Abstract
Soil moisture is one of the critical variables in maintaining the global water cycle balance. Moreover, it plays a vital role in climate change, crop growth, and environmental disaster event monitoring, and it is important to monitor soil moisture continuously. Recently, Global Navigation Satellite System interferometric reflectometry (GNSS-IR) technology has become essential for monitoring soil moisture. However, the sparse distribution of GNSS-IR soil moisture sites has hindered the application of soil moisture products. In this paper, we propose a multi-data fusion soil moisture inversion algorithm based on machine learning. The method uses the Genetic Algorithm Back-Propagation (GA-BP) neural network model, by combining GNSS-IR site data with other surface environmental parameters around the site. In turn, soil moisture is obtained by inversion, and we finally obtain a soil moisture product with a high spatial and temporal resolution of 500 m per day. The multi-surface environmental data include latitude and longitude information, rainfall, air temperature, land cover type, normalized difference vegetation index (NDVI), and four topographic factors (elevation, slope, slope direction, and shading). To maximize the spatial and temporal resolution of the GNSS-IR technique within a machine learning framework, we obtained satisfactory results with a cross-validated R-value of 0.8660 and an ubRMSE of 0.0354. This indicates that the machine learning approach learns the complex nonlinear relationships between soil moisture and the input multi-surface environmental data. The soil moisture products were analyzed compared to the contemporaneous rainfall and National Aeronautics and Space Administration (NASA)’s soil moisture products. The results show that the spatial distribution of the GA-BP inversion soil moisture products is more consistent with rainfall and NASA products, which verifies the feasibility of using this experimental model to generate 500 m per day the GA-BP inversion soil moisture products.
Highlights
We propose a multi-data fusion learning method based on machine learning by combining ground-based Global Navigation Satellite System interferometric reflectometry (GNSS-IR) technology soil moisture data and surface environmental data
Input the mapped input data set into the Genetic Algorithm BackPropagation (GA-BP) neural network model that reaches the threshold and obtain the genetic algorithm (GA)-BP inversion soil moisture data set for mapping through the training output
Tofor verify the validity of each model, we quantitatively evaluated the training and test sets using the Pearson correlation coefficient R, root mean square error (RMSE), unbiased root mean square error, and mean bias
Summary
36 km radiometer based on the SMAP task, generating an optimal 10 km soil moisture product with better performance than the reflectance radiometer alon0065 [10] On this basis, Piles combined the accuracy of SMOS observations with the high spatial resolution of visible/infrared satellite data, effectively capturing soil moisture variability at spatial scales of 10 and 1 km without a significant reduction in root mean square error [11]. Cui et al combined soil moisture data from the Fengyun-3B satellite with surface temperature, normalized difference vegetation index, albedo, digital elevation model based on generalized regression neural networks, longitude, and latitude; they improved the spatial and temporal resolution of the Fengyun-3B satellite from 0.25◦.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
