Robin Zbinden

45 posts

Robin Zbinden banner
Robin Zbinden

Robin Zbinden

@ZbindenRobin

PhD Student @EPFL_en with @devistuia 🇨🇭 Deep Learning applied to Ecology and Species Distribution Modeling 💻🦜🌍

Beigetreten Ağustos 2021
272 Folgt138 Follower
Robin Zbinden
Robin Zbinden@ZbindenRobin·
@gencersumbul @ChiaraVanalli @b_kellenb @devistuia Huge thanks to my coauthors and collaborators for making this possible🙌 MaskSDM is just the beginning: there’s a lot more to explore in combining AI and ecology to tackle the biodiversity crisis💚🌍
English
0
0
1
38
Robin Zbinden
Robin Zbinden@ZbindenRobin·
@gencersumbul @ChiaraVanalli @b_kellenb @devistuia A major contribution is our new Shapley value computation method, which avoids common linear assumptions by leveraging MaskSDM’s flexible input design. This provides more precise insights into how different environmental factors shape species distributions, locally and globally📊
Robin Zbinden tweet media
English
0
0
0
27
Robin Zbinden
Robin Zbinden@ZbindenRobin·
@gencersumbul @ChiaraVanalli @b_kellenb @devistuia A single MaskSDM model performs nearly as well on each tested subset of inputs as an oracle model trained specifically on that subset. This makes it possible to obtain predictions, performance metrics, and maps for any variable subset using only simple inference passes 📈🗺️
Robin Zbinden tweet media
English
0
0
0
22
Robin Zbinden
Robin Zbinden@ZbindenRobin·
@gencersumbul @ChiaraVanalli @b_kellenb @devistuia Leveraging MaskSDM, we modeled the distributions of 12,738 plant species worldwide using the sPlotOpen dataset. MaskSDM can be applied anywhere and adapts to the data available, making it ideal for global biodiversity assessments 🌍🌏🌎
Robin Zbinden tweet media
English
0
0
0
23
Robin Zbinden
Robin Zbinden@ZbindenRobin·
@gencersumbul @ChiaraVanalli @b_kellenb @devistuia MaskSDM uses transformer-based masked modeling (e.g., BERT, MAE, 4M) adapted for ecology. This lets the model learn from incomplete inputs and still predicts reliably. It’s also multimodal: tabular data, satellite images, time series, and more. More coming soon… stay tuned😉
Robin Zbinden tweet media
English
0
0
0
25
Robin Zbinden
Robin Zbinden@ZbindenRobin·
MaskSDM brings three key advantages for species distribution modeling (SDM): 🧩 Flexibility — choose which variables and modalities to use ⚙️ Robustness — works even with missing data 🔍 Explainability — a new Shapley values method shows which factors matter most for each species
Robin Zbinden tweet media
English
0
0
0
29
Robin Zbinden
Robin Zbinden@ZbindenRobin·
@VictorKristof Je consulte désormais toujours Predikon en premier, car les estimations sont beaucoup plus fiables que celles de GFS Bern qui a annoncé à 12h01 que BienPropre serait accepté !
Français
0
1
1
89
Victor Kristof
Victor Kristof@VictorKristof·
Différence avec le résultat final (à 12h01, ~20% des bulletins): 🚗#Autoroutes: 0.24% 🏢#SousLocation: 0.18% 🏠#BienPropre: 0.13% 🩺#FinancementUniforme: 0.03% 🎯Prédictions très précises et stables tout au long de la journée.
Victor Kristof@VictorKristof

🤖🗳️ Nos prédictions (predikon.ch) pour #CHvote (~20% des bulletins): 🚗#Autoroutes: 47.06±1.37% 🏢#SousLocation: 48.24±1.32% 🏠#BienPropre: 46.04±1.46% 🩺#FinancementUniforme: 53.34±1.21% (Intervalle de confiance 95%) #CHvote

Français
1
1
6
445
Robin Zbinden retweetet
Lenka Zdeborova
Lenka Zdeborova@zdeborova·
I would like to think about this as an invitation that physics extends towards AI/ML to think like physicists: -"Let's figure out how the world works". This is unlike computer scientists, who often see worst cases and adversaries. Nor mathematicians who need theorems everywhere.
The Nobel Prize@NobelPrize

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

English
12
48
345
37.4K
Robin Zbinden retweetet
devistuia
devistuia@devistuia·
🚨 job alert! We just opened a PhD position in my lab for a crazy interesting and important project with @ETH_en and the @ICRC We will look into new ways to use nightlight 🛰 data for characterising humanitarian crisis situations! Apply: careers.epfl.ch/job/Sion-PhD-p… @EssTechEPFL
English
4
45
88
10.5K
Robin Zbinden retweetet
Benjamin Kellenberger
Benjamin Kellenberger@b_kellenb·
Today, I have started my new position as Lecturer/researcher in the People & Nature Lab at University College London (@ucl, @UCLCBER )! I will be working with fabulous @ProfKateJones on technology and machine learning for environmental good. Stay tuned for news and opportunities!
Benjamin Kellenberger tweet media
English
11
8
82
3.9K
Keiller
Keiller@Keiller·
📢📢 Call for papers!! Workshop on Machine Vision for Earth Observation and Environment Monitoring @BMVCconf #BMVC2024 We invite submissions with at most 9 pages (references excluded), following BMVC guidelines. Submission instructions: mveo.github.io/submission.html
English
5
7
19
2.7K
Robin Zbinden
Robin Zbinden@ZbindenRobin·
What is the best time to go to lunch to avoid queues at EPFL? 🕧🥗 Are more energy drinks and coffees bought during exam sessions? 🥤☕ These are the types of questions we explored in this study, to which I contributed during my master's!
Kristina Gligorić@krisgligoric

Check out our new work, now out in Frontiers in Nutrition: "Measuring and Shaping the Nutritional Environment via Food Sales Logs: Case Studies of Campus-Wide Food Choice and a Call to Action"! frontiersin.org/articles/10.33…

English
0
0
5
268
Robin Zbinden
Robin Zbinden@ZbindenRobin·
6/7 Through qualitative analyses, we also demonstrate the role of pseudo-absence samples in mitigating geographic biases.
Robin Zbinden tweet media
English
1
0
1
173

Entdecken

@gencersumbul @ChiaraVanalli @b_kellenb @devistuia @VictorKristof @EPFL_en @ETH_en @ICRC