Manuel A. Matı́as

The paper uses synthetic data generated from a mechanistic model to train deep learning networks that classify seagrass meadow resilience from spatial patterns, showing effective generalization to real-world data.

This paper develops a mechanistic framework linking within-host pathogen dynamics to vector-mediated transmission under climate forcing, showing temperature affects epidemic spread through changes in host infectiousness duration.

The paper quantifies the sublethal effects of thermal stress on seagrass meadows using a new index, showing increased fragmentation and habitat loss despite temperatures below lethal thresholds.

This study shows that intermittent precipitation and spatial Allee effects create irregular vegetation patterns and influence ecosystem resilience in semi-arid environments.

This paper develops a deep learning framework to map seagrass meadows using satellite imagery and a georeferenced dataset, improving scalability and accuracy for conservation monitoring.

The paper uses high-resolution climate data to show increased risk of Pierce's Disease in global wine regions under climate change.

The paper identifies universal spatial patterns in coral reefs using global data, revealing fractal geometries and power-law distributions across different reef provinces.

This paper uses phylogenetic and historical data to explain why European vineyards have not been affected by Pierce's disease despite the presence of Xylella fastidiosa.