Paper List
-
Pharmacophore-based design by learning on voxel grids
This paper addresses the computational bottleneck and limited novelty in conventional pharmacophore-based virtual screening by introducing a voxel cap...
-
CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design
This paper addresses the critical limitation of current protein structure prediction models (like AlphaFold3) where high-confidence scores (pLDDT) can...
-
On the Approximation of Phylogenetic Distance Functions by Artificial Neural Networks
This paper addresses the core challenge of developing computationally efficient and scalable neural network architectures that can learn accurate phyl...
-
EcoCast: A Spatio-Temporal Model for Continual Biodiversity and Climate Risk Forecasting
This paper addresses the critical bottleneck in conservation: the lack of timely, high-resolution, near-term forecasts of species distribution shifts ...
-
Training Dynamics of Learning 3D-Rotational Equivariance
This work addresses the core dilemma of whether to use computationally expensive equivariant architectures or faster symmetry-agnostic models with dat...
-
Fast and Accurate Node-Age Estimation Under Fossil Calibration Uncertainty Using the Adjusted Pairwise Likelihood
This paper addresses the dual challenge of computational inefficiency and sensitivity to fossil calibration errors in Bayesian divergence time estimat...
-
Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training
This paper addresses the core challenge of accurately predicting protein fitness with only a handful of experimental observations, where data collecti...
-
scCluBench: Comprehensive Benchmarking of Clustering Algorithms for Single-Cell RNA Sequencing
This paper addresses the critical gap of fragmented and non-standardized benchmarking in single-cell RNA-seq clustering, which hinders objective compa...
EcoCast: A Spatio-Temporal Model for Continual Biodiversity and Climate Risk Forecasting
Concordia University | Algoma University
The 30-Second View
IN SHORT: This paper addresses the critical bottleneck in conservation: the lack of timely, high-resolution, near-term forecasts of species distribution shifts under rapidly changing environmental conditions, moving beyond static models to operational, data-driven decision support.
Innovation (TL;DR)
- Methodology First transformer-based model applied to ecological and climate risk forecasting in Africa, using sequence-to-point prediction (12-month environmental sequences → next-month species occurrence) with explicit temporal dependency modeling via self-attention.
- Methodology Integration of continual learning (rehearsal + EWC) into biodiversity forecasting, enabling model updates with new data streams without catastrophic forgetting, crucial for non-stationary climate impacts.
- Biology Operational near-term forecasting paradigm (monthly to seasonal) that requires no future climate projections, using observed environmental sequences to predict immediate conservation-relevant shifts, bridging geophysical forecasting architectures with species distribution modeling.
Key conclusions
- EcoCast achieves macro-averaged F1 score of 0.65 and PR-AUC of 0.72 on 2023 holdout data for five African bird species, representing +34 and +43 percentage point improvements respectively over Random Forest baseline (F1=0.31, PR-AUC=0.29).
- Transformer architecture successfully captures critical temporal dependencies: annual seasonality via positional encoding, lagged environmental responses (2-4 month delays), and cross-species ecological signals through joint multi-label training.
- The framework demonstrates operational feasibility with monthly forecast updates using near-real-time data (ERA5 available within 5 days, final data 2-3 months later), enabling alignment with conservation planning cycles rather than static decadal projections.
Abstract: Increasing climate change and habitat loss are driving unprecedented shifts in species distributions. Conservation professionals urgently need timely, high-resolution predictions of biodiversity risks, especially in ecologically diverse regions like Africa. We propose EcoCast, a spatio-temporal model designed for continual biodiversity and climate risk forecasting. Utilizing multisource satellite imagery, climate data, and citizen science occurrence records, EcoCast predicts near-term (monthly to seasonal) shifts in species distributions through sequence-based transformers that model spatio-temporal environmental dependencies. The architecture is designed with support for continual learning to enable future operational deployment with new data streams. Our pilot study in Africa shows promising improvements in forecasting distributions of selected bird species compared to a Random Forest baseline, highlighting EcoCast's potential to inform targeted conservation policies. By demonstrating an end-to-end pipeline from multi-modal data ingestion to operational forecasting, EcoCast bridges the gap between cutting-edge machine learning and biodiversity management, ultimately guiding data-driven strategies for climate resilience and ecosystem conservation throughout Africa.