Search

As an emerging research hotspot in contemporary remote sensing, hyperspectral change detection (HCD) has attracted increasing attention in remote sensing Earth observation, covering land mapping changes and anomaly detection. This is primarily attributable to the unique capacity of hyperspectral imagery (HSI) to amalgamate both the spectral and spatial information in the scene, facilitating a more exhaustive analysis and change detection on the Earth's surface, proving to be successful across diverse domains, such as disaster monitoring and geological surveys. Although numerous HCD algorithms have been developed, most of them face three major challenges: (i) susceptibility to inherent data noise, (ii) inconsistent accuracy of detection, especially when dealing with multi-scale changes, and (iii) extensive hyperparameters and high computational costs. As such, we propose a singular spectrum analysis-driven-lightweight network for HCD, where three crucial components are incorporated to tackle these challenges. Firstly, singular spectrum analysis (SSA) is applied to alleviate the effect of noise. Next, a 2-D self-attention-based spatial–spectral feature-extraction module is employed to effectively handle multi-scale changes. Finally, a residual block-based module is designed to effectively extract the spectral features for efficiency. Comprehensive experiments on three publicly available datasets have fully validated the superiority of the proposed SSA-LHCD model over eight state-of-the-art HCD approaches, including four deep learning models. [ABSTRACT FROM AUTHOR]

Centrifugal granulation technology using a spinning cup opens a potential way to recycle steel slag that is currently difficult to reuse. The objective of this research was to study the flow characteristics of a molten slag–metal mixture that was produced during smelting reduction in molten steel slag, passing over a spinning cup, so as to explore the feasibility of using centrifugal granulation technology to treat the steel slag. This was achieved by developing and implementing a computational fluid dynamics (CFD) model that incorporated free-surface multiphase flow to predict the thickness of the liquid slag film at the edge of the spinning cup (slag film thickness for short), which was an important parameter for estimating the size of the slag particles resulting from centrifugal granulation of the molten slag–metal mixture. The influences of various relevant parameters, including spinning cup diameter, slag feeding rate, cup spinning speed, etc., on the slag film thickness were analyzed. Additionally, hot experiments on centrifugal granulation of a molten slag–metal mixture were conducted to verify the results of the numerical simulations. The experimental results indicated a progressive reduction in the Sauter mean diameter of the slag particles as the metallic iron content in the slag increased. Specifically, when the iron content rose from 5% to 15% at a cup spinning speed of 2500 RPM, the Sauter mean diameter decreased by 13.77%. The numerical simulation results showed that the slag film thickness had a positive relationship to the slag feeding rate but a negative relationship to the spinning cup diameter and the cup spinning speed. Furthermore, the ratio between the mean slag particle diameter and the slag film thickness decreased nearly linearly with the increase in the metallic iron content in slag, with the average ratio being approximately 4.25, and this relationship was useful for estimating the slag particle size from the slag film thickness. Therefore, the present research results can provide theoretical guidance for the industrial application of spinning cup centrifugal granulation technology to effectively treat and recycle steel slags. [ABSTRACT FROM AUTHOR]