With the further development of mobile GIS, intelligent GIS and socialized GIS, the geospatial information service based on natural language processing is an inevitable trend in the field of geographical information science. The intelligent conversion from text to map is one of the important research directions. Both natural language and maps have the ability to express spatial relationship of geographical entities. Natural language has the natural characteristic of usability and is highly abstract, while map language is more intuitive and revealing. The ubiquitous natural language contains a great deal of geographic information. Converting natural language to map language can help people intuitively understand the geographic space environment and bring out new discoveries. The current research difficulties focus on that how to make a computer construct graphical information from natural language and have the intelligent spatial cognitive thinking ability. This paper proposes a method that using point coordinated pairs, straight line segments and rectangular/circular shapes to quantitatively represent point, polyline and polygon geographical entities in natural language respectively. First the spatial relations description types in natural language between point and point, point and line, point and surface, line and line, line and surface, surface and surface geographic entities are summarized. Second, approximate transformation model of spatial relationships in natural language which considering the geometric types of geographical entities is constructed, and an approximate expression strategy based on spatial relationships description in natural language is proposed. Third, a prototype system is designed to implement "text-map" conversion, and scenic spot travel notes are selected as the experimental text to finish the experiment. The experimental results showed that the method mentioned above was feasible, the goal that converting qualitative spatial relationships in natural language to quantitative (or approximately quantitative) graphical spatial relationships could be achieved. This paper lays a foundation for the study of the conversion from natural language to map.
Under the influence of time, position and purpose, people move between different places in a city for various activities. The spatio-temporal data recording human trajectories implicate the functions of different regions in the city. Taxi is an important way that people travel in a city. The trajectories of taxis record spatio-temporal characteristics of taxi passengers' trips, from which corresponding functions of regions can be detected. This paper tries to figure out dynamic functions of regions where passengers take in or take off taxis by analyzing the regular pattern of ODs (origins and destination) of taxi trajectory data. However, taxi data always contain multi-dimensional information, one-dimensional or two-dimensional model is not enough to express the multi-dimensional information. As a result, we use tensor decomposition model to handle the taxi OD data from multiple dimensions, including day dimension, hour dimension and space dimension, and reveal the pattern of passengers' trips. We divide the region that covers the urban area within Sixth Ring Road of Beijing into 11 663 grids of 500 m×500 m in size. The Os and Ds of taxi trajectories are mapped into the grids and the number of Os and Ds in each grid is counted by hour and day separately. Then, we build 3-rd order tensors of Os and Ds, respectively. The result of tensor decomposition contains three matrixes which show hour patterns, day patterns and spatial patterns of Os and Ds and a core tensor which shows the intensity of relations between the three matrixes. The tensor decomposition found 8 temporal patterns of Os and Ds: morning rush pattern, daytime pattern, evening rush pattern and night pattern on weekdays and weekends separately. Mapping the temporal patterns of Os and Ds into space, 8 spatial patterns of Os and Ds were detected which reveals people's different activities in space during different time periods. By analyzing the patterns in each dimension and the relations between different dimensions, the functions of grids can be identified. Combined with points of interest (POI), more specific functions can be identified. This study demonstrate that the function of a region is not static but dynamic with changes with the need of people. The paper reveals the hidden real-time information of taxi data, which can provide a scientific reference for city planners.
The very high resolution remotely sensed imagery has been widely applied in automatic extraction of ground objects, However, it is hard to conduct timely operational building roof mapping with high accuracy using conventional algorithms. This paper investigate building roof segmentation with deep learning method, since the convolution operations upon images is not sensitive to deformation,rotation and illumination condition, a Deep Convolutional Neural Network (DCNN) is designed for building roof extraction, the proposed network has a cascaded structure with fully convolutional layers, with strategies for feature reuse and enhancement in the design of DCNN, it is expected to accurately extract building roof. The experiment is carried out upon building sample data set acquired in Massachusetts, USA, the results show that the proposed network achieved overall accuracy of 92.3%, and the comparison with other methods suggest the proposed network is able to map building roof with high accuracy.
This study proposed a method of traffic risk assessment of snow disaster based on multi-source information fusion including meteorological observation information and network information. Using the meteorological monitoring data in long time scale, the temporal and spatial characteristics of snowfall in Hebei province was analyzed with regard to frequency of snowfall and maximum of snow depth. The snow hazard intensity in different cases of return period events was calculated by function distribution fitting. Besides, we classified the exposure of highway in Hebei province by collecting the information of road congestion during holidays including Spring Festival and National Day from portal news websites, highway websites and so on. Finally, the risk matrix method was adopted to analyze the traffic risk of snow in Hebei province. That method was applied to Hebei province, and the study results were as follows: ① In recent 5 years, the snowfall in Hebei province has decreased. However, the snowfalls in different area fluctuated from decade to decade over a long-term scale. The high value areas of snow depth were located in Zhangjiakou, Chengde, and Shijiazhuang City, but they changed in different decades; the high frequency areas of snowfall were basically fixed, which was located in Kangbao, Guyuan and Chongli County in Zhangjiakou City, and the northwest of Fengning County in Chengde City. ② The sections of highway with high exposure were important provincial and city-level linking-up roads and the expressways which mainly connected Beijing with Shanghai, Guangzhou, Harbin and other major cities. ③ Affected by the comprehensive effects of hazard intensity and exposure, the high-risk sections of snow disaster were mainly concentrated in Beijing-Hong Kong-Macao Expressway (Shi'an Expressway G4), Jingkun Expressway G5, Beijing-Chengde Expressway G45, Changshen Expressway G25, and Zhangjiakou-Chengde Expressway G95, which need good risk prevention measures prepared against the snow disaster.
Taking the Chengguan District of Lanzhou City as a research area in the slope disaster-prone area, the surface deformation rate of surface deformation points is extracted by PS-InSAR technology, and the deformation rate can effectively reflect the distribution and uplifting of geological disasters in the spatial range. Based on the coKriging interpolation, combined with the generalized linear model (GLM) and the particle swarm optimization (PSO) algorithm, the coKrigong interpolation is optimized by fitting the linear model to construct the PSO-GLM-coKriging interpolation model to the surface deformation rate. The main variables, DEM, geotechnical porosity and NDVI fitting parameters were covariates, and spatial interpolation simulations were performed. Compared with the co-Kriging model and the GLM-co-Kriging model, the PSO-GLM-coKriging interpolation model has higher precision and better simulation effect, eliminating the complexity of multi-dimensional generation and improving the small-scale range. Interpolation effect, the error of the three models is 1.25mm/year, 0.70mm/year, 0.47mm/year. By comparison, the PSO-GLM-coKriging interpolation model has higher simulation accuracy and better simulation results. In the overall range, the interpolation results of the three models are similar in spatial distribution, in line with the actual situation of the surface. Therefore, the interpolation simulation of the blank area of ??the deformation point is carried out by the PSO-GLM interpolation model to fill the gap that the PS-InSAR technology can not extract the surface information at the non-deformation point, and the ground subsidence and uplift with sudden degeneration and sudden landslides will be completed. Geological disasters have been effectively combined, and the coupling relationship between geological disasters with high uncertainty and the monitoring of surface deformation can be established, which provides certain data and theoretical support for the planning and construction of urbanization in Chengguan District.
To study the coupling between construction land expansion and urban heat island（UHI）expansion in Guangdong-Hong Kong-Macao Greater Bay, it is of great significance and scientific value to improve the ecological environment of the Greater Bay and realize the healthy development of urbanization. In this paper, the Guangdong-Hong Kong-Macao Greater Bay was used as the research area. We selected remote sensing image data and surface temperature data in 2000, 2008 and 2016 to extract construction land in the Greater Bay, classify heat island intensity level and identify UHI regions. Then this paper used overall coupling model and spatial coupling model to reveal the coupling relationship between the construction land expansion and UHI expansion of the Greater Bay in different periods. The overall coupling situation was reflected by measuring the spatial overlap and change track consistency of land expansion and UHI expansion. And the spatial coupling relationship between the land expansion and UHI expansion was studied by using the revised coordination coefficient model. The results showed that: (1) From 2000 to 2016, the trend of construction land expansion and UHI expansion in the Greater Bay was synchronous. And the expansion rate between 2008 and 2016 was faster than that from 2000 to 2008; (2) The area of UHI increased constantly, and multiple UHI centers appeared. On the two sides of the Pearl River Estuary, an inverted "U" shaped UHI belt has been formed, which linked Zhongshan, Foshan, Guangzhou, Dongguan, Shenzhen and Hongkong; (3) The overall coupling situation of the construction land expansion and UHI in the Greater Bay was constantly strengthening. By 2016, the distance between the gravity center of the two types of indexes reached the nearest distance in the study period, and the overall coupling situation was also the greatest at this time. (4) During the research period, there was no serious imbalance of construction land expansion and UHI expansion in the Greater Bay. In the two types of index coupling types in the Greater Bay area, the space coupling categories of construction land expansion and UHI expansion were mainly coupling category, approximate coupling category and slightly uncoupling category. The degree of space coupling was high. And there was little change in the number of each category, but the number of "double high" coupled units was greatly increased.
The ice-snow tourism is becoming a new option for People who want to travel in the winter. Xinjiang is rich in ice and snow tourism resources. Therefore, it will be a problem of local tourism exploitation to be tackled immediately how to tap and utilize resources. From the light of tourism resources suitability, the thesis evaluates on the tourism resources suitability of researching zone, selecting 18 elements including natural conditions, tourism resources, social economy and transportation connectivity, taking Analytic Hierarchy Process (AHP) and Entropy Weight Method (EWM) to identify the group weight and using GIS spatial analysis and Multi-criteria Evaluation (MCE) model. The results show: (1)As natural condition goes, the eastern part of Yili District and the plain and the hills in the rim of Mountains in northern part of Altay District are suitable for ice-snow tourism; (2) The relevant infrastructure of the tourism resources are nearly self-contained in Altay and Urumqi. Changji District and Yili District are also competitive in tourism resources. (3)As for social economy, the cites in northern Xinjiang like Yili, Urumqi and Altay District are stronger in acceptance ability of visitors than that in Southern Xinjiang. (4) The traffic accessibility of the areas along the U-Chang economic belt and Yili District is clearly better than that in the cities in southern part of Xinjiang. The comprehensive suitability index of ice-snow tourism in Xinjiang is between 1.8622 and 7.5724, of which the north slopes of the Tianshan Mountains, north Altay District, Yili District, north Tacheng District, and central Hami District are in high suitability; Most part of southern Xinjiang are moderately suitable regions. For better development, we need to reinforce exploitation and coordination new tourism resources and actively undertake large snow sports competitions as well. We should take advantages of the Silk Road to develop cities' transportation, to accelerate the development of ice and snow tourism in Xinjiang. This study can provide spatial guidance and scientific evidence for ice-snow tourism development and site selection.
Under the background of global warming, the urban heat wave in summer has become one of the most serious meteorological disasters, which has brought tremendous impact on the health and economic development of urban residents. Taking the heat wave disaster event occurred in Nanjing from August 7 to 13, 2013 as an example, the near-surface air temperatures were estimated based on the downscaled MODIS land surface temperature using the Landsat 8 OLI image data, MODIS data products, and field-measurement meteorological data. Combined with the spatial interpolation data of the relative humidity, the hot index and the high temperature heat-wave index at the resolution of 100m were calculated, and then their spatial and temporal distribution characteristics were analyzed. The results show that during the evolution of the high temperature heat wave in Nanjing, the hot index increased firstly and then decreased with time. The hot index was highest on Aug. 11th with an average of 86.99, and it fell off to the lowest value of 85.05 on Aug. 12th; the heat wave intensity mainly concentrates on mild and moderate degrees, and its range also shows a tendency of expanding firstly and then decreasing with time. In terms of spatial distribution, the hot index is higher in northern region and central urban areas and mainly display as a moderate heat wave, while the heat index in the southern suburbs and central suburbs is lower and the heat wave is mild, and the mountain and the water areas have the lowest heat index.
Based on the 3S techniques and the Revised Universal Soil Loss Equation (RUSLE), we analyzed the spatial and temporal variation in water loss and soil erosion since 2000 for the special topography of the Huangfan Plain-Hilly area in Xuzhou. The results show that between 2000 and 2014 over Xuzhou area, the area for the micro degree of soil erosion grade took account for 76.34%, the moderate degree took account for 10%~17% and the strong degree took account for the least proportion. The micro degree area happened usually in the neighborhood of the downstream of the surrounding area of the Weishan Lake, hilly down land of the Grand Canal, main urban area, the Yellow River flood plain of abandoned yellow river’s left bank and the local area of Fengxian, Xinyi and Pizhou every year. The annual changes in erosion area around Suining, Fengxian and Pizhou were more obvious than the other areas and the total area of soil erosion was declining in general.
：Mangrove dynamics is one of the hotspots of geography, ecology and wetland science. Remote sensing technology is characterized by macroscopicity, high efficiency and economy, and plays an increasingly important role in the dynamic monitoring of mangroves. This paper searches and summarizes the articles published by Web of Science and China Knowledge Network from 2000 on the basis of keywords, from research area distribution, number of documents, remote sensing data sources and methods, global mangrove dynamics and national red The five aspects of dynamic change analysis of forests summarize the research progress on dynamic monitoring of mangrove remote sensing in the past 20 years. The research results show that multi-sensor high spatial and temporal resolution data will become an important data source for mangrove remote sensing dynamic monitoring. The fusion of radar data and optical remote sensing data will help to further enhance the mangrove satellite remote sensing monitoring capability. The UAV platform is equipped with various types of sensors (such as multi-spectral, hyperspectral or lidar sensors), which can obtain mangrove ecosystem parameters from different aspects. Combined with remote sensing intelligent analysis algorithms, it helps mangrove remote sensing research in the depth direction. development of. The total area of ??mangrove forests monitored by mangrove remote sensing is roughly 11 million to 24 million hectares , and the overall trend is still decreasing. In the region, the area of ??mangroves in China has recovered. At the end of this paper, the development trend of mangrove remote sensing dynamic monitoring is prospected.
The principle component analysis (PCA) technique, as one of the common method of extracting alteration information of remote sensing, is characterized by undemanding quality of atmospheric correction images, easily realization, effective, and steadily i.e., and is widely used by geologists. Based on the number and type of the input images and times of the PCA, this paper subdivided the PCA analysis into the standard principle component analysis (SPCA), feature oriented principal components selection (FPCS), directed principal component analysis (DPCA), the secondary principle component analysis and the principle component analysis of different images, of which the FPCS comprise four bands and three bands principle component analysis. Based on the above mentioned, every PCA and selection criteria have been systematically introduced, especially for the Crosta technique of the FPCS and the software defoliant technique of the DPCA. Images of TM/ETM+、ASTER are selected as examples to analyze the part of application techniques of PCA on extracting alteration information of remote sensing. The results indicate that different PCA all are in favor of extracting information of iron and clay alteration. The methods of SPCA, Crosta technique, modified Crosta technique, software defoliant technique and mask or inhibition of interference information+PCA have been effectively applicated in the medium-low vegetated-covered area. In contrast, in the high vegetated-cover area, the principle component of alteration information derived from PCA was adopted to conduct color composite. The resulted color images were then visual interpreted to estimate the type and extent of alteration. Among these techniques, the “Mask and Crosta technique”, the “Mask and software defoliant technique” and the secondary principle component analysis also can achieve good results in the high vegetated-cover area. For areas characterized by numerous kinds of interference information and complex lithology, firstly, it is practicable to divide the area into several sub-areas based on kinds of interference information and lithology; secondly, different methods of extracting alteration information should be proposed according to the features of every sub-areas; lastly, synthesizing alteration information extracted from every sub-areas.
Use of remote sensing indices to explain the changes and distribution in urban surface temperature has become a hot topic in the study of urban thermal environment. However, there are obvious differences in interpretation of surface temperature using the same remote sensing index in different studies. The reason for this is that when we use remote sensing index to explain the land surface temperature changes, the spatial differences caused by the interaction of different underlying surfaces are ignored. In this paper, we select Putian metropolitan area as study area to explain the spatial difference of LST using the 2016 Landsat 8 image as the data source. Three remote sensing indices were used for the explanation: normalized difference vegetation index (NDVI), normalized difference building index (NDBI), and modified normalized difference water index (MNDWI). Then we use GF2 image to extract land cover types during the same period. the LST and its relationship with remote sensing indices was anayzed for different underlying surfaces. Then we use the OLS and GWR methods to construct the remote sensing index-LST model, and analyzed the spatial autocorrelation for model residuals. The results show: (1)The underlying surface has a significant impact on LST. Due to the continuity of the geospatial space, LST appear abnormal changes between different underlying surfaces. For example, the high temperature area is mainly concentrated on the artificial surface, but LST drops near water or forest lands as compared to its values on pure artificial surface; (2) NDVI and MNDWI have different positive and negative correlations with LST in water area and non-water area due to their own value range characteristics, while NDBI shows a stable positive correlation when quantifying its relationship with LST. (3)Compared with the OLS model, GWR can better explain the relationship between the remote sensing index and LST by fully considering the spatial difference. Through the spatial autocorrelation analysis for model residuals, there is an aggregation of model residuals under OLS, while the model residual under GWR shows a random distribution. Compared to GWR, OLS has stronger spatial limitations in describing he relationship between remote sensing index and LST.
Quantitative estimation fractional cover of non-photosynthetic vegetation (fNPV) is critical for grassland ecosystem carbon storage, vegetation productivity, soil wind erosion. Remote sensing is an important tool for estimating the fractional cover of non-photosynthetic vegetation as a key descriptor of grassland ecosystem function. Developing tools that allow for monitoring of non-photosynthetic vegetation in space and time is a key step needed to improve management of grassland. In this paper, the data source of the ground-based measured endmember spactrum, mixed scenario spactrum and coverage information is presented. Firstly, we used the mean spectrum of NPV, PV and BS three components to simulate the mixed spectral through a linear spectral mixture model, and then the correlation between different multispectral indices and fNPV was evaluated. On this basis, explore the NDVI-DFI feature space correspond to the fundamental assumption of ternary linear mixed model. Finally, the validity of the estimate fNPV of multispectral index is verified by the field mixed scenario. The results show that the SWIR band is the sensitivity of the NPV, PV and BS, based on the improved OLI-DFI index are effective to distinguish the NPV, PV and BS potential. In the simulate mixed scenario, OLI-DFI and MODIS-DFI index correlated with fNPV, the coefficient of determination (R2) was 0.84 and 0.94, and root mean square error(RMSE) was 0.09 and 0.05(n=66, p<0.001). However, the NDI and NDSVI index correlation with fNPV is very low. Additionally, compared to simulate the mixing, in the field mixed scenario, OLI-DFI and MODIS- DFI index for estimating the effectiveness of the fNPV all have a certain degree of decline, R2 was 0.65 and 0.75, RMSE was 0.14 and 0.12, respectively. Based on the OLI data to construct the NDVI-DFI feature space to satisfy the fundamental assumption of ternary linear mixed model, which can effectively estimate the fNPV. The research will provide theoretical basis for the estimation of fNPV multispectral remote sensing.
Three multi-temporal remote sensing images of 2007, 2013 and 2016 were applied to retrieve the turbidity of the Aojiang River in Lianjiang county of Fujian province to investigate water quality change of the river caused by regional construction-induced soil erosion. The remotely sensed data were correlated with in situ measured water monitoring data to generate a statistical model used for retrieving water turbidity of the river. The results showed that the overall turbidity of the river in 2007 was low (23 NTU) and the spatial distribution of the river turbidity was relatively uniform because there was no obvious exploitation in the river area. However, the water turbidity was greatly enhanced in 2013 with a mean of near 40 NTU and the spatial distribution of the river turbidity became diverse. The turbidity in the river sections around the Guian New Area was nearly 3 times higher than that of upstream. The difference can be up to 60 NTU. This high turbidity water can be traced downstream for more than 13 km. The high water turbidity of the river in 2013 was due largely to the exploitation and construction practices near the river. The regional construction-induced soil erosion has brought massive mud and sand particles to the river and thus resulted in a high concentration of suspended particles of the river. The overall turbidity of 2016 was lower down as the construction of the Guian New Area was almost completed and the associated soil erosion has significantly decreased. The spatial distribution of the river turbidity returned to relatively uniform. Nevertheless, the turbidity in the river section close to the core of the Guian New Area was still high (39 NTU), which was about 5 NTU higher than that of upstream. The study also found that high turbidity of the river has reduced the dissolved oxygen content, leading to a poor water quality. With the current rapid urbanization process in China, the soil erosion induced in regional development should be taken into consideration in future construction practices to avoid their considerable impacts on the river's water quality.
