Viola Steidl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Viola Steidl has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Xiao Xiang Zhu
Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany
12 shared publications - Jonathan Louis Bamber
Bristol Glaciology Centre, School of Geographical Sciences, University of Bristol, BS8 1SS, UK
6 shared publications - Fupeng Li
Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany
5 shared publications Jürgen Kusche
Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-23
Reply on RC2
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- 9 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-23
Open AccessReply on RC2
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- Open Access
- 9 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-23
Reply on RC1
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- 9 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-23
Open AccessReply on RC1
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- Open Access
- 11 September 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-23
Comment on egusphere-2026-2312
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- 11 September 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-23
Open AccessComment on egusphere-2026-2312
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- Open Access
- 4 August 2026
- Published by Copernicus GmbH
- p. 1-23
Comment on egusphere-2026-2312
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- 4 August 2026
- Published by Copernicus GmbH
- p. 1-23
Open AccessComment on egusphere-2026-2312
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- Open Access
- 23 June 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-23
Hierarchical Graph Networks for Seasonal Forecasts of Terrestrial Water Storage Anomalies
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- 23 June 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-23
Open AccessHierarchical Graph Networks for Seasonal Forecasts of Terrestrial Water Storage Anomalies
Fresh water availability is critical for ecosystems, agriculture, industry, and human communities. Anticipating drought conditions benefits from forecasting changes in terrestrial water storage (TWS), the total water stored on land across all compartments, including groundwater, rivers, glaciers, and soil moisture. While individual compartments, such as groundwater, are difficult to observe directly at large scales, TWS integrates their combined changes and can be measured globally through satellite gravimetry. Since 2002, the GRACE and GRACE Follow-On (GRACE-FO) missions have delivered monthly, global estimates of terrestrial water storage anomalies (TWSA), deviations from a long-term mean, making TWSA the most accessible large-scale indicator of hydrological change. Predicting TWSA is nonetheless challenging as it reflects processes operating at vastly different temporal and spatial scales. We present HiGNN-LSTM, a hierarchical graph neural network that represents the Earth across two spatial scales, coupled with an LSTM module to forecast global TWSA for up to six months ahead. As a proof of concept, we show that the hierarchical graph neural network can automatically generate meaningful input features for TWSA forecasting from ERA5 climate variables, without requiring manual predictor selection or lag-correlation analysis. Trained on a GRACE-like reconstruction of TWSA extending from 1979 to 2020, the model substantially reduces the one-month-lead RMSE relative to a seasonal climatology baseline (1.83 cm vs 3.70 cm) and consistently outperforms a ConvLSTM across the full six-month horizon. Skill over climatology shrinks at longer leads and is lost by six months, indicating that most of the gain concentrates at short leads. Evaluation against GRACE- and GRACE-FO-derived TWSA highlights the difficulty of transferring a model trained on reconstructed TWSA to satellite-derived observations.
- Open Access
- 14 March 2026
- Published by Copernicus GmbH
Hierarchical Graph Networks for ForecastingTerrestrial Water Storage Anomalies
The availability of fresh water is vital to the ecosystem and communities. In a changing climate, the increased risk of droughts makes it crucial to have an accurate understanding of changes in terrestrial water storage (TWS). Predicting changes in TWS is inherently difficult since it integrates the changes of all water compartments, with underlying processes that operate on vastly different temporal and spatial scales. Forecasting tasks nowadays are often solved using machine learning models. However, these models require vast amounts of data. In contrast, total water storage anomalies (TWSA) derived from GRACE/GRACE-FO observations only date back to 2002 and are available at a grid of 1°x1° at monthly resolution. Nevertheless, Li et al., (2024) showed that machine-learning approaches could forecast TWSA tendencies for up to one year ahead. They cleverly exploit temporal lag relationships between TWSA and ocean, atmospheric, or land variables.In our work, we explore a novel design of a hierarchical graph using domain knowledge of hydrological basins to encode these processes in a latent feature sequence using an encoder-processor-decoder style graph neural network. The subsequent recurrent neural network then forecasts TWSA from the latent feature sequence and 12-month history of TWSA for up to six months ahead. The gridded product of the seasonal forecast of global TWSA shows improvement over a seasonal long-term mean.Li, F., Kusche, J., Sneeuw, N., Siebert, S., Gerdener, H., Wang, Z., Chao, N., Chen, G., and Tian, K.: Forecasting Next Year’s Global Land Water Storage Using GRACE Data, Geophys. Res. Lett., 51, e2024GL109101, https://doi.org/10.1029/2024GL109101, 2024.
- 14 March 2026
- Published by Copernicus GmbH
Open AccessHierarchical Graph Networks for ForecastingTerrestrial Water Storage Anomalies
The availability of fresh water is vital to the ecosystem and communities. In a changing climate, the increased risk of droughts makes it crucial to have an accurate understanding of changes in terrestrial water storage (TWS). Predicting changes in TWS is inherently difficult since it integrates the changes of all water compartments, with underlying processes that operate on vastly different temporal and spatial scales. Forecasting tasks nowadays are often solved using machine learning models. However, these models require vast amounts of data. In contrast, total water storage anomalies (TWSA) derived from GRACE/GRACE-FO observations only date back to 2002 and are available at a grid of 1°x1° at monthly resolution. Nevertheless, Li et al., (2024) showed that machine-learning approaches could forecast TWSA tendencies for up to one year ahead. They cleverly exploit temporal lag relationships between TWSA and ocean, atmospheric, or land variables.In our work, we explore a novel design of a hierarchical graph using domain knowledge of hydrological basins to encode these processes in a latent feature sequence using an encoder-processor-decoder style graph neural network. The subsequent recurrent neural network then forecasts TWSA from the latent feature sequence and 12-month history of TWSA for up to six months ahead. The gridded product of the seasonal forecast of global TWSA shows improvement over a seasonal long-term mean.Li, F., Kusche, J., Sneeuw, N., Siebert, S., Gerdener, H., Wang, Z., Chao, N., Chen, G., and Tian, K.: Forecasting Next Year’s Global Land Water Storage Using GRACE Data, Geophys. Res. Lett., 51, e2024GL109101, https://doi.org/10.1029/2024GL109101, 2024.
- Open Access
- 7 February 2025
- Published by Copernicus GmbH in The Cryosphere
- Vol. 19 (2) , 645-661
Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard
The ice thickness of the world's glaciers is mostly unmeasured, and physics-based models to reconstruct ice thickness cannot always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross-validation scheme, we evaluate the performance of the physics-informed neural network. The results of these proof-of-concept experiments let us identify several challenges and opportunities that affect the model's performance in a real-world setting.
- 7 February 2025
- Published by Copernicus GmbH in The Cryosphere
- Vol. 19 (2) , 645-661
Open AccessPhysics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard
The ice thickness of the world's glaciers is mostly unmeasured, and physics-based models to reconstruct ice thickness cannot always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross-validation scheme, we evaluate the performance of the physics-informed neural network. The results of these proof-of-concept experiments let us identify several challenges and opportunities that affect the model's performance in a real-world setting.
- Open Access
- 20 January 2025
- Published by Copernicus GmbH
Physics-aware Machine Learning to Estimate Ice Thickness of Glaciers in West Svalbard
Glacier ice thickness is a fundamental variable required for modelling flow and mass balance. However, direct measurements of ice thickness are scarce. Physics-based and data-driven approaches aim to reconstruct glacier ice thicknesses from the limited in-situ data. Farinotti et al. compared 17 models and found that their ice thickness estimates differ considerably on test glaciers.[1] Following these results, Farinotti et al. created an ensemble of models to develop the so-called consensus estimate of the ice thickness for the world’s glaciers in 2019.[2] Later, Millan et al. derived ice thickness estimates for the world’s glaciers using ice motion as the primary constraint. However, these results differ considerably from existing estimates and the 2019 consensus estimates.[3] It is evident, therefore, that significant uncertainty remains in ice thickness estimates.Deep learning approaches are flexible and adapt well to complex structures and non-linear behaviour. However, they do not guarantee physical correctness of the predicted quantities. Therefore, we employ a physics-informed neural network (PINN), which integrates physical laws into their training process and is not purely data-driven. We include, for example, the conservation of mass in the loss function and estimate the depth-averaged flow velocity. Teisberg et al. also employed a mass-conserving PINN to interpolate the ice thickness of the well-studied Byrd glacier in Antarctica.[4] In this work, we extend the methodology by integrating the ratio between slope and surface flow velocities in estimating the depth-averaged flow velocity and mapping the coordinate variables to higher dimensional Fourier Features.[5] This allows to encompass glaciers in western Svalbard, addressing challenges posed by basal sliding, surface melting, and complex glacier geometries. Using surface velocity data from Millan et al. and topographical data from Copernicus DEM GLO-90[6] gathered through OGGM[7], the model predicts ice thickness on glaciers with limited measurements. We are extending it to perform as a predictor of thickness for glaciers with no observations. Here, we present the machine learning pipeline, including the physical constraints employed and preliminary results for glaciers in western Svalbard. [1] Daniel Farinotti et al., ‘How Accurate Are Estimates of Glacier Ice Thickness? Results from ITMIX, the Ice Thickness Models Intercomparison eXperiment’, The Cryosphere 11, no. 2 (April 2017): 949–70, https://doi.org/10.5194/tc-11-949-2017. [2] Daniel Farinotti et al., ‘A Consensus Estimate for the Ice Thickness Distribution of All Glaciers on Earth’, Nature Geoscience 12, no. 3 (March 2019): 168–73, https://doi.org/10.1038/s41561-019-0300-3. [3] Romain Millan et al., ‘Ice Velocity and Thickness of the World’s Glaciers’, Nature Geoscience 15, no. 2 (February 2022): 124–29, https://doi.org/10.1038/s41561-021-00885-z. [4] Thomas O. Teisberg, Dustin M. Schroeder, and Emma J. MacKie, ‘A Machine Learning Approach to Mass-Conserving Ice Thickness Interpolation’, in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021, 8664–67, https://doi.org/10.1109/IGARSS47720.2021.9555002. [5] Matthew Tancik et al., ‘Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains’, (arXiv, 18 June 2020), https://doi.org/10.48550/arXiv.2006.10739. [6] {https://doi.org/10.5270/ESA-c5d3d65} [7] Fabien Maussion et al., ‘The Open Global Glacier Model (OGGM) v1.1’, Geoscientific Model Development 12, no. 3 (March 2019): 909–31, https://doi.org/10.5194/gmd-12-909-2019.
- 20 January 2025
- Published by Copernicus GmbH
Open AccessPhysics-aware Machine Learning to Estimate Ice Thickness of Glaciers in West Svalbard
Glacier ice thickness is a fundamental variable required for modelling flow and mass balance. However, direct measurements of ice thickness are scarce. Physics-based and data-driven approaches aim to reconstruct glacier ice thicknesses from the limited in-situ data. Farinotti et al. compared 17 models and found that their ice thickness estimates differ considerably on test glaciers.[1] Following these results, Farinotti et al. created an ensemble of models to develop the so-called consensus estimate of the ice thickness for the world’s glaciers in 2019.[2] Later, Millan et al. derived ice thickness estimates for the world’s glaciers using ice motion as the primary constraint. However, these results differ considerably from existing estimates and the 2019 consensus estimates.[3] It is evident, therefore, that significant uncertainty remains in ice thickness estimates.Deep learning approaches are flexible and adapt well to complex structures and non-linear behaviour. However, they do not guarantee physical correctness of the predicted quantities. Therefore, we employ a physics-informed neural network (PINN), which integrates physical laws into their training process and is not purely data-driven. We include, for example, the conservation of mass in the loss function and estimate the depth-averaged flow velocity. Teisberg et al. also employed a mass-conserving PINN to interpolate the ice thickness of the well-studied Byrd glacier in Antarctica.[4] In this work, we extend the methodology by integrating the ratio between slope and surface flow velocities in estimating the depth-averaged flow velocity and mapping the coordinate variables to higher dimensional Fourier Features.[5] This allows to encompass glaciers in western Svalbard, addressing challenges posed by basal sliding, surface melting, and complex glacier geometries. Using surface velocity data from Millan et al. and topographical data from Copernicus DEM GLO-90[6] gathered through OGGM[7], the model predicts ice thickness on glaciers with limited measurements. We are extending it to perform as a predictor of thickness for glaciers with no observations. Here, we present the machine learning pipeline, including the physical constraints employed and preliminary results for glaciers in western Svalbard. [1] Daniel Farinotti et al., ‘How Accurate Are Estimates of Glacier Ice Thickness? Results from ITMIX, the Ice Thickness Models Intercomparison eXperiment’, The Cryosphere 11, no. 2 (April 2017): 949–70, https://doi.org/10.5194/tc-11-949-2017. [2] Daniel Farinotti et al., ‘A Consensus Estimate for the Ice Thickness Distribution of All Glaciers on Earth’, Nature Geoscience 12, no. 3 (March 2019): 168–73, https://doi.org/10.1038/s41561-019-0300-3. [3] Romain Millan et al., ‘Ice Velocity and Thickness of the World’s Glaciers’, Nature Geoscience 15, no. 2 (February 2022): 124–29, https://doi.org/10.1038/s41561-021-00885-z. [4] Thomas O. Teisberg, Dustin M. Schroeder, and Emma J. MacKie, ‘A Machine Learning Approach to Mass-Conserving Ice Thickness Interpolation’, in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021, 8664–67, https://doi.org/10.1109/IGARSS47720.2021.9555002. [5] Matthew Tancik et al., ‘Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains’, (arXiv, 18 June 2020), https://doi.org/10.48550/arXiv.2006.10739. [6] {https://doi.org/10.5270/ESA-c5d3d65} [7] Fabien Maussion et al., ‘The Open Global Glacier Model (OGGM) v1.1’, Geoscientific Model Development 12, no. 3 (March 2019): 909–31, https://doi.org/10.5194/gmd-12-909-2019.
- Open Access
- 28 August 2024
- Published by Copernicus GmbH
- Vol. 2024, 1-19
Reply on RC1
The ice thickness of the world’s glaciers is mostly unmeasured and physics-based models to reconstruct ice thickness can not always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross validation scheme we evaluate the performance of the physics-informed neural network. The results of the experiments let us identify several challenges and opportunities that affect the model’s performance in a real-world setting.
- 28 August 2024
- Published by Copernicus GmbH
- Vol. 2024, 1-19
Open AccessReply on RC1
The ice thickness of the world’s glaciers is mostly unmeasured and physics-based models to reconstruct ice thickness can not always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross validation scheme we evaluate the performance of the physics-informed neural network. The results of the experiments let us identify several challenges and opportunities that affect the model’s performance in a real-world setting.
- Open Access
- 28 August 2024
- Published by Copernicus GmbH
- Vol. 2024, 1-19
Reply on RC2
The ice thickness of the world’s glaciers is mostly unmeasured and physics-based models to reconstruct ice thickness can not always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross validation scheme we evaluate the performance of the physics-informed neural network. The results of the experiments let us identify several challenges and opportunities that affect the model’s performance in a real-world setting.
- 28 August 2024
- Published by Copernicus GmbH
- Vol. 2024, 1-19
Open AccessReply on RC2
The ice thickness of the world’s glaciers is mostly unmeasured and physics-based models to reconstruct ice thickness can not always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross validation scheme we evaluate the performance of the physics-informed neural network. The results of the experiments let us identify several challenges and opportunities that affect the model’s performance in a real-world setting.