Kathryn Lawson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kathryn Lawson has a total of 131 co-authors. Here are the top co-authors by number of shared publications:
- Chaopeng Shen
Civil and Environmental Engineering, The Pennsylvania State University, University Park, USA
72 shared publications - Jiangtao Liu
Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
31 shared publications - Yalan Song
Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
24 shared publications - Farshid Rahmani
Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
19 shared publications - Tadd Bindas
Civil and Environmental Engineering, The Pennsylvania State University, University Park, PA, USA
15 shared publications - Ming Pan
Center for Western Weather and Water Extremes Scripps Institution of Oceanography University of California San Diego La Jolla CA USA
14 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62 (11)
Systematic Discrepancies Should Be Addressed Before Effective Parameter Learning: Insights From Soil Moisture Simulations Using Differentiable Process‐Based Models
Differentiable hydrologic models combining neural networks with process‐based backbones—fully implemented or approximated by surrogate models—offer highly competitive accuracy and improved interpretability compared to either model type used alone. However, the impacts of surrogate model fidelity (accurate sensitivity of relationships compared to the original model) and systematic discrepancies between models and observations on parameter learning effectiveness remain underexplored. This study evaluates optimization performance of the differentiable HBV model ( δ HBV) and its surrogate variants in simulating soil moisture across the contiguous United States. Results show that high‐fidelity surrogate models can support effective differentiable parameter learning once systematic discrepancies are addressed. In contrast, unresolved systematic discrepancies degrade optimization performance, with particularly severe deterioration when low‐fidelity surrogates are used. These findings provide one possible explanation for the modest improvements reported in recent surrogate‐based differentiable parameter learning (dPL) applications. Linear correction partially mitigates these systematic discrepancies, improves optimization performance, and reduces compensatory parameter adjustment, although it does not resolve the underlying model–observation mismatch. Structural refinement remains a physically grounded long‐term direction, while pragmatic correction modules can provide useful partial mitigation when such refinement is not yet available. In addition, fully implementing differentiable process‐based models or using a rigorously trained surrogate can improve gradient fidelity and reduce amplified deterioration associated with surrogate infidelity.
- 11 November 2026
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62 (11)
Open AccessSystematic Discrepancies Should Be Addressed Before Effective Parameter Learning: Insights From Soil Moisture Simulations Using Differentiable Process‐Based Models
Differentiable hydrologic models combining neural networks with process‐based backbones—fully implemented or approximated by surrogate models—offer highly competitive accuracy and improved interpretability compared to either model type used alone. However, the impacts of surrogate model fidelity (accurate sensitivity of relationships compared to the original model) and systematic discrepancies between models and observations on parameter learning effectiveness remain underexplored. This study evaluates optimization performance of the differentiable HBV model ( δ HBV) and its surrogate variants in simulating soil moisture across the contiguous United States. Results show that high‐fidelity surrogate models can support effective differentiable parameter learning once systematic discrepancies are addressed. In contrast, unresolved systematic discrepancies degrade optimization performance, with particularly severe deterioration when low‐fidelity surrogates are used. These findings provide one possible explanation for the modest improvements reported in recent surrogate‐based differentiable parameter learning (dPL) applications. Linear correction partially mitigates these systematic discrepancies, improves optimization performance, and reduces compensatory parameter adjustment, although it does not resolve the underlying model–observation mismatch. Structural refinement remains a physically grounded long‐term direction, while pragmatic correction modules can provide useful partial mitigation when such refinement is not yet available. In addition, fully implementing differentiable process‐based models or using a rigorously trained surrogate can improve gradient fidelity and reduce amplified deterioration associated with surrogate infidelity.
- Open Access
- 6 October 2026
- Published by IOP Publishing in Machine Learning: Earth
Surrogate-Aided Differentiable Hydrologic Model Optimization with Sensitivity Constraints
- 6 October 2026
- Published by IOP Publishing in Machine Learning: Earth
Open AccessSurrogate-Aided Differentiable Hydrologic Model Optimization with Sensitivity Constraints
- Open Access
- 12 August 2026
- Published by Copernicus GmbH
- p. 1-46
Comment on egusphere-2026-1982
Accurate flood inundation modeling using high-resolution hydrodynamic simulations is computationally demanding, limiting their use for large-scale analysis and rapid scenario evaluation. Although machine learning surrogates have been developed, many struggle to reproduce the full spatiotemporal evolution of flood dynamics while maintaining physical consistency across spatial scales. In particular, simultaneously capturing basin-scale wave propagation and fine-scale inundation boundaries remains challenging. This study presents a multi-resolution deep learning framework for dynamic flood prediction. The approach combines a coarse-resolution neural operator that captures large-scale hydrodynamic behavior with a terrain-aware refinement module that reconstructs a fine-scale boundary structure. The framework is trained on high-fidelity two-dimensional shallow-water simulations and evaluated across riverine, dam-break, and complex floodplain systems, including tests under structured bathymetric uncertainty. Results demonstrate accurate reconstruction of continuous water depth fields, wet-dry delineation, and peak flow magnitude and timing. The model preserves the evolution of domain-integrated water volume over time, ensuring physically consistent mass dynamics rather than purely geometric agreement, and maintains probabilistic consistency when input topography is uncertain. The framework, therefore, provides high-resolution flood predictions at substantially reduced computational cost relative to direct high-resolution simulation. These findings show that multi-resolution deep learning can approximate hydrodynamic flood processes with strong physical fidelity and robustness to geometric uncertainty, supporting scalable flood hazard assessment and rapid predictive modeling.
- 12 August 2026
- Published by Copernicus GmbH
- p. 1-46
Open AccessComment on egusphere-2026-1982
Accurate flood inundation modeling using high-resolution hydrodynamic simulations is computationally demanding, limiting their use for large-scale analysis and rapid scenario evaluation. Although machine learning surrogates have been developed, many struggle to reproduce the full spatiotemporal evolution of flood dynamics while maintaining physical consistency across spatial scales. In particular, simultaneously capturing basin-scale wave propagation and fine-scale inundation boundaries remains challenging. This study presents a multi-resolution deep learning framework for dynamic flood prediction. The approach combines a coarse-resolution neural operator that captures large-scale hydrodynamic behavior with a terrain-aware refinement module that reconstructs a fine-scale boundary structure. The framework is trained on high-fidelity two-dimensional shallow-water simulations and evaluated across riverine, dam-break, and complex floodplain systems, including tests under structured bathymetric uncertainty. Results demonstrate accurate reconstruction of continuous water depth fields, wet-dry delineation, and peak flow magnitude and timing. The model preserves the evolution of domain-integrated water volume over time, ensuring physically consistent mass dynamics rather than purely geometric agreement, and maintains probabilistic consistency when input topography is uncertain. The framework, therefore, provides high-resolution flood predictions at substantially reduced computational cost relative to direct high-resolution simulation. These findings show that multi-resolution deep learning can approximate hydrodynamic flood processes with strong physical fidelity and robustness to geometric uncertainty, supporting scalable flood hazard assessment and rapid predictive modeling.
- Open Access
- 12 August 2026
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (16)
Geospatial Foundation Embeddings as Transferable Catchment Descriptors
Deep learning hydrological models rely on static catchment attributes to characterize basin heterogeneity, but these traditional descriptors suffer from regional inconsistency and limited temporal representativeness. This study evaluates geospatial foundation model embeddings (from AlphaEarth and StefaLand) as transferable catchment descriptors for rainfall‐runoff modeling. Temporal validation across 531 CAMELS basins showed that deep learning models trained on AlphaEarth embeddings alone achieved comparable performance to those trained on traditional attributes (median Nash‐Sutcliffe Efficiency (NSE) 0.779 vs. 0.781). In a global prediction in ungauged basins (PUB) scenario with 3,434 basins, combining embeddings with traditional attributes improved median NSE from 0.683 to 0.720. A dual‐path gated model revealed structured spatiotemporal reliance patterns: models preferentially utilized embeddings during snowmelt transitions and in humid basins, with limited reliance in arid catchments. Independent validation with StefaLand embeddings from a land‐surface foundation model yielded consistent temporal validation results, supporting the broader use of learned embeddings as transferable catchment descriptors.
- 12 August 2026
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (16)
Open AccessGeospatial Foundation Embeddings as Transferable Catchment Descriptors
Deep learning hydrological models rely on static catchment attributes to characterize basin heterogeneity, but these traditional descriptors suffer from regional inconsistency and limited temporal representativeness. This study evaluates geospatial foundation model embeddings (from AlphaEarth and StefaLand) as transferable catchment descriptors for rainfall‐runoff modeling. Temporal validation across 531 CAMELS basins showed that deep learning models trained on AlphaEarth embeddings alone achieved comparable performance to those trained on traditional attributes (median Nash‐Sutcliffe Efficiency (NSE) 0.779 vs. 0.781). In a global prediction in ungauged basins (PUB) scenario with 3,434 basins, combining embeddings with traditional attributes improved median NSE from 0.683 to 0.720. A dual‐path gated model revealed structured spatiotemporal reliance patterns: models preferentially utilized embeddings during snowmelt transitions and in humid basins, with limited reliance in arid catchments. Independent validation with StefaLand embeddings from a land‐surface foundation model yielded consistent temporal validation results, supporting the broader use of learned embeddings as transferable catchment descriptors.
- Open Access
- 28 July 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-46
Reply on RC1
Accurate flood inundation modeling using high-resolution hydrodynamic simulations is computationally demanding, limiting their use for large-scale analysis and rapid scenario evaluation. Although machine learning surrogates have been developed, many struggle to reproduce the full spatiotemporal evolution of flood dynamics while maintaining physical consistency across spatial scales. In particular, simultaneously capturing basin-scale wave propagation and fine-scale inundation boundaries remains challenging. This study presents a multi-resolution deep learning framework for dynamic flood prediction. The approach combines a coarse-resolution neural operator that captures large-scale hydrodynamic behavior with a terrain-aware refinement module that reconstructs a fine-scale boundary structure. The framework is trained on high-fidelity two-dimensional shallow-water simulations and evaluated across riverine, dam-break, and complex floodplain systems, including tests under structured bathymetric uncertainty. Results demonstrate accurate reconstruction of continuous water depth fields, wet-dry delineation, and peak flow magnitude and timing. The model preserves the evolution of domain-integrated water volume over time, ensuring physically consistent mass dynamics rather than purely geometric agreement, and maintains probabilistic consistency when input topography is uncertain. The framework, therefore, provides high-resolution flood predictions at substantially reduced computational cost relative to direct high-resolution simulation. These findings show that multi-resolution deep learning can approximate hydrodynamic flood processes with strong physical fidelity and robustness to geometric uncertainty, supporting scalable flood hazard assessment and rapid predictive modeling.
- 28 July 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-46
Open AccessReply on RC1
Accurate flood inundation modeling using high-resolution hydrodynamic simulations is computationally demanding, limiting their use for large-scale analysis and rapid scenario evaluation. Although machine learning surrogates have been developed, many struggle to reproduce the full spatiotemporal evolution of flood dynamics while maintaining physical consistency across spatial scales. In particular, simultaneously capturing basin-scale wave propagation and fine-scale inundation boundaries remains challenging. This study presents a multi-resolution deep learning framework for dynamic flood prediction. The approach combines a coarse-resolution neural operator that captures large-scale hydrodynamic behavior with a terrain-aware refinement module that reconstructs a fine-scale boundary structure. The framework is trained on high-fidelity two-dimensional shallow-water simulations and evaluated across riverine, dam-break, and complex floodplain systems, including tests under structured bathymetric uncertainty. Results demonstrate accurate reconstruction of continuous water depth fields, wet-dry delineation, and peak flow magnitude and timing. The model preserves the evolution of domain-integrated water volume over time, ensuring physically consistent mass dynamics rather than purely geometric agreement, and maintains probabilistic consistency when input topography is uncertain. The framework, therefore, provides high-resolution flood predictions at substantially reduced computational cost relative to direct high-resolution simulation. These findings show that multi-resolution deep learning can approximate hydrodynamic flood processes with strong physical fidelity and robustness to geometric uncertainty, supporting scalable flood hazard assessment and rapid predictive modeling.
- Open Access
- 21 July 2026
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62 (7)
Diffusion‐Based Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation
Hourly predictions are critical for issuing flood warnings as the hourly flood peaks can be distinctly higher than the corresponding daily ones. Currently a popular hourly data‐driven prediction scheme is multi‐time‐scale long short‐term memory (MTS‐LSTM), yet such models face challenges in probabilistic forecasts or integrating observations when available. Diffusion artificial intelligence (AI) models represent a promising method to predict high‐resolution information, for example, hourly streamflow. Here we develop a denoising diffusion probabilistic model (h‐Diffusion) for hourly streamflow prediction that conditions on either observed or simulated daily discharge from hydrologic models to generate hourly hydrographs. The model is benchmarked on the CAMELS hourly data set against record‐holding MTS‐LSTM and multi‐frequency LSTM (MF‐LSTM) baselines. Results show that h‐Diffusion outperforms baselines in terms of general performance as well as extreme metrics. Furthermore, the h‐Diffusion model can utilize the inpainting technique and recent observations to accomplish data assimilation that largely improves flood forecasting performance, or even inversely estimate rainfall. These advances can greatly reduce flood forecasting uncertainty and provide a unified probabilistic framework for downscaling, prediction, and data assimilation at the hourly scale, revealing risks that daily models cannot express.
- 21 July 2026
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 62 (7)
Open AccessDiffusion‐Based Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation
Hourly predictions are critical for issuing flood warnings as the hourly flood peaks can be distinctly higher than the corresponding daily ones. Currently a popular hourly data‐driven prediction scheme is multi‐time‐scale long short‐term memory (MTS‐LSTM), yet such models face challenges in probabilistic forecasts or integrating observations when available. Diffusion artificial intelligence (AI) models represent a promising method to predict high‐resolution information, for example, hourly streamflow. Here we develop a denoising diffusion probabilistic model (h‐Diffusion) for hourly streamflow prediction that conditions on either observed or simulated daily discharge from hydrologic models to generate hourly hydrographs. The model is benchmarked on the CAMELS hourly data set against record‐holding MTS‐LSTM and multi‐frequency LSTM (MF‐LSTM) baselines. Results show that h‐Diffusion outperforms baselines in terms of general performance as well as extreme metrics. Furthermore, the h‐Diffusion model can utilize the inpainting technique and recent observations to accomplish data assimilation that largely improves flood forecasting performance, or even inversely estimate rainfall. These advances can greatly reduce flood forecasting uncertainty and provide a unified probabilistic framework for downscaling, prediction, and data assimilation at the hourly scale, revealing risks that daily models cannot express.
- Open Access
- 6 July 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-46
Reply on RC1
Accurate flood inundation modeling using high-resolution hydrodynamic simulations is computationally demanding, limiting their use for large-scale analysis and rapid scenario evaluation. Although machine learning surrogates have been developed, many struggle to reproduce the full spatiotemporal evolution of flood dynamics while maintaining physical consistency across spatial scales. In particular, simultaneously capturing basin-scale wave propagation and fine-scale inundation boundaries remains challenging. This study presents a multi-resolution deep learning framework for dynamic flood prediction. The approach combines a coarse-resolution neural operator that captures large-scale hydrodynamic behavior with a terrain-aware refinement module that reconstructs a fine-scale boundary structure. The framework is trained on high-fidelity two-dimensional shallow-water simulations and evaluated across riverine, dam-break, and complex floodplain systems, including tests under structured bathymetric uncertainty. Results demonstrate accurate reconstruction of continuous water depth fields, wet-dry delineation, and peak flow magnitude and timing. The model preserves the evolution of domain-integrated water volume over time, ensuring physically consistent mass dynamics rather than purely geometric agreement, and maintains probabilistic consistency when input topography is uncertain. The framework, therefore, provides high-resolution flood predictions at substantially reduced computational cost relative to direct high-resolution simulation. These findings show that multi-resolution deep learning can approximate hydrodynamic flood processes with strong physical fidelity and robustness to geometric uncertainty, supporting scalable flood hazard assessment and rapid predictive modeling.
- 6 July 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-46
Open AccessReply on RC1
Accurate flood inundation modeling using high-resolution hydrodynamic simulations is computationally demanding, limiting their use for large-scale analysis and rapid scenario evaluation. Although machine learning surrogates have been developed, many struggle to reproduce the full spatiotemporal evolution of flood dynamics while maintaining physical consistency across spatial scales. In particular, simultaneously capturing basin-scale wave propagation and fine-scale inundation boundaries remains challenging. This study presents a multi-resolution deep learning framework for dynamic flood prediction. The approach combines a coarse-resolution neural operator that captures large-scale hydrodynamic behavior with a terrain-aware refinement module that reconstructs a fine-scale boundary structure. The framework is trained on high-fidelity two-dimensional shallow-water simulations and evaluated across riverine, dam-break, and complex floodplain systems, including tests under structured bathymetric uncertainty. Results demonstrate accurate reconstruction of continuous water depth fields, wet-dry delineation, and peak flow magnitude and timing. The model preserves the evolution of domain-integrated water volume over time, ensuring physically consistent mass dynamics rather than purely geometric agreement, and maintains probabilistic consistency when input topography is uncertain. The framework, therefore, provides high-resolution flood predictions at substantially reduced computational cost relative to direct high-resolution simulation. These findings show that multi-resolution deep learning can approximate hydrodynamic flood processes with strong physical fidelity and robustness to geometric uncertainty, supporting scalable flood hazard assessment and rapid predictive modeling.
- Open Access
- 20 May 2026
- Published by Copernicus GmbH
- Vol. 2026, 1
Reply on RC2
Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called δCLIMBA, or dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts.
- 20 May 2026
- Published by Copernicus GmbH
- Vol. 2026, 1
Open AccessReply on RC2
Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called δCLIMBA, or dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts.
- Open Access
- 20 May 2026
- Published by Copernicus GmbH
- Vol. 2026, 1
Reply on RC1
Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called δCLIMBA, or dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts.
- 20 May 2026
- Published by Copernicus GmbH
- Vol. 2026, 1
Open AccessReply on RC1
Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called δCLIMBA, or dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts.
- Open Access
- 20 May 2026
- Published by Copernicus GmbH
- p. 1
Comment on egusphere-2026-2546
Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called δCLIMBA, or dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts.
- 20 May 2026
- Published by Copernicus GmbH
- p. 1
Open AccessComment on egusphere-2026-2546
Systematic biases in General Circulation Model (GCM) outputs limit their direct applicability in regional planning, making bias correction a technically demanding but necessary step for both short-term and long-term impact assessment. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and heavy-tailed extremes. However, traditional statistical bias-correction methods have limited ability to learn systematic patterns from large datasets or generalize to new locations. While machine learning (ML) provides greater flexibility, it can produce unpredictable and difficult-to-interpret results, limiting generalization across GCMs and locations. In this study, we propose a differentiable bias-adjustment framework called δCLIMBA, or dCLIMBA, that learns a spatiotemporally adaptive parametric bias-adjustment procedure, rather than corrected precipitation directly, between historical CMIP6 model outputs and a gridded observation-based dataset, Livneh. Results demonstrate that the proposed method corrects the magnitude and distribution of extreme precipitation with particularly strong performance in the upper tail. The quantile distribution of precipitation was well reproduced across diverse U.S. cities, and spatial patterns were comparable to those from the widely used LOCA2 statistical downscaling product. In addition, the framework showed partial future trend preservation and promising attenuation of marginal biases in unseen regions. This work presents a modular and efficient bias-correction approach. The differentiable approach provides an easy-to-use option for connecting atmospheric-model outputs to on-the-ground impacts.