AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean

Spyros Kondylatos, Ioannis Prapas, Gustau Camps-Valls, Ioannis Papoutsis

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Statistical analysis of ML practice · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use all datacube variables instead of only ignition points as input (ablation)U-Net (EfficientNet-B1) · Mesogeos Track B burned areaAUPRC: 0.394 -> 0.418Improved
use all datacube variables instead of only ignition points as input (ablation)U-Net (EfficientNet-B1) · Mesogeos Track B burned areaCE loss: 0.0177 -> 0.0166Improved
Transformer encoder instead of LSTMfire danger classifier · Mesogeos Track Aprecision: 0,763 -> 0,802Improved
Transformer encoder instead of LSTMfire danger classifier · Mesogeos Track Arecall: 0,812 -> 0,759Hurt
Gated Transformer Network instead of LSTMfire danger classifier · Mesogeos Track AAUPRC: 0,853 -> 0,858No clear effect
Gated Transformer Network instead of Transformerfire danger classifier · Mesogeos Track AAUPRC: 0,856 -> 0,858No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy