A probabilistic generative deep learning framework reconstructs global historical climate fields from 1850 onward, revealing higher early 20th-century warming driven by stronger polar trends and localized modern hotspots compared to existing products.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Rigorous analysis reveals that variance-autocorrelation indicator agreement is driven by the initial data point, with missing values reducing agreement and outliers systematically overestimating resilience via autocorrelation.
citing papers explorer
-
Generative deep learning improves reconstruction of global historical climate records
A probabilistic generative deep learning framework reconstructs global historical climate fields from 1850 onward, revealing higher early 20th-century warming driven by stronger polar trends and localized modern hotspots compared to existing products.
-
The influence of data gaps and outliers on resilience indicators
Rigorous analysis reveals that variance-autocorrelation indicator agreement is driven by the initial data point, with missing values reducing agreement and outliers systematically overestimating resilience via autocorrelation.