Journal article · 2026 · Open access
Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh
Next Energy, 12, 100678 · Published 28 May 2026 · DOI 10.1016/j.nxener.2026.100678
In brief
“Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh” is a 2026 journal article by Jerin Sultana and Sajeeb Saha, published in Next Energy. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Next Energy.
- Citations
- 0
- References
- 34
- Authors
- 2
Abstract
Bangladesh’s tropical location makes it particularly vulnerable to the effects of climate change, with rising temperatures and extreme heat posing threats to agriculture, the economy, and public health. Accurate weather forecasting is essential for effective decision-making and building climate resilience; however, it faces challenges due to the non-linear nature of climate data. While traditional forecasting models have been extensively studied, they often lack robustness and fail to capture the complex patterns inherent in climate systems. This highlights the need for more advanced methodologies to enhance forecast accuracy and support climate adaptation efforts. This study analyzed 122 years of historical weather data to predict monthly temperatures for 2022 in Bangladesh, utilizing seven deep learning models including CNN, LSTM, BiLSTM, ConvLSTM, and three hybrid architectures (CNN+BiLSTM, CNN+ConvLSTM, and CNN+LSTM). The paper employed metrics such as MAE, MSE, RMSE, and R 2 , with the CNN+LSTM model demonstrating superior performance, achieving an MAE of 0.04 ∘ C and an R 2 of 0.96. To the best of our knowledge, this research represents the first comparative study in Bangladesh that utilizes century-long historical climate data to apply and compare various deep learning models for long-term temperature forecasting. Furthermore, this research forecasts monthly temperature trend Bangladesh from 2023 to 2033. This study establishes a novel benchmark in Bangladesh that policymakers can use to create early alert systems for disaster-related activities, address climate change, plan for heat-resistant urban development, and formulate public health and agricultural adaptation policies.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Sultana, J., & Saha, S. (2026). Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh. Next Energy, 12, 100678. https://doi.org/10.1016/j.nxener.2026.100678
MLA 9
Sultana, Jerin, and Sajeeb Saha. “Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh.” Next Energy, vol. 12, 2026, p. 100678. https://doi.org/10.1016/j.nxener.2026.100678.
Chicago
Sultana, Jerin and Sajeeb Saha. 2026. “Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh.” Next Energy 12: 100678. https://doi.org/10.1016/j.nxener.2026.100678.
Harvard
Sultana, J. and Saha, S. (2026) ‘Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh’, Next Energy, 12, p. 100678. doi:10.1016/j.nxener.2026.100678.
IEEE
J. Sultana and S. Saha, “Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh,” Next Energy, vol. 12, p. 100678, 2026, doi: 10.1016/j.nxener.2026.100678.
BibTeX
@article{sultana2026leveraging,
title = {{Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh}},
author = {Sultana, Jerin and Saha, Sajeeb},
journal = {Next Energy},
year = {2026},
volume = {12},
pages = {100678},
doi = {10.1016/j.nxener.2026.100678},
url = {https://doi.org/10.1016/j.nxener.2026.100678}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- deep learning
- CNN-LSTM hybrid model
- ConvLSTM
- BiLSTM
- climate change vulnerability
- climate resilience
- historical weather data
- Bangladesh
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?
Sultana, J., & Saha, S. (2026). Leveraging deep neural networks for long-term temperature forecasting in climate-vulnerable Bangladesh. Next Energy, 12, 100678. https://doi.org/10.1016/j.nxener.2026.100678
How many times has this paper been cited?
0 times, according to OpenAlex on 20 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 at Next Energy: sign in and open the full text from this page.
Who wrote this paper?
Jerin Sultana, Sajeeb Saha.
What is the DOI of this paper?
10.1016/j.nxener.2026.100678, permanently at https://doi.org/10.1016/j.nxener.2026.100678. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 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.