Hyperspectral image (HSI) subspace clustering re- mains a challenging task due to the poor spatial and rich spectral resolutions of HSIs. Most of the existing HSI subspace clustering approaches just extract the spatial and spectral features, ignoring the intrinsic distribution information of data and leading to low accuracy of clustering generally. To solve this problem, this paper presents a diffusion subspace clustering model (DiffSC) which learns distribution information of HSI data simultane- ously through a diffusion module (DM). Specifically, due to the diffusion probabilistic model (DPM) learning raw object data distribution to generate data of the same distribution, which has received wide attention in generation tasks and outperforms other generative models significantly, we attempt to apply the DPM in the field of feature extraction. DiffSC performs distribution information extraction of hyperspectral images by DM and fuses them with spatial-spectral features extracted by deep subspace clustering for training jointly. Experiment outcomes demonstrate that intermediate activation of specific timestep in the inverse diffusion process captures latent distribution information of images effectively and improves the HSI clustering accuracy significantly. Since the DPM is simplified, it can be easily trained from scratch. We evaluate the presented DiffSC on five real HSI datasets, and the experiments indicate that DiffSC can obtain the most advanced clustering outcomes that notably outperform most existing HSI subspace clustering approaches.

Large-scale hyperspectral image (HSI) clustering remains a fundamental and challenging task due to tremendous spatial scales, abundant spectral band information, and lack of prior information. Most existing clustering methods either ignore the spectral band correlation leading to low clustering performance nor unprocessable due to the large spatial scale. To solve these difficulties, this paper presents a dual smooth graph convolutional clustering (DSGCC) framework for large-scale HSI clustering. Specifically, the superpixel is introduced to decrease the spatial scale of HSI and reduce graph node number for subsequent network training. Furthermore, a smooth graph filter is presented, which extracts the smooth features and filters the high-frequency interference in graph learning. In addition, we propose a layer-wise graph reconstruction (LGR) mechanism, which constrains all hidden layers output by graph reconstruction loss. Finally, we introduce a self-training method that utilizes soft labels to supervise during clustering and learns the robust embedding for node clustering. DSGCC is an end-to-end network that is optimized by joint loss which is easily trained from scratch. We assess DSGCC on five commonly used large-scale HSI datasets, and experiments denote that DSGCC achieves the optimum clustering performance which is superior to existing HSI clustering approaches. On Salinas, Indian Pines, Pavia University, WHU-Hi-LongKou, and WHU-Hi-HongHu datasets, the clustering overall accuracy (OA) of DSGCC are 85.43%, 65.45%, 70.48%, 87.30%, and 77.34%, respectively.

The recent launch of the Chinese FengYun-3G/3F (FY-3G/3F) satellites provides new opportunities for Earth observation enabled by their unique combination of non-sun-synchronous and sun-synchronous orbits. This study provides the first comprehensive evaluation of the Level-1 brightness temperature (BT) products from both the FY-3G MWRI-RM and FY-3F MWRI-II microwave imagers. Using a globally collocated dataset with the GPM Microwave Imager (GMI) as the reference, we assess the radiometric consistency through direct comparison and quantify the random errors of using the Triple Collocation (TC) method. Results show that both two sensors have high consistency and low systematic bias, with Mean Bias Deviations (MBD) generally below 1.0 K and Root Mean Square Deviations (RMSD) of lower than 3.0 K for most channels. Nevertheless, the TC results uncover a significant performance divergence in their random errors, particularly over land. Specifically, MWRI-II exhibits a high level of performance, with an overall Root Mean Square Error (RMSE) over barren land of 0.72 K, compared to 0.82 K for GMI. In contrast, while the MWRI-RM performs well over oceans, its TC-derived errors are substantially larger over vegetated land, reaching a peak RMSE of 4.67 K. The findings from this study suggest that the FY-3F MWRI-II BT has good potential in a wide range of scientific applications, while the FY-3G MWRI-RM BT, though valuable for oceanic studies, requires substantial refinement of its land surface processing to realize its full potential.