Hyperspectral data has low spatial resolution in contrast to its high spectral resolution. This limited spatial resolution leads to the presence of mixed pixels in the hyperspectral data cube. To address this issue, we have developed several spectral unmixing methods, which can be found in the following links:

• R. Rajabi, H. Ghassemian, “Spectral Unmixing of Hyperspectral Imagery using Multilayer NMF”, IEEE Geoscience and Remote Sensing Letters, vol. 12, pp. 38-42, 2015.
• S. Khoshsokhan, R. Rajabi and H. Zayyani, “Sparsity-Constrained Distributed Unmixing of Hyperspectral Data,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 4, April 2019.
• S. Khoshsokhan, R. Rajabi and H. Zayyani, “Clustered multitask nonnegative matrix factorization for spectral unmixing of hyperspectral data,”Journal of Applied Remote Sensing, vol. 12, no. 4, May 2019.