Layered Soil Remote Sensing with Multi-Channel Passive Microwave
Observations and Physics Driven Artificial Intelligence: A Theoretical
Study
Abstract
The vertical distribution of soil properties is crucial in accurately
representing various environmental processes such as freeze-thaw cycles
and diurnal variations. In this paper, considering the complexity of the
multi-parameter features of layered soil, we evaluate the potential to
retrieve the vertical distribution of the moisture and temperature of
soil using multi-channel passive microwave observations. To enhance the
inversion rate and accuracy, a novel Physics-Driven Artificial Neural
Network (P-ANN) inversion algorithm combining multi-angle (30 to 50
degree), multi-frequency (L-, C-, and X-band), and multi-polarization
(horizontal and vertical polarization) passive observations is proposed.
In this approach, the multi-channel physical brightness temperature
simulations corresponding to the predicted soil state parameters are
integrated into the loss function of a standard fully connected neural
network, enabling efficient convergence with limited sampling data in
the training process. Testing results exhibit that the inversion
performance of P-ANN is superior than that of conventional neural
network approaches which only adopts errors in soil states in the loss
function to train the network. Test also shows the proposed P-ANN
approach outperforms traditional optimization algorithms in dealing with
layered soil retrieval. In order to further improve the retrieval
accuracy, an advanced local optimization scheme is also proposed, where
the output from P-ANN is further treated as the initial value to a local
optimization algorithm, achieving even closer results to the true values
without excessive computational resources. In addition, to estimate the
reliability of the model predictions, this paper also establishes a
statistical relationship between the soil inversion error and the error
of corresponding brightness temperatures from the testing process.
When the trained neural network is in operation, the error of brightness
temperature is calculated through the physical model, and the
reliability of retrieval soil results is then acquired by putting the
calculated brightness temperature errors into the pre-established
statistical relationship. The proposed concepts and approaches have
demonstrated the feasibility of using P-ANN model with multidimensional
observations to invert the layered soil structure. The proposed approach
holds great potentials for various remote sensing applications as well
as a wide range of inverse problem challenges.