MH
M. Huber
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Towards constraining soil and vegetation dynamics in land surface models
Modeling ASCAT backscatter incidence-angle dependence with a Deep Neural Network
Journal article
(2022)
-
Xu Shan, Susan Steele-Dunne, Manuel Huber, Sebastian Hahn, Wolfgang Wagner, Bertrand Bonan, Clement Albergel, Jean-Christophe Calvet, Ou Ku, Sonja Georgievska
A Deep Neural Network (DNN) is used to estimate the Advanced Scatterometer (ASCAT) C-band microwave normalized backscatter (σ40o), slope (σ′) and curvature (σ″) over France. The Interactions between Soil, Biosphere and Atmosphere (ISBA) land surface model (LSM) is used to produce land surface variables (LSVs) that are input to the DNN. The DNN is trained to simulate σ40o, σ′ and σ″ from 2007 to 2016. The predictive skill of the DNN is evaluated during an independent validation period from 2017 to 2019. Normalized sensitivity coefficients (NSCs) are computed to study the sensitivity of ASCAT observables to changes in LSVs as a function of time and space. Model performance yields a near-zeros bias in σ40o and σ′. The domain-averaged values of ρ are 0.84 and 0.85 for σ40o and σ′, compared to 0.58 for σ″. The domain-averaged unbiased RMSE is 8.6% of the dynamic range for σ40o and 13% for σ′, with land cover having some impact on model performance. NSC results show that the DNN-based model could reproduce the physical response of ASCAT observables to changes in LSVs. Results indicated that σ40o is sensitive to surface soil moisture and LAI and that these sensitivities vary with time, and are highly dependent on land cover type. The σ′ was shown to be sensitive to LAI, but also to root zone soil moisture due to the dependence of vegetation water content on soil moisture. The DNN could potentially serve as an observation operator in data assimilation to constrain soil and vegetation water dynamics in LSMs.
...
A Deep Neural Network (DNN) is used to estimate the Advanced Scatterometer (ASCAT) C-band microwave normalized backscatter (σ40o), slope (σ′) and curvature (σ″) over France. The Interactions between Soil, Biosphere and Atmosphere (ISBA) land surface model (LSM) is used to produce land surface variables (LSVs) that are input to the DNN. The DNN is trained to simulate σ40o, σ′ and σ″ from 2007 to 2016. The predictive skill of the DNN is evaluated during an independent validation period from 2017 to 2019. Normalized sensitivity coefficients (NSCs) are computed to study the sensitivity of ASCAT observables to changes in LSVs as a function of time and space. Model performance yields a near-zeros bias in σ40o and σ′. The domain-averaged values of ρ are 0.84 and 0.85 for σ40o and σ′, compared to 0.58 for σ″. The domain-averaged unbiased RMSE is 8.6% of the dynamic range for σ40o and 13% for σ′, with land cover having some impact on model performance. NSC results show that the DNN-based model could reproduce the physical response of ASCAT observables to changes in LSVs. Results indicated that σ40o is sensitive to surface soil moisture and LAI and that these sensitivities vary with time, and are highly dependent on land cover type. The σ′ was shown to be sensitive to LAI, but also to root zone soil moisture due to the dependence of vegetation water content on soil moisture. The DNN could potentially serve as an observation operator in data assimilation to constrain soil and vegetation water dynamics in LSMs.
Agricultural SandboxNL
A Crop Parcel Level Database Using Sentinel-1 SAR and Google Earth Engine
Conference paper
(2021)
-
Vineet Kumar, Manuel Huber, Maurice Shorachi, Bjorn Rommen, Susan C. Steele-Dunne
The systematic high temporal coverage of Sentinel-1 Synthetic Aperture Radar (SAR) is ideal for agricultural monitoring. The availability of these data on cloud computing infrastructure eliminates the need for massive computing power to process imagery. However, their distribution as SAR imagery still limits their accessibility for non-expert users. In Agricultural SandboxNL, Copernicus Sentinel-1 imagery on the Google Earth Engine (GEE) was mined to produce a database of spatially-tagged, parcel-level backscatter for every agricultural parcel in the Netherlands from 2017 to 2019. The database includes descriptors from the publicly available Basisregistratie Gewaspercelen, allowing the user to query the database by crop type and administrative boundary for any region of interest within The Netherlands. Publication of this database reduces the burden of processing and extracting a large volume of Sentinel-1 SAR data for experts. More importantly, it provides easy access to the Sentinel-1 data for agriculture/agronomy experts with limited SAR processing experience. In addition, the GEE package Sen1byParcel developed for Agricultural SandboxNL is made publicly available so that Sentinel-1 imagery can be extracted for any user-provided shapefile.
...
The systematic high temporal coverage of Sentinel-1 Synthetic Aperture Radar (SAR) is ideal for agricultural monitoring. The availability of these data on cloud computing infrastructure eliminates the need for massive computing power to process imagery. However, their distribution as SAR imagery still limits their accessibility for non-expert users. In Agricultural SandboxNL, Copernicus Sentinel-1 imagery on the Google Earth Engine (GEE) was mined to produce a database of spatially-tagged, parcel-level backscatter for every agricultural parcel in the Netherlands from 2017 to 2019. The database includes descriptors from the publicly available Basisregistratie Gewaspercelen, allowing the user to query the database by crop type and administrative boundary for any region of interest within The Netherlands. Publication of this database reduces the burden of processing and extracting a large volume of Sentinel-1 SAR data for experts. More importantly, it provides easy access to the Sentinel-1 data for agriculture/agronomy experts with limited SAR processing experience. In addition, the GEE package Sen1byParcel developed for Agricultural SandboxNL is made publicly available so that Sentinel-1 imagery can be extracted for any user-provided shapefile.