Geographically And Temporally Weighted Regression Research Articles

Analyzing the relationship between air pollution and various types of crime.

Air pollution has a severe impact on human physical and mental health. When the air quality is poor enough to cause respiratory irritation, people tend to stay home and avoid any outdoor activities. In addition, air pollution may cause mental health problems (depression and anxiety) which were associated with high crime risk. Therefore, in this study, it is hypothesized that increasing air pollution level is associated with higher indoor crime rates, but negatively associated with outdoor crime rates because it restricts people’s daily outdoor activities. Three types of crimes were used for this analysis: robbery (outdoor crime), domestic violence (indoor crime), and fraud (cybercrime). The results revealed that the geographically and temporally weighted regression (GTWR) model performed best with lower AIC values. In general, in the higher population areas with more severe air pollution, local authorities should allocate more resources, extra police officers, or more training programs to help them prevent domestic violence, rather than focusing on robbery.

Driving Factors for the Spatiotemporal Heterogeneity in Technical Efficiency of China’s New Energy Industry

The new energy industry (NEI) is key to achieving a clean and low-carbon economy. Improving its technical efficiency, a factor reflecting the ability of an enterprise or industry to produce maximum economic outputs from a given set of inputs and production technologies, is vital for the healthy development of the NEI. Nevertheless, due to the fragmentation of industry data, it is still difficult to accurately measure the technical efficiency of China’s NEI and understand the driving factors behind it. Based on the panel data derived from 17,457 observations on new energy enterprises in 29 Chinese provinces during 1998 and 2013 (latest data available), this paper uses data envelopment analysis (DEA) and geographically and temporally weighted regression (GTWR) for the first time to investigate the spatiotemporal characteristics and driving factors of the technical efficiency of China’s NEI. The results show that the technical efficiency of China’s NEI was relatively low and increased modestly from 0.44 in 1998 to 0.52 in 2013. Exploring the reasons from the perspective of spatiotemporal heterogeneity, we find that enterprise scale and technological progress are the major driving factors for increasing NEI’s technical efficiency. However, the role of economic development in improving efficiency has gradually disappeared. Moreover, the negative effect of state-owned enterprises on efficiency becomes increasingly obvious. The effect of new energy resources is negligible. Our main contribution is the technical efficiency of China’s NEI which is measured at the provincial level and its main driving factors are explored by considering spatiotemporal heterogeneity. Accordingly, we put forward some specific recommendations to improve the technical efficiency of China’s NEI.

Characterizing the complex influence of the urban built environment on the dynamic population distribution of Shenzhen, China, using geographically and temporally weighted regression

Big data can provide new insights for smart city planning. This study exploits mobile-phone locating-request (MPLR) data as a proxy for real-time intra-urban population distribution. It models the relationship between the dynamic population distribution and the urban built environment using geographically and temporally weighted regression (GTWR), which can account for spatial and temporal non-stationarity simultaneously. A case study is undertaken based on MPLR records in Shenzhen, China and points of interest-based urban environment data aggregated to grid zones. Compared with previous models, GTWR yields a better result. Furthermore, the spatiotemporal coefficients are analyzed and compared. The results suggest that the patterns of urban population distribution are more complex during weekends than during weekdays. The coefficients of the company density variable are significantly higher during weekdays than weekends, while the coefficients associated with residential buildings are lower during weekday afternoons. Hence, the urban built environment plays an important role in the dynamic distribution of the population at different times. The findings show that the GTWR model in combination with MPLR and points of interest-based urban environment data can assist urban planners in gaining a better understanding of the spatiotemporal dynamics of the population distribution, thereby providing potential inputs to the rational allocation of public resources over space and time.

Mixed geographically and temporally weighted regression for spatio-temporal deformation modelling

When the regression coefficient of independent variable has both global stationarity and spatio-temporal non-stationarity properties, the deformation model based on the geographically and temporally weighted regression (GTWR) will no longer be applicable. In order to resolve this problem, we propose an improved method to establish the spatio-temporal deformation model using mixed geographically and temporally weighted regression (MGTWR). In this method, both the global regression coefficient and the variable regression coefficient are selected for regression coefficient hypothesis test, and the local linear two-step estimation method is used to fit the MGTWR model. A dam deformation modelling example shows that the MGTWR model improves the average prediction accuracy by 57.6% compared to the GTWR model when the regression coefficients have both global stationarity and spatio-temporal non-stationarity properties.

Coupling coordination analysis and spatiotemporal heterogeneity between urbanization and ecosystem health in Chongqing municipality, China

Rapid urbanization has seriously disturbed the structure and function of ecosystems and caused many eco-environmental problems, in turn, these problems also reduce the quality of urbanization and threaten the sustainable development of urban. Currently, most studies only focus on the impact of urbanization on ecosystem components (i.e., structure, functions or services), few studies have explored the coordination and spatiotemporal heterogeneity between urbanization and ecosystem health from a systematic view. Therefore, in viewing of this, this study integrated coupling coordination degree model (CCDM) and geographically and temporally weighted regression (GTWR) to measure the interaction relationship and spatiotemporal heterogeneity between urbanization and ecosystem health (UAEH) in Chongqing at the county scale from 1997 to 2015. Results showed that: 1) the degree of coordination between UAEH in Chongqing increased gradually from 1997 to 2015, developed from the moderately unbalance stage to moderately balance stage, and experienced a transition from urbanization lag to ecosystem health lag. Moreover, the coupling coordination degree showed a decreased spatial trend from the western to the eastern of Chongqing. 2) The restriction effect between UAEH gradually weakened from 1997 to 2015, and the synergistic effect between them gradually strengthened. Additionally, the interaction between UAEH tended to converge, and the negative effects between UAEH were mainly distributed in the central and western of Chongqing. In these area, population urbanization aggravated the deterioration of the natural ecosystem, in turn, the decline of ecosystem vigor and resilience also restricted the sustainable development of urbanization. Finally, this study also puts forward some corresponding policy recommendations based on each region's coupling type.

Decoupling relationship between haze pollution and economic growth: A new decoupling index

Economic development is accompanied by the production of pollutants. Coordinating the relationship between economic development and haze pollution is of great significance to future development in China. Based on the original decoupling index (Tapio decoupling index), this study developed a new decoupling index that overcomes some of the original defects and highlights the trends to a better extent. It also analyzes the transformation relationship among the new decoupling index, the original decoupling index and the EKC curve. Firstly, we compared the changing trends of the two decoupling indexes and then derived the factors that influence the new and original decoupling indexes based on C-D-Kaya equation. Finally, we compared the factors influencing the two decoupling indexes from the perspective of decomposition analysis and measurement. The conclusions are as follows: (1) Based on the limit theory, the boundary point for relative decoupling and absolute decoupling derived from the original decoupling index can be used to determine the inflection point of the EKC curve. The new decoupling index can also reflect this property. At the inflection point of the EKC curve, the ratio of the new decoupling index of two adjacent periods satisfies equation (12), which is only related to GDP. (2) In 2003, the new decoupling index showed a downward trend, and the fluctuation was smaller than that of the original decoupling index. The original decoupling index is more sensitive to short-term policies than the new decoupling index, but the new decoupling index is more conducive to the comprehensive analysis of China’s decoupling trend. (3) After decomposing the new decoupling index and the original decoupling index, per capita GDP and the emission coefficient are the largest positive and negative driving forces, respectively. However, the trend of the contribution made by each factor was more obvious when the new decoupling index was used. The emission coefficient for Shandong made the largest negative contribution, and the per capita GDP for Shanxi made the greatest positive contribution. (4) The geographically and temporally weighted regression (GTWR) analysis showed that the fitting degree of the new decoupling index is much higher than that of the original decoupling index. The analysis of the influencing factors affecting the new decoupling index showed that there was temporal and spatial heterogeneity among the factors in east, middle, and west China, and there were significant differences in the impacts due to energy structure, energy intensity, technological progress, and urban population factors, respectively. These findings will significantly improve the formulation of efficient and pertinent policies for energy conservation and haze reduction.

Geographically and temporally weighted neural network for winter wheat yield prediction

Accurate prediction of crop yield is essential for agricultural trading, market risk management and food security. Although various statistical models and machine learning models have been developed to enhance prediction accuracy, spatial and temporal non-stationarity, an intrinsic attribute of many geographical processes, is still rarely considered in crop yield modeling. From a statistical point of view, this study respectively provided evidence for the existence of spatial non-stationarity and temporal non-stationarity in winter wheat yield prediction based on geographically weighted regression (GWR) and temporally weighted regression (TWR). Then, a geographically and temporally weighted neural network (GTWNN) model was proposed by integrating artificial neural network (ANN) into geographically and temporally weighted regression (GTWR) using publicly available data sources, including satellite imagery and climate data. For a more credible evaluation, the leave-one-year-out strategy was adopted to make out-of-sample prediction resulting in a total of 12 test years from 2008 to 2019. The experiment results showed that the proposed GTWNN outperformed ANN, GTWR and support vector regression (SVR) achieving the average coefficient of determination (R2) values of 0.766, 0.759 and 0.720 at the three prediction times of end of July, end of June and end of May. Moreover, an extended Moran's I was adopted to assess the degree of spatiotemporal autocorrelation of the prediction errors. The error aggregation of GTWNN was lower than other models, indicating that GTWNN is applicable to addressing spatial non-stationarity in modeling the relationship between predictors and yield response. The methodology proposed in this paper can be extended to handle spatiotemporal non-stationarity in other crop yield predictions and even other environmental phenomena.

Multiscale geographically and temporally weighted regression with a unilateral temporal weighting scheme and its application in the analysis of spatiotemporal characteristics of house prices in Beijing

ABSTRACT Geographically and temporally weighted regression (GTWR) has been demonstrated as an effective tool for exploring spatiotemporal data under spatial and temporal heterogeneity. Exploiting the advantages of the two most popular GTWR methods, we propose an alternative GTWR with a good balance between complexity and interpretability via a unilateral temporal weighting scheme called unilateral GTWR (UGTWR). When compared to the other two popular GTWR methods, the simulation experiment shows that UGTWR has comparable estimation accuracy and model fit, but it is more efficient. Furthermore, we propose its multiscale extension, coined multiscale UGTWR (MUGTWR), to characterize the spatiotemporal dynamic regression relationships at multiple scales. The proposed MUGTWR was applied to the analysis of house prices in the period of 2014–2018 in Beijing as a case study. Our analysis reveals that MUGTWR can effectively capture different levels of spatiotemporal heterogeneity in selected factors affecting house prices at different scales. Therefore, this study is useful for the formulation of housing policy in which the spatiotemporal dynamics of house prices with respect to specific factors can be considered.

Understanding how relationships between crash frequency and correlates vary for multilane rural highways: Estimating geographically and temporally weighted regression models

Safety Performance Functions (SPFs) are critical tools in the management of highway safety projects. SPFs are used to predict the average number of crashes per year at a location, such as a road segment or an intersection. The Highway Safety Manual (HSM) provides default safety performance functions (SPFs), but it is recommended that states in the U.S. develop jurisdiction-specific SPFs using local crash data. To do this for the state of Tennessee, crash and road inventory data were integrated for multi-lane rural highway segments for the years 2013−2017. In addition to developing SPFs similar to those contained in the HSM, this study applied a new methodology to capture variation in crashes in both space and time. Specifically, Geographically and Temporally Weighted Regression (GTWR) models for the localization of SPFs were developed. The new methodology incorporates temporal aspects of crashes in the models because the impact of a specific variable on crash frequency may vary over time due to several reasons. Results indicate that GTWR models remarkably outperform the traditional regression models by capturing spatio-temporal heterogeneity. Most parameter estimates were found to vary substantially across space and time. In other words, the association of contributing variables with the number of crashes can vary from one region or period of time to another. This finding weakens the idea of transferring default SPFs to other states and applying a single localized SPF to all regions of a state. Enabled by growing computational power, these results emphasize the importance of accounting for spatial and temporal heterogeneity and developing highly localized SPFs. The methodology of this study can be used by researchers to follow the temporal trend and location of critical factors to identify sites for safety improvements.

Modeling the Spatiotemporal Association Between COVID-19 Transmission and Population Mobility Using Geographically and Temporally Weighted Regression.

The ongoing Coronavirus Disease 2019 (COVID‐19) has posed a serious threat to human public health and global economy. Population mobility is an important factor that drives the spread of COVID‐19. This study aimed to quantitatively evaluate the impact of population flow on the spread of COVID‐19 from a spatiotemporal perspective. To this end, a case study was carried out in Hubei Province, which was once the most affected area of COVID‐19 outbreak in Mainland China. The geographically and temporally weighted regression (GTWR) model was applied to model the spatiotemporal association between COVID‐19 epidemic and population mobility. Two patterns of population flows, including the population inflow from Wuhan and intra‐city population movement, were considered to construct explanatory variables. Results indicate that the GTWR model can reveal the spatial–temporal‐varying relationships between COVID‐19 and population mobility. Moreover, the association between COVID‐19 case counts and population movements presented three stages of temporal variation characteristics due to the virus incubation period and implementation of strict lockdown measures. In the spatial dimension, evident geographical disparities were observed across Hubei Province. These findings can provide policymakers useful knowledge about the impact of population movement on the spatio‐temporal transmission of COVID‐19. Thus, targeted interventions, if necessary in certain time periods, can be implemented to restrict population flow in cities with high transmission risk.

Penerapan Model Geographically Dan Temporally Weighted Regression Pada Kecelakaan Lalu Lintas

Geographically and temporally weighted regression (GTWR) is a model that is used to deal with instability in data both spatially and temporally and to produce local parameters. In this paper, The GTWR model is used to analyze the factors that are thought to significantly influence the number of traffic accidents in Mempawah Regency. The data used in this study came from 8 districts with the variables used were the number of traffic accidents, the number of population (gender ratio, length of damaged road conditions, and percentage of adolescence. The parameter estimation of the GTWR model was obtained using the weighted least square (WLS) method. The optimal bandwidth selection uses the Cross-Validation (CV) method and the weighting used is the Fixed bisquare function. The results of the analysis show that using the GTWR model, it was found that only the population size variable significantly affected the number of traffic accidents in all locations in Mempawah Regency from 2015 to 2018. The GTWR model was known to be better than the multiple regression model because it produced smaller AIC and RSS values and a larger R-square value.

Spatiotemporal pattern analysis of PM2.5 and the driving factors in the middle Yellow River urban agglomerations

During the development of the Middle Yellow River Urban Agglomerations (Central Plains Urban Agglomeration (CPUA), Guanzhong Plains Urban Agglomeration (GPUA), Jinzhong Urban Agglomeration (JZUA)), “urban disease” was prominent, and the concentrations of PM2.5 in many cities in the region were ultra-high, resulting in serious air pollution. Taking into account the hysteresis of PM2.5 pollution, from the point of view of socioeconomic, this paper uses the geographically and temporally weighted regression (GTWR) model and the latest available data of PM2.5 concentration and socio-economic factors of the urban agglomeration in the Middle Yellow River from 2015 to 2018 to explore the spatiotemporal heterogeneity of PM2.5 concentrations and the driving factors. The results indicate that: (1) The spatiotemporal distribution profiles of PM2.5 concentrations in urban agglomerations in the middle Yellow River have certain regularities. It reveals a U-shaped pattern in each year, and the seasonal changes show the spring and winter are high and summer and autumn are low. (2) PM2.5 in the Middle Yellow River Urban Agglomerations has obvious spatial agglomeration characteristics. (3) There are obvious spatiotemporal heterogeneity in the change of the intensity and direction of each driving factor. Based on the above analysis, three suggestions were put forward: (1) Increase the proportion of new energy in heating. (2) Establish regional joint prevention and control and long-term incentive mechanisms. (3) Different urban agglomerations should formulate differentiated PM2.5 emission reduction strategies.

Spatio-Temporal Non-Stationarity and Its Influencing Factors of Commercial Land Price: A Case Study of Hangzhou, China

Investigating the characteristics and mechanisms of the spatial and temporal variations of commercial land prices and its major subdivisions has great theoretical and practical significance in the study of urban economy and its spatial refinement management. Unlike general commodity prices, land prices are influenced by geographical location and tend to fluctuate over time. However, most scholars have not explored the influence mechanism of commercial land prices in both time and space. To help bridge this gap, this study takes the sample commercial land prices in the main urban area of Hangzhou from 2006 to 2015 as the empirical research object and investigates the spatiotemporal evolution mechanism of urban commercial land prices through a comparative analysis of the multiple regression analysis (MRA) with ordinary least squares (OLS), the geographically weighted regression (GWR), the temporally weighted regression (TWR), and the geographically and temporally weighted regression (GTWR) models. Results indicate that the land prices of land for financial facilities (Commercial Land Category 1) and commercial-business land (Commercial Land Category 2) in Hangzhou show different spatial and temporal evolutions and are influenced by the common factors of residential land price level (PL), maturity of living services (EN), and plot ratio (FRO) in the district. Meanwhile the main difference between the two influencing factors is the significant difference in sensitivity to locational centrality and industrial structure. Furthermore, we find that the spatial and temporal evolution of commercial land prices has three main mechanism: location selection, point-axis evolution, and function-promoting. Our findings will provide guidelines for scientifically guiding the coordinated development of urban land price and industrial economy and realizing the fine management and allocation of urban spatial resources.

A Two-Step Integrated MLP-GTWR Method to Estimate 1 km Land Surface Temperature with Complete Spatial Coverage in Humid, Cloudy Regions

There is an increasing demand for a land surface temperature (LST) dataset with both fine spatial and temporal resolutions due to the key role of LST in the Earth’s land–atmosphere system. Currently, the technique most commonly used to meet the demand is thermal infrared (TIR) remote sensing. However, cloud contamination interferes with TIR transmission through the atmosphere, limiting the potential of space-borne TIR sensors to provide the LST with complete spatio-temporal coverage. To solve this problem, we developed a two-step integrated method to: (i) estimate the 10-km LST with a high spatial coverage from passive microwave (PMW) data using the multilayer perceptron (MLP) model; and (ii) downscale the LST to 1 km and fill the gaps based on the geographically and temporally weighted regression (GTWR) model. Finally, the 1-km all-weather LST for cloudy pixels was fused with Aqua MODIS clear-sky LST via bias correction. This method was applied to produce the all-weather LST products for both daytime and nighttime during the years 2013–2018 in South China. The evaluations showed that the accuracy of the reproduced LST on cloudy days was comparable to that of the MODIS LST in terms of mean absolute error (2.29–2.65 K), root mean square error (2.92–3.25 K), and coefficients of determination (0.82–0.92) against the in situ measurements at four flux stations and ten automatic meteorological stations with various land cover types. The spatial and temporal analysis showed that the MLP-GTWR LST were highly consistent with the MODIS, in situ, and ERA5-Land LST, with the satisfactory ability to present the LST pattern under cloudy conditions. In addition, the MLP-GTWR method outperformed a gap-filling method and another TIR-PMW integrated method due to the local strategy in MLP and the consideration of temporal non-stationarity relationship in GTWR. Therefore, the test of the developed method in the frequently cloudy South China indicates the efficient potential for further application to other humid regions to generate the LST under cloudy condition.

Spatial-interaction network analysis of built environmental influence on daily public transport demand

Many studies have evaluated the influence of the built environment on public transport. Some studies assign subjective weights to environmental factors, which could oversimplify spatial heterogeneity and overlook the temporal dimension. On the other hand, the spatial-interaction network of public transport system is seldom considered. In this paper, we propose an improved framework to explore how individual factors unevenly affect public transport demand over space and time using a geographically and temporally weighted regression (GTWR) model. The proposed framework extends the local built environmental factors by including two network factors extracted from the spatial-interaction network of the public transport system. We conduct a case study in Beijing, China using 686 traffic analysis zones (TAZs). The actual usage of public transport, namely the public transport index (PTI), is estimated by passenger flow divided by the total amount of human flow in a given TAZ. The daily patterns of the spatial heterogeneity in some selected places in the study area is identified and analyzed. It is also found that the estimated coefficient of the variables of the spatial-interaction network is significantly larger than other static environmental factors, indicating that spatial-interaction network can more effectively reflect spatiotemporal heterogeneity in public transport demand. This study provides a better decision-making support for more accurately identifying which factors are most worthy of development, and when and where they can be implemented to improve public transit services.

Mixed Geographically and Temporally Weighted Autoregressive to Modeling the Levels of Poverty Population in Java in 2012-2018

Geographically and temporally weighted regression (GTWR) is a method applied when there is spatial and temporal diversity in the observation. In the GTWR model not all variables were local or insignificant (global in nature) so the GTWR model was developed into Mixed Geographically and Temporally Weighted Regression (MGTWR). The GTWR model can also add an autoregressive component of response variable, the resulting model is known as a geographically and temporally weighted autoregressive model (GTWAR). This study develops the MGTWR model and the GTWAR model which produces a Geographically and Temporally Weighted Autoregressive model (MGTWAR) which is used to model data on the percentage of poor people in regency/municipality on Java Island in 2012-2018. The results showed that MGTWAR produced Akaike Information Criterion (AIC) smaller than GTWR, and the coefficient of determination (R2) is higher than GTWR.

Geographically and Temporally Weighted Regression Model with Gaussian Kernel Weighted Function and Bisquare Kernel Weighted Function

The Geographically and Temporally Weighted Regression (GTWR) model is a development of the Geographically Weighted Regression (GWR) model. Estimation of parameters in the GTWR model uses Weighted Least Square (WLS). The purpose of this study is to build two GTWR models using the Gaussian kernel weight function and the Bisquare kernel weight function on the percentage of poor people in East Java Province in 2010-2015. Each weighted function produces 228 different models at each location and time. The GTWR method with the Gaussian Kernel weight function produces parameter estimates at the observation location in the range between 0.7796 to 48.1435. Meanwhile, the parameter estimation of the GTWR model with the Kernel Bisquare weight function ranges from 0.7828 to 48.1444. The two weight functions can model the percentage of poor people in East Java Province in 2010-2015, with R2 values of 98.994% and 98.987%, respectively.

Spatiotemporal effects of climate factors on childhood hand, foot, and mouth disease: a case study using mixed geographically and temporally weighted regression models

ABSTRACT Hand, foot, and mouth disease (HFMD) is a global infectious disease severely threatening children’s health. It has been recognized that climate factors play an important role in the transmission of HFMD. In this paper, the bootstrap test in the geographically weighted regression (GWR) literature is extended to geographically and temporally weighted regression (GTWR) models for identifying homogeneous explanatory variables and spatiotemporally heterogeneous ones. The resulting mixed GTWR model is then used to investigate spatiotemporal effect of climate factors on the HFMD incidence in Inner Mongolia, China, a provincial autonomous region with extensive area and different climatic conditions. The results demonstrate that the effect of relative humidity is global over space and time, while that of air temperature, air pressure and wind speed varies spatiotemporally. The extended bootstrap test provides a solid statistical basis for model selection. The findings from the study may provide not only a deep understanding of spatiotemporal variation characteristics of the climatic effect on the HFMD incidence, but also some useful evidences for taking measures of the disease prevention and control at the county level in different seasons.

Regional differences and driving factors analysis of carbon emission intensity from transport sector in China

Realizing the coordinated development of regional emission reduction and low-carbon transportation has become a hot issue concerned by governments worldwide. Using data from 30 provinces of China’s transport sector, this paper investigates and evaluates the regional differences of carbon emission intensity (CEI). Additionally, we employ the extended STIRPAT (stochastic impacts by regression on population, affluence and technology) and GTWR (geographically and temporally weighted regression) model to reveal the influence of driving factors on CEI from spatial-temporal perspectives. The results indicate the following: (1) CEI tends to decrease and presents a pattern of low in the southeast and high in the northwest in space. (2) The eastern region has the greatest degree of regional difference, and the central region has the smallest. The major reason for the widening of the overall differences in China is the within-group differences in the three geographical regions. (3) CEI in China’s transport sector has regional characteristics, and the effect of urbanization, energy structure, population scale and industrial structure on CEI vary among the regions. Energy intensity occupies a pivotal position among all the driving factors and poses a positive impact on the CEI of transport sector.

Spatial–Temporal Vegetation Dynamics and Their Relationships with Climatic, Anthropogenic, and Hydrological Factors in the Amur River Basin

Information about the growth, productivity, and distribution of vegetation, which are highly relied on and sensitive to natural and anthropogenic factors, is essential for agricultural production management and eco-environmental sustainability in the Amur River Basin (ARB). In this paper, the spatial–temporal trends of vegetation dynamics were analyzed at the pixel scale in the ARB for the period of 1982–2013 using remotely sensed data of long-term leaf area index (LAI), fractional vegetation cover (FVC), and terrestrial gross primary productivity (GPP). The spatial autocorrelation characteristics of the vegetation indexes were further explored with global and local Moran’s I techniques. The spatial–temporal relationships between vegetation and climatic factors, land use/cover types and hydrological variables in the ARB were determined using a geographical and temporal weighted regression (GTWR) model based on the observed meteorological data, remotely sensed vegetation information, while the simulated hydrological variables were determined with the soil and water assessment tool (SWAT) model. The results suggest that the variation in area-average annual FVC was significant with an increase rate of 0.0004/year, and LAI, FVC, and GPP all exhibited strong spatial heterogeneity trends in the ARB. For LAI and FVC, the most significant changes in local spatial autocorrelation were recognized over the Sanjiang Plain, and the low–low agglomeration in the Sanjiang Plain decreased continuously. The GTWR model results indicate that natural and anthropogenic factors jointly took effect and interacted with each other to affect the vegetated regime of the region. The decrease in the impact of precipitation to vegetation growth over the Songnen Plain was determined as having started around 1991, which was most likely attributed to dramatic changes in water use styles induced by local land use changes, and corresponded to the negative correlation between pasture areas and vegetation indexes during the same period. The analysis results presented in this paper can provide vital information to decision-makers for use in managing vegetation resources.