Models and Datasets for "Extracting Paleoweather from Paleoclimate through a Deep Learning Reconstruction of Last Millennium Atmospheric Blocking"

Associated publication: Karamperidou, C., 2024: Extracting paleoweather from paleoclimate through a deep learning reconstruction of Last Millennium atmospheric blocking, Nature Communications Earth & Environment. DOI : 10.1038/s43247-024-01687-y. This repository contains: the architecture and weights of PaleoBlockNet v1.0 the following ensemble DL reconstructions of JJA frequency of blocked days inferred by PaleoBlockNet: the 10-member NTREND-based DL reconstruction; uses as input the NTREND DA N.Hemisphere MJJA surface temperature anomaly by King et al. (2021) the 100-member PHYDA-based DL reconstruction; uses as input the PHYDA JJA surface temperature anomaly by Steiger et al. (2018) the 12-member LME-based DL reconstruction; uses as input the CESM-LME surface temperature anomaly; this is a sensitivity experiment (see publication for details). Integrated Gradients that assign importance to the input features for PaleoblockNet's blocking inferences If you use this dataset, please cite the associated publication and the present repository. To interactively explore the datasets, a web interface has been developed and can be accessed at https://www2.hawaii.edu/~ckaramp/paleoblocknet Contact the author Christina Karamperidou (https://www2.hawaii.edu/~ckaramp) for more information about the details of these datasets.