paper-with-me

Papers

Reconstructing Historical Climate Fields With Deep Learning

2023-11-30 · Nils Bochow, Anna Poltronieri, Martin Rypdal, Niklas Boers

Historical records of climate fields are often sparse due to missing measurements, especially before the introduction of large-scale satellite missions. Several statistical and model-based methods have been introduced to fill gaps and reconstruct historical records. Here, we employ a recently introduced deep-learning approach based on Fourier convolutions, trained on numerical climate model output, to reconstruct historical climate fields. Using this approach we are able to realistically reconstruct large and irregular areas of missing data, as well as reconstruct known historical events such as strong El Ni\~no and La Ni\~na with very little given information. Our method outperforms the widely used statistical kriging method as well as other recent machine learning approaches. The model generalizes to higher resolutions than the ones it was trained on and can be used on a variety of climate fields. Moreover, it allows inpainting of masks never seen before during the model training.

📄 PDF Abstract BibTeX arXiv:2311.18348

Code (1)

NilsBochow/lama_reconstruction 공식 구현 pytorch

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior

2026-05-17 · Yue Wang, Daniele Visioni arxiv

High-resolution precipitation information is essential for climate impact assessment, yet global climate models remain too coarse to resolve key small-scale processes. Existing machine learning downscaling methods often …

Transferring climate change physical knowledge

2023-09-26 · Francesco Immorlano, Veronika Eyring, Thomas le Monnier de Gouville, Gabriele Accarino 외

Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of clima…

Transfer Learning

Deep Learning for Weather Forecasting: A CNN-LSTM Hybrid Model for Predicting Historical Temperature Data

2024-10-19 · Yuhao Gong, Yuchen Zhang, Fei Wang, Chi-Han Lee

As global climate change intensifies, accurate weather forecasting has become increasingly important, affecting agriculture, energy management, environmental protection, and daily life. This study introduces a hybrid mod…

energy managementManagementPredictionWeather Forecasting

Controlling Weather Field Synthesis Using Variational Autoencoders

2021-07-30 · Dario Augusto Borges Oliveira, Jorge Guevara Diaz, Bianca Zadrozny, Campbell Watson

One of the consequences of climate change is anobserved increase in the frequency of extreme cli-mate events. That poses a challenge for weatherforecast and generation algorithms, which learnfrom historical data but shou…

Meta-modeling strategy for data-driven forecasting

2020-11-14 · Dominic J. Skinner, Romit Maulik

Accurately forecasting the weather is a key requirement for climate change mitigation. Data-driven methods offer the ability to make more accurate forecasts, but lack interpretability and can be expensive to train and de…

BIG-bench Machine Learning