Construction of crash prediction model of freeway basic segment based on interactive influence of explanatory variables

In order to improve the prediction precision of the safety performance function （SPF） of freeway basic segments, design and crash data of 640 segments are collected from different institutions. Three negative binomial （NB） regression models and three generalized negative binomial （GNB） regression models are built to prove that the interactive influence of explanatory variables plays an important role in fitting goodness. The effective use of the GNB model in analyzing the interactive influence of explanatory variables and predicting freeway basic segments is demonstrated. Among six models, the two models （one is the NB model and the other is the GNB model. ） which consider the interactive influence of the annual average daily traffic （AADT） and length are more reasonable for predicting results. Furthermore, a comprehensive study is carried out to prove that when considering the interactive influence, the NB and GNB models have almost the same fitting performance in estimating the crashes, among which the GNB model is slightly better for prediction performance.

A Sequential Regression Model for Big Data with Attributive Explanatory Variables

As the applications for modeling of big data and analysis advance in scope,computational efficiency faces greater challenges in terms of storage and speed.In many practical problems,a great amount of historical data is sequentially collected and used for online statistical modeling.For modeling sequential data,we propose a sequential linear regression method that extracts essential information from historical data.This carefully selected information is then utilized to update a model according to a sequential estimation scheme.With this technique,the earlier data no longer needs to be stored,and the sequential updating is computationally efficient in speed and storage.A weighted strategy is introduced on the current model to determine the impact of data from different periods.When compared with estimation methods that use historical data,our numerical experiments demonstrate that our solution increases the speed while decreasing the storage load.

Rank-Ordering of Topographic Variables Correlated with Temperature

Spatial variations in temperature may be ascribed to many variables. Among these, variables pertaining to topography are prominent. Thus various topographic variables were calculated from 50 m-resolution digital terrain models (DTMs) for three study areas in France and for Slovenia. The “classic” geomatic variables (altitude, aspect, gradient, etc.) are supplemented by the description of landforms (amplitude of humps and hollows). Special care is taken in managing collinearity among variables and building windows with different dimensions. Statistical processing involves linear regressions of daily temperatures taken as the response variables and six topographic variables (explanatory variables). Altitude accounts significantly for the spatial variation in temperatures in 90% of cases, except in the Gironde, a lowlying area (50%). The scale of landforms also appears to be highly correlated to the measured temperature. Variations in the frequency with which topographic descriptors account for temperatures are examined from several standpoints. Altitude is less frequently taken as an explanatory variable for spatial variation of temperatures in winter (75%) than in spring (80%) and late summer (85%). Minimum temperatures are influenced on average much more by the amplitude of humps and hollows (56%) than maximum temperatures (38%) are. The frequency with which these two landforms account for the spatial variation of temperature is reversed between the minima and maxima.

Land use intensity dynamics in the Andhikhola watershed, middle hill of Nepal

Land use intensity is a valuable concept to understand integrated land use system, which is unlike the traditional approach of analysis that often examines one or a few aspects of land use disregarding multidimensionality of the intensification process in the complex land system. Land use intensity is based on an integrative conceptual framework focusing on both inputs to and outputs from the land. Geographers’ non-stationary data-analysis technique is very suitable for most of the spatial data analysis. Our study was carried out in the northeast part of the Andhikhola watershed lying in the Middle Hills of Nepal, where over the last two decades, heavy loss of labor due to outmigration of rural farmers and increasing urbanization in the relatively easy accessible lowland areas has caused agricultural land abandonment. Our intention in this study was to ascertain factors of spatial pattern of intensity dynamism between human and nature relationships in the integrated traditional agricultural system. High resolution aerial photo and multispectral satellite image were used to derive data on land use and land cover. In addition, field verification, information collected from the field and census report were other data sources. Explanatory variables were derived from those digital and analogue data. Ordinary Least Square(OLS) technique was used for filtering of the variables. Geographically Weighted Regression(GWR) model was used to identify major determining factors of land use intensity dynamics. Moran’s I technique was used for model validation. GWR model was executed to identify the strength of explanatory variables explaining change of land use intensity. Accordingly, 10 variables were identified having the greatest strength to explain land use intensity change in the study area, of which physical variables such as slope gradient, temperature and solar radiation revealed the highest strength followed by variables of accessibility and natural resource. Depopulation in recent decades has been a major driver of land use intensity change but spatial variability of land use intensity was highly controlled by physical suitability, accessibility and availability of natural resources.