首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 46 毫秒
1.
ABSTRACT

Geographically Weighted Regression (GWR) has been broadly used in various fields to model spatially non-stationary relationships. Multi-scale Geographically Weighted Regression (MGWR) is a recent advancement to the classic GWR model. MGWR is superior in capturing multi-scale processes over the traditional single-scale GWR model by using different bandwidths for each covariate. However, the multiscale property of MGWR brings additional computation costs. The calibration process of MGWR involves iterative back-fitting under the additive model (AM) framework. Currently, MGWR can only be applied on small datasets within a tolerable time and is prohibitively time-consuming to run with moderately large datasets (greater than 5,000 observations). In this paper, we propose a parallel implementation that has crucial computational improvements to the MGWR calibration. This improved computational method reduces both memory footprint and runtime to allow MGWR modelling to be applied to moderate-to-large datasets (up to 100,000 observations). These improvements are integrated into the mgwr python package and the MGWR 2.0 software, both of which are freely available to download.  相似文献   

2.
Geographically weighted regression (GWR) is an important local technique to model spatially varying relationships. A single distance metric (Euclidean or non-Euclidean) is generally used to calibrate a standard GWR model. However, variations in spatial relationships within a GWR model might also vary in intensity with respect to location and direction. This assertion has led to extensions of the standard GWR model to mixed (or semiparametric) GWR and to flexible bandwidth GWR models. In this article, we present a strongly related extension in fitting a GWR model with parameter-specific distance metrics (PSDM GWR). As with mixed and flexible bandwidth GWR models, a back-fitting algorithm is used for the calibration of the PSDM GWR model. The value of this new GWR model is demonstrated using a London house price data set as a case study. The results indicate that the PSDM GWR model can clearly improve the model calibration in terms of both goodness of fit and prediction accuracy, in contrast to the model fits when only one metric is singly used. Moreover, the PSDM GWR model provides added value in understanding how a regression model’s relationships may vary at different spatial scales, according to the bandwidths and distance metrics selected. PSDM GWR deals with spatial heterogeneities in data relationships in a general way, although questions remain on its model diagnostics, distance metric specification, and computational efficiency, providing options for further research.  相似文献   

3.
In this article, we respond to ‘A comment on geographically weighted regression with parameter-specific distance metrics’ by Oshan et al. (2019), published in this journal, where several concerns on the parameter-specific distance metric geographically weighted regression (PSDM GWR) technique are raised. In doing so, we review the developmental timeline of the multiscale geographically weighed regression modelling framework with related and equivalent models, including flexible bandwidth GWR, conditional GWR and PSDM GWR. In our response, we have tried to answer all the concerns raised in terms of applicability, veracity, interpretability and computational efficiency of the PSDM GWR model.  相似文献   

4.
Georeferenced user-generated datasets like those extracted from Twitter are increasingly gaining the interest of spatial analysts. Such datasets oftentimes reflect a wide array of real-world phenomena. However, each of these phenomena takes place at a certain spatial scale. Therefore, user-generated datasets are of multiscale nature. Such datasets cannot be properly dealt with using the most common analysis methods, because these are typically designed for single-scale datasets where all observations are expected to reflect one single phenomenon (e.g., crime incidents). In this paper, we focus on the popular local G statistics. We propose a modified scale-sensitive version of a local G statistic. Furthermore, our approach comprises an alternative neighbourhood definition that enables to extract certain scales of interest. We compared our method with the original one on a real-world Twitter dataset. Our experiments show that our approach is able to better detect spatial autocorrelation at specific scales, as opposed to the original method. Based on the findings of our research, we identified a number of scale-related issues that our approach is able to overcome. Thus, we demonstrate the multiscale suitability of the proposed solution.  相似文献   

5.
ABSTRACT

Geographically weighted regression (GWR) is a classic and widely used approach to model spatial non-stationarity. However, the approach makes no precise expressions of its weighting kernels and is insufficient to estimate complex geographical processes. To resolve these problems, we proposed a geographically neural network weighted regression (GNNWR) model that combines ordinary least squares (OLS) and neural networks to estimate spatial non-stationarity based on a concept similar to GWR. Specifically, we designed a spatially weighted neural network (SWNN) to represent the nonstationary weight matrix in GNNWR and developed two case studies to examine the effectiveness of GNNWR. The first case used simulated datasets, and the second case, environmental observations from the coastal areas of Zhejiang. The results showed that GNNWR achieved better fitting accuracy and more adequate prediction than OLS and GWR. In addition, GNNWR is applicable to addressing spatial non-stationarity in various domains with complex geographical processes.  相似文献   

6.
Scientific interpretation of the relationships between agricultural landscape patterns and urbanization is important for ecological planning and management. Ordinary least squares (OLS) regression is the primary statistical method in previous studies. However, this global regression lacks the ability to uncover some local-specific relationships and spatial autocorrelation in model residuals. This study employed geographically weighted regression (GWR) to examine the spatially varying relationships between several urbanization indicators (urbanization intensity index, distance to urban centers and distance to road) and changes in metrics describing agricultural landscape patterns (total area, patch density, perimeter area ratio distribution and aggregation index) at two block scales (5 km and 10 km). Results denoted that GWR was more powerful than OLS in interpreting relationships between agricultural landscape patterns and urbanization, since GWR was characterized by higher adjust R2, lower Akaike Information Criterion values and reduced spatial autocorrelations in model residuals. Character and strength of the relationships identified by GWR varied spatially. In addition, GWR results were scale-dependent and scale effects were particularly significant in three aspects: kernel bandwidth of weight determination, block scale of pattern analysis, and window size of local variance analysis. Homogeneity and heterogeneity in the relationships between agricultural landscape patterns and urbanization were subject to the coupled influences of the three scale effects. We argue that the spatially varying relationships between agricultural landscape patterns and urbanization are not accidental but nearly universal. This study demonstrated that GWR has the potential to provide references for ecological planners and managers to address agricultural landscapes issues at all scales.  相似文献   

7.
The geographically weighted regression (GWR) has been widely applied to many practical fields for exploring spatial non-stationarity of a regression relationship. However, this method is inherently not robust to outliers due to the least squares criterion in the process of estimation. Outliers commonly exist in data sets and may lead to a distorted estimate of the underlying regression relationship. Using the least absolute deviation criterion, we propose two robust scenarios of the GWR approaches to handle outliers. One is based on the basic GWR and the other is based on the local linear GWR (LGWR). The proposed methods can automatically reduce the impact of outliers on the estimates of the regression coefficients and can be easily implemented with modern computer software for dealing with the linear programming problems. We then conduct simulations to assess the performance of the proposed methods and the results demonstrate that the methods are quite robust to outliers and can retrieve the underlying coefficient surfaces satisfactorily even though the data are seriously contaminated or contain severe outliers.  相似文献   

8.
In recent years, the evolution and improvement of LiDAR (Light Detection and Ranging) hardware has increased the quality and quantity of the gathered data, making the storage, processing and management thereof particularly challenging. In this work we present a novel, multi-resolution, out-of-core technique, used for web-based visualization and implemented through a non-redundant, data point organization method, which we call Hierarchically Layered Tiles (HLT), and a tree-like structure called Tile Grid Partitioning Tree (TGPT). The design of these elements is mainly focused on attaining very low levels of memory consumption, disk storage usage and network traffic on both, client and server-side, while delivering high-performance interactive visualization of massive LiDAR point clouds (up to 28 billion points) on multiplatform environments (mobile devices or desktop computers). HLT and TGPT were incorporated and tested in ViLMA (Visualization for LiDAR data using a Multi-resolution Approach), our own web-based visualization software specially designed to work with massive LiDAR point clouds.  相似文献   

9.
Levels of spatial segregation in Western European cities are persistent over space and time. To demonstrate the degree or appearance of spatial segregation, most studies on urban residential patterns still rely on fixed spatial units, aspatial measures and single scales. However, a spatial or temporal comparison of patterns and levels of segregation based on such units or metrics is not without problems. To that end, this paper takes an explicit geographic approach and considers individualized neighborhoods using EquiPop-software, allowing various scales. Using the k-nearest neighbors for all individuals increases international comparability and facilitates interpretation, so far often hampered in segregation research. This multiscalar, multigroup comparative approach on ethnic urban geographies – using Belgium as a case study – provides an empirical illustration of a valuable method and tool applicable in segregation research, thereby furthering the comprehension of the increasingly diverse urban geographies and building on emerging work in the US, Europe and beyond.  相似文献   

10.
Over the last 20 years there has been a surge of interest in paleolimnology and as a result a large accumulation of lake sedimentation records. This emerging archive has allowed us to develop empirical models to describe which variables explain significant variation in sedimentation rates over the past ∼150 years across large spatial scales. We hypothesized that latitude would be a significant explanatory variable of profundal zone lake sedimentation rates across a temperate to polar gradient. We further hypothesized that along a more longitudinally-constrained dataset (i.e. east coast of North America), latitude would explain a greater proportion of the variance. To test these hypotheses, we collated data from 125 natural, average-sized lakes (with surface area <500 km2) by recording authors’ estimates of sedimentation rates (measured as mm/year) or by digitizing recent sediment profiles and calculating sedimentation rates over the past ∼150 years. We found that, at both scales, latitude was the strongest predictor of lake sedimentation rates (full dataset: r 2 = 0.28, P = 0.001, n = 125; east coast dataset: r 2 = 0.58, P < 0.001, n = 43). By conducting a multiple linear regression analysis, we found that 70% of the variance in sedimentation rates from the east coast transect was explained by latitude and elevation alone. This latter model is of sufficient strength that it is a robust predictive tool. Given that climate and land-use strongly co-vary with latitude and that both of these factors have previously been shown to influence lake sedimentation rates, it appears that latitude is a surrogate measure for climate and land-use changes. We also show support for land-use as an important variable influencing sedimentation rates by demonstrating large increases in recent versus Holocene accumulation rates. These results indicate that it is possible to make generalizations about sedimentation rates across broad spatial scales with even limited geographic data.  相似文献   

11.
Accurately mapping the spatial distribution of soil total nitrogen is important to precision agriculture and environmental management. Geostatistical methods have been frequently used for predictive mapping of soil properties. Recently, a local regression method, geographically weighted regression (GWR), got the attention of environmentalists as an alternative in spatial modeling of environmental attributes, due to its capability of incorporating various auxiliary variables with spatially varied correlation coefficients. The objective of this study is to compare GWR and ordinary cokriging (OCK) in predictive mapping of soil total nitrogen (TN) using multiple environmental variables. 353 soil Samples within the surface horizon of 0–20 cm in a study area were collected, and their TN contents were measured for calibrating and validating the GWR and OCK interpolations. The environmental variables finally chosen as auxiliary data include elevation, land use types, and soil types. Results indicate that, although OCK is slightly better than GWR in global accuracy of soil TN prediction (the adjusted R2 for GWR and OCK are 0.5746 and 0.6858, respectively), the soil TN map interpolated by GWR shows many details reflecting the spatial variations of major auxiliary variables while OCK smoothes out almost all local details. Geographically weighted regression could account for both the spatial trend and local variations, whilst OCK had difficulties to capture local variations. It is concluded that GWR is a more promising spatial interpolation method compared to OCK in predicting soil TN and potentially other soil properties, if a suitable set of auxiliary variables are available and selected.  相似文献   

12.
This study presents a growth curve developed from direct and indirect growth rates of Rhizocarpon geographicum lichens from study sites on Mounts Baker, Rainier, Adams, and Hood in the northern Cascade Range of the western USA. Our observations of direct growth rates are based on 31 measurements of 11 lichens growing on different surfaces. This direct growth rate dataset is complemented by indirect growth rates based on measurements of the largest lichen observed on 20 different surfaces over 24–33‐yr periods. The direct and indirect datasets produce statistically indistinguishable mean radial growth rates of 0.48 and 0.50 mm yr?1, respectively. Statistical analysis of zero and first order fits of our growth rate data suggests that lichen growth is best characterized by the average of our mean growth rate (zero order) models at 0.49 mm yr?1. Our revised growth curve for the study area extends the applicable range for dating rock surface in the study area to the seventeenth century, approximately 175 years longer than previous calibrated curves.  相似文献   

13.
ABSTRACT

The aim of this article is to describe a convenient but robust method for defining neighbourhood relations among buildings based on ordinary Delaunay diagrams (ODDs) and area Delaunay diagrams (ADDs). ODDs and ADDs are defined as a set of edges connecting the generators of adjacent ordinary Voronoi cells (points representing centroids of building polygons) and a set of edges connecting two centroids of building polygons, which are the generators of adjacent area Voronoi cells, respectively. Although ADDs are more robust than ODDs, computation time of ODDs is shorter than that of ADDs (the order of their computation time complexity is O(nlogn)). If ODDs can approximate ADDs with a certain degree of accuracy, the former can be used as an alternative. Therefore, we computed the ratio of the number of ADD edges to that of ODD edges overlapping ADDs at building and regional scales. The results indicate that: (1) for approximately 60% of all buildings, ODDs can exactly overlap ADDs with extra ODD edges; (2) at a regional scale, ODDs can overlap approximately 90% of ADDs with 10% extra ODD edges; and (3) focusing on judging errors, although ADDs are more accurate than ODDs, the difference is only approximately 1%.  相似文献   

14.
Landscape pattern is an important determinant of soil contamination at multiple scales, and a proper understanding of their relationship is essential for alleviating soil contamination and making decisions for land planners. Both soil contamination and landscape patterns are heterogeneous across spaces and scale-dependent, but most studies were carried out on a single scale and used the conventional multivariate analyses (e.g. correlation analysis, ordinary least squared regression-OLS) that ignored the issue of spatial autocorrelation. To move forward, this paper examined spatially varying relationships between agricultural soil trace metal contamination and landscape patterns at three block scales (i.e. 5 km × 5  km, 10 km × 10 km, 15 km × 15 km) in the Pearl River Delta (PRD), south China, using geographically weighted regression (GWR). This paper found that GWR performed better than OLS in terms of increasing R square of the model, lowering Akaike Information Criterion values and reducing spatial autocorrelation. GWR results revealed great spatial variations in the relationships across scales, with an increasing explanatory power of the model from small to large block scales. Despite a few negative correlations, more positive correlations were found between soil contamination and different aspects of landscape patterns of water, urban land and the whole landscape (i.e. the proportion, mean patch area, the degree of landscape fragmentation, landscape-level structural complexity, aggregation/connectivity, road density and river density). Similarly, more negative correlations were found between soil contamination and landscape patterns of forest and the distance to the river and industry land (p < 0.05). Furthermore, most significant correlations between soil contamination and landscape variables occurred in the western PRD across scales, which could be explained by the prevailing wind, the distribution of pollutant sources and the pathway of trace metal inputs.  相似文献   

15.
By incorporating temporal effects into the geographically weighted regression (GWR) model, an extended GWR model, geographically and temporally weighted regression (GTWR), has been developed to deal with both spatial and temporal nonstationarity simultaneously in real estate market data. Unlike the standard GWR model, GTWR integrates both temporal and spatial information in the weighting matrices to capture spatial and temporal heterogeneity. The GTWR design embodies a local weighting scheme wherein GWR and temporally weighted regression (TWR) become special cases of GTWR. In order to test its improved performance, GTWR was compared with global ordinary least squares, TWR, and GWR in terms of goodness-of-fit and other statistical measures using a case study of residential housing sales in the city of Calgary, Canada, from 2002 to 2004. The results showed that there were substantial benefits in modeling both spatial and temporal nonstationarity simultaneously. In the test sample, the TWR, GWR, and GTWR models, respectively, reduced absolute errors by 3.5%, 31.5%, and 46.4% relative to a global ordinary least squares model. More impressively, the GTWR model demonstrated a better goodness-of-fit (0.9282) than the TWR model (0.7794) and the GWR model (0.8897). McNamara's test supported the hypothesis that the improvements made by GTWR over the TWR and GWR models are statistically significant for the sample data.  相似文献   

16.
Terrain attributes such as slope gradient and slope shape, computed from a gridded digital elevation model (DEM), are important input data for landslide susceptibility mapping. Errors in DEM can cause uncertainty in terrain attributes and thus influence landslide susceptibility mapping. Monte Carlo simulations have been used in this article to compare uncertainties due to DEM error in two representative landslide susceptibility mapping approaches: a recently developed expert knowledge and fuzzy logic-based approach to landslide susceptibility mapping (efLandslides), and a logistic regression approach that is representative of multivariate statistical approaches to landslide susceptibility mapping. The study area is located in the middle and upper reaches of the Yangtze River, China, and includes two adjacent areas with similar environmental conditions – one for efLandslides model development (approximately 250 km2) and the other for model extrapolation (approximately 4600 km2). Sequential Gaussian simulation was used to simulate DEM error fields at 25-m resolution with different magnitudes and spatial autocorrelation levels. Nine sets of simulations were generated. Each set included 100 realizations derived from a DEM error field specified by possible combinations of three standard deviation values (1, 7.5, and 15 m) for error magnitude and three range values (0, 60, and 120 m) for spatial autocorrelation. The overall uncertainties of both efLandslides and the logistic regression approach attributable to each model-simulated DEM error were evaluated based on a map of standard deviations of landslide susceptibility realizations. The uncertainty assessment showed that the overall uncertainty in efLandslides was less sensitive to DEM error than that in the logistic regression approach and that the overall uncertainties in both efLandslides and the logistic regression approach for the model-extrapolation area were generally lower than in the model-development area used in this study. Boxplots were produced by associating an independent validation set of 205 observed landslides in the model-extrapolation area with the resulting landslide susceptibility realizations. These boxplots showed that for all simulations, efLandslides produced more reasonable results than logistic regression.  相似文献   

17.
Abstract

The potentially severe strain that subnormal winter temperatures would impose upon reduced heating fuel supplies prompted publication of a long-range, national, winter weather forecast in November 1973. However, limitation of the art of weather forecasting that stem ultimately from the complex episodic nature of weather behavior diminish the reliability of this outlook. In spite of the complexity encountered along the way, a journey into weather records of the past does reveal some observations about weather activity that are useful in assessing winter temperature prospects. These observations include the characteristic nonuniformity of weather behavior, the existence of long-range and seasonal climatic trends, and the thermal effects of early-season establishment of a heavy snow cover.  相似文献   

18.
ABSTRACT

Defining and identifying duplicate records in a dataset is a challenging task which grows more complex when the modeled entities themselves are hard to delineate. In the geospatial domain, it may not be clear where a mountain, stream, or valley ends and begins, a problem carried over when such entities are catalogued in gazetteers. In this paper, we take two gazetteers, GeoNames and SwissNames3D, and perform matching – identifying records in each that are about the same entity – across a sample of natural feature records. We first perform rule-based matching, establishing competitive results, then apply machine learning using Random Forests, a method well-suited to the matching task. We report on the performance of a wider array of matching features than has been previously studied, including domain-specific ones such as feature type, land cover class, and elevation. Our results show an increase in performance using machine learning over rules, with a notable performance gain from considering feature types, but negligible gains from other specialized matching features. We argue that future work in this area should strive to be more reproducible and report results on a realistic testing pipeline including candidate selection, feature extraction, and classification.  相似文献   

19.
Theory suggests that with sufficient environmental variation, pollen limitation might be observed at some places or times, and resource limitation at others, but there are no empirical data about the effect of seasonal change on the variation of pollen limitation and resource limitation within a flowering season. In this study, we examined pollen and resource limitation by comparing fruit set and seed production in natural- and hand-pollinated Hedysarum scoparium flowers in the middle reaches of the Hexi Corridor region, China, in 2010. We also described a role for the first substantial autumn rainfall in mediating a shift between pollen and resource limitation in H. scoparium, but did not analyze this experimentally. Our results indicated that H. scoparium was resource limited at peak flowering during the summer, and was pollen limited at peak flowering during the autumn. The seasonal change (summer to autumn) mediated the shift between pollen and resource limitations in H. scoparium. The shift timing depended on the date of the first autumn rainfall in 2010. Changes in the first substantial rainfall in autumn may affect fruiting of H. scoparium, thus affecting population persistence of this species and development/structure of the local ecosystem if such conditions persist.  相似文献   

20.
There has been long and wide-ranging debate in the social science literature about how best to conceptualise and to measure segregation. A popular measure is the dissimilarity index, usually attributed to Duncan and Duncan who were aware of its geographical limitations – that it, like most indices, is invariant to the precise spatial patterning of the segregation measured. Whilst one response to this shortcoming has been to develop a spatial adjustment, a number of papers from the 1980s and 1990s took the approach of treating the measurement as a (spatial) optimisation problem. This paper revisits that optimisation literature, arguing that what was computationally prohibitive in the past is now possible in the open-source software, R, and emblematic of the sorts of problem that might be more routinely solved in a cyberinfrastructure tailored to geographical analysis. Applying this method to UK Census data for London, and comparing the optimisation measure with the standard and adjusted dissimilarity indices, claims of ethnic desegregation are considered.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号