Daniel Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Daniel Cheng has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
Eric Larour
Jet Propulsion Laboratory, California Institute of Technology, Pasadena CA, USA
9 shared publicationsWayne Hayes
University of California at Irvine, Irvine, CA, USA
7 shared publications- Michael Wood
Moss Landing Marine Laboratories San Jose State University Moss Landing CA USA
5 shared publications - Eric Rignot
Jet Propulsion Laboratory California Institute of Technology Pasadena CA USA
4 shared publications - Isabella Velicogna
Department of Earth System Science, University of California Irvine, Irvine, USA
4 shared publications - Yara Mohajerani
Earth System Science University of California Irvine CA USA
4 shared publications
Latest Publications
- Open Access
- 21 October 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-24
Mixed up labels
Projections of sea level change require ice sheet models that reconcile observations with ice flow dynamics to constrain poorly observed processes and parameters. We use the Ice-sheet and Sea-level System Model (ISSM) to construct a state and parameter estimate of Ronne Ice Shelf (RIS) and its drainage basin from 1992 to 2018. We assimilate time-varying observations of surface velocity and elevation change to reconstruct a dynamically consistent model of time-mean basal friction and ice rheology, and sub-shelf basal melting rates. Relative to existing methods, we reduce uncertainty weighted root mean square errors (RMSE) in elevation change and velocity by 21.2 % and 43.6 %, respectively. Our inferred basal melt estimates capture spatio-temporal patterns driven by ocean currents at 5 km spatial resolution, and match monthly amplitudes 43.1 % closer to observations relative to existing estimates. Detrended mass change in the upstream grounded basin also correlates with Gravity Recovery and Climate Experiment (GRACE-GFZ) estimates (R = 0.754). This physically-consistent 26-year reconstruction provides a framework for applications to Antarctica and beyond, with implications for prognostic modeling and future sea level projections.
- 21 October 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-24
Open AccessMixed up labels
Projections of sea level change require ice sheet models that reconcile observations with ice flow dynamics to constrain poorly observed processes and parameters. We use the Ice-sheet and Sea-level System Model (ISSM) to construct a state and parameter estimate of Ronne Ice Shelf (RIS) and its drainage basin from 1992 to 2018. We assimilate time-varying observations of surface velocity and elevation change to reconstruct a dynamically consistent model of time-mean basal friction and ice rheology, and sub-shelf basal melting rates. Relative to existing methods, we reduce uncertainty weighted root mean square errors (RMSE) in elevation change and velocity by 21.2 % and 43.6 %, respectively. Our inferred basal melt estimates capture spatio-temporal patterns driven by ocean currents at 5 km spatial resolution, and match monthly amplitudes 43.1 % closer to observations relative to existing estimates. Detrended mass change in the upstream grounded basin also correlates with Gravity Recovery and Climate Experiment (GRACE-GFZ) estimates (R = 0.754). This physically-consistent 26-year reconstruction provides a framework for applications to Antarctica and beyond, with implications for prognostic modeling and future sea level projections.
- Open Access
- 21 October 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-24
State and parameter estimation for Ronne Ice Shelf over 1992–2018
Projections of sea level change require ice sheet models that reconcile observations with ice flow dynamics to constrain poorly observed processes and parameters. We use the Ice-sheet and Sea-level System Model (ISSM) to construct a state and parameter estimate of Ronne Ice Shelf (RIS) and its drainage basin from 1992 to 2018. We assimilate time-varying observations of surface velocity and elevation change to reconstruct a dynamically consistent model of time-mean basal friction and ice rheology, and sub-shelf basal melting rates. Relative to existing methods, we reduce uncertainty weighted root mean square errors (RMSE) in elevation change and velocity by 21.2 % and 43.6 %, respectively. Our inferred basal melt estimates capture spatio-temporal patterns driven by ocean currents at 5 km spatial resolution, and match monthly amplitudes 43.1 % closer to observations relative to existing estimates. Detrended mass change in the upstream grounded basin also correlates with Gravity Recovery and Climate Experiment (GRACE-GFZ) estimates (R = 0.754). This physically-consistent 26-year reconstruction provides a framework for applications to Antarctica and beyond, with implications for prognostic modeling and future sea level projections.
- 21 October 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-24
Open AccessState and parameter estimation for Ronne Ice Shelf over 1992–2018
Projections of sea level change require ice sheet models that reconcile observations with ice flow dynamics to constrain poorly observed processes and parameters. We use the Ice-sheet and Sea-level System Model (ISSM) to construct a state and parameter estimate of Ronne Ice Shelf (RIS) and its drainage basin from 1992 to 2018. We assimilate time-varying observations of surface velocity and elevation change to reconstruct a dynamically consistent model of time-mean basal friction and ice rheology, and sub-shelf basal melting rates. Relative to existing methods, we reduce uncertainty weighted root mean square errors (RMSE) in elevation change and velocity by 21.2 % and 43.6 %, respectively. Our inferred basal melt estimates capture spatio-temporal patterns driven by ocean currents at 5 km spatial resolution, and match monthly amplitudes 43.1 % closer to observations relative to existing estimates. Detrended mass change in the upstream grounded basin also correlates with Gravity Recovery and Climate Experiment (GRACE-GFZ) estimates (R = 0.754). This physically-consistent 26-year reconstruction provides a framework for applications to Antarctica and beyond, with implications for prognostic modeling and future sea level projections.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-8
Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning
Continuous monitoring of glacier calving fronts is essential for sea level rise projections. This study benchmarks Deep Learning systems for front delineation in Synthetic Aperture Radar imagery. While Deep Learning systems exhibit errors up to 221 m, human annotators deviate by only 38 m, underscoring the need for further research.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-8
Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning
Continuous monitoring of glacier calving fronts is essential for sea level rise projections. This study benchmarks Deep Learning systems for front delineation in Synthetic Aperture Radar imagery. While Deep Learning systems exhibit errors up to 221 m, human annotators deviate by only 38 m, underscoring the need for further research.
- Open Access
- 12 August 2022
- Published by Copernicus GmbH in The Cryosphere
- Vol. 16 (8) , 3215-3233
TermPicks: a century of Greenland glacier terminus data for use in scientific and machine learning applications
Marine-terminating outlet glacier terminus traces, mapped from satellite and aerial imagery, have been used extensively in understanding how outlet glaciers adjust to climate change variability over a range of timescales. Numerous studies have digitized termini manually, but this process is labor intensive, and no consistent approach exists. A lack of coordination leads to duplication of efforts, particularly for Greenland, which is a major scientific research focus. At the same time, machine learning techniques are rapidly making progress in their ability to automate accurate extraction of glacier termini, with promising developments across a number of optical and synthetic aperture radar (SAR) satellite sensors. These techniques rely on high-quality, manually digitized terminus traces to be used as training data for robust automatic traces. Here we present a database of manually digitized terminus traces for machine learning and scientific applications. These data have been collected, cleaned, assigned with appropriate metadata including image scenes, and compiled so they can be easily accessed by scientists. The TermPicks data set includes 39 060 individual terminus traces for 278 glaciers with a mean of 136 ± 190 and median of 93 of traces per glacier. Across all glaciers, 32 567 dates have been digitized, of which 4467 have traces from more than one author, and there is a duplication rate of 17 %. We find a median error of ∼ 100 m among manually traced termini. Most traces are obtained after 1999, when Landsat 7 was launched. We also provide an overview of an updated version of the Google Earth Engine Digitization Tool (GEEDiT), which has been developed specifically for future manual picking of the Greenland Ice Sheet.
- 12 August 2022
- Published by Copernicus GmbH in The Cryosphere
- Vol. 16 (8) , 3215-3233
Open AccessTermPicks: a century of Greenland glacier terminus data for use in scientific and machine learning applications
Marine-terminating outlet glacier terminus traces, mapped from satellite and aerial imagery, have been used extensively in understanding how outlet glaciers adjust to climate change variability over a range of timescales. Numerous studies have digitized termini manually, but this process is labor intensive, and no consistent approach exists. A lack of coordination leads to duplication of efforts, particularly for Greenland, which is a major scientific research focus. At the same time, machine learning techniques are rapidly making progress in their ability to automate accurate extraction of glacier termini, with promising developments across a number of optical and synthetic aperture radar (SAR) satellite sensors. These techniques rely on high-quality, manually digitized terminus traces to be used as training data for robust automatic traces. Here we present a database of manually digitized terminus traces for machine learning and scientific applications. These data have been collected, cleaned, assigned with appropriate metadata including image scenes, and compiled so they can be easily accessed by scientists. The TermPicks data set includes 39 060 individual terminus traces for 278 glaciers with a mean of 136 ± 190 and median of 93 of traces per glacier. Across all glaciers, 32 567 dates have been digitized, of which 4467 have traces from more than one author, and there is a duplication rate of 17 %. We find a median error of ∼ 100 m among manually traced termini. Most traces are obtained after 1999, when Landsat 7 was launched. We also provide an overview of an updated version of the Google Earth Engine Digitization Tool (GEEDiT), which has been developed specifically for future manual picking of the Greenland Ice Sheet.
- Open Access
- 14 October 2021
- Published by Copernicus GmbH in EGUsphere
- Vol. 2021, 1-41
TermPicks: A century of Greenland glacier terminus data for use in machine learning applications
Marine-terminating outlet glacier terminus traces, mapped from satellite and aerial imagery, have been used extensively in understanding how outlet glaciers adjust to climate change variability over a range of time scales. Numerous studies have digitized termini manually, but this process is labor-intensive, and no consistent approach exists. A lack of coordination leads to duplication of efforts, particularly for Greenland, which is a major scientific research focus. At the same time, machine learning techniques are rapidly making progress in their ability to automate accurate extraction of glacier termini, with promising developments across a number of optical and SAR satellite sensors. These techniques rely on high quality, manually digitized terminus traces to be used as training data for robust automatic traces. Here we present a database of manually digitized terminus traces for machine learning and scientific applications. These data have been collected, cleaned, assigned with appropriate metadata including image scenes, and compiled so they can be easily accessed by scientists. The TermPicks data set includes 39,060 individual terminus traces for 278 glaciers with a mean and median number of traces per glacier of 136 ± 190 and 93, respectively. Across all glaciers, 32,567 dates have been picked, of which 4,467 have traces from more than one author (duplication of 14 %). We find a median error of ∼100 m among manually-traced termini. Most traces are obtained after 1999, when Landsat 7 was launched. We also provide an overview of an updated version of The Google Earth Engine Digitization Tool (GEEDiT), which has been developed specifically for future manual picking of the Greenland Ice Sheet.
- 14 October 2021
- Published by Copernicus GmbH in EGUsphere
- Vol. 2021, 1-41
Open AccessTermPicks: A century of Greenland glacier terminus data for use in machine learning applications
Marine-terminating outlet glacier terminus traces, mapped from satellite and aerial imagery, have been used extensively in understanding how outlet glaciers adjust to climate change variability over a range of time scales. Numerous studies have digitized termini manually, but this process is labor-intensive, and no consistent approach exists. A lack of coordination leads to duplication of efforts, particularly for Greenland, which is a major scientific research focus. At the same time, machine learning techniques are rapidly making progress in their ability to automate accurate extraction of glacier termini, with promising developments across a number of optical and SAR satellite sensors. These techniques rely on high quality, manually digitized terminus traces to be used as training data for robust automatic traces. Here we present a database of manually digitized terminus traces for machine learning and scientific applications. These data have been collected, cleaned, assigned with appropriate metadata including image scenes, and compiled so they can be easily accessed by scientists. The TermPicks data set includes 39,060 individual terminus traces for 278 glaciers with a mean and median number of traces per glacier of 136 ± 190 and 93, respectively. Across all glaciers, 32,567 dates have been picked, of which 4,467 have traces from more than one author (duplication of 14 %). We find a median error of ∼100 m among manually-traced termini. Most traces are obtained after 1999, when Landsat 7 was launched. We also provide an overview of an updated version of The Google Earth Engine Digitization Tool (GEEDiT), which has been developed specifically for future manual picking of the Greenland Ice Sheet.
- Open Access
- 1 April 2021
- Published by Copernicus GmbH in The Cryosphere
- Vol. 15 (3) , 1663-1675
Calving Front Machine (CALFIN): glacial termini dataset and automated deep learning extraction method for Greenland, 1972–2019
Sea level contributions from the Greenland Ice Sheet are influenced by the rapid changes in glacial terminus positions. The documentation of these evolving calving front positions, for which satellite imagery forms the basis, is therefore important. However, the manual delineation of these calving fronts is time consuming, which limits the availability of these data across a wide spatial and temporal range. Automated methods face challenges that include the handling of clouds, illumination differences, sea ice mélange, and Landsat 7 scan line corrector errors. To address these needs, we develop the Calving Front Machine (CALFIN), an automated method for extracting calving fronts from satellite images of marine-terminating glaciers, using neural networks. The results are often indistinguishable from manually curated fronts, deviating by on average 86.76 ± 1.43 m from the measured front. Landsat imagery from 1972 to 2019 is used to generate 22 678 calving front lines across 66 Greenlandic glaciers. This improves on the state of the art in terms of the spatiotemporal coverage and accuracy of its outputs and is validated through a comprehensive intercomparison with existing studies. The current implementation offers a new opportunity to explore subseasonal and regional trends on the extent of Greenland's margins and supplies new constraints for simulations of the evolution of the mass balance of the Greenland Ice Sheet and its contributions to future sea level rise.
- 1 April 2021
- Published by Copernicus GmbH in The Cryosphere
- Vol. 15 (3) , 1663-1675
Open AccessCalving Front Machine (CALFIN): glacial termini dataset and automated deep learning extraction method for Greenland, 1972–2019
Sea level contributions from the Greenland Ice Sheet are influenced by the rapid changes in glacial terminus positions. The documentation of these evolving calving front positions, for which satellite imagery forms the basis, is therefore important. However, the manual delineation of these calving fronts is time consuming, which limits the availability of these data across a wide spatial and temporal range. Automated methods face challenges that include the handling of clouds, illumination differences, sea ice mélange, and Landsat 7 scan line corrector errors. To address these needs, we develop the Calving Front Machine (CALFIN), an automated method for extracting calving fronts from satellite images of marine-terminating glaciers, using neural networks. The results are often indistinguishable from manually curated fronts, deviating by on average 86.76 ± 1.43 m from the measured front. Landsat imagery from 1972 to 2019 is used to generate 22 678 calving front lines across 66 Greenlandic glaciers. This improves on the state of the art in terms of the spatiotemporal coverage and accuracy of its outputs and is validated through a comprehensive intercomparison with existing studies. The current implementation offers a new opportunity to explore subseasonal and regional trends on the extent of Greenland's margins and supplies new constraints for simulations of the evolution of the mass balance of the Greenland Ice Sheet and its contributions to future sea level rise.
- Open Access
- 4 March 2021
- Published by Copernicus GmbH
Dense Glacial Termini Time Series Analysis: Insights from Calving Front Machine (CALFIN)
Sea level contributions from the Greenland Ice Sheet are influenced by the rapid changes in glacial terminus positions. While manual delineation is labor intensive, recent developments in the field of automated calving front extraction have allowed for high spatio-temporal resolution analysis of Greenlandic glaciers. Specifically, we analyze new developments and results from the Calving Front Machine (CALFIN). CALFIN uses machine learning in the form of deep neural networks to automatically generate 25,000+ calving front positions from 1972 to 2020 across 80+ Greenlandic basins, using Landsat and Sentinel-1 imagery. With this data, we perform a correlative analysis between area changes, centerline length changes, discharge, thickness, bed topography, and temperature, among others. Trends on the local and regional scales are examined for insights in conjunction with existing studies in the field. Ultimately, the current implementation offers a new opportunity to explore trends on the extent of Greenland's margins, and supplies new constraints for simulations of the evolution of the mass balance of the Greenland Ice Sheet and its contributions to future sea level rise. We welcome any critiques, suggestions, or questions regarding the dataset and/or our methods. This work was conducted as a collaboration between NASA’s Jet Propulsion Laboratory and the University of California, Irvine.
- 4 March 2021
- Published by Copernicus GmbH
Open AccessDense Glacial Termini Time Series Analysis: Insights from Calving Front Machine (CALFIN)
Sea level contributions from the Greenland Ice Sheet are influenced by the rapid changes in glacial terminus positions. While manual delineation is labor intensive, recent developments in the field of automated calving front extraction have allowed for high spatio-temporal resolution analysis of Greenlandic glaciers. Specifically, we analyze new developments and results from the Calving Front Machine (CALFIN). CALFIN uses machine learning in the form of deep neural networks to automatically generate 25,000+ calving front positions from 1972 to 2020 across 80+ Greenlandic basins, using Landsat and Sentinel-1 imagery. With this data, we perform a correlative analysis between area changes, centerline length changes, discharge, thickness, bed topography, and temperature, among others. Trends on the local and regional scales are examined for insights in conjunction with existing studies in the field. Ultimately, the current implementation offers a new opportunity to explore trends on the extent of Greenland's margins, and supplies new constraints for simulations of the evolution of the mass balance of the Greenland Ice Sheet and its contributions to future sea level rise. We welcome any critiques, suggestions, or questions regarding the dataset and/or our methods. This work was conducted as a collaboration between NASA’s Jet Propulsion Laboratory and the University of California, Irvine.
- Open Access
- 14 October 2020
- Published by Copernicus GmbH in EGUsphere
- Vol. 2020, 1-17
Calving Front Machine (CALFIN): Glacial Termini Dataset and Automated Deep Learning Extraction Method for Greenland, 1972–2019
We present Calving Front Machine (CALFIN), an automated method for extracting calving fronts from satellite images of marine-terminating glaciers. The results use Landsat imagery from 1972 to 2019 to generate 22 678 calving front lines across 66 Greenlandic glaciers. The method uses deep learning, and builds on existing work by Mohajerani et al., Zhang et al., and Baumhoer et al. Additional post-processing techniques allow for accurate segmentation of imagery into Shapefile outputs. This method is uniquely robust to the impact of clouds, illumination differences, ice mélange, and Landsat-7 Scan Line Corrector errors. CALFIN provides improvements on the current state of the art. A model inter-comparison is performed to evaluate performance against existing methodologies. CALFIN's ability to generalize to SAR imagery is also evaluated. CALFIN's fronts are often indistinguishable from manually-curated fronts, deviating by 2.25 pixels (86.76 meters) from the true front on a diverse set of 162 testing images. The current implementation offers a new opportunity to explore sub-seasonal trends on the extent of Greenland's margins, and supplies new constraints for simulations of the evolution of the mass balance of the Greenland Ice Sheet and its contributions to future sea level rise.
- 14 October 2020
- Published by Copernicus GmbH in EGUsphere
- Vol. 2020, 1-17
Open AccessCalving Front Machine (CALFIN): Glacial Termini Dataset and Automated Deep Learning Extraction Method for Greenland, 1972–2019
We present Calving Front Machine (CALFIN), an automated method for extracting calving fronts from satellite images of marine-terminating glaciers. The results use Landsat imagery from 1972 to 2019 to generate 22 678 calving front lines across 66 Greenlandic glaciers. The method uses deep learning, and builds on existing work by Mohajerani et al., Zhang et al., and Baumhoer et al. Additional post-processing techniques allow for accurate segmentation of imagery into Shapefile outputs. This method is uniquely robust to the impact of clouds, illumination differences, ice mélange, and Landsat-7 Scan Line Corrector errors. CALFIN provides improvements on the current state of the art. A model inter-comparison is performed to evaluate performance against existing methodologies. CALFIN's ability to generalize to SAR imagery is also evaluated. CALFIN's fronts are often indistinguishable from manually-curated fronts, deviating by 2.25 pixels (86.76 meters) from the true front on a diverse set of 162 testing images. The current implementation offers a new opportunity to explore sub-seasonal trends on the extent of Greenland's margins, and supplies new constraints for simulations of the evolution of the mass balance of the Greenland Ice Sheet and its contributions to future sea level rise.
- Open Access
- 23 March 2020
- Published by Copernicus GmbH
Calving Front Machine (CALFIN): Automated Calving Front Dataset and Deep Learning Methodology for East/West Greenland, 1972-2019
We present Calving Front Machine (CALFIN), an automated method for extracting calving fronts from satellite imagery. We generate results for 66 glaciers along East/West Greenland from 1972 to 2019. We output these results as a dataset, and provide new constraints on glacial evolution over the time period. This method is uniquely robust to clouds, illumination differences, ice mélange, and Landsat-7 Scan Line Corrector errors. The current implementation offers a new opportunity to explore previous trends, and validate existing models moving forward.This method utilizes deep learning, in the form of the Google DeeplabV3+ Xception derived CALFIN Neural Network. This approach builds on existing work by Mohajerani et al., Zhang et al., and Baumhoer et al. Additional post-processing techniques allow our method to achieve accurate and useful segmentation of raw images into Shapefile outputs. We achieve are often indistinguishable from the manually-curated fronts, deviating from such test data by 1 pixel (about 80 meters) or less XXX% of the time across 162 test images.CALFIN excels among the current state of the art. We show this by performing a model inter-comparison to evaluate CALFIN's performance against existing methodologies. We also showcase CALFIN's ability to generalize to SAR and MODIS imagery. We achieve a mean error of 2.25 pixels (86.76 meters) from the true front on a diverse set of 162 testing images.
- 23 March 2020
- Published by Copernicus GmbH
Open AccessCalving Front Machine (CALFIN): Automated Calving Front Dataset and Deep Learning Methodology for East/West Greenland, 1972-2019
We present Calving Front Machine (CALFIN), an automated method for extracting calving fronts from satellite imagery. We generate results for 66 glaciers along East/West Greenland from 1972 to 2019. We output these results as a dataset, and provide new constraints on glacial evolution over the time period. This method is uniquely robust to clouds, illumination differences, ice mélange, and Landsat-7 Scan Line Corrector errors. The current implementation offers a new opportunity to explore previous trends, and validate existing models moving forward.This method utilizes deep learning, in the form of the Google DeeplabV3+ Xception derived CALFIN Neural Network. This approach builds on existing work by Mohajerani et al., Zhang et al., and Baumhoer et al. Additional post-processing techniques allow our method to achieve accurate and useful segmentation of raw images into Shapefile outputs. We achieve are often indistinguishable from the manually-curated fronts, deviating from such test data by 1 pixel (about 80 meters) or less XXX% of the time across 162 test images.CALFIN excels among the current state of the art. We show this by performing a model inter-comparison to evaluate CALFIN's performance against existing methodologies. We also showcase CALFIN's ability to generalize to SAR and MODIS imagery. We achieve a mean error of 2.25 pixels (86.76 meters) from the true front on a diverse set of 162 testing images.