A high-resolution database of historical and future climate for Africa developed with deep neural networks

Abstract This study contributes an accessible, comprehensive database of interpolated climate data for Africa that includes monthly, annual, decadal, and 30-year normal climate data for the last 120 years (1901 to present) as well as multi-model CMIP6 climate change projections for the 21st century....

Full description

Saved in:
Bibliographic Details
Main Authors: Sarah A. Namiiro, Andreas Hamann, Tongli Wang, Dante Castellanos-Acuña, Colin R. Mahony
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05575-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238121265233920
author Sarah A. Namiiro
Andreas Hamann
Tongli Wang
Dante Castellanos-Acuña
Colin R. Mahony
author_facet Sarah A. Namiiro
Andreas Hamann
Tongli Wang
Dante Castellanos-Acuña
Colin R. Mahony
author_sort Sarah A. Namiiro
collection DOAJ
description Abstract This study contributes an accessible, comprehensive database of interpolated climate data for Africa that includes monthly, annual, decadal, and 30-year normal climate data for the last 120 years (1901 to present) as well as multi-model CMIP6 climate change projections for the 21st century. The database includes variables relevant for ecological research and infrastructure planning, and it comprises more than 25,000 climate grids that can be queried with a provided ClimateAF software package. In addition, 30 arcsecond (~1 km) resolution gridded data are available for download. The climate grids were developed with a three-step approach, using thin-plate spline interpolations of weather station data as a first approximation. Subsequently, a novel deep learning approach is used to model orographic precipitation, rain shadows, lake and coastal effects at moderate resolution. Lastly, lapse-rate based downscaling is applied to generate high-resolution grids. The climate estimates were optimized and cross-validated with a checkerboard approach to ensure that training data was spatially distanced from validation data. We conclude with a discussion of applications and limitations of this database.
format Article
id doaj-art-0b3ba2a0bdbc4a188e4819c9bea46627
institution Kabale University
issn 2052-4463
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-0b3ba2a0bdbc4a188e4819c9bea466272025-08-20T04:01:43ZengNature PortfolioScientific Data2052-44632025-07-0112111310.1038/s41597-025-05575-8A high-resolution database of historical and future climate for Africa developed with deep neural networksSarah A. Namiiro0Andreas Hamann1Tongli Wang2Dante Castellanos-Acuña3Colin R. Mahony4Department of Renewable Resources, University of Alberta, 751 General Services BuildingDepartment of Renewable Resources, University of Alberta, 751 General Services BuildingCentre for Forest Conservation Genetics, Department of Forest and Conservation Sciences, University of British ColumbiaDepartment of Renewable Resources, University of Alberta, 751 General Services BuildingBritish Columbia Ministry of ForestsAbstract This study contributes an accessible, comprehensive database of interpolated climate data for Africa that includes monthly, annual, decadal, and 30-year normal climate data for the last 120 years (1901 to present) as well as multi-model CMIP6 climate change projections for the 21st century. The database includes variables relevant for ecological research and infrastructure planning, and it comprises more than 25,000 climate grids that can be queried with a provided ClimateAF software package. In addition, 30 arcsecond (~1 km) resolution gridded data are available for download. The climate grids were developed with a three-step approach, using thin-plate spline interpolations of weather station data as a first approximation. Subsequently, a novel deep learning approach is used to model orographic precipitation, rain shadows, lake and coastal effects at moderate resolution. Lastly, lapse-rate based downscaling is applied to generate high-resolution grids. The climate estimates were optimized and cross-validated with a checkerboard approach to ensure that training data was spatially distanced from validation data. We conclude with a discussion of applications and limitations of this database.https://doi.org/10.1038/s41597-025-05575-8
spellingShingle Sarah A. Namiiro
Andreas Hamann
Tongli Wang
Dante Castellanos-Acuña
Colin R. Mahony
A high-resolution database of historical and future climate for Africa developed with deep neural networks
Scientific Data
title A high-resolution database of historical and future climate for Africa developed with deep neural networks
title_full A high-resolution database of historical and future climate for Africa developed with deep neural networks
title_fullStr A high-resolution database of historical and future climate for Africa developed with deep neural networks
title_full_unstemmed A high-resolution database of historical and future climate for Africa developed with deep neural networks
title_short A high-resolution database of historical and future climate for Africa developed with deep neural networks
title_sort high resolution database of historical and future climate for africa developed with deep neural networks
url https://doi.org/10.1038/s41597-025-05575-8
work_keys_str_mv AT sarahanamiiro ahighresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT andreashamann ahighresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT tongliwang ahighresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT dantecastellanosacuna ahighresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT colinrmahony ahighresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT sarahanamiiro highresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT andreashamann highresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT tongliwang highresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT dantecastellanosacuna highresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks
AT colinrmahony highresolutiondatabaseofhistoricalandfutureclimateforafricadevelopedwithdeepneuralnetworks