Robin Zbinden
@rzbinden.bsky.social
PhD Student at EPFL, in the ECEO Lab of Devis Tuia 🇨🇭
Deep Learning for Ecology and Species Distribution Modeling 💻🦜🌍
Deep Learning for Ecology and Species Distribution Modeling 💻🦜🌍
6/8 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📊
November 28, 2025 at 10:25 AM
6/8 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📊
5/8 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 📈🗺️
November 28, 2025 at 10:24 AM
5/8 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 📈🗺️
4/8 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 🌍🌏🌎
November 28, 2025 at 10:23 AM
4/8 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 🌍🌏🌎
3/8 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 😉
November 28, 2025 at 10:21 AM
3/8 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 😉
2/8 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
🧩 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
November 28, 2025 at 10:20 AM
2/8 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
🧩 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