Dataset for Integrating Structural Information into Data Fusion: Enhancing CAMS data through Network Centrality and Machine Learning

This dataset contains the environmental, structural, and geographic data utilized in the paper "Integrating Structural Information into Data Fusion: Enhancing CAMS data through Network Centrality and Machine Learning". The data spans the region of Lombardy, Italy, covering a time window from 2018 to 2021. It is comprised of regional in-situ air quality monitoring data, Copernicus Atmosphere Monitoring Service (CAMS) European reanalysis products, as well as OpenStreetMap (OSM) road and buildings network for the entirety of Lombardy. The structure of the dataset is the following: dataset/ ├── arpa_stations/ | Air quality and weather station locations (GeoJSON) ├── osm/ | Lombardy buildings & roads data (GeoJSON + GeoParquet) ├── raw_cams_data/ | CAMS reanalysis atmospheric data (NetCDF) ├── nodes/ | GCAF node network outputs: centrality + coregistered CAMS values (Hive–partitioned GeoParquet) └── stac_items/ | STAC catalog metadataThis research was supported by the project “Romanian Hub for Artificial Intelligence - HRIA”, Smart Growth, Digitization and Financial Instruments Program, 2021-2027, MySMIS no. 351416.