Spatial Weight Research Articles

Water‐surface infrared small object detection based on spatial feature weighting and class balancing method

AbstractInfrared imaging is widely used due to its penetration capability to operate under many weather or lighting condition. However, due to the far distance of aerial view, feature blur, and the scarcity of aerial infrared data, the detection of small infrared targets on the water surface remains a challenging problem. In response to the problem of unclear features, we propose the spatial feature weighting method based on 2D Gaussian distribution. This method increases the weight of the target area by adaptively adjusting the feature activation. Secondly, for the problem of rare aerial perspective infrared data, we propose the cross‐spectral data migration method. By introducing the domain difference loss function to optimize the pseudo‐label selection process, the range of target domain distribution is expanded, and the adaptability of the detector is improved. Finally, in response to the problem of underfitting caused by category imbalance in transfer learning, we propose the class balancing method that effectively reduces the false detection. Extensive experiments were conducted on both benchmark datasets and the self‐built dataset to evaluate the effectiveness and robustness of our method. The proposed method was evaluated with different models and various scenarios, and the results demonstrated the effectiveness.

Synergetic Development Measure of Airport Groups Composite System and Its Influencing Factors Analysis: Some Evidence from China

Whether airport groups develop synergistically has become a concern for the aviation industry. Existing studies have neglected the dynamic comprehensive evaluation and analysis of influencing factors of synergy degree. Taking the synergistic development of airport groups as the research perspective, we integrate the dynamic comprehensive evaluation model into the traditional synergy model. From two dimensions of airport development and regional economy, we measured the static synergy degree of the Chengdu-Chongqing airport group and the dynamic synergetic development degree on the overall time series. Further, using a spatial econometric model, we construct a distance economy-nested spatial weight matrix so as to explore the influence of each indicator on the synergy degree of the composite system. The results show that the overall synergy of the Chengdu-Chongqing airport group is above 0.5 in terms of static synergy degree. The clustering spectrum shows that the Chengdu-Chongqing airport group can be divided into three categories and basically forms the characteristic of “two main and multiple auxiliary airports.” In terms of dynamic synergetic development degree and comprehensive evaluation value, the change speed of synergy degree is relatively smooth in the early stage and fluctuates in the later stage, and the overall dynamic evaluation value of the Chongqing regional airports is high. The effects of the explanatory variables of the airport group composite system on the synergy degree show more direct effects than spillover effects, and the direct effects are all positive feedback effects, while the negative spillover effects of the explanatory variables cannot be ignored.

Green finance, the low-carbon energy transition, and environmental pollution: evidence from China.

With 2008-2020 China's provincial panel data as the research object, we use the entropy weight method to compute green finance and pollution, and we empirically study the scope of the spillover effects and threshold impacts of green finance on environmental pollution using the spatial Durbin model and threshold regression model. The findings are as follows: first, under different spatial weight matrices, green finance has a spatial spillover effect on pollution. And the effect boundary is approximately 500km. Second, with the low-carbon energy transition, technological progress, and green finance as threshold variables, there are a single threshold, single threshold, and double threshold, respectively, that have significant threshold effects. Third, the spillover and threshold effects of green finance on pollution differ by region. The indirect effect is negative in the eastern region and positive in the central and western regions. There is a single threshold effect of low-carbon energy transition and green finance in the western region, a single threshold effect of green finance in the central region, and a single threshold effect of technological progress in the eastern region. On this basis, we put forward. specific policy recommendations.

Multi-scale telecoupling effects of land use change on ecosystem services in urban agglomerations --A case study in the middle reaches of Yangtze River urban agglomerations

A systematic understanding of the influences of land use change/land cover change (LUCC) on ecosystem services (ES) is significant for maintaining sustainable development of ecosystems. Previous studies on the effects of LUCC on ES have been discussed at multiple dimensions and scales, but there is still a lack of systematic studies on the influences of LUCC and its telecoupling effects on ES at different spatial scales and in different levels of urban agglomerations from a systemic perspective. Therefore, this paper endeavours to fill in the blanks. On the basis of quantifying the spatial and temporal evolution characteristics of LUCC and ES in the middle reaches of Yangtze River urban agglomerations (MRYRUA) and its three major metropolitan areas (C-Z-T metropolitan; Wu-Han Metropolian; Poyang Lake Metropolian), a spatial self-lagging of X model (SLX) based on the gravitational spatial weight matrix is constructed to explore this problem. The results show that the overall land use intensity of the MRYRUA has increased by 0.07% from 1990 to 2020, with the largest increase in the C-Z-T metropolitan area. Carbon fixation, soil conservation, habitat quality and water purification service show different degrees of fluctuation within the three metropolitan areas, with the greatest fluctuation in C-Z-T metropolitan area. At different spatial scales, LUCC and its telecoupling effect have a significantly negative effect on ES, and with the expansion of the scale, the negative effect will be strengthened gradually, while the influences of LUCC and its telecoupling effects on ES differ significantly in different levels of urban agglomerations. This paper can provide a reference for the implementation of differentiated land use and ecological protection policies for different levels of urban agglomerations.

Spatial spillovers and world energy intensity convergence

This paper studies the influence of spatial spillovers on energy intensity growth and convergence across 153 countries from 1999 to 2018. The inclusion of spatially lagged variables allows the study of the influence of trade, technological diffusion and policy mimicry on these two processes. Contrary to previous literature, we consider different spatial specifications and weight matrices to test whether spatial spillovers are exogenous or endogenous, as well as their range of influence. Our study finds the spatial lag of X model (SLX), with local spatial weight matrices, fits better to the data. Convergence is found for the world as a whole, conditional to the spatial distribution of countries and several long-term economic characteristics. In this sense, clusters of nearby countries present higher rates of convergence. Besides, domestic capital accumulation, total factor productivity growth and renewable energy consumption significantly determine the characteristics of clubs of convergence. Furthermore, spatial spillovers associated to capital accumulation, population growth and renewable energy consumption also contribute to the definition of these clubs.

The Impact of Green Finance on High-Quality Economic Development in China: Vertical Fiscal Imbalance as the Moderating Effect

The vigorous development of green finance has become a national strategy in China. Green finance is gradually becoming a key driver of high-quality economic development and a key area of concern for China’s economy and ecological environment. Based on the panel data of 30 Chinese provinces from 2001 to 2019, we analyzed the impact and mechanism of vertical fiscal imbalance (VFI) and green finance (GF) on high-quality economic development (HQD) and then used the fixed-effect model and spatial Durbin model for empirical testing. We found that GF can significantly contribute to HQD, but VFI has a negative moderating effect in contrast to the positive effect of GF on HQD. This negative moderating effect is strongest in the central region. According to the analysis of the spatial econometric model based on geography, economy, and the nested spatial weight matrix, we found that the local GF has a negative spatial transmission effect on the HQD of other regions. Therefore, it is recommended that the coordinated development of green finance among regions be promoted, while affairs and expenditure responsibilities be reasonably distributed between the central and local governments to drive HQD effectively.

A vision subsampling probsparse self-attention-based informer for bearing remaining useful life prediction

Bearing remaining useful life (RUL) prediction has always been a central topic in the industry field, the aim of which is to optimize system safety and sustainability. The validity of prediction models and the accuracy of prediction results are affected by mid-term singularities and terminal mutations, under time-domain bearing vibration information. In this paper, a network structure-cascaded dilated convolution vision informer (CDC-Vii) is put forward to precisely forecast the RUL of bearings, which uses the time–frequency fault features as input. CDC-Vii breaks the limitation of the original Informer, which is only sensitive to time-series information. An adaptive fault frequency band selection algorithm is proposed, which can reduce training time while utilizing rich time–frequency information. Based on the Informer architecture, the attention mechanism is improved to form vision subsampling probsparse self-attention (VSPS). VSPS can precisely assign spatial attention weights and reduce computational complexity. At the same time, a truncated relative position encoding technique is proposed to strengthen the position dependence between attention information. Moreover, cascaded dilated convolution enhances the image contrast of faulty frequency bands while enlarging the use of the receptive field. Experiments on two extensively utilized bearing datasets reveal that CDC-Vii surpasses the advanced RUL prediction models.

Forecasting per Capita Energy Consumption in China Using a Spatial Discrete Grey Prediction Model

To overcome the limitations of the present grey models in spatial data analysis, a spatial weight matrix is incorporated into the grey discrete model to create the SDGM(1,1,m) model, and the L1-SDGM(1,1,m) model is proposed, considering the time lag effect to realize the simultaneous forecasting of spatial data. The validation of the SDGM(1,1,m) and L1-SDGM(1,1,m) models is achieved, and finally, the per capita energy consumption levels (PCECs) of 30 provinces in China from 2020 to 2025 is predicted using SDGM(1,1,m) with a metabolic mechanism. We draw the following conclusions. First, the SDGM(1,1,m) and L1-SDGM(1,1,m) models established in this paper are reasonable and improve forecasting accuracy while supporting interactive regional forecasting. Second, although SDGM(1,1,m) resembles the DGM(1,n) model, their modeling conditions and targets are different. Third, the SDGM(1,1,m) and L1-SDGM(1,1,m) models can be used to effectively analyze the spatial spillover effects within the selected modeling interval while achieving accurate predictions; notably, from 2010 to 2017, the PCECs of Inner Mongolia and Qinghai were most affected by spatial factors, while the PCECs of Jilin, Jiangxi, and other provinces were influenced little by spatial factors. Fourth, predictions indicate that the PCECs of most Chinese provinces will increase under the current grey conditions, while the PCECs of provinces such as Beijing are expected to decrease.

A Multi-Feature Fusion Model Based on Denoising Convolutional Neural Network and Attention Mechanism for Image Classification

Spatial location features extracted by denoising convolutional neural network. At this time, an attention mechanism is introduced into denoising convolutional neural network. The dual attention model of local area is presented from two dimensions of channel and space—channel attention mechanism weights channel and spatial attention mechanism weights location. A variety of machine learning methods are used to classify and train different features. Multi-semantic features and heterogeneous features are fused by adaptive weighted fusion algorithm. Finally, the data sets Cifar-10, STL-10, Cifar-100 and GHIM-1OK are verified on the proposed method. Compared with a single semantic feature, the accuracy is improved by 10%-15%. Compared with several advanced algorithms, the performance has a significant advantage, which proves the complementarity of heterogeneous features and multi-network semantic features and the effectiveness of the adaptive weighted fusion algorithm.

Comparison of Queen Contiguity and Customized Weighting Matrices on Spatial Regression to Identify Factors Impacting Poverty in East Java

Poverty is crucial problem that negative impact on all sectors, including economic, social, and cultural development in East Java Province. Poverty can also increase unemployment, crime, trigger social disasters and hinder progress East Java province. One efforts overcome problem of poverty in East Java province is detect factors that influence. This effort can be done through statistical modeling to determine factors that influence poverty in East Java province. statistical model that can identify factors that influence poverty and explain relationship between region and surrounding area is spatial regression analysis. In spatial regression analysis, spatial weighting matrix is needed to determine spatial influences between regions where one region influences neighboring regions. spatial weighting matrices that is often used is queen contiguity, and according to Anselin (1988:20), this spatial weighting also considers initial information, purpose of case studied, and theory underlying the research. This weighting uses social and economic variables case under study, namely customized weighting matrix. Based on results of this study, shows that best spatial regression and spatial weighting models are General Spatial Model (GSM) with customized weighting because customized weighting produces better estimation results than SAR, SEM and GSM models with queen contiguity weighting in district and city poverty modeling in East Java province with Akaike Infomation Criterion (AIC) value of 188.77 and detemination coefficient (R2) of 84.95%. School's Expected Time, Life Expectancy Score, and Employment Participation Rate are factors that will have substantial impact on percentage of population living in poverty East Java's districts and cities in 2021.

Geographically Weighted Panel Regression for Modeling The Percentage of Poor Population in West Sumatra

Geographically Weighted Panel Regression (GWPR) model applies panel regression to spatial data, and parameter estimation is carried out using spatial weight at each observation point. The purpose of this study is to determine the GWPR model and the factors that influence the percentage of poor people in each district/city in West Sumatra Province from 2015 to 2021. And the adaptive bisquare kernel function was used to provide spatial weighting, and Cross-Validation (CV) criteria were used to identify the optimal bandwidth. The research data was secondary data sourced from the official website and West Sumatra published books in Sumatera Barat Dalam Angka from 2015 to 2021. The GWR model and the FEM panel data regression model are combined to create the GWPR model. The results of this study is there are a differences between models and factors that affecting the poor percentages in 19 districts/cityes of West Sumatra.

Analysis of Factors Influencing the Population Growth Rate in West Sumatra Using Geographically Weighted Logistic Regression

The model of Geographically Weighted Logistic Regression (GWLR) was the development of a model of logistic regression that was implemented to data in spatial. GWLR model parameter estimation was carried out at each location for observation using spatial weighting. The research purposes was to reveal the GWLR model on the dichotomous data of the Population Growth Rate (PGR) indicator in each Districts/Cities in West Sumatra in 2020 and learn more factors that influence the probability that the population growth rate will increase in 19 Districts/Cities in West Sumatra in 2020. The parameters estimation of the GWLR model uses the Maximum Likelihood Estimation (MLE) method. Spatial weighting for parameter estimation is determined using the Fixed Gaussian Kernel weighting function and determining the optimal bandwidth using Akaike's Information Citerion (AIC) criteria. The variable of response that is categorical in this study is the rate of population growth in each districts/cities in West Sumatra in 2020 and the predictor variables are the couples number of childbearing age, the live births number, the in-migration number, and the out-migration number. The reseacrh result obtained from research were that the GWLR model is better than the logistic regression model and 4 groups of Districts/Cities are formed based on factors that affect the increase in population growth rate.

Public Spending and Financial Inclusion and Their Impact on Inclusive Growth In Indonesia: A Spatial Approach

Inclusive growth results in equal access to the benefits of growth and, by that, reduces disparities. Public spending plays an important role in supporting economic growth and people's welfare. On the other hand, financial inclusion has the ability to expand opportunities to participate in growth. Using data on government spending and financial inclusion in 34 provinces in Indonesia in 2015-2019, this study aims to examine the link between the two towards inclusive growth. As a result, spending on education and financial inclusion, as well as investment and trade openness, can promote inclusive growth. Expanding access to education as a result of public investment in education will boost labor capacity and productivity. Meanwhile, access to more affordable credit will be realized through an inclusive financial system. Conversely, due to health development gaps, health spending has a negative impact on inclusive growth. The spatial error model with queen contiguity spatial weight matrix shows a significant spatial effect on the error term or residual. The implication is that policies for expanding education, health, and digital access as well as increasing investment and financial literacy need to be carried out to ensure people's affordability to economic opportunities by considering regional aspects.

The impact of religious tourism on the economy and tourism industry

Today, tourism, with its distinct and unique features, has become one of the largest and most profitable industries in the world economy and has provided a platform for changes in geographical spaces. This study was conducted with the aim of investigating the effects of religious tourism on the economic development of traditional settlements. The research method is descriptive and analytical. The independent variable is ‘religious tourism’, which is quantified by 10 components, and the dependent variables are ‘income’ and ‘employment’ in tourist areas, which are studied with 10 components in Russia, respectively. Data analysis was carried out in SPSS software, then a Pearson’s correlation test and simple linear regression were used. Moreover, Geographic Information System (GIS) software was used to show the traditional spatial weighting of the study. The regression results show that religious tourism has been effective by 0.77 on income, 0.66 on employment, and 0.72 on the economy of traditional settlements. In fact, the development of religious tourism in areas with religious and traditional rituals has had a positive effect on creating employment, increasing income and economic prosperity. In general, religious tourism, with its structural and functional features, is considered an important factor in revitalising the economy of regions with this privilege.Contribution: This article has proven the strong role of religious tourism on the economy and tourism industry in Russia with a quantitative analysis, which deserves the attention of cultural and tourism policymakers. In addition, the results of this research can be considered by other countries with different religions.

Spatial patterning of benthic macroinvertebrate communities using Geo-self-organizing map (Geo-SOM): A case study in the Nakdong River, South Korea

Characterizing community responses to environmental disturbances is difficult because of the complexity of heterogeneous ecosystems. A geographical self-organizing map (Geo-SOM) was applied to present the spatial distribution patterns of benthic communities in a river. The benthic macroinvertebrate communities were collected in the mainstream of the Nakdong River in South Korea. Geo-SOM is a machine learning technique that extracts spatial patterns of given data across spatial weight k values (0–5), which control the vicinity of the map, to extract geographical information effectively. In the results, clusters were formed mainly according to the topography on a large scale and anthropogenic impacts on a small-scale showing consistency in spatial patterning for benthic communities in the gradient across different degrees of spatial weight. Geo-SOM provided both comprehensive and detailed views for presenting species-space relationships. Corresponding to the decrease in k value (more weight in geographical information), we accumulated data variations to present a comprehensive view of spatial species distributions. Overall, correlations between species were more associated with latitude rather than longitude. The feasibility of spatial clustering was also demonstrated with the effective differentiation of community indices. Community indices were effectively differentiated into clusters in the Geo-SOM. Finally, Geo-SOM is a useful tool for extracting the spatial distribution patterns of communities in a comprehensible manner for the monitoring and management of communities in aquatic ecosystems.

Spatial Analysis of Dengue Disease in Jakarta Province

Dengue disease is a virus-borne illness spread by the bite of the female Aedes aegypti mosquito. Jakarta Province has a vulnerability to dengue disease due to high population density and percentage of urban slum households. This study applied a spatial autoregressive (SAR) model to identify the risk factors that affect the number of dengue disease cases in Jakarta Province. The spatial dependency was accounted for using the queen contiguity spatial weight matrix. The number of flood-prone points, the number of slum neighborhood associations, the population density, the number of hospitals and the number of public health centers per 1,000 population and spatial lag significantly impact the number of dengue disease cases in Jakarta Province. When dengue disease cases increase in one sub-district, the number of dengue disease cases in the sub-districts around it will increase as well because of the positive and significant spatial lag coefficient. Based on the direct impact, each addition of one percent of flood-prone points in one sub-district will increase the number of dengue disease cases in that sub-district by 3.86 cases

A generalized spatial autoregressive neural network method for three-dimensional spatial interpolation

Abstract. Spatial interpolation, a fundamental spatial analysis method, predicts unsampled spatial data from the values of sampled points. Generally, the core of spatial interpolation is fitting spatial weights via spatial correlation. Traditional methods express spatial distances in a conventional Euclidean way and conduct relatively simple spatial weight calculation processes, limiting their ability to fit complex spatial nonlinear characteristics in multidimensional space. To tackle these problems, we developed a generalized spatial distance neural network (GSDNN) unit to generally and adaptively express spatial distances in complex feature space. By combining the spatial autoregressive neural network (SARNN) with the GSDNN unit, we constructed a generalized spatial autoregressive neural network (GSARNN) to perform spatial interpolation in three-dimensional space. The GSARNN model was examined and compared with traditional methods using two three-dimensional cases: a simulated case and a real Argo case. The experiment results demonstrated that exploiting the feature extraction ability of neural networks, the GSARNN achieved superior interpolation performance and was more adaptable than inverse distance weighted, ordinary Kriging, and SARNN methods.

Spatial effects of air pollutants reduction on CO2 emissions.

The sources of air pollutants and CO2 are basically the same, hence the reduction of air pollutants will affect CO2 emissions. Considering the regional integration of economic development as well as air pollution control, it is necessary to analyze the impact of air pollutants reduction in a region on CO2 emissions in its surrounding regions. Furthermore, as different stages of air pollutants reduction have different effects on CO2 emissions, it is also important to study the heterogeneity of this impact. In this article, we took China as the research case and built a spatial panel model based on the data of 240 cities above the prefecture level from 2005 to 2016 to study the impact of two different stages of air pollutants reduction-front reduction of air pollutants (FRAP) and end-of-pipe treatment of air pollutants (EPAP) on CO2 emissions-and their spatial spillover effects. On this basis, we further modified traditional spatial weight matrix and constructed the matrices of cities in the same and different provinces to discuss the influence of provincial administrative boundaries on the spillover effect between cities. The results show that FRAP affects CO2 emissions mainly through the local synergistic effect, and its spatial spillover effect is not significant. The local effect of EPAP on CO2 emissions is antergic, and the spatial spillover effect is significant. The increase of a city's EPAP will increase the CO2 emissions in surrounding regions. Besides, provincial boundaries weaken the spatial spillover effects of FRAP and EPAP on CO2 emissions in prefecture-level cities. There is a significant spatial spillover effect between cities in the same province, but the spillover effect does not exist for cities in different provinces nearby.

Global Value Chains, Digital Economy, and Upgrading of China’s Manufacturing Industry

This study utilized panel data from 31 provinces in China from 2006 to 2020 to investigate the impact of the digital economy on the upgrading of the manufacturing industry’s global value chain. Two types of spatial weighting matrices were used to construct SAR, SEM, SAC, and SDM models. The results revealed that technological innovation plays a direct mediating role in the upgrading of the manufacturing industry, and the global value chain has a positive regulatory effect on the relationship between the digital economy and the manufacturing industry’s upgrading. Under the economic distance spatial weighting matrix, the spatial spillover effect of the digital economy on the manufacturing industry’s global value chain is not significant, whereas, under the geographic distance spatial weighting matrix, the digital economy has a positive and significant spatial spillover effect. The SDM model showed the best explanatory effect. This implies that geographic spatial dependence has a significant impact on the upgrading of the manufacturing industry’s industrial structure, and it is positively influenced by nearby provinces. Understanding the impact mechanism and spatial spillover effects of the digital economy on the manufacturing industry’s upgrading can help promote efficient, fair, and balanced regional development. It can also aid in constructing a new domestic and international “dual circulation” development pattern that evolves with the global manufacturing value chain, sharing the dividends of the digital economy’s impact on the global value chain’s development.

Dominant Modes of Agricultural Production Helped Structure Initial COVID-19 Spread in the U.S. Midwest

The spread of COVID-19 is geographically uneven in agricultural regions. Explanations proposed include differences in occupational risks, access to healthcare, racial inequalities, and approaches to public health. Here, we additionally explore the impacts of coexisting modes of agricultural production across counties from twelve midwestern U.S. states. In modeling COVID-19 spread before vaccine authorization, we employed and extended spatial statistical methods that make different assumptions about the natures and scales of underlying sociospatial processes. In the process, we also develop a novel approach to visualizing the results of geographically weighted regressions that allows us to identify distinctive regional regimes of epidemiological processes. Our approaches allowed for models using abstract spatial weights (e.g., inverse-squared distances) to be meaningfully improved by also integrating process-specific relations (e.g., the geographical relations of the food system or of commuting). We thus contribute in several ways to methods in health geography and epidemiology for identifying contextually sensitive public engagements in socio-eco-epidemiological issues. Our results further show that agricultural modes of production are associated with the spread of COVID-19, with counties more engaged in modes of regenerative agricultural production having lower COVID-19 rates than those dominated by modes of conventional agricultural production, even when accounting for other factors.