paper-with-me

Papers

A Likelihood-Based Generative Approach for Spatially Consistent Precipitation Downscaling

2024-06-26 · Jose González-Abad

Deep learning has emerged as a promising tool for precipitation downscaling. However, current models rely on likelihood-based loss functions to properly model the precipitation distribution, leading to spatially inconsistent projections when sampling. This work explores a novel approach by fusing the strengths of likelihood-based and adversarial losses used in generative models. As a result, we propose a likelihood-based generative approach for precipitation downscaling, leveraging the benefits of both methods.

📄 PDF Abstract BibTeX arXiv:2407.04724

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep generative model super-resolves spatially correlated multiregional climate data

2022-09-26 · Norihiro Oyama, Noriko N. Ishizaki, Satoshi Koide, Hiroaki Yoshida

Super-resolving the coarse outputs of global climate simulations, termed downscaling, is crucial in making political and social decisions on systems requiring long-term climate change projections. Existing fast super-res…

Generative Adversarial NetworkSuper-Resolution

Flow Matching for Convective-Scale Precipitation Downscaling

2026-05-29 · Tom Wetherell arxiv

Generative machine learning is an increasingly important complement to dynamical downscaling for producing high-resolution precipitation projections, with diffusion models currently the leading approach. Flow matching is…

EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules

2025-09-30 · Maybritt Schillinger, Maxim Samarin, Xinwei Shen, Reto Knutti 외 arxiv

The practical use of future climate projections from global circulation models (GCMs) is often limited by their coarse spatial resolution, requiring downscaling to generate high-resolution data. Regional climate models (…

Computational Efficiency

On the modern deep learning approaches for precipitation downscaling

2022-07-02 · Bipin Kumar, Kaustubh Atey, Bhupendra Bahadur Singh, Rajib Chattopadhyay 외

Deep Learning (DL) based downscaling has become a popular tool in earth sciences recently. Increasingly, different DL approaches are being adopted to downscale coarser precipitation data and generate more accurate and re…

Deep LearningGenerative Adversarial NetworkSuper-Resolution

On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling

2025-12-01 · Paula Harder, Christian Lessig, Matthew Chantry, Francis Pelletier 외 arxiv

Deep learning offers promising capabilities for the statistical downscaling of climate and weather forecasts, with generative approaches showing particular success in capturing fine-scale precipitation patterns. However,…