Luca Santini

An arboreal camera-trap image form the Brazilian Amazon rainforest. An animal is detected by TropiCam-AI, which analyzes its features and tries to determine what species it is.

TropiCam-AI analyzes the prompted image, and classifies it at the species level as a black spider monkey. Users can decide to let the model predict at the taxonomic level that achieves the highes confidence and accuracy, or force predictions at the desired taxonomic level.

New paper out in @methodsinecoevol.bsky.social!

📷We present TropiCam-AI: a machine learning model that identifies 84 taxa of Neotropical arboreal mammals and birds from camera-trap images and videos. 🐒🦜

📃Paper → doi.org/10.1111/2041-210x.70213
🌐Project → github.com/andrewzamp/TropiCam-AI

Misurare l’energia della biodiversità per la salute degli ecosistemi Biodiversità significa non solo ricchezza e abbondanza delle forme di vita in un luogo, ma anche delle relazioni che esse intessono tra loro. La vita chiama vita, una specie crea i presupposti per l’e...

Un articolo divulgativo in Scienza in Rete sul nostro recente articolo su Nature. www.scienzainrete.it/articolo/mis...

Mammal density estimates are usually higher in small study areas. This can reflect several factors, like studies targeting high-density sites, edge effects from high perimeter-area ratios, or methodological artefacts; however, the actual causes remain untested. Understanding how this pattern originates and its consistency across methods is crucial for reliable population assessments and comparative analyses. Using a global dataset of mammal density estimates, we quantified the effect of sampling extent on population density across different estimators, and then ran simulations to isolate its contribution from other biological signals. We found that when sampled area is below ~3 times animal home-range size, density is systematically overestimated (+80% on average) due to high perimeter-area ratio. Yet, some methods (e.g. capture-recapture) are more sensitive than others (e.g. spatial capture-recapture), while others are robust to this effect (e.g. Random Encounter Model). Explicitly accounting for this bias will improve both local population assessments and cross-study analyses.

Does survey area extent bias population density estimates? Spoiler: yes, and method matters.

Want the details? Come check my poster next week at
@britishecologicalsociety.org #BES2025 (Tuesday 16th, 18:00 - Lennox Suite, n°A5.25), and let's have a chat!💬

Co-authored with @lsantinieco.bsky.social.

🐬 New paper out! We use the TetraDENSITY database to test how fishing affects cetacean species in the Mediterranean. We found that different fishing activities alter natural population density patterns, with destructive demersal fishing having the strongest negative impact
👉 doi.org/10.1002/ecog...

Our new paper in Nature uses ecological energetics to track ten ecosystem functions of all birds and mammals in sub-Saharan Africa. It shows that the ecological power of African wildlife has declined by a third since pre-colonial times @natureportfolio.nature.com

This fantastic study was majestically led by Ty Loft, together with @ymalhi.bsky.social @josephtobias.bsky.social @ioliverasmenor.bsky.social @zethdafer.bsky.social and others

Our new @nature.com shows that energy flows mediated by mammals and birds across sub-Saharan Africa have declined by >30% unevenly across functional groups, with major consequences ecosystem functions
shorturl.at/AD0Yb

Advancing causal inference in ecology: Pathways for biodiversity change detection and attribution Understanding the causes of biodiversity change is essential for addressing environmental challenges. While causal attribution has advanced in other fields, ecologists remain cautious about causal...

Here we review causal inference in ecology to attribute change in biodiversity research. We identify common challenges and provide an overview of different approaches. By Franziska Shrodt and many others besjournals.onlinelibrary.wiley.com/doi/full/10....

Why relying on the "equlilibrium assumption", i.e., biodiversity being in an equilibrium state w/ its environmental conditions, to model biodiversity trends in response to environmental changes?

➡️ We propose a paradigm shift: embracing the quasi-permanent non-equilibrium state 🤯

shorturl.at/qU99d

Correcting environmental sampling bias improves transferability of species distribution models Sampling bias is an inherent problem in widely available biodiversity data, undermining the robustness of correlative species distribution models (SDMs). To some extent, subsampling occurrence data c...

Important paper!
nsojournals.onlinelibrary.wiley.com/doi/full/10....

Triangle of links between the processes, highlighting their general interactions.

Animal energetics, movement, and coexistence are inextricably linked. What insights emerge when we consider these processes together? In our new paper, we present a conceptual framework that integrates these domains, outlines their connections, and highlights the value of their joint study.

with @m-dimarco.bsky.social, Pierfilippo Cerretti, Marta Carboni and @luigimaiorano.bsky.social

SDMs are powerful tools, but only if feed them with the right variables (be biologists, not blind programmers!). We show how data dredging approaches relying on the 19 bioclimatic variables can lead to misleading predictions & interpretation. Led by @giordanomancini.bsky.social
shorturl.at/Y2BpC

3-year #Postdoc opportunity at the University of York!
I am #hiring a Postdoc to join my URF project on exploring how #biodiversity change is unfolding in the #Anthropocene.

Deadline: 10th August 2025.

All details and the link to apply: shorturl.at/qOQst

@anthropocenebio.bsky.social #ecology

Read our latest paper on the application of macroecological theory to better understand human impact on biodiversity, great collaborative work led by @pierregauz.bsky.social
onlinelibrary.wiley.com/doi/10.1111/...

This study was led by Laura Paltinieri, @anabenlop.bsky.social & @lsantinieco.bsky.social as part of the EU COST Action network ClimBats. You can read Laura's blog on this paper here:

besclimatechange.wordpress.com/2025/07/01/h...

🌍🌐🧪

Please share.
We have a fully-funded PhD position on animal migration. If interested, please apply by 27 July. More about us: shawanchowdhury.com. @idiv-research.bsky.social @monashbiol.bsky.social @uq-cbcs.bsky.social

#PhDposition #Ecology #Conservation #Migration #Rstats #AcademicTwitter

Presenting my poster on mammalian population density responses to anthropogenic gradients today at 16:30, find me at panel N. 84 #iccb2025.bsky.social

The first paper of the "Urbis project" focusing on the urban ecosystem of Rome is out in Urban Forestry & Urban Greening!
Here we characterize the urban landscape and propose a multiscale framework to better support urban biodiversity research and planning
doi.org/10.1016/j.la...

About to start my course for the Early Career Conference of the Italian Chapter of the SCB

PhyBaSE: A Bayesian structural equation model approach to causal inference in phylogenetic comparative analyses One of the main limitations of phylogenetic comparative analyses is that associations between traits can only be interpreted as correlations. Here, we present a novel Bayesian structural equation ...

PhyBaSE: A Bayesian structural equation model approach to causal inference in phylogenetic comparative analyses
besjournals.onlinelibrary.wiley.com/doi/10.1111/...

Geography and availability of natural habitat determine whether cropland intensification or expansion is more detrimental to biodiversity - Nature Ecology & Evolution Both agricultural expansion and intensification drive biodiversity losses. Here the authors quantify and compare globally the biodiversity impact of land conversion and yield increases.

Geography and availability of natural habitat determine whether cropland intensification or expansion is more detrimental to biodiversity
www.nature.com/articles/s41...

Correlation coefficients between bat forearm length and climatic variables

New paper published in Ecography coming out of the ClimBats COST Action on effects of climate on #bat morphology across space and time. Led by @laura-paltrinieri.bsky.social, @anabenlop.bsky.social and @lsantinieco.bsky.social 🦇🌡️🌧️

nsojournals.onlinelibrary.wiley.com/doi/10.1002/...

Check out our latest paper on climate-driven changes in bat morphology across space and time, see thread by @laura-paltrinieri.bsky.social 👇🏻👇🏻👇🏻

I'm thrilled to share our new review paper with the world.

In this study, featuring a long list of collaborators from the COST Action ClimBAT, we predict that climate change will reshape European bat communities and functional assemblages 🦇🦇🦇 with potential major consequences for ecosystems. @orlyrazgour.bsky.social
shorturl.at/HRMtY

Our paper presenting the predictions of generation length for all amphibians and reptiles is finally published online in Ecography! Great work led by Giordano Mancini. They'll soon be incorporated in the sRedList platform!

Personally, I find it odd that some reviewers write essays on how to improve an ms

I feel they misinterpret the role of reviewer - to check the quality of the ms and any errors

Instead approaching the task as if they are being asked to rewrite the ms with their own arguments & style

The #biosphere is changing: Check our global mapping of ecological novelty in wild #ecosystems (due to #climatechange, #defaunation & floristic disruption) - just out in @natureecoevo.bsky.social ♨️🐘🌿🌐 Big thx to @mattkerr.bsky.social for the huge effort! #novelecosystems #invasivespecies #megafauna

🌿 PhD Opportunity in Agroecology & Biodiversity! 🦋

Join our work group at the University of Göttingen!

Fully funded PhD (TV-L E13, 65%) on carabid communities & biological control in agroecosystems in the HEAVEN project.

📆 Apply by 20.03.2025

👉🏼 obp.uni-goettingen.de/de-de/OBF/In...