1. Towards constraining soil and vegetation dynamics in land surface models: Modeling ASCAT backscatter incidence-angle dependence with a Deep Neural Network.
- Author
-
Shan, Xu, Steele-Dunne, Susan, Huber, Manuel, Hahn, Sebastian, Wagner, Wolfgang, Bonan, Bertrand, Albergel, Clement, Calvet, Jean-Christophe, Ku, Ou, and Georgievska, Sonja
- Subjects
- *
ARTIFICIAL neural networks , *VEGETATION dynamics , *SURFACE dynamics , *BACKSCATTERING , *SOIL moisture , *SOIL dynamics , *LAND cover - Abstract
A Deep Neural Network (DNN) is used to estimate the Advanced Scatterometer (ASCAT) C-band microwave normalized backscatter (σ 40 o ), 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 σ 40 o , 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 σ 40 o and σ ′. The domain-averaged values of ρ are 0.84 and 0.85 for σ 40 o and σ ′, compared to 0.58 for σ ″. The domain-averaged unbiased RMSE is 8.6% of the dynamic range for σ 40 o 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 σ 40 o 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 was trained to predict ASCAT backscatter, slope and curvature. • Input variables describing the soil and vegetation were obtained from the ISBA LSM. • Excellent agreement was achieved between observed and predicted ASCAT observables. • Sensitivity of ASCAT observables to inputs is consistent with microwave theory. • The DNN can be used as a measurement operator to assimilate ASCAT data into ISBA. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF