Nighttime light data record the artificial light on the Earth's surface and can be used to estimate the degree of pollution associated with particulate matter with an aerodynamic diameter of less than 2.5 μm (PM2.5) in the ground-level atmosphere. This study proposes a simple method for monitoring PM2.5 concentrations at night by using nighttime light imagery from the Defense Meteorological Satellite Program-Operational Linescan System (DMSP-OLS). This research synthesizes remote sensing and geographic information system techniques and establishes a back propagation neural-network (BP network) model. The BP network model for nighttime light data performed well in estimating the PM2.5 pollution in Beijing. The correlation coefficient between the BP network model predictions and the corrected PM2.5 concentration was 0.975; the root mean square error was 26.26 μg/m 3 , with a corresponding average PM2.5 concentration of 155.07 μg/m 3 ; and the average accuracy was 0.796. The accuracy of the results primarily depended on the method of selecting regions in the DMSP nighttime light data. This study provides an opportunity to measure the nighttime environment. Furthermore, these results can assist government agencies in determining particulate matter pollution control areas and developing and implementing environmental conservation planning.
In order to improve the authenticity of multispectral remote sensing image data analysis, the KNN algorithm and hyperspectral remote sensing technology are used to organically combine advanced multimedia technology with spectral technology to subdivide the spectrum. Different classification methods are used to classify CHRIS 0°, and the results are analyzed and compared: SVM classification accuracy is the highest 72 8448%, Kappa coefficient is 0.6770, and SVM is used to classify CHRIS images from five angles, and the results are compared and analyzed: the classification accuracy is from high to low, and the order is FZA = 0 > FZA = −36 > FZA = −55 > FZA = 36 > FZA = 55; SVM is used to classify the multiangle combined image, and the result is compared with the CHRIS 0° result: the overall classification accuracy of angle-combined image types is lower than that of single-angle images; the SVM is used to classify the band-combined image, and the result is compared with CHRIS 0°: the overall classification accuracy of the band combination image forest type is very low, and the effect is not as good as the combining multiangle image classification results. It is verified that if CHRIS multiangle hyper-spectral data are used for classification, the SVM method should be used to classify spectral remote sensing image data with the best effect.
Remote sensing image technology is of great significance for dynamic management and monitoring of ground buildings. In order to improve the data fusion ability of remote sensing image of ground buildings, a data fusion method of remote sensing image of ground buildings based on multi-level fuzzy evaluation is proposed. This method constructs a remote sensing image acquisition model of ground buildings, and uses image enhancement methods to realize the gray information analysis and image enhancement of the remote sensing image rate of ground buildings. Finally, combining the remote sensing image data fusion method and the fuzzy region reconstruction method, it reconstructs the pixels of the dynamically changed ground buildings. The simulation results show that the remote sensing image data fusion accuracy of ground buildings is good, and the remote sensing feature extraction accuracy of ground buildings is high. The dynamic real-time monitoring of remote sensing image of ground buildings is realized.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.