Yueli Chen
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
Yueli Chen has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Lingxiao Wang
School of Geographical Sciences, Nanjing University of Information Science & Technology (NUIST), Nanjing 210044, China
4 shared publications Ralf Ludwig
4 shared publications- Monique Bernier
INRS-Institut National de la Recherche Scientifique (INRS), Québec, QC G1K 9A9, Canada
3 shared publications - Andrea Reimuth
Ludwig-Maximilians-Universität München
2 shared publications - Xiao Xiang Zhu
Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany
2 shared publications - Chong Wang
School of Geographical Sciences, Nanjing University of Information Science & Technology, Nanjing 210044, China
1 shared publication
Latest Publications
- Open Access
- 14 March 2026
- Published by Copernicus GmbH
Mapping Global 3D Building Density with the Global Building Atlas: Implications for Environmental Risk Hotspots
Environmental risk assessments require spatially explicit information on how people and assets are concentrated within the built environment. However, exposure metrics based solely on 2D building footprints or population grids fail to capture the vertical dimension that strongly influences heat exposure, air‑pollution accumulation, flood impacts, and infrastructure vulnerability. Leveraging the newly released Global Building Atlas (GBA)—a harmonized and globally consistent dataset of building footprints and height estimates, and currently the most comprehensive source of building information available—we introduce a global Building Density Index (BDI) that integrates key building parameters, including footprint area, building volume, height and distances, to quantify built‑up intensity as an indicator of environmental risk hotspots. The consistent global coverage of the GBA enables direct comparison of vertical density patterns across regions.The BDI reveals pronounced regional contrasts in built‑volume concentration and illustrates how cities balance horizontal expansion, vertical growth, and the availability of land for settlement. Land-scarce regions, particularly in East and Southeast Asia, exhibit strong vertical densification, resulting in extremely high built volume concentrations even where horizontal extent is limited. In contrast, many rapidly expanding cities in Africa and South Asia primarily rely on horizontal expansion, consuming large areas of developable land while maintaining low vertical density. Latin American cities typically achieve high density through compact mid-rise forms, reflecting a distinct interplay between limited land availability and moderate vertical growth.The BDI substantially improves the identification of zones where heat exposure, air‑pollution susceptibility, and built-up intensity combine to elevate environmental risks. By capturing the three-dimensional structure of the built environment, it offers a more realistic representation of how urban morphology amplifies or moderates these risks. As a globally consistent measure, the BDI provides a robust foundation for examining how land availability, horizontal expansion, and vertical growth interact to shape environmental vulnerability across diverse urban regions.
- 14 March 2026
- Published by Copernicus GmbH
Open AccessMapping Global 3D Building Density with the Global Building Atlas: Implications for Environmental Risk Hotspots
Environmental risk assessments require spatially explicit information on how people and assets are concentrated within the built environment. However, exposure metrics based solely on 2D building footprints or population grids fail to capture the vertical dimension that strongly influences heat exposure, air‑pollution accumulation, flood impacts, and infrastructure vulnerability. Leveraging the newly released Global Building Atlas (GBA)—a harmonized and globally consistent dataset of building footprints and height estimates, and currently the most comprehensive source of building information available—we introduce a global Building Density Index (BDI) that integrates key building parameters, including footprint area, building volume, height and distances, to quantify built‑up intensity as an indicator of environmental risk hotspots. The consistent global coverage of the GBA enables direct comparison of vertical density patterns across regions.The BDI reveals pronounced regional contrasts in built‑volume concentration and illustrates how cities balance horizontal expansion, vertical growth, and the availability of land for settlement. Land-scarce regions, particularly in East and Southeast Asia, exhibit strong vertical densification, resulting in extremely high built volume concentrations even where horizontal extent is limited. In contrast, many rapidly expanding cities in Africa and South Asia primarily rely on horizontal expansion, consuming large areas of developable land while maintaining low vertical density. Latin American cities typically achieve high density through compact mid-rise forms, reflecting a distinct interplay between limited land availability and moderate vertical growth.The BDI substantially improves the identification of zones where heat exposure, air‑pollution susceptibility, and built-up intensity combine to elevate environmental risks. By capturing the three-dimensional structure of the built environment, it offers a more realistic representation of how urban morphology amplifies or moderates these risks. As a globally consistent measure, the BDI provides a robust foundation for examining how land availability, horizontal expansion, and vertical growth interact to shape environmental vulnerability across diverse urban regions.
- Open Access
- 14 March 2026
- Published by Copernicus GmbH
Towards a global assessment of rooftop rainwater harvesting for hydro-meteorological hazard mitigation
Urban areas worldwide are increasingly exposed to hydro-meteorological extremes, including intense rainfall events and prolonged dry periods, which exacerbate flood hazards and water scarcity. Rooftop rainwater harvesting is widely discussed as a decentralised adaptation option that may contribute both to urban water supply and to the mitigation of hydrological extremes. However, existing assessments are largely limited to local case studies, and a consistent global-scale framework that links rooftop harvesting potential to hydro-meteorological hazard characteristics is still missing.In this contribution, we present a global assessment framework to quantify the potential of rooftop rainwater harvesting using high-resolution building footprint data in combination with reanalysis-based precipitation datasets. The approach integrates detailed global building roof areas (LoD1) with ERA5-Land precipitation data for the period 2014–2024. Mean monthly precipitation climatologies are used to estimate long-term average harvestable water volumes, while daily precipitation data are considered to characterise precipitation intensity, seasonality, and temporal continuity relevant for flood and drought mitigation. Capture efficiency is applied to account for system-level losses.By explicitly combining multiple precipitation timescales, the proposed framework enables a differentiated interpretation of rooftop rainwater harvesting potential under varying hydro-climatic regimes. While monthly precipitation provides a basis for estimating average water supply contributions, daily-scale metrics enable the assessment of conditions under which rooftop harvesting may be relevant for mitigating flood peaks or buffering dry spells. The study aims to provide a globally consistent, spatially explicit basis for evaluating rooftop rainwater harvesting as a complementary measure for increasing urban resilience to hydro-meteorological hazards.
- 14 March 2026
- Published by Copernicus GmbH
Open AccessTowards a global assessment of rooftop rainwater harvesting for hydro-meteorological hazard mitigation
Urban areas worldwide are increasingly exposed to hydro-meteorological extremes, including intense rainfall events and prolonged dry periods, which exacerbate flood hazards and water scarcity. Rooftop rainwater harvesting is widely discussed as a decentralised adaptation option that may contribute both to urban water supply and to the mitigation of hydrological extremes. However, existing assessments are largely limited to local case studies, and a consistent global-scale framework that links rooftop harvesting potential to hydro-meteorological hazard characteristics is still missing.In this contribution, we present a global assessment framework to quantify the potential of rooftop rainwater harvesting using high-resolution building footprint data in combination with reanalysis-based precipitation datasets. The approach integrates detailed global building roof areas (LoD1) with ERA5-Land precipitation data for the period 2014–2024. Mean monthly precipitation climatologies are used to estimate long-term average harvestable water volumes, while daily precipitation data are considered to characterise precipitation intensity, seasonality, and temporal continuity relevant for flood and drought mitigation. Capture efficiency is applied to account for system-level losses.By explicitly combining multiple precipitation timescales, the proposed framework enables a differentiated interpretation of rooftop rainwater harvesting potential under varying hydro-climatic regimes. While monthly precipitation provides a basis for estimating average water supply contributions, daily-scale metrics enable the assessment of conditions under which rooftop harvesting may be relevant for mitigating flood peaks or buffering dry spells. The study aims to provide a globally consistent, spatially explicit basis for evaluating rooftop rainwater harvesting as a complementary measure for increasing urban resilience to hydro-meteorological hazards.
- Open Access
- 14 March 2026
- Published by Copernicus GmbH
A hybrid physical–deep learning approach for high-resolution detection of marine heatwaves
Marine heatwaves (MHWs) have intensified globally in recent years, driving widespread coral bleaching, ecosystem degradation, and escalating economic losses. In some coastal regions, coral bleaching rates have exceeded 80%, while fisheries-related damages have been estimated at over USD 3.1 billion annually. Despite these impacts, the characteristics and underlying mechanisms of nearshore MHWs remain poorly constrained, largely due to the lack of high-resolution sea surface temperature (SST) observations. Thermal infrared satellite products are subject to persistent data gaps caused by cloud cover, particularly in coastal environments where strong land–sea interactions, multiscale physical processes, and pronounced spatial heterogeneity limit conventional MHW detection.A physics-informed deep-learning framework is developed to reconstruct all-weather, high-resolution SST fields for nearshore regions. By integrating physical constraints with multi-source geophysical predictors, the approach generates a 2 km-resolution SST dataset with high accuracy, achieving a root-mean-square error of 0.30 °C, a mean bias of 0.01 °C, and a coefficient of determination (R²) of 0.99 against independent reference observations. The reconstructed SST fields enable robust identification of nearshore MHWs and resolve fine-scale thermal structures that are not captured by existing coarse-resolution datasets.Based on the reconstructed SST product, the spatiotemporal evolution of nearshore MHWs is systematically characterized, and associated physical and ecological implications are examined. Case studies in the South China Sea and the Mediterranean Sea reveal multiple unprecedented extreme events in recent years, including record-breaking MHWs in the Mediterranean during the past three years in terms of both intensity and spatial extent. High-resolution analyses further reveal an enhanced spatial correspondence between MHWs and coral reef distributions, indicating intensified thermal stress in ecologically vulnerable coastal zones. Accurate, all-weather, high-resolution SST reconstruction therefore provides a critical basis for advancing nearshore MHW detection and improving assessments of emerging coastal climate risks.
- 14 March 2026
- Published by Copernicus GmbH
Open AccessA hybrid physical–deep learning approach for high-resolution detection of marine heatwaves
Marine heatwaves (MHWs) have intensified globally in recent years, driving widespread coral bleaching, ecosystem degradation, and escalating economic losses. In some coastal regions, coral bleaching rates have exceeded 80%, while fisheries-related damages have been estimated at over USD 3.1 billion annually. Despite these impacts, the characteristics and underlying mechanisms of nearshore MHWs remain poorly constrained, largely due to the lack of high-resolution sea surface temperature (SST) observations. Thermal infrared satellite products are subject to persistent data gaps caused by cloud cover, particularly in coastal environments where strong land–sea interactions, multiscale physical processes, and pronounced spatial heterogeneity limit conventional MHW detection.A physics-informed deep-learning framework is developed to reconstruct all-weather, high-resolution SST fields for nearshore regions. By integrating physical constraints with multi-source geophysical predictors, the approach generates a 2 km-resolution SST dataset with high accuracy, achieving a root-mean-square error of 0.30 °C, a mean bias of 0.01 °C, and a coefficient of determination (R²) of 0.99 against independent reference observations. The reconstructed SST fields enable robust identification of nearshore MHWs and resolve fine-scale thermal structures that are not captured by existing coarse-resolution datasets.Based on the reconstructed SST product, the spatiotemporal evolution of nearshore MHWs is systematically characterized, and associated physical and ecological implications are examined. Case studies in the South China Sea and the Mediterranean Sea reveal multiple unprecedented extreme events in recent years, including record-breaking MHWs in the Mediterranean during the past three years in terms of both intensity and spatial extent. High-resolution analyses further reveal an enhanced spatial correspondence between MHWs and coral reef distributions, indicating intensified thermal stress in ecologically vulnerable coastal zones. Accurate, all-weather, high-resolution SST reconstruction therefore provides a critical basis for advancing nearshore MHW detection and improving assessments of emerging coastal climate risks.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-12
Reconstruction of Thermal Infrared Sea Surface Temperature Using a Diffusion Model
Sea surface temperature (SST) is a vital parameter in oceanography and climate science, influencing various fields. While remote sensing provides daily SST data, thermal infrared (TIR)-based sensors offer higher spatial resolution but struggle with cloud penetration, often resulting in data gaps and inaccuracies. This study proposes an SST reconstruction framework based on a diffusion model that integrates spatiotemporal information using Himawari TIR and OSTIA SST data, yielding a fully covered SST dataset with a spatial resolution of 0.02°. The model demonstrates good performance in reconstructing SST in the South China Sea (SCS), achieving a coefficient of determination (R²) of 0.92, a bias of 0.06 °C, an root mean square error (RMSE) of 0.39 °C, and a peak signal-to-noise ratio (PSNR) of 57.93. Furthermore, the transferability of the model is confirmed through accurate SST predictions in the Indian Ocean after training on SCS data, indicating its applicability across different regions with limited Himawari data and its potential for broader geographical applications. Compared to the original Himawari data, the reconstructed SST reduces the RMSE from 1.01 °C to 0.29 °C, increases the R² from 0.71 to 0.86, and adjusts the bias from –0.54 °C to 0.02 °C, thereby enhancing accuracy. By integrating temporal information, the proposed approach captures both spatial and temporal characteristics of SST, effectively representing seasonal variations, small-scale pulsations, rapid coastal changes, and stable offshore fluctuations. This study lays the groundwork for applying the proposed framework to other regions, highlighting its potential for broader applications in generating high-resolution, all-weather SST data.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-12
Reconstruction of Thermal Infrared Sea Surface Temperature Using a Diffusion Model
Sea surface temperature (SST) is a vital parameter in oceanography and climate science, influencing various fields. While remote sensing provides daily SST data, thermal infrared (TIR)-based sensors offer higher spatial resolution but struggle with cloud penetration, often resulting in data gaps and inaccuracies. This study proposes an SST reconstruction framework based on a diffusion model that integrates spatiotemporal information using Himawari TIR and OSTIA SST data, yielding a fully covered SST dataset with a spatial resolution of 0.02°. The model demonstrates good performance in reconstructing SST in the South China Sea (SCS), achieving a coefficient of determination (R²) of 0.92, a bias of 0.06 °C, an root mean square error (RMSE) of 0.39 °C, and a peak signal-to-noise ratio (PSNR) of 57.93. Furthermore, the transferability of the model is confirmed through accurate SST predictions in the Indian Ocean after training on SCS data, indicating its applicability across different regions with limited Himawari data and its potential for broader geographical applications. Compared to the original Himawari data, the reconstructed SST reduces the RMSE from 1.01 °C to 0.29 °C, increases the R² from 0.71 to 0.86, and adjusts the bias from –0.54 °C to 0.02 °C, thereby enhancing accuracy. By integrating temporal information, the proposed approach captures both spatial and temporal characteristics of SST, effectively representing seasonal variations, small-scale pulsations, rapid coastal changes, and stable offshore fluctuations. This study lays the groundwork for applying the proposed framework to other regions, highlighting its potential for broader applications in generating high-resolution, all-weather SST data.
- Open Access
- 30 December 2023
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 126
Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes
- 30 December 2023
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 126
Open AccessRetrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes
- Open Access
- 15 May 2023
- Published by Copernicus GmbH
Exploring the merging potential of high temporal resolution and high spatial resolution microwave remote sensing data
Microwave remote sensing can provide effective monitoring of landscape FT dynamics. Its sensitivity to surface permittivity, which is predominantly influenced by the phases of water, can be used to measure landscape freeze/thaw state information. The technique of Interferometric Synthetic Aperture Radar (InSAR) enables to map the ground movement through the use of Synthetic Aperture Radar (SAR). Compared to optical imagery, microwave data has advantages that it would not be affected by cloud cover, smoke or daylight and exhibits useful penetration depths of soil and vegetation. Both active and passive microwave remote sensing with different wavelengths have shown their principal capacity in many studies and have complementary advantages to each other. While many passive sensors (such as SMAP and SMOS) are providing observations with high temporal resolution and good worldwide coverage at the deca-kilometer scale, there are a series of active sensors providing observations with worse temporal resolution but much better spatial resolution at the scale from a few meters to a few deca-meters, for example, the Sentinel-1 mission from the European Space Agency (ESA) with 5 x 5 m spatial resolution and 6-12 days repeat cycle. Hence, the combined use of different microwave data can be expected further to promote the monitoring of permafrost-related phenomena and permafrost-dominated landscapes.An assumption of near-linear relation between the measurements from the passive and active sensors has been used in NASA’s Soil Moisture Active Passive (SMAP) active-passive baseline algorithm for downscaling coarse-resolution radiometer brightness temperature (TB) using high-resolution radar backscatter (σ 0). Recent research proved that a good linear relationship could be found at a global scale (Zeng et al., 2021). However, the relation is significantly affected by environmental factors, for example, the density of vegetation cover. Based on the findings, we attempt to explore the possibility of merging microwave remote-sensing data from different platforms in this work. We are committed to exploring suitable data sources for merging, as well as the possibility of taking environmental factors into consideration. The capacity and limitation of the merging process will be discussed.
- 15 May 2023
- Published by Copernicus GmbH
Open AccessExploring the merging potential of high temporal resolution and high spatial resolution microwave remote sensing data
Microwave remote sensing can provide effective monitoring of landscape FT dynamics. Its sensitivity to surface permittivity, which is predominantly influenced by the phases of water, can be used to measure landscape freeze/thaw state information. The technique of Interferometric Synthetic Aperture Radar (InSAR) enables to map the ground movement through the use of Synthetic Aperture Radar (SAR). Compared to optical imagery, microwave data has advantages that it would not be affected by cloud cover, smoke or daylight and exhibits useful penetration depths of soil and vegetation. Both active and passive microwave remote sensing with different wavelengths have shown their principal capacity in many studies and have complementary advantages to each other. While many passive sensors (such as SMAP and SMOS) are providing observations with high temporal resolution and good worldwide coverage at the deca-kilometer scale, there are a series of active sensors providing observations with worse temporal resolution but much better spatial resolution at the scale from a few meters to a few deca-meters, for example, the Sentinel-1 mission from the European Space Agency (ESA) with 5 x 5 m spatial resolution and 6-12 days repeat cycle. Hence, the combined use of different microwave data can be expected further to promote the monitoring of permafrost-related phenomena and permafrost-dominated landscapes.An assumption of near-linear relation between the measurements from the passive and active sensors has been used in NASA’s Soil Moisture Active Passive (SMAP) active-passive baseline algorithm for downscaling coarse-resolution radiometer brightness temperature (TB) using high-resolution radar backscatter (σ 0). Recent research proved that a good linear relationship could be found at a global scale (Zeng et al., 2021). However, the relation is significantly affected by environmental factors, for example, the density of vegetation cover. Based on the findings, we attempt to explore the possibility of merging microwave remote-sensing data from different platforms in this work. We are committed to exploring suitable data sources for merging, as well as the possibility of taking environmental factors into consideration. The capacity and limitation of the merging process will be discussed.
- Open Access
- 25 November 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (23) , 5966
Retrieving Soil Moisture in the Permafrost Environment by Sentinel-1/2 Temporal Data on the Qinghai–Tibet Plateau
Soil moisture (SM) products presently available in permafrost regions, especially on the Qinghai–Tibet Plateau (QTP), hardly meet the demands of evaluating and modeling climatic, hydrological, and ecological processes, due to their significant bias and low spatial resolution. This study developed an algorithm to generate high-spatial-resolution SM during the thawing season using Sentinel-1 (S1) and Sentinel-2 (S2) temporal data in the permafrost environment. This algorithm utilizes the seasonal backscatter differences to reduce the effect of surface roughness and uses the normalized difference vegetation index (NDVI) and the normalized difference moisture index (NDMI) to characterize vegetation contribution. Then, the SM map with a grid spacing of 50 m × 50 m in the hinterland of the QTP with an area of 505 km × 246 km was generated. The results were independently validated based on in situ data from active layer monitoring sites. It shows that this algorithm can retrieve SM well in the study area. The coefficient of determination (R2) and root-mean-square error (RMSE) are 0.82 and 0.06 m3/m3, respectively. This study analyzed the SM distribution of different vegetation types: the alpine swamp meadow had the largest SM of 0.26 m3/m3, followed by the alpine meadow (0.23), alpine steppe (0.2), and alpine desert (0.16), taking the Tuotuo River basin as an example. We also found a significantly negative correlation between the coefficient of variation (CV) and SM in the permafrost area, and the variability of SM is higher in drier environments and lower in wetter environments. The comparison with ERA5-Land, GLDAS, and ESA CCI showed that the proposed method can provide more spatial details and achieve better performance in permafrost areas on QTP. The results also indicated that the developed algorithm has the potential to be applied in the entire permafrost regions on the QTP.
- 25 November 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (23) , 5966
Open AccessRetrieving Soil Moisture in the Permafrost Environment by Sentinel-1/2 Temporal Data on the Qinghai–Tibet Plateau
Soil moisture (SM) products presently available in permafrost regions, especially on the Qinghai–Tibet Plateau (QTP), hardly meet the demands of evaluating and modeling climatic, hydrological, and ecological processes, due to their significant bias and low spatial resolution. This study developed an algorithm to generate high-spatial-resolution SM during the thawing season using Sentinel-1 (S1) and Sentinel-2 (S2) temporal data in the permafrost environment. This algorithm utilizes the seasonal backscatter differences to reduce the effect of surface roughness and uses the normalized difference vegetation index (NDVI) and the normalized difference moisture index (NDMI) to characterize vegetation contribution. Then, the SM map with a grid spacing of 50 m × 50 m in the hinterland of the QTP with an area of 505 km × 246 km was generated. The results were independently validated based on in situ data from active layer monitoring sites. It shows that this algorithm can retrieve SM well in the study area. The coefficient of determination (R2) and root-mean-square error (RMSE) are 0.82 and 0.06 m3/m3, respectively. This study analyzed the SM distribution of different vegetation types: the alpine swamp meadow had the largest SM of 0.26 m3/m3, followed by the alpine meadow (0.23), alpine steppe (0.2), and alpine desert (0.16), taking the Tuotuo River basin as an example. We also found a significantly negative correlation between the coefficient of variation (CV) and SM in the permafrost area, and the variability of SM is higher in drier environments and lower in wetter environments. The comparison with ERA5-Land, GLDAS, and ESA CCI showed that the proposed method can provide more spatial details and achieve better performance in permafrost areas on QTP. The results also indicated that the developed algorithm has the potential to be applied in the entire permafrost regions on the QTP.
- Open Access
- 27 March 2022
- Published by Copernicus GmbH
Retrieving freeze/thaw-cycles using Machine Learning approach in Nunavik (Québec, Canada)
In the terrestrial cryosphere, freeze/thaw (FT) state transition plays an important and measurable role for climatic, hydrological, ecological, and biogeochemical processes in permafrost landscapes.Satellite active and passive microwave remote sensing has shown its principal capacity to provide effective monitoring of landscape FT dynamics. Many algorithms have been developed and evaluated over time in this scope. With the advancement of data science and artificial intelligence methods, the potential of better understanding the cryosphere is emerging.This work is dedicated to exploring an effective approach to retrieve FT state based on microwave remote sensing data using machine learning methods, which is expected to fill in some hidden blind spots in the deterministic algorithms. Time series of remote sensing data will be created as training data. In the initial stage, the work aims to test the feasibility and establish the basic neural network based on fewer training factors. In the advanced stage, we will improve the model in terms of structure, such as adding more complex dense layers and testing optimizers, and in terms of discipline, such as introducing more influencing factors for training. Related parameters, for example, land cover types, will be included in the analysis to improve the method and understanding of FT-related processes.
- 27 March 2022
- Published by Copernicus GmbH
Open AccessRetrieving freeze/thaw-cycles using Machine Learning approach in Nunavik (Québec, Canada)
In the terrestrial cryosphere, freeze/thaw (FT) state transition plays an important and measurable role for climatic, hydrological, ecological, and biogeochemical processes in permafrost landscapes.Satellite active and passive microwave remote sensing has shown its principal capacity to provide effective monitoring of landscape FT dynamics. Many algorithms have been developed and evaluated over time in this scope. With the advancement of data science and artificial intelligence methods, the potential of better understanding the cryosphere is emerging.This work is dedicated to exploring an effective approach to retrieve FT state based on microwave remote sensing data using machine learning methods, which is expected to fill in some hidden blind spots in the deterministic algorithms. Time series of remote sensing data will be created as training data. In the initial stage, the work aims to test the feasibility and establish the basic neural network based on fewer training factors. In the advanced stage, we will improve the model in terms of structure, such as adding more complex dense layers and testing optimizers, and in terms of discipline, such as introducing more influencing factors for training. Related parameters, for example, land cover types, will be included in the analysis to improve the method and understanding of FT-related processes.
- Open Access
- 8 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 802
Retrieving Freeze/Thaw Cycles Using Sentinel-1 Data in Eastern Nunavik (Québec, Canada)
In the terrestrial cryosphere, freeze/thaw (FT) state transitions play an important and measurable role in climatic, hydrological, ecological, and biogeochemical processes in permafrost landscapes. Active and passive microwave remote sensing has shown a principal capacity to provide effective monitoring of landscape FT dynamics. The study presents a seasonal threshold approach, which examines the timeseries progression of remote sensing measurements relative to signatures acquired during seasonal frozen and thawed reference states. This is used to estimate the FT state from the Sentinel-1 database and applied and evaluated for the region of Eastern Nunavik (Québec, Canada). An optimization process of the threshold is included. In situ measurements from the meteorological station network were used for the validation process. Overall, acceptable estimation accuracy (>70%) was achieved in most tests; on the best-performing sites, an accuracy higher than 90% was reached. The performance of the seasonal threshold approach over the study region was further discussed with consideration of land cover, spatial heterogeneity, and soil depth. This work is dedicated to providing more accurate data to capture the spatiotemporal heterogeneity of freeze/thaw transitions and to improving our understanding of related processes in permafrost landscapes.
- 8 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 802
Open AccessRetrieving Freeze/Thaw Cycles Using Sentinel-1 Data in Eastern Nunavik (Québec, Canada)
In the terrestrial cryosphere, freeze/thaw (FT) state transitions play an important and measurable role in climatic, hydrological, ecological, and biogeochemical processes in permafrost landscapes. Active and passive microwave remote sensing has shown a principal capacity to provide effective monitoring of landscape FT dynamics. The study presents a seasonal threshold approach, which examines the timeseries progression of remote sensing measurements relative to signatures acquired during seasonal frozen and thawed reference states. This is used to estimate the FT state from the Sentinel-1 database and applied and evaluated for the region of Eastern Nunavik (Québec, Canada). An optimization process of the threshold is included. In situ measurements from the meteorological station network were used for the validation process. Overall, acceptable estimation accuracy (>70%) was achieved in most tests; on the best-performing sites, an accuracy higher than 90% was reached. The performance of the seasonal threshold approach over the study region was further discussed with consideration of land cover, spatial heterogeneity, and soil depth. This work is dedicated to providing more accurate data to capture the spatiotemporal heterogeneity of freeze/thaw transitions and to improving our understanding of related processes in permafrost landscapes.
- Open Access
- 4 March 2021
- Published by Copernicus GmbH
Retrieving freeze/thaw-cycles using Sentinel 1 data in Eastern Nunavik (Québec, Canada)
In the terrestrial cryosphere, freeze/thaw (FT) state transitions play an important and measurable role for climatic, hydrological, ecological, and biogeochemical processes in permafrost landscapes. Satellite active and passive microwave remote sensing has shown its principal capacity to provide effective monitoring of landscape FT dynamics. Sentinel-1 continues to deliver high-resolution microwave remote sensing than ever before and has therefore a large potential of usage for monitoring. In light of this, the capability and responses of its radar backscatter to landscape FT processes in different surface soil depths should be examined to provide a thorough grounding for a robust application of the F/T retrieval algorithm.This study presents a seasonal threshold approach, which examines the time series progression of remote sensing measurements relative to signatures acquired during seasonal reference frozen and thawed states. It is developed to estimate the FT-state from the Sentinel 1 database and applied and evaluated for the region of Eastern Nunavik (Québec, Canada). In this course, the FT state transitions derived from Sentinel 1 data are compared to temporally overlapping situ measurements of soil moisture from different depths within the top 20cm soil. This work allows to explore differences in the sensitivity of the Sentinel 1 at different surface soil depths in higher detail; this information is used to examine the penetration performance of the Sentinel 1 under different conditions of permafrost and permafrost-dominated landscapes.This work is dedicated to providing more accurate data to capture the spatio-temporal heterogeneity of freeze/thaw transitions. As Sentinel-1 continues to deliver high-quality information, the provided threshold algorithm delivers an extended time series to analyze FT-states and improve our understanding of related processes in permafrost landscapes.
- 4 March 2021
- Published by Copernicus GmbH
Open AccessRetrieving freeze/thaw-cycles using Sentinel 1 data in Eastern Nunavik (Québec, Canada)
In the terrestrial cryosphere, freeze/thaw (FT) state transitions play an important and measurable role for climatic, hydrological, ecological, and biogeochemical processes in permafrost landscapes. Satellite active and passive microwave remote sensing has shown its principal capacity to provide effective monitoring of landscape FT dynamics. Sentinel-1 continues to deliver high-resolution microwave remote sensing than ever before and has therefore a large potential of usage for monitoring. In light of this, the capability and responses of its radar backscatter to landscape FT processes in different surface soil depths should be examined to provide a thorough grounding for a robust application of the F/T retrieval algorithm.This study presents a seasonal threshold approach, which examines the time series progression of remote sensing measurements relative to signatures acquired during seasonal reference frozen and thawed states. It is developed to estimate the FT-state from the Sentinel 1 database and applied and evaluated for the region of Eastern Nunavik (Québec, Canada). In this course, the FT state transitions derived from Sentinel 1 data are compared to temporally overlapping situ measurements of soil moisture from different depths within the top 20cm soil. This work allows to explore differences in the sensitivity of the Sentinel 1 at different surface soil depths in higher detail; this information is used to examine the penetration performance of the Sentinel 1 under different conditions of permafrost and permafrost-dominated landscapes.This work is dedicated to providing more accurate data to capture the spatio-temporal heterogeneity of freeze/thaw transitions. As Sentinel-1 continues to deliver high-quality information, the provided threshold algorithm delivers an extended time series to analyze FT-states and improve our understanding of related processes in permafrost landscapes.