Identifying high resolution benchmark data needs and Novel data-driven methodologies for Climate Downscaling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Curran, Declan, Saleem, Hira, Salim, Flora
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914816871890944
author Curran, Declan
Saleem, Hira
Salim, Flora
author_facet Curran, Declan
Saleem, Hira
Salim, Flora
contents We address the essential role of information retrieval in enhancing climate downscaling, focusing on the need for high-resolution datasets and the application of deep learning models. We explore the requirements for acquiring detailed spatial and temporal climate data, crucial for accurate local forecasts, and discuss how deep learning (DL) techniques can significantly improve downscaling precision by modelling the complex relationships between climate variables. Additionally, we examine the specific challenges related to the retrieval of relevant climatic data, emphasizing methods for efficient data extraction and utilization to support advanced model training. This research underscores an integrated approach, combining information retrieval, deep learning, and climate science to refine the process of climate downscaling, aiming to produce more accurate and actionable local climate projections.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20346
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Identifying high resolution benchmark data needs and Novel data-driven methodologies for Climate Downscaling
Curran, Declan
Saleem, Hira
Salim, Flora
Atmospheric and Oceanic Physics
We address the essential role of information retrieval in enhancing climate downscaling, focusing on the need for high-resolution datasets and the application of deep learning models. We explore the requirements for acquiring detailed spatial and temporal climate data, crucial for accurate local forecasts, and discuss how deep learning (DL) techniques can significantly improve downscaling precision by modelling the complex relationships between climate variables. Additionally, we examine the specific challenges related to the retrieval of relevant climatic data, emphasizing methods for efficient data extraction and utilization to support advanced model training. This research underscores an integrated approach, combining information retrieval, deep learning, and climate science to refine the process of climate downscaling, aiming to produce more accurate and actionable local climate projections.
title Identifying high resolution benchmark data needs and Novel data-driven methodologies for Climate Downscaling
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2405.20346