Journal article · 2026 · Open access
Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data
Journal of Earth System Science, 135(4), 249 · Published 27 September 2026 · DOI 10.1007/s12040-026-02936-8
In brief
“Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data” is a 2026 journal article by Danish Ansari and Tabish Umar Ansari, published in Journal of Earth System Science. OpenAlex counts 1 citations as of 21 November 2026. It is open access under a CC BY-NC licence: the full text is free to read.
- Citations
- 1
- Most cited in
- 2025 (1)
- References
- 55
- Authors
- 2
Abstract
Global climate change leads to distinct regional impacts. Future climate projections are available through global model outputs, but they lack the spatial detail needed to inform local decision-making for adaptation. Regional- and local-scale climate information can be generated by ‘downscaling’ these global model outputs through regional climate model simulations, which require enormous supercomputing resources, thereby limiting the availability of local-scale projections, especially in underdeveloped regions. Here, we build and test four different computationally efficient machine learning models as an alternative to regional climate models for downscaling daily temperature data over India. We utilise publicly available CMIP6 coarse (1.87° × 1.87°) resolution climate data and relate them to the finer (0.1° × 0.1°) resolution ERA5-Land reanalyses 2 m daily temperatures as a target to train our models over the 2018–2022 period. We progressively improve our model design by utilising spatial learning (through a convolutional neural network) and then including temporal learning (through ConvLSTM) and optimising the target region for downscaling. We systematically evaluate all four models for a temporally near year 2017 and a temporally distant year 2007 and select the best model variant to project daily temperatures over India for the medium-term future, 2030. We present seasonal maps, frequency distributions, as well as city-specific time-series of daily temperatures for the downscaled data vis-à-vis the original global model data. We find a slight overall increase in the annual averaged downscaled temperatures for 2030 (0.3°C) and an even larger increase in the most frequent (i.e., modal) temperature (1°C), but also a decrease over certain regions, particularly in the Indo-Gangetic plain, in summer and monsoon as compared to the coarse-scale temperatures in the global model data for 2030. Our deep learning model compares favourably with reference data from the ERA5-Land reanalyses and runs much faster, with much fewer computational resources than a typical physics-based regional climate model and therefore opens up the possibility of democratising the field of climate downscaling. Research highlights ML-based coarse-grid to fine-grid downscaling of daily temperatures over India: Four neural network architectures, two CNNs and two RNNs, are built and tested as computationally-light replacements for physics-based models. Excluding the Tibetan plateau with complex topography from the target region and including a 14-day weather history into the model input stream improves model performance. All model architectures show better performance at the coasts and worse performance over the Thar desert and Himalayan foothills and struggle to predict fine-grid temperatures during pre-monsoon. The best model architecture (with 14-day history and cropped target region) is ultimately used to rapidly downscale future CMIP6 projections…
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ansari, D., & Ansari, T. U. (2026). Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data. Journal of Earth System Science, 135(4), 249. https://doi.org/10.1007/s12040-026-02936-8
MLA 9
Ansari, Danish, and Tabish Umar Ansari. “Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data.” Journal of Earth System Science, vol. 135, no. 4, 2026, p. 249. https://doi.org/10.1007/s12040-026-02936-8.
Chicago
Ansari, Danish and Tabish Umar Ansari. 2026. “Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data.” Journal of Earth System Science 135 (4): 249. https://doi.org/10.1007/s12040-026-02936-8.
Harvard
Ansari, D. and Ansari, T. U. (2026) ‘Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data’, Journal of Earth System Science, 135(4), p. 249. doi:10.1007/s12040-026-02936-8.
IEEE
D. Ansari and T. U. Ansari, “Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data,” Journal of Earth System Science, vol. 135, no. 4, p. 249, 2026, doi: 10.1007/s12040-026-02936-8.
BibTeX
@article{ansari2026deep,
title = {{Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data}},
author = {Ansari, Danish and Ansari, Tabish Umar},
journal = {Journal of Earth System Science},
year = {2026},
volume = {135},
number = {4},
pages = {249},
doi = {10.1007/s12040-026-02936-8},
url = {https://doi.org/10.1007/s12040-026-02936-8}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models
- climate downscaling
- CMIP6
- India
- ConvLSTM
- convolutional neural networks
- ERA5-Land reanalysis
- regional climate model
- climate change adaptation
Work with this paper
Most-cited papers in Environmental Science
- Biodiversity hotspots for conservation prioritiesNorman Myers, Russell A. Mittermeier, Cristina Goettsch Mittermeier and 2 more · Nature · 2000 · 32,720 citations
- The Tragedy of the CommonsGarrett Hardin · Science · 1968 · 26,194 citations
- River flow forecasting through conceptual models part I — A discussion of principlesJ.E. Nash, John V. Sutcliffe · Journal of Hydrology · 1970 · 24,625 citations
- The value of the world's ecosystem services and natural capitalRobert Costanza, Ralph C. d’Arge, R.S. de Groot and 10 more · Nature · 1997 · 23,508 citations
- Climate change 2007: the physical science basisSusan Solomon, Dahe Qin, Martin Manning and 5 more · 2007 · 23,383 citations
Questions about this paper
How do I cite this paper in APA style?
Ansari, D., & Ansari, T. U. (2026). Deep learning for climate downscaling: generating high-resolution gridded temperature projections over India from low-resolution CMIP6 data. Journal of Earth System Science, 135(4), 249. https://doi.org/10.1007/s12040-026-02936-8
How many times has this paper been cited?
1 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: sign in and open the PDF from this page.
Who wrote this paper?
Danish Ansari, Tabish Umar Ansari.
What is the DOI of this paper?
10.1007/s12040-026-02936-8, permanently at https://doi.org/10.1007/s12040-026-02936-8. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.