The complexity of land types and the limited spatial resolution of Synthetic Aperture Radar (SAR) imagery have led to the widespread presence of mixed pixels in radar backscatter images. The signal mixture of Endmembers within mixed pixels hinders the establishment of accurate relationships between pure Endmember’s parameters and the corresponding backscatter coefficient, thereby significantly reducing the accuracy of surface parameter inversion. However, few studies focused on decomposing and estimating the pure backscatter signals within mixed pixels. This paper proposes a novel approach based on hyperspectral unmixing techniques and the microwave backscatter contribution decomposition model to estimate the pure backscatter coefficients of all Endmembers within mixed pixels. Experimental results demonstrate that the proposed method can relatively accurately estimate the backscatter coefficients of all end members of mixed pixels. For mixed pixels composed of grassland and soil in the test area, the proportion of pixels with a relative error within 20% in estimating soil and grass endmember backscattering coefficients was close to 80% of the total number of tested pixels. Furthermore, the spatial distribution of the estimated Endmember backscattering coefficients exhibited a high degree of consistency with the endmember types, structures, and conditions that influence their backscattering behavior.

The complexity of land types and the limited spatial resolution of Synthetic Aperture Radar (SAR) imagery have led to widespread mixed-pixel contamination in radar backscatter images. The radar backscatter echo signals from a mixed pixel are often a combination of backscattering contributions from multiple endmembers. The signal mixture of endmembers within mixed pixels hinders the establishment of accurate relationships between pure endmembers’ parameters and the corresponding backscatter coefficient, thereby significantly reducing the accuracy of surface parameter inversion. However, few studies have focused on decomposing and estimating the pure backscatter signals within mixed pixels. This paper proposes a novel approach based on hyperspectral unmixing techniques and the microwave backscatter contribution decomposition (MBCD) model to estimate the pure backscatter coefficients of all Endmembers within mixed pixels. Experimental results demonstrate that the model performance varied significantly with endmember abundance. Specifically, high accuracy was achieved in estimating soil backscattering coefficients when vegetation coverage was below 25% ($R^2\approx 0.88$, with 98% of pixels showing relative errors within 0–20%); however, this accuracy declined as vegetation coverage increased. For grass endmembers, the model maintained high estimation precision across the entire grassland area (vegetation coverage 0.2–0.8), yielding an of 0.80 with 83% of pixels falling within the 0–20% relative error range. In addition, the model performance is influenced by the number of endmembers.