We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean. Mesogeos integrates variables representing wildfire drivers (meteorology, vegetation, human activity) and historical records of wildfire ignitions and burned areas for 17 years (2006-2022). It is designed as a cloud-friendly spatio-temporal dataset, namely a datacube, harmonizing all variables in a grid of 1km x 1km x 1-day resolution. The datacube structure offers opportunities to assess machine learning (ML) usage in various wildfire modeling tasks. We extract two ML-ready datasets that establish distinct tracks to demonstrate this potential: (1) short-term wildfire danger forecasting and (2) final burned area estimation given the point of ignition. We define appropriate metrics and baselines to evaluate the performance of models in each track. By publishing the datacube, along with the code to create the ML datasets and models, we encourage the community to foster the implementation of additional tracks for mitigating the increasing threat of wildfires in the Mediterranean.

翻译：我们提出了Mesogeos，这是一个用于地中海地区野火建模的大规模多用途数据集。Mesogeos整合了代表野火驱动因素（气象、植被、人类活动）的变量以及17年（2006-2022年）的历史野火点燃和过火面积记录。它被设计成一个云端友好的时空数据集，即数据立方体，将所有变量统一为1公里×1公里×1天的分辨率网格。该数据立方体结构为评估机器学习在各种野火建模任务中的使用提供了机会。我们提取了两个ML就绪数据集，建立了不同的赛道以展示这一潜力：（1）短期野火危险预报；（2）给定点燃点的最终过火面积估算。我们定义了适当的指标和基线来评估每个赛道中模型的性能。通过发布数据立方体，以及创建ML数据集和模型的代码，我们鼓励社区推动更多赛道的实施，以减轻地中海地区日益严重的野火威胁。