rhine meta-population (i.e., Jura, Vosges-Palatinian and Black Forest populations) and
the Alpine population. These populations are currently considered endangered or critically endangered
due to high anthropogenic mortality, small population size and low genetic diversity, and isolation. We
assessed lynx persistence over a 50-year time horizon by implementing a spatially-explicit individual-
based model, while accounting for road mortality and habitat selection. Forecasts showed a steady
growth rapidly reaching a more stable phase for the Alpine and Jura populations, and a more hetero-
geneous positive growth with less precision for the Vosges-Palatinian and Black Forest populations.
Exchanges of individuals between populations were limited, the Jura population playing the role of a
crossroad. Finally, the persistence of lynx in Western Europe seems likely on a large scale over the next
50 years. Indeed, simulations showed high female occupancy as well as average lynx density over the
core areas of the four studied populations. Nevertheless, these results should be interpreted with the
model limitations in mind, concerning the absence of movement barriers and inbreeding depression."
1143
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 16/04/2025
🐺📈 Avec @milleretcyril.bsky.social et Christophe Duchamp, nous venons de mettre à jour les estimations de survie et effectifs de la population de loups en France pour l'hiver 2023/2024, tout est là hal.science/hal-05016361v1 @ofbiodiversite.bsky.social @cnrsecologie.bsky.social
Variations da la probabilité de survie lors de 3 périodes (1995-2013 ; 2014-2018 ; 2019-2024). Les barres représentent les bornes hautes et basses de l’intervalle de confiance à 95%, et la barre horizontale noire, les estimations moyennes. Le seuil de tolérance moyen est de 34% de mortalité (soit 66% de survie) est donné (pointille rouge) avec son intervalle de confiance (en grisé ; Marescot et al. 2012). Des taux des survies en dessous de cet intervalle présentent donc un risque important de générer des taux de croissance négatifs de la population (selon Marescot et al. 2012). Les taux de survie sont présentés après avoir pris en compte l’effet transient sur la survie (Pradel et al. 1997).Tendance démographique de la population de loups en France estimée par modèles de capture recapture et à partir du suivi génétique non-invasif. Les barres représentent les estimations basses et hautes des intervalles de confiance à 95% des effectifs chaque hiver depuis 1995/96. La valeur moyenne des estimations est représentée par une barre horizontale blanche. Les valeurs utilisées dans cette figure sont disponibles dans le Tableau S1.
193
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 11/04/2025
🚨🎉 New paper "Ten quick tips to get you started with Bayesian statistics", hope you'll like it 😇🤗 ✍🏽 w/ Andy Royle, Marc Kéry and Chloé Nater 🔗 dx.plos.org/10.1371/jour... @plos.org @cnrsecologie.bsky.social @cnrsoccitanieest.bsky.social @umontpellier.bsky.social
Graphical summary of 10 quick tips to get started with Bayesian statistics and how they fit into a larger view of an analytical workflow with Bayesian models.
316269
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 17/12/2024
www.biorxiv.org/content/10.1... @doctorzen.net
Cover page of the preprint "Trends in hoaxes of academic communication" in Biorxiv with following abstract: "Academic journals use peer review to weed out false information, but peer review and other editorial processes are normally confidential. Therefore, individuals sometimes create hoaxes to test whether editorial processes are as robust as they are claimed, or whether they are done at all. This article tracks the occurrence of hoaxes aimed at scholarly publishers and academic conferences since 2000. Since 2009, successful hoaxes usually appeared at a year of one or more a year, usually motivated by academics or journalists exposing so-called "predatory" journals. The apparent rise in the number of hoaxes reflects a lack of transparency in editorial processes at both legitimate and "predatory" journals. Reaction of academic communities to hoaxes varies widely depending on the perceived intent of the target of the hoaxes and whether the hoax demonstrates what the hoaxer claims."
112
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 20/11/2024
I have a new paper 😇 in which I show how to analyse data collected on stream networks using occupancy models, check it out here onlinelibrary.wiley.com/doi/10.1002/... 😉 I also have a few slides there that give additional explanations doi.org/10.6084/m9.f...
Cover page of the paper entitled "Spatial Occupancy Models for Data Collected on Stream Networks" published in the journal Aquatic Conservation: Marine and Freshwater Ecosystems. The abstract is:
1. To effectively monitor biodiversity in streams and rivers, we need to quantify species distribution accurately.
2. Occupancy models are useful for distinguishing between the non-detection of a species and its actual absence. While these models can account for spatial autocorrelation, they are not suited for streams and rivers due to their unique network spatial structure.
3. Here, I propose spatial occupancy models specifically designed for data collected on stream and river networks. I present the statistical developments and illustrate their application using data on a semi-aquatic mammal.
4. Overall, spatial stream network occupancy models offer a robust method for assessing biodiversity in freshwater ecosystems.A figure showing the importance to account for stream distance and flow connectivity when analysing data on stream networks. Four sites are represented on a river, two sites are flow connected and two are flow unconnected.
1448
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 30/12/2023
I’m learning Julia and oh my it is a mighty tool for scientists! I'm using diff eqns to fit models to data. Here are examples from others incl logistic, Lotka-Volterra & reaction-diffusion. t.co/vcGBzGjuwF 🙏 C Rackauckas, L Roques, J Papaïx, S Soubeyrand, H Ge, L Mailleret, L Marques & al
Trace and density plots of the three main parameters of a logistic model fitted to noisy (simulated) data.Simulated and MCMC-estimated trajectories from a logistic model.
0151
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 11/12/2023
Un point d'étape sur nos projets sur la loutre d'Europe. J'y parle de connectivité, trame turquoise, pièges photos, ADN env, cacas, représentations des usagers et médiation scientifique. Et de caca, j'ai déjà dit caca? diapos doi.org/10.6084/m9.f... vidéo youtu.be/7pVFJgw2EhU?... 📸 Yann Raulet
Diapo de présentation de nos projets sur la loutre, le Lez, la connectivité écologique et la médiation scientifique.
031
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 06/12/2023
Merci Instant Science pour la petite attention, on se voit l'année prochaine, pour la 2ème édition du Festival des sciences participatives et citoyennes #VaSavoir ?!
carte postale envoyée par les collègues d'Instant Science nous remerciant de notre participation au premier festival des sciences participatives et citoyennes VaSavoir.Portrait de la team loutre avec de gauche à droite, Yann Raulet, Olivier Gimenez et Simon Lacombe.
010
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 03/12/2023
Curious too. Marie Chandelier is a researcher in linguistics, and brings a qualitative approach which helps a lot to put the results from the quantitative approach into perspective. This transpires even more in this paper oliviergimenez.github.io/pubs/Chandel...
cover page of paper "Content analysis of newspaper coverage of wolf recolonization in France using structural topic modeling" by Marie Chandelier and colleagues.
121
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 03/12/2023
Awesome paper led by Gilles Maurer & Marie Chandelier on the media coverage of the Asian elephant using topic modelling and linguistics 🐘📰 Free PDF here authors.elsevier.com/sd/article/S...
cover page of paper Polarized media coverage of conflicting, yet emblematic species: The ambivalent portrayal of the Asian elephantFig. 2. Social network analysis of topics and their co-occurrence in the corpus.
Topics are defined by their numbers shown in the main graph and the insert for few topics of specific interest. Topic's most probable stems are displayed within the network nodes. Communities of topics are shown in colours and based on modularity partition. 2.b: The insert is showing the eigenvector centrality value for each topic of the network. The colour gradient depends on the eigenvector centrality value.
130
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 28/11/2023
Petit exposé sur les modèles et leurs applications en écologie à l'occasion d'un atelier d'échanges Modélisations « Biodiversité et Infrastructures Linéaires de Transport » organisé par le Cerema, l’OFB, le centre de ressources TVB et ITTECOP. doi.org/10.6084/m9.f...
Diapo de couverture d'un exposé sur les modèles et leurs applications
010
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 25/10/2023
Et hop, un petit article dans l'écho du PNA loutre sur notre projet OtterConnect otterconnect.netlify.app C'est par ici sfepm.org/sites/default/
120
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 21/10/2023
📢 Ne ratez pas le festival Va Savoir?! sur les sciences participatives & citoyennes 27-28-29 octobre à La Halle Tropisme 🤩 On y sera pour parler du retour de la loutre à Montpellier et ailleurs otterconnect.netlify.app 🦦😇 👉 www.instantscience.fr/festival-va-... #VaSavoir #SciencesParticipatives
bannière du festival Va Savoir
012
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 06/10/2023
10-14 June 2024 5-day workshop on "Modeling distribution, abundance, demography and population dynamics using R, JAGS and NIMBLE" at the Spanish Game Research Center (IREC) in Ciudad Real 🇪🇸 by M. Kéry M. Schaub @GGuillera @jj_lahoz M. Victoria Jiménez-Franco J. Jiménez 🤩
010
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 30/09/2023
Interested in landscape connectivity? Circuit theory is great but how to use it w/ spatial occupancy models? No problem, Maelis Kervellec got you covered in her new paper 🤩🥳 NIMBLE for the win 😉 biorxiv.org/content/10.1... w/ Thibaut Couturier & colleagues from Office Français de la Biodiversité
Distribution of sampling sites for the two case studies in France. On the top panels, black crosses symbolize the center of 300m transect monitoring otter spaint in the Massif Central, background raster represents the median posterior cost value estimated from the distance to rivers (a) and corresponding standard deviation (b). On the bottom panels, 100km2 squares delineate sampling sites of lynx presence in the Jura mountains, background raster represents the median posterior cost value estimated from the distance to highways (c) and corresponding standard deviation (d).
1115
Olivier Gimenez 🦦 @oaggimenez.bsky.social · 26/09/2023
Hi everyone ! I'm Olivier, a statistician turned ecologist or ecological statistician. I study carnivores asking basic questions like how many and where. You can find me in the beautiful city of Montpellier, southern France. Thanks David !
Cover page of the OtterConnect project website, an applied research project to better understand otter recolonization
2367