Search papers, labs, and topics across Lattice.
Affiliation:
3
0
2
3
Deep neural distribution models only outperform classic single-species baselines on rare taxa, and even that advantage completely vanishes unless traditional spatial bias-correction techniques are applied during training.
Geographic modulation of Sparse Autoencoders reveals interpretable rules from complex climate data, transforming how we understand extreme Earth events.
Super-resolved atmospheric data can now be trusted to respect fundamental physics, enhancing extreme event detection accuracy.
