Article

Self-Supervised Temporal Reconstruction of Subhourly Climate Records since 1806

2025-12-23

Abstract excerpt

<title>Abstract</title> <p>Fast‑evolving weather events typically develop on 5–15 min scales and can significantly influence human activities and planning. However, most global atmospheric reanalyses provide data only every 1–3 hours, making it difficult to capture rapid changes such as short-duration heavy rainfall. Traditional machine learning approaches rely on high-frequency data as supervision labels during...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8f32bd10-1940-5bb0-ab66-36803268fe3b
DOI: 10.21203/rs.3.rs-8341528/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Self-Supervised Temporal Reconstruction of Subhourly Climate Records since 1806DOI 10.21203/rs.3.rs-8341528/v1Read

Learning optimal CNN architectures for Precipitation Downscaling with Differentiable Architecture SearchSemantic proximity Read

Atmospheric Dynamical Amplification Intensifies Future Extreme Precipitation RisksSemantic proximity Read

Anthropogenic influence on extreme precipitation over global land areas seen in multiple observational datasetsSemantic proximity Read

Graph-Based Learning for Multi-Horizon Martian Atmospheric ForecastingSemantic proximity Read

A foundation model for multivariate time series forecastingSemantic proximity Read

Cyclone Intensity Estimation: A Studyof Neural Architecture Search andTransfer Learning in CNNsSemantic proximity Read

A Stacked Deep Learning Framework for 100m Gridded Anthropogenic Heat Inventory Mapping in 64 Belt and Road CountriesSemantic proximity Read

The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature WarmingSemantic proximity Read

Conventional time series, machine and deep learning approaches for rainfall forecasting in a bimodal climate in Embu County, Kenya: A comparative study of SARIMA, ANN, LSTM, CNN and hybrid modelsSemantic proximity Read

Coupled SWAT and SWT-CNN-LSTM model to improve watershed streamflow simulationSemantic proximity Read

A Method for Detection and Attribution of Regional Precipitation Change Using Granger Causality Application to the United States Historical RecordSemantic proximity Read

Characteristics of Summer Precipitation Recycling Ratio and Moisture Sources over Eastern China: Comparing Two RCMs with ERA5Semantic proximity Read