BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios

Abstract Traditional downscaling techniques often fail to accurately represent critical extremes necessary for effective adaptation planning. This paper introduces the first application of Bidirectional Long Short-Term Memory (BiLSTM) networks with an adaptive Kalman filter for multi-scenario, high-...

Full description

Saved in:
Bibliographic Details
Main Authors: Melika Jahangiri, Mahdi Asghari, Mohammad Hossein Niksokhan, Mohammad Reza Nikoo
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-08264-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387836700098560
author Melika Jahangiri
Mahdi Asghari
Mohammad Hossein Niksokhan
Mohammad Reza Nikoo
author_facet Melika Jahangiri
Mahdi Asghari
Mohammad Hossein Niksokhan
Mohammad Reza Nikoo
author_sort Melika Jahangiri
collection DOAJ
description Abstract Traditional downscaling techniques often fail to accurately represent critical extremes necessary for effective adaptation planning. This paper introduces the first application of Bidirectional Long Short-Term Memory (BiLSTM) networks with an adaptive Kalman filter for multi-scenario, high-resolution precipitation downscaling. We applied our methodology to Tehran, Iran, and systematically compared and ranked the performance of different CMIP6 projections, with the best performing model being MIROC (NSE: 0.902, R2: 0.91, RMSE: 7.76). The optimized BiLSTM network alone demonstrated strong performance (R2: 0.638, KGE: 0.684), with the adaptive Kalman filter dynamically adjusting its parameters according to precipitation intensity. Our novel contributions are a symmetric dependence loss for predicting extremes and graduated correction using percentiles. Examination of the Shared Socioeconomic Pathways (SSPs) 1 to 5 revealed surprising findings: the SSP1-2.6 (more sustainable) pathway predicted the highest extremes, with a 24.3% increase in 99th percentile intensity over the past. SSP2-4.5, SSP3-7.0, and SSP5-8.5 had increases of 17.8%, 16.5%, and 21.1%, respectively. Generated Intensity–Duration–Frequency curves indicated dramatic changes for short-duration events (10–30 min) under SSP5-8.5 with essential implications for infrastructure planning. Extreme precipitation events (> 95th percentile) revealed a frequency increase from 2.1 to 3.5% for SSP1-2.6 for events exceeding 20 mm/day. The integrated framework effectively translates coarse climate model outputs into practical engineering tools, providing the required quantitative information for planning climate-resilient infrastructure.
format Article
id doaj-art-4fac268c876a48e1a7f61cd77dcd22b8
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4fac268c876a48e1a7f61cd77dcd22b82025-08-20T03:42:28ZengNature PortfolioScientific Reports2045-23222025-07-0115112310.1038/s41598-025-08264-zBiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenariosMelika Jahangiri0Mahdi Asghari1Mohammad Hossein Niksokhan2Mohammad Reza Nikoo3Faculty of Environment, University of TehranFaculty of Environment, University of TehranFaculty of Environment, University of TehranDepartment of Civil and Architectural Engineering, Sultan Qaboos UniversityAbstract Traditional downscaling techniques often fail to accurately represent critical extremes necessary for effective adaptation planning. This paper introduces the first application of Bidirectional Long Short-Term Memory (BiLSTM) networks with an adaptive Kalman filter for multi-scenario, high-resolution precipitation downscaling. We applied our methodology to Tehran, Iran, and systematically compared and ranked the performance of different CMIP6 projections, with the best performing model being MIROC (NSE: 0.902, R2: 0.91, RMSE: 7.76). The optimized BiLSTM network alone demonstrated strong performance (R2: 0.638, KGE: 0.684), with the adaptive Kalman filter dynamically adjusting its parameters according to precipitation intensity. Our novel contributions are a symmetric dependence loss for predicting extremes and graduated correction using percentiles. Examination of the Shared Socioeconomic Pathways (SSPs) 1 to 5 revealed surprising findings: the SSP1-2.6 (more sustainable) pathway predicted the highest extremes, with a 24.3% increase in 99th percentile intensity over the past. SSP2-4.5, SSP3-7.0, and SSP5-8.5 had increases of 17.8%, 16.5%, and 21.1%, respectively. Generated Intensity–Duration–Frequency curves indicated dramatic changes for short-duration events (10–30 min) under SSP5-8.5 with essential implications for infrastructure planning. Extreme precipitation events (> 95th percentile) revealed a frequency increase from 2.1 to 3.5% for SSP1-2.6 for events exceeding 20 mm/day. The integrated framework effectively translates coarse climate model outputs into practical engineering tools, providing the required quantitative information for planning climate-resilient infrastructure.https://doi.org/10.1038/s41598-025-08264-zPrecipitation downscalingBiLSTM neural networksAdaptive Kalman filteringExtreme event forecastingClimate change scenariosDeep learning
spellingShingle Melika Jahangiri
Mahdi Asghari
Mohammad Hossein Niksokhan
Mohammad Reza Nikoo
BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios
Scientific Reports
Precipitation downscaling
BiLSTM neural networks
Adaptive Kalman filtering
Extreme event forecasting
Climate change scenarios
Deep learning
title BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios
title_full BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios
title_fullStr BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios
title_full_unstemmed BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios
title_short BiLSTM-Kalman framework for precipitation downscaling under multiple climate change scenarios
title_sort bilstm kalman framework for precipitation downscaling under multiple climate change scenarios
topic Precipitation downscaling
BiLSTM neural networks
Adaptive Kalman filtering
Extreme event forecasting
Climate change scenarios
Deep learning
url https://doi.org/10.1038/s41598-025-08264-z
work_keys_str_mv AT melikajahangiri bilstmkalmanframeworkforprecipitationdownscalingundermultipleclimatechangescenarios
AT mahdiasghari bilstmkalmanframeworkforprecipitationdownscalingundermultipleclimatechangescenarios
AT mohammadhosseinniksokhan bilstmkalmanframeworkforprecipitationdownscalingundermultipleclimatechangescenarios
AT mohammadrezanikoo bilstmkalmanframeworkforprecipitationdownscalingundermultipleclimatechangescenarios