Towards constraining soil and vegetation dynamics in land surface models: Modeling ASCAT backscatter incidence-angle dependence with a Deep Neural Network

A Deep Neural Network (DNN) is used to estimate the Advanced Scatterometer (ASCAT) C-band microwave normalized backscatter (ao40), slope (a ') and curvature (a '') 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 ao40, a ' and a '' 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 ao40 and a '. The domain-averaged values of rho are 0.84 and 0.85 for ao40 and a ', compared to 0.58 for a ''. The domain-averaged unbiased RMSE is 8.6% of the dynamic range for a40 o and 13% for a ', 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 ao40 is sensitive to surface soil moisture and LAI and that these sensitivities vary with time, and are highly dependent on land cover type. The a ' 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.

Automated summary

In this study, a deep neural network model was used to estimate the parameters of ASCAT C-band microwave scattering, and the model was trained and validated in France. The sensitivity of ASCAT observables to land surface variables was also investigated. The results showed that the DNN model performed well in predicting and reproducing the scattering characteristics of ASCAT, and indicated that soil moisture, vegetation index, and land cover type had significant impacts on ASCAT observations.