Search

Precipitation nowcasting has important implications for urban operation and flood prevention. Radar echo extrapolation is the common method in precipitation nowcasting. Using deep learning models to extrapolate radar echo data has great potential. The increase of lead time leads to a weaker correlation between real rainfall evolution and generated images. The evolution information is easily lost during extrapolation, which is reflected as echoes attenuation. Existing models, including Generative Adversarial Network (GAN)-based models, are all difficult to reduce loss and curb attenuation, which results in insufficient rainfall prediction accuracy. Aim to the problem, a Spatiotemporal Process Intensification Network (GAN-argcPredNet v2.0) based on GAN-argcPredNet v1.0 is designed. GAN-argcPredNet v2.0 reduces the loss by intensifying the influence of the previously input evolution information. A Spatiotemporal Information Changes Prediction (STIC-Prediction) network is designed as generator. With the intensification of echo feature sequence, the generator focuses on the spatiotemporal variation and generates more accurate images. Furthermore, discriminator is a Channel-Spatial Convolution (CS-Convolution) network. The discriminator intensifies the discrimination of echoes information by strengthening spatial information of single image. Identification results are fed back to the generator, which reduces the loss of important evolutionary information. The experiments are based on the radar dataset of South China. The results show that GAN-argcPredNet v2.0 performs better than other models. In heavy rainfall prediction, compared with baseline, the Probability of Detection (POD), the Critical Success Index (CSI), and the Heidke Skill Score (HSS) increase by 24.8 %, 22.2 % and 21.5 % respectively. The False Alarm Ratio (FAR) decreases by 3.76 %.

Index-based methods are widely applied to urban impervious surface area (ISA) mapping, but the confusion between ISA and soil remains unsolved. In this article, the near-infrared (NIR)-blue bands were selected as feature space by analyzing the spectra from the US Geological Survey spectral library, and a simple impervious surface ratio index (ISRI) was developed by shifting the NIR-blue coordinate origin toward the convergence point of the fitting lines of ISA and soil. The ISRI was then validated for threshold simulation, separability, and correlation analysis. Results demonstrated that ISRI had a good performance for ISA mapping in four cities in China with different geographic environments, with all extraction accuracies all above 90%. ISRI had a high separability between ISA and soil and was better than other indices (normalized difference built-up index and biophysical composition index). Further, ISRI has a close relationship with the ISA proportion. Therefore, ISRI would be a simple and reliable index for urban ISA mapping.

The hyperspectral image (HSI) has been widely used in many applications due to its fruitful spectral information. However, the limitation of imaging sensors has reduced its spatial resolution that causes detail loss. One solution is to fuse the low spatial resolution hyperspectral image (LR-HSI) and the panchromatic image (PAN) with inverse features to get the high-resolution hyperspectral image (HR-HSI). Most of the existing fusion methods just focus on small fusion ratios like 4 or 6, which might be impractical for some large ratios' HSI and PAN image pairs. Moreover, the ill-posedness of restoring detail information in HSI with hundreds of bands from PAN image with only one band has not been solved effectively, especially under large fusion ratios. Therefore, a lightweight unmixing-based pan-guided fusion network (Pgnet) is proposed to mitigate this ill-posedness and improve the fusion performance significantly. Note that the fusion process of the proposed network is under the projected low-dimensional abundance subspace with an extremely large fusion ratio of 16. Furthermore, based on the linear and nonlinear relationships between the PAN intensity and abundance, an interpretable PAN detail inject network (PDIN) is designed to inject the PAN details into the abundance feature efficiently. Comprehensive experiments on simulated and real datasets demonstrate the superiority and generality of our method over several state-of-the-art (SOTA) methods qualitatively and quantitatively (The codes in pytorch and paddle versions and dataset could be available at https://github.com/rs-lsl/Pgnet). (This is a improved version compared with the publication in Tgrs with the modification in the deduction of the PDIN block.)

Terrain surfaces can be relatively accurately obtained from light detection and ranging data using least-squares interpolation. However, the accuracy of the extraction results is low in regions with relatively large terrain undulations, and large buildings and vegetation with large areas and relatively low permeabilities cannot be eliminated. In this letter, we propose a region growing filtering method based on moving-window weighted iterative least-squares fitting. This technique uses the moving-window weighted iterative least squares fitting method to select the seed point. After multiple iterations, we take the difference between the original data and the fitting results and retain the points with differences within the threshold range. We use these points as the seed points and adopt the region growing method to reconstruct the complete point set of ground points. We use five test data sets provided by the International Society for Photogrammetry and Remote Sensing and data from the Iowa River Basin in the United States for experiments. The results indicate that the proposed method can effectively remove buildings and vegetation, but it still requires further improvement for the removal of bridges and objects at the edge.

Dark target detection is important for engineering applications but the existing methods do not consider the imaging environment of dark targets, such as the adjacency effect. The adjacency effect will affect the quantitative applications of remote sensing, especially for high contrast images and images with ever-increasing resolution. Further, most studies have focused on how to eliminate the adjacency effect and there is almost no research about the application of the adjacency effect. However, the adjacency effect leads to some unique characteristics for the dark target surrounded by a bright background. This paper utilizes these characteristics to assist in the detection of the dark object, and the low-high threshold detection strategy and the adaptive threshold selection method under the assumption of Gaussian distribution are designed. Meanwhile, preliminary case experiments are carried out on the crack detection of concrete slope protection. Finally, the experiment results show that it is feasible to utilize the adjacency effect for dark target detection.

Monitoring urban compositions spatially and temporally is a crucial issue for urban planning and management. Nowadays, remote sensing techniques have been widely applied for urban compositions extraction. Compared with other remote sensing techniques, spectral indices have significant advantages due to their parameter-free and easy implementation. However, existing indices cannot extract different urban compositions well, and some of them can only extract one composition with less attention to other urban compositions. In this study, based on the water- impervious surface-pervious surface (W-I-P) model, a novel urban composition index (UCI) was developed by analyzing the robust features from the global spectral samples. Additionally, a semi-empirical threshold of UCI was proposed to extract different urban compositions (water, impervious surface area and pervious surface area). Four cities of China were selected as study areas, Landsat-8 images and Google Earth images were used for quantitative analysis. Correlation analysis, separability analysis, and accuracy assessment were conducted among UCI and five other existed indices (single and multiple composition indices) at the urban and global scales. Results indicated that UCI had a stronger correlation with the ISA proportion and a higher separability between each urban composition. UCI also achieved the highest overall accuracy and Kappa coefficient in urban compositions extraction. The suggested semi-empirical threshold was also testified to be reliable and can be a reference for practical application. There is convincing evidence that UCI is a simple, efficient, and reliable index for urban compositions extraction.

Mapping and tracing the changes in canola planting areas and yields in China are of great significance for macro-policy regulation and national food security. The bright yellow flower is a distinctive feature of canola, compared to other crops, and is also an important factor in predicting canola yield. Thus, yellowness indices were previously used to detect the canola flower using aerial imagery or median-resolution satellite data like Sentinel-2. However, it remains challenging to map the canola planting area and to trace long-term canola yields in China due to the wide areal extent of cultivation, different flowering periods in different locations and years, and the lack of high spatial resolution data within a long-term period. In this study, a novel canola index, called the enhanced area yellowness index (EAYI), for mapping canola flowers and based on Moderate Resolution Imaging Spectroradiometer (MODIS) time-series data, was developed. There are two improvements in the EAYI compared with previous studies. First, a method for estimating flowering period, based on geolocation and normalized difference vegetation index (NDVI) time-series, was established, to estimate the flowering period at each place in each year. Second, the EAYI enhances the weak flower signal in coarse pixels by combining the peak of yellowness index time-series and the valley of NDVI time-series during the estimated flowering period. With the proposed EAYI, canola flowering was mapped in five typical canola planting areas in China, during 2003-2017. Three different canola indices proposed previously, the normalized difference yellowness index (NDYI), ratio yellowness index (RYI) and Ashourloo canola index (Ashourloo CI), were also calculated for a comparison. Validation using the samples interpreted through higher resolution images demonstrated that the EAYI is better correlated with the reference canola coverage with R2 ranged from 0.31 to 0.70, compared to the previous indices with R2 ranged from 0.02 to 0.43. Compared with census canola yield data, the total EAYI was well correlated with actual yield in Jingmen, Yili and Hulun Buir, and well correlated with meteorological yields in all five study areas. In contrast, previous canola indices show a very low or even a negative correlation with both actual and meteorological yields. These results indicate that the EAYI is a potential index for mapping and tracing the change in canola areas, or yields, with MODIS data.

Quantifying global population exposure to rainstorms is a key component of population risk assessments for rainstorms and induced floods. Based on daily precipitation data from the NEX-GDDP dataset, rainfall from rainstorms is first calculated by a multi-model ensemble method for four periods from 1986 to 2100. Combined with population data from the SSP2 scenario, the global population exposure to rainstorms is then calculated and analyzed. Finally, the contribution rates of climate change effect, population change effect, and joint change effect on exposure change are quantitatively assessed. The results showed that (1) Population exposure to rainstorms shows a linear upward trend from base period to the late 21st century period in most regions, and the mid-21st century period compared with base period has the fastest rate of increase. (2) The spatial patterns of population exposure to rainstorms are very similar for the four periods and the areas with high exposure are mainly distributed in Asia, population exposure of Africa is gradually increasing. The countries with high exposure show little volatility, especially the top eight countries. (3) The change in total exposure is mainly due to population change. Based on the composition of the total exposure change for each country, the number of countries whose climate change effect is greater than that of population change is gradually increasing, and this number reaches more than a quarter of the total when the late 21st century period is compared with the mid-21st century period.

The distribution and dynamic changes in impervious surface areas (ISAs) are crucial to understanding urbanization and its impact on urban heat islands, earth surface energy balance, hydrological cycles, and biodiversity. Remotely sensed data play an essential role in ISA mapping, and numerous methods have been developed and successfully applied for ISA extraction. However, the heterogeneity of ISA spectra and the high similarity of the spectra between ISA and soil have not been effectively addressed. In this study, we selected data from the US Geological Survey (USGS) and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) spectral libraries as samples and used blue and near-infrared bands as characteristic bands based on spectral analysis to propose a novel index, the perpendicular impervious surface index (PISI). Landsat 8 operational land imager data in four provincial capital cities of China (Wuhan, Shenyang, Guangzhou, and Xining) were selected as test data to examine the performance of the proposed PISI in four different environments. Threshold analysis results show that there is a significant positive correlation between PISI and the proportion of ISA, and threshold can be adjusted according to different needs with different accuracy. Furthermore, comparative analyses, which involved separability analysis and extraction precision analysis, were conducted among PISI, biophysical composition index (BCI), and normalized difference built-up index (NDBI). Results indicate that PISI is more accurate and has better separability for ISA and soil as well as ISA and vegetation in the ISA extraction than the BCI and NDBI under different conditions. The accuracy of PISI in the four cities is 94.13%, 96.50%, 89.51%, and 93.46% respectively, while BCI and NDBI showed accuracy of 77.53%, 93.49%, 78.02%, and 84.03% and 58.25%, 57.53%, 77.77%, and 64.83%, respectively. In general, the proposed PISI is a convenient index to extract ISA with higher accuracy and better separability for ISA and soil as well as ISA and vegetation. Meanwhile, as PISI only uses blue and near-infrared bands, it can be used in a wider variety of remote sensing images.

A study of the frequency, intensity, and risk of extreme climatic events or natural hazards is important for assessing the impacts of climate change. Many models have been developed to assess the risk of multiple hazards, however, most of the existing approaches can only model the relative levels of risk. This paper reports the development of a method for the quantitative assessment of the risk of multiple hazards based on information diffusion. This method was used to assess the risks of loss of human lives from 11 types of meteorological hazards in China at the prefectural and provincial levels. Risk curves of multiple hazards were obtained for each province and the risks of 10-year, 20-year, 50-year, and 100-year return periods were mapped. The results show that the provinces (municipalities, autonomous regions) in southeastern China are at higher risk of multiple meteorological hazards as a result of their geographical location and topography. The results of this study can be used as references for the management of meteorological disasters in China. The model can be used to quantitatively calculate the risks of casualty, direct economic losses, building collapse, and agricultural losses for any hazards at different spatial scales.

Spatial distribution and population density are important parameters in studies on urban development, resource allocation, emergency management, and risk analysis. High-resolution height data can be used to estimate the total or spatial pattern of the urban population for small study areas, e.g., the downtown area of a city or a community. However, there has been no case of population estimation for large areas. This paper tries to estimate the urban population of prefectural cities in China using building height data. Building height in urban population settlement (Mdiffs) was first extracted using the digital surface model (DSM), digital elevation model (DEM), and land use data. Then, the relationships between the census-based urban population density (CPD) and the Mdiffs density (MDD) for different regions were regressed. Using these results, the urban population for prefectural cities of China was finally estimated. The results showed that a good linear correlation was found between Mdiffs and the census data in each type of region, as all the adjusted R2 values were above 0.9 and all the models passed the significance test (95% confidence level). The ratio of the estimated population to the census population (PER) was between 0.7 and 1.3 for 76% of the cities in China. This is the first attempt to estimate the urban population using building height data for prefectural cities in China. This method produced reasonable results and can be effectively used for spatial distribution estimates of the urban population in large scale areas.

Indicator-geostatistics based super-resolution mapping (IGSRM) is a popular super-resolution mapping (SRM) method. Unlike most existing SRM methods that produce only one SRM result each, IGSRM generates multiple equally plausible super-resolution realizations (i.e., SRM results). However, multiple super-resolution realizations are not desirable in many applications, where only one SRM result is usually required. These super-resolution realizations may have different strengths and weaknesses. This paper proposes a novel two-step combination method of generating a single SRM result from multiple super-resolution realizations obtained by IGSRM. In the first step of the method, a constrained majority rule is proposed to combine multiple super-resolution realizations generated by IGSRM into a single SRM result under the class proportion constraint. In the second step, partial pixel swapping is proposed to further improve the SRM result obtained in the previous step. The proposed combination method was evaluated for two study areas. The proposed method was quantitatively compared with IGSRM and Multiple SRM (M-SRM), an existing multiple SRM result combination method, in terms of thematic accuracy and geometric accuracy. Experimental results show that the proposed method produces SRM results that are better than those of IGSRM and M-SRM. For example, in the first example, the overall accuracy of the proposed method is 7.43–10.96% higher than that of the IGSRM method for different scale factors, and 1.09–3.44% higher than that of the M-SRM, while, in the second example, the improvement in overall accuracy is 2.42–4.92%, and 0.08–0.90%, respectively. The proposed method provides a general framework for combining multiple results from different SRM methods.

Quantitative estimation of the typhoon rainfall is one of the focus in the typhoon research field. In this paper, in order to improve estimation accuracy in the scope and rainfall, the authors use the cloud classify rainfall forecast model based on edge extraction with multi-attribute typhoon data such as infrared data, water vapor data and temperature of brightness blackbody(TBB) data etc. First of all, we use the edge extraction to get the outline of the rainfall, then use the cloud classify rainfall estimation model to obtain the predicted rainfall in the inner area. At last, authors take "Phoenix" typhoon, in 2008, as an example to improve the estimation accuracy in rainfall distribution as well as the cloud rainfall by using the method of cloud rainfall estimation with multi-attribute typhoon data and edge extraction.

Flood risk assessment is of very importance for disaster mitigation, which is complemented by environment stability, hazard statistical and vulnerability possibility. Each factor usually contains a series of indicators and a comprehensive analysis of each factor must be superimposed on the various indicators. The traditional methods on how to determine the relative weight of each indicator are experts_scoring and AHP, which require a given weight by experts. In this paper, maximum entropy is applied into determining weight of each indicator and cloud model, one kind of uncertain artificial intelligence models, is used to classify the grades of flood risk objectively. Finally, a case study in Huaihe River Basin of China is made and some conclusions are drawn.

In this paper, we propose a novel change detection method. Multiple classifiers fusion combine results from various simple changes detection methods to improve change detection accuracy. In detail, we make use of multiple classifiers fusion based on fuzzy integrals for change detection. If the fuzzy measures are well defined, the accuracy of change detection can be improved distinctly. In this paper, we determine the fuzzy measures based on the Genetic Algorithm (GA). Though multiple classifiers fusion has robust performance, the input change detection result is still important. We review proposed pre-classification change detection method, and propose two contextual Fuzzy-C Means (FCM) algorithms and the Self Organization Feature Map (SOFM) change detection method. We select multi-spectral TM and pan SPOT image pairs as test data and apply five different change detection methods. The first experiment shows that different methods will produce different change detection accuracy, and different methods will complement each other. In addition, we apply fuzzy integral aided by genetic algorithm for combining different detection methods. The final experiment shows that our proposed method can improve change detection accuracy and has better performance than single detection method.

In order to focus on the serious area affected by earthquakes and other hazards, and to meet the demands of post-disaster reconstruction, the disaster-affected area must be evaluated scientifically. In general, select indicator set firstly, then construct comprehensive disaster index, finally divide the disaster-affected area into different grade zones according to a certain threshold determined by a total consideration. This kind of method is simple and easy to operate, but prone to be interfered by subjective factors. In response to this problem, a new evaluation method based on cloud model, one kind of uncertain artificial intelligence models, is proposed. The new method can obtain a "soft" grade zoning by directly learning from objective data set, the evaluation results are more scientific. In this paper, the authors take Wenchuan seismic disaster- affected grade zoning as an example to testify the feasibility and reliability of this new method.

Nowadays, Remote sensing is widely applied into flood monitoring. In order to obtain the accurate flooded area, water body need be well segmented, however, image segmentation is still a hard problem. In fact, each image segmentation method has its advantages and disadvantages, single method is hard to acquire satisfactory results, so two or more methods combination are applied. In this paper, the algorithm of combination watershed transformation and region merging based on morphologic gradient is introduced and applied in a typical flooded region, Quyuan town of Hunan province of China to extract the area of target water bodies, at the same time, other segmentation methods: ISODATA and the combination segmentation methods of optimal threshold and mathematical morphology, are also applied. Finally, compared with actually measurement area of the target water body by Differential GPS, some suggestive conclusions are drawn.

Real coded Genetic Algorithms (RGAs) have received a great deal of attention regarding their potential as optimization techniques for complex functions. Regularization was applied to solve ill-posed problems with an additional information about the solutions. In this paper, we introduce a new method named Regularization Regression based on RGAs to rebuild traditional regression methods, in which different regularization terms, regularization parameters and proper loss functions are designed flexibly according to prior knowledge of different problems.