nyi Li

An evaluation of Suomi NPP-VIIRS data for surface water detection

Measuring surface water using remote sensing technology is an essential research topic in many research areas, including flood-related studies and water resource management. Recent advances in satellite remote sensing provide more efficient ways of monitoring surface water from space. As a newly available data source with a high frequency of global coverage and moderate resolution, Visible Infrared Imaging Radiometer Suite on board the Suomi National Polar-orbiting Partnership (Suomi NPP-VIIRS) has the advantage of monitoring the earth surface intensively and continuously. This study conducts an exploratory evaluation on the performance of Suomi NPP-VIIRS data for surface water detection. A Modified Histogram method was proposed and applied to its shortwave infrared (SWIR) band to estimate the water fraction within each single pixel. The estimated surface water fraction was then compared with that derived from a corresponding Moderate Resolution Imaging Spectroradiometer (MODIS) image and evaluated using a higher-resolution Landsat Operational Land Imager image. Evaluation results demonstrate that surface water was successfully delineated using the Suomi NPP-VIIRS SWIR band, even at sub-pixel level, bearing in mind that cloud and shadow may interfere surface water detection. A more precise detection result usually requires some additional approaches to help distinguish surface water from cloud and shadow. It was also revealed that the Suomi NPP-VIIRS can be an ideal surrogate of MODIS.

Improved Urban Flooding Mapping from Remote Sensing Images Using Generalized Regression Neural Network-Based Super-Resolution Algorithm

Urban flooding is a serious natural hazard to many cities all over the world, which has dramatic impacts on the urban environment and human life. Urban flooding mapping has practical significance for the prevention and management of urban flood disasters. Remote sensing images with high temporal resolutions are widely used for urban flooding mapping, but have a limitation of relatively low spatial resolutions. In this study, a new method based on a generalized regression neural network (GRNN) is proposed to achieve improved accuracy in super-resolution mapping of urban flooding (SMUF) from remote sensing images. The GRNN-SMUF algorithm was proposed and then assessed using Landsat 5 and Landsat 8 images of Brisbane city in Australia and Wuhan city in China. Compared to three traditional methods, GRNN-SMUF mapped urban flooding more accurately according to both visual and quantitative assessments. The results of this study will improve the accuracy of urban flooding mapping using easily-available remote sensing images with medium-low spatial resolutions and will be propitious to the prevention and management of urban flood disasters.

Integrating Entropy-Based Naïve Bayes and GIS for Spatial Evaluation of Flood Hazard

Regional flood risk caused by intensive rainfall under extreme climate conditions has increasingly attracted global attention. Mapping and evaluation of flood hazard are vital parts in flood risk assessment. This study develops an integrated framework for estimating spatial likelihood of flood hazard by coupling weighted naïve Bayes (WNB), geographic information system, and remote sensing. The north part of Fitzroy River Basin in Queensland, Australia, was selected as a case study site. The environmental indices, including extreme rainfall, evapotranspiration, net-water index, soil water retention, elevation, slope, drainage proximity, and density, were generated from spatial data representing climate, soil, vegetation, hydrology, and topography. These indices were weighted using the statistics-based entropy method. The weighted indices were input into the WNB-based model to delineate a regional flood risk map that indicates the likelihood of flood occurrence. The resultant map was validated by the maximum inundation extent extracted from moderate resolution imaging spectroradiometer (MODIS) imagery. The evaluation results, including mapping and evaluation of the distribution of flood hazard, are helpful in guiding flood inundation disaster responses for the region. The novel approach presented consists of weighted grid data, image-based sampling and validation, cell-by-cell probability inferring and spatial mapping. It is superior to an existing spatial naive Bayes (NB) method for regional flood hazard assessment. It can also be extended to other likelihood-related environmental hazard studies.

Surface Water Mapping from Suomi NPP-VIIRS Imagery at 30 m Resolution via Blending with Landsat Data

Monitoring the dynamics of surface water using remotely sensed data generally requires both high spatial and high temporal resolutions. One effective and popular approach for achieving this is image fusion. This study adopts a widely accepted fusion model, the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM), for blending the newly available coarse-resolution Suomi NPP-VIIRS data with Landsat data in order to derive water maps at 30 m resolution. The Pan-sharpening technique was applied to preprocessing NPP-VIIRS data to achieve a higher-resolution before blending. The modified Normalized Difference Water Index (mNDWI) was employed for mapping surface water area. Two fusion alternatives, blend-then-index (BI) or index-then-blend (IB), were comparatively analyzed against a Landsat derived water map. A case study of mapping Poyang Lake in China, where water distribution pattern is complex and the water body changes frequently and drastically, was conducted. It has been revealed that the IB method derives more accurate results with less computation time than the BI method. The BI method generally underestimates water distribution, especially when the water area expands radically. The study has demonstrated the feasibility of blending NPP-VIIRS with Landsat for achieving surface water mapping at both high spatial and high temporal resolutions. It suggests that IB is superior to BI for water mapping in terms of efficiency and accuracy. The finding of this study also has important reference values for other blending works, such as image blending for vegetation cover monitoring.

Integration of Bayesian regulation back-propagation neural network and particle swarm optimization for enhancing sub-pixel mapping of flood inundation in river basins

ABSTRACT Sub-pixel mapping of flood inundation (SMFI) is one of the hotspots in remote sensing and relevant research and application fields. In this study, a novel method based on the integration of Bayesian regulation back-propagation neural network (BRBP) and particle swarm optimization (PSO), so-called IBRBPPSO, is proposed for SMFI in river basins. The IBRBPPSO–SMFI algorithm was developed and evaluated using Landsat images from the Changjiang river basin in China and the Murray-Darling basin in Australia. Compared with traditional SMFI methods, IBRBPPSO–SMFI consistently achieves the most accurate SMFI results in terms of visual and quantitative evaluations. IBRBPPSO–SMFI is superior to PSO–SMFI with not only an improved accuracy, but also an accelerated convergence speed of the algorithm. IBRBPPSO–SMFI reduces the uncertainty in mapping inundation in river basins by improving the accuracy of SMFI. The result of this study will also enrich the SMFI methodology, and thereby benefit the environmental studies of river basins.

Feature selection for residential area recognition in high resolution images based on particle swarm optimization

Automatic recognition of residential areas in high resolution images becomes one of hotspots in the remote sensing field. Feature selection of residential areas is crucial which affects the corresponding recognition results; however, it is very difficult to select optimal residential area features. Particle swarm optimization (PSO) is a new evolutionary computing technique which was developed through the simulation of simplified social models of bird flocks. Because it has some intelligent properties such as adaptation and self-organizing, PSO has the strong ability to search for the optimal solutions for optimization problems. The difficulty mentioned above is a combination optimization problem in essence and therefore discrete binary PSO is applied in solving this combination optimization problem adaptively in this paper. The particles in the swarm are constructed and the swarm search strategy is proposed to meet the needs of feature selection for residential area recognition. The experimental results show that the PSO method is an effective feature selection method which decreases the feature number obviously, and at the same time improves the recognition accuracy of residential areas effectively.

Adaptive Multi-scale Segmentation of High Resolution Remote Sensing Images Based on Particle Swarm Optimization

Multi-scale segmentation method is suitable for segmenting high resolution remote sensing images, however, it is difficult to get optimal multi-scale segmentation parameters using traditional methods. Particle swarm optimization (PSO) is a new evolutionary computing technique Based on swarm intelligence of bird flocks. Due to its intelligent properties, PSO is applied in selection of image multi-scale segmentation parameters adaptively in this paper. The particles in the swarm are constructed and the swarm search strategy is proposed to meet the needs of multi-scale segmentation parameter selection. The experimental results show that the PSO method is an effective parameter selection method and multi-scale segmentation Based on PSO can obtain satisfactory image segmentation results.

Fuzzy Classification of High Resolution Remote Sensing Scenes Using Visual Attention Features

In recent years the spatial resolutions of remote sensing images have been improved greatly. However, a higher spatial resolution image does not always lead to a better result of automatic scene classification. Visual attention is an important characteristic of the human visual system, which can effectively help to classify remote sensing scenes. In this study, a novel visual attention feature extraction algorithm was proposed, which extracted visual attention features through a multiscale process. And a fuzzy classification method using visual attention features (FC-VAF) was developed to perform high resolution remote sensing scene classification. FC-VAF was evaluated by using remote sensing scenes from widely used high resolution remote sensing images, including IKONOS, QuickBird, and ZY-3 images. FC-VAF achieved more accurate classification results than the others according to the quantitative accuracy evaluation indices. We also discussed the role and impacts of different decomposition levels and different wavelets on the classification accuracy. FC-VAF improves the accuracy of high resolution scene classification and therefore advances the research of digital image analysis and the applications of high resolution remote sensing images.

Integration of fuzzy theory and particle swarm optimization for high-resolution satellite scene recognition

With the rapid development of satellite imaging technology, large amounts of satellite images with high spatial resolutions are now available. High-resolution satellite imagery provides rich texture and structure information, which in the meantime poses a great challenge for automatic satellite scene recognition. In this study, a novel integration method of fuzzy theory and particle swarm optimization (IFTPSO) is proposed to achieve an increased accuracy of satellite scene recognition (SSR) in high-resolution satellite imagery. The particle encoding, fitness function and swarm search strategy are designed for IFTPSO-SSR. The IFTPSO-SSR method was evaluated using the satellite scenes from QuickBird, IKONOS and ZY-3. IFTPSO-SSR outperformed three traditional recognition methods with the highest recognition accuracy. The parameter sensitivity of IFTPSO-SSR was also discussed. The proposed method of this study can enhance the performance of satellite scene recognition in high-resolution satellite imagery, and thereby advance the research and applications of artificial intelligence and satellite image analysis.

Remote sensing image fusion based on frequency domain segmenting

Remote sensing image fusion has become one of hotspots in the researches and applications of Geoinformatics in recent years. It has been widely used to integrate low-resolution multispectral images with high-resolution panchromatic images. In order to obtain good fusion effects, high frequency components of panchromatic images and low frequency components of multispectral images should be identified and combined in a reasonable way. However, it is very difficult due to complex processes of remote sensing image formation. In order to solve this problem, a new remote sensing image fusion method based on frequency domain segmenting is proposed in this paper. Discrete wavelet packet transform is used as the mathematical tool to segment the frequency domain of remote sensing images after analyzing the frequency relationship between high-resolution panchromatic images and low-resolution multispectral images. And several wavelet packet coefficient features are extracted and combined as the fusion decision criteria. Besides visual perception and some statistical parameters, classification accuracy parameters are also used to evaluate the fusion effects in the experiment. And the results show that fused images by the proposed method are not only suitable for human perception but also suitable for some computer applications such as remote sensing image classification.