Spatial Weight Research Articles

High-resolution full-coverage ozone (O3) estimates using a data-driven spatial random forest model in Beijing-Tianjin-Hebei region, China

The Beijing-Tianjin-Hebei (BTH) region is severely polluted by ozone (O3). Accurate O3 estimates are essential for identifying high-polluted zones and developing targeted interventions to relieve the burden of diseases. Although many studies have estimated high-resolution O3 concentrations in BTH, the estimation accuracies are still insufficient. In this study, we incorporated data-driven spatial weight matrices (DDWs) into a random forest (RF) model to fully utilize both the spatial homogeneity and heterogeneity of maximum daily 8-h ozone concentration (MDA8O3), and obtained full-coverage MDA8O3 concentrations at 1km×1km in BTH from 2014 to 2022. DDW-RF exhibited satisfactory accuracy (10-fold cross-validation R2=0.937, RMSE=13.919 μg/m3). Overall O3 level presented a spatial pattern of lower in the north and higher in the southeast and showed a distinct temporal trend, i.e., first increasing and then decreasing during 2014-2021 and increasing slightly in 2022. The accurate MDA8O3 estimates indicates that more attention and resources should be poured into the areas adjacent to Bohai Rim, Shandong and Henan. Regulated operation of factories under specific meteorological conditions and upgrading industrial structure and production modes are recommended to mitigate the formation of O3 precursors and reduce O3 generation. Our findings provide evidence and reference for environmental cleaning policies and targeted interventions.

Cooperative Innovation Under the “Belt and Road Initiative” for Reducing Carbon Emissions: An Estimation Based on the Spatial Difference-in-Differences Model

The Belt and Road Initiative holds significant importance for achieving the United Nations’ Sustainable Development Goals, particularly Goals 9 and 17. Drawing on data from the Web of Science database, the BRI database, and the World Bank database, this study explores the potential carbon emission reduction effects that cooperative innovations may bring to participating countries under the Belt and Road Initiative. The study constructs variable endogenous spatio-temporal weight matrices based on initial spatial weight matrices and, drawing on trends in co-authored publications, innovatively establishes time dummy variables and event dummy variables in a difference-in-differences (DID) model. This approach fully considers the interconnected, shared model of the Belt and Road Initiative and the spatial effects of policy implementation. A spatial DID model was established for 106 BRI participating countries and regions from 2005 to 2021. The results reveal the following: first, cooperative innovation under the BRI significantly reduces carbon emission intensity in participating countries. Second, the BRI primarily achieves carbon reduction through investment, innovation, and trade mechanisms. Third, the results of the global SDID model indicate that cooperative innovation with China negatively impacts carbon emission intensity. Also, this effect exhibits spatial spillover, suggesting that there is a policy spillover effect. Fourth, the decomposition of local policy shock effects indicates that the influences of cooperative innovation exhibit spatial heterogeneity, with varying degrees of direct and indirect effects on carbon emission intensity across different countries.

Temporal–spatial correlation and graph attention-guided network for micro-expression recognition in English learning livestreams

Micro-expressions, fleeting facial movements lasting 1/25 to 1/3 of a second, offer crucial insights into genuine emotions, particularly valuable in online education settings. The rapid growth of English learning livestreams has heightened the need for accurate, real-time micro-expression recognition to enhance learner engagement and instructional effectiveness. However, existing methods need help with the subtle nature of these expressions, especially in dynamic, low-resolution streaming environments. This paper presents TSG–MER–ELL, a novel end-to-end network for micro-expression recognition in English learning livestreams, integrating temporal–spatial correlation and graph attention mechanisms. The framework addresses the unique challenges of real-time emotion analysis in online language education, where subtle facial cues are crucial in understanding learner engagement and comprehension. The temporal–spatial correlation module employs action units with spatio-temporal graph convolution to aggregate features from diverse facial regions, while transformer encoders construct long-range correlations. The graph attention module builds upon local facial areas to guide self-attention computations, yielding precise local correlation features. These global and local features are fused for the final micro-expression classification. We introduce an adaptive loss function that balances accuracy, efficiency, and relevance to linguistic context. Extensive experiments on SMIC, CASME II, and SAMM datasets, adapted for English learning scenarios, demonstrate TSG–MER–ELL’s superior performance over ten state-of-the-art baselines. The TSG–MER–ELL framework achieves top UF1 and UAR scores across all datasets, significantly improving recognition speed and accuracy. Ablation studies and visualizations of temporal–spatial features and graph attention weights provide insights into the framework’s effectiveness in capturing subtle emotional cues. TSG–MER–ELL’s robust performance in varied online learning conditions highlights its potential to enhance engagement, personalize instruction, and improve overall outcomes in virtual English language education.

Integrating spatial relationships in the DEA approach for ecological efficiency evaluation: A case study of the Chaohu watershed

This study introduces an innovative Data Envelopment Analysis (DEA) model that integrates spatial relationships among decision-making units (DMUs) to determine relative prices of all variables for evaluating ecological efficiency more accurately, particularly in the context of water resource management. To better capture ecological performance, we propose a model that includes spatial correlation, addressing interdependencies that traditional DEA models often overlook. By incorporating a spatial weight matrix, the model delineates interactions between DMUs, offering a comprehensive evaluation that considers both technical efficiency and the spatial efficiency impact. We demonstrate the utility of our model through an empirical analysis of 17 national monitoring cross-sections within the Chaohu Watershed, a critical ecological and economic zone within China’s Yangtze River Delta. This research contributes to the fields of environmental economics, resource management, and spatial analysis by providing a robust methodological framework and actionable insights for sustainable environmental stewardship.

Spatial effects of ecological cognition on firewood collection by households in protected areas: An analysis based on the giant panda nature reserves

The issues of unbalanced and inadequate energy development in rural China remain prominent, particularly in areas rich in natural resources, such as nature reserves, where households still tend to rely on traditional energy utilization modes. On one hand, the traditional use of firewood for energy results in low energy efficiency and indoor air pollution; On the other hand, it exacerbates problems such as habitat degradation for wildlife and environmental collapse. Although previous studies have explored rural energy source utilization from varies of aspects, there are still limitations in examining the impact of ecological cognition on household behaviors from a spatial correlation perspective. This study conducts a field survey of rural households in the giant panda nature reserves in Sichuan and Shaanxi Provinces to explore the impact of ecological cognition on rural households' firewood collection behaviors. By incorporating a spatial weight matrix, the study further analyzes the spatial spillover effects and the spatial heterogeneity of ecological cognition on rural households' firewood collection. The results show that: (1) ecological cognition significantly reduces firewood collection behaviors; (2) household income also decreases the consumption of firewood energy; (3) ecological cognition exhibits spatial spillover effects on rural households' firewood collection, indicating that household ecological cognition can impact surrounding households' ecological cognition and indirectly affect their firewood collection behaviors; and (4) significant spatial heterogeneity exists inside and outside the protected area. Ecological cognition significantly influences the firewood utilization of rural households within protected areas through spatial spillover effects, whereas its impact outside the protected areas is minimal. Strengthening forest ecological education to further raise ecological awareness, focusing on low-income households to provide energy subsidies, and utilizing the spatial spillover effects to enhance information dissemination channels are recommended for policy implications.

Spatial Spillover Effects of Smallholder Households’ Adoption Behaviour of Soil Management Practices Among Push–Pull Farmers in Rwanda

Push–pull technology (PPT) integrates maize with the legume fodder Desmodium sp. and the border crop Brachiaria sp., aiming to enhance maize production in Rwanda. Despite its potential, the adoption of complementary soil management practices (SMP), vital for PPT’s success, remains low. This study employs spatial econometric methods to evaluate the determinants of SMP adoption and the interdependencies in decision-making among PPT-practicing farmers. We constructed a spatial weight matrix based on a global Moran’s I index and identified optimal model parameters through principal component analysis. Utilizing a spatial Durbin probit model (SDPM), we assessed the spatial interdependence of SMP adoption decisions among maize farmers. Our findings reveal significant spatial dependence in SMP adoption within a 1.962 km radius, with improved seed usage, household income, yield, farmer group membership and size of land cultivated being key factors positively influencing adoption. We propose a “nonequilibrium promotion strategy” to enhance SMP adoption, emphasizing the establishment of pilot regions to broaden outreach. Additionally, fostering technical training and selecting farmers with adequate resources as demonstration leaders can enhance spatial spillover effects. This research provides insights for developing policies to scale up push–pull technology in Rwanda and across Sub-Saharan Africa.

Selection of spillover channels in spatial dynamic panel models using heterogeneous shrinkage on spatial parameters

ABSTRACT This paper proposes a Bayesian approach to estimating heterogeneous spatial dynamic panel models, subject to possible shrinkage on spatial dependence parameters. This amounts to heterogeneous selection of candidate spatial weight matrices that represent different spillover channels. The shrinkage methods include both the traditional and more flexible ones that allow the shrinkage strength to vary across spatial parameters. Monte Carlo results indicate that when the true model has a relatively low proportion of nonzero spatial parameters, flexible shrinkage in general leads to lower average root mean squared errors in estimating these parameters. An empirical study using this approach shows that there exists substantial heterogeneity in spillover channels across counties that determine the correlation patterns of county COVID-19 vaccination rates in four states in the United States.

Mask-guided network for finger vein feature extraction and biometric identification

The problems of complex background, low quality of finger vein images, and poor discriminative features have been the bottleneck of feature extraction and finger vein recognition. To this end, we propose a feature extraction algorithm based on the open-set testing protocol. In order to eliminate the interference of irrelevant areas, this paper proposes the idea of segmentation-assisted classification, that is, using the rough mask of the finger vein to constrain the feature learning process so that the network can focus on the vein area and learn greater weight for the vein. Specifically, the feature maps of the shallow layers of the network are first sent to the feature pyramid module to fuse the primary features of different scales, which are then sent to the spatial attention module to obtain the spatial weight map of the image. Based on the results of several classical vein skeleton extraction algorithms, a weighting method is used to obtain a more accurate mask to constrain the learning of the spatial weight map. Finally, a hybrid loss function combining triplet loss and cross-entropy loss is used to reduce the distance between feature vectors of the same categories and increase the distance between feature vectors of different categories in the Euclidean space, thereby improving feature discriminability. Good recognition results were achieved on the three public data sets of SDUMLA, MMCBNU, and FVUSM, and the values of equal error rate (EER) on them are as low as 2.50%, 0.20%, and 0.14%, respectively.

ENSO predictive analytics based on layered rendering

El Niño-Southern Oscillation (ENSO) is a periodic climate phenomenon in the equatorial Pacific that significantly influences global climate patterns. Accurate prediction and monitoring of ENSO events are essential for meteorological agencies and governmental institutions. This study introduces a content-guided attention module within a convolutional neural network to improve prediction accuracy. This module models inter-channel relationships and enhances information interaction by integrating channel and spatial attention weights. These advancements substantially improve prediction accuracy and help overcome the spring prediction barrier in ENSO forecasting. The research emphasizes global feature modeling and proposes a novel content-guided ENSO prediction model. It also includes an ocean data generation model utilizing global attention. Furthermore, a layered rendering technique is employed to invert ocean data, facilitating detailed analysis and contributing to the development of an ocean synthetic dataset.

Multiple environmental regulations and green technology innovation: a boundary theory perspective

Purpose Based on boundary theory, the authors try to clarify the boundaries of multiple environmental regulations. This paper aims to explore the strategic choices of multiple environmental regulations, analyze their spatial impact on green technology innovation and clarify the implementation priorities of multiple environmental regulations in various regions. Design/methodology/approach The authors construct an asymmetric response model based on the boundary theory perspective to analyze the strategic choices of different environmental regulations. In addition, dynamic spatial econometric methods are used to empirically analyze the differentiated regulatory boundaries of command-control type, market-incentive and voluntary-participation in environmental regulations and their spatial effects on green technology innovation. Findings Strict compulsory boundaries are formed in China when the command-control and market-incentive types are selected in a dynamic spatial and competitive game environment. When voluntary participation is selected, strict compulsory or loose basic boundaries are formed in each region. The command-control type is highly dependent on geographical distance, the market-incentive type is more dependent on an economic connection and the voluntary-participation type has obvious spatial spillover effects under the spatial weight matrix of geographical distance and economic connection. When Eastern China chooses voluntary participation in environmental regulation, the incentive effect on green technology innovation is the strongest. Middle China is the market-incentive type, and Western China is the command-control type. Command-control type and market-incentive type form strong complementary effects in dynamic spatial environments. Originality/value From the boundary theory perspective, this study analyzes the differentiated dynamic spatial boundaries of command-control, market-incentive and voluntary-participation in environmental regulations. Analyze the spatial impact of multiple environmental regulations on green technology innovation and clarify the implementation priorities of multiple environmental regulations in various regions.

A groundwater level spatiotemporal prediction model based on graph convolutional networks with a long short-term memory

ABSTRACT The performance of regional groundwater level (GWL) prediction model hinges on understanding intricate spatiotemporal correlations among monitoring wells. In this study, a graph convolutional network (GCN) with a long short-term memory (LSTM) (GCN–LSTM) model is introduced for GWL prediction utilizing data from 16 wells located in the northeastern Xiangtan City, China. This model is designed to account for both the hybrid temporal dependencies and spatial autocorrelations among wells. It consists of two parts: the spatial part employs GCNs to extract spatial characteristics from a spatial self-similarity weight matrix and an attribute self-similarity weight matrix among wells; the temporal part utilizes a LSTM module to capture the temporal patterns of GWL sequences, along with monthly precipitation and temperature data. This model dynamically predicts changes in groundwater levels, achieving higher accuracy on average compared to single-well predictions using LSTM. By incorporating both temporal dependencies and spatial autocorrelations, the GCN–LSTM model demonstrated an average improvement in goodness-of-fit of approximately 11.21% over the LSTM-based model for individual wells. Its application holds significant reference value for the sustainable utilization and development of groundwater resources in Xiangtan City.

Analysis of the degree of correlation of spatial distribution of electricity theft and exogenous variables: case study of Florianopolis, Brazil

Abstract This article presents a geospatial study case on electricity theft. The main objective is to identify the degree of correlation between exogenous variables and areas with a high density of irregular cases. Firstly, the geospatial study is carried out to asses the null hypothesis and check whether the data pattern presents clustering, for this the ANN method is applied, which ruled out the null hypothesis for the data set. Once the clustering pattern is confirmed, the spatial weight matrix is created to study spatial autocorrelation by applying Global Moran’s I and Local Moran’s I. Moran scatterplot is used to evaluate the degree of fitness, identify outliers, and local pockets of stationarity. The Local Moran index is used to determine the location of the clusters and the relationship between the points. In the data pre-processing step, spatial interpolation is implemented to the exogenous variables as a tool to better association of consumer units points and socioeconomic variables, the method utilized is IDW interpolation. The R-squared value of the spatial lag model after model tuning by feature selection was 87 % indicating that the model fit the observed data well.

Spatial weighting — An effective incorporation of geological expertise into deep learning models

The concept of weighting plays a pivotal role in modern geostatistics and spatial statistics. Originating from the weighted average in ancient mathematics, it has undergone significant expansion and evolution alongside advancements in science and technology. The concept of harnessing the distribution and relationships within spatial data has been effectively utilized in various methodologies in spatial statistics, including geographically weighted regression (GWR), spatial interpolation, and spatial clustering. These approaches significantly enhance the accuracy and reliability of mineral resource predictions. The advent of big data and artificial intelligence technologies, particularly deep learning, has led to substantial improvements in predictive capabilities. However, deep learning models often neglect the spatial relationships inherent in geoscientific data, resulting a lack of geological interpretability. To tackle this challenge, researchers have explored novel methods to integrate geological knowledge and spatial weighting into deep learning models. Building upon these advancements, the current study incorporates the distance between samples and target granitic intrusions in the southeastern Yunnan mineral district, China as weighting information within deep learning models. By amalgamating the concept of “spatial weighting” with deep learning, it aims to improve model prediction performance while concurrently enhancing geological interpretability, offering fresh insights and methodologies for mineral exploration.

The spatial spillover impact of artificial intelligence on energy efficiency: Empirical evidence from 278 Chinese cities

Within the framework of global sustainable development, improving energy efficiency (EE) is recognized as a crucial strategy to address environmental challenges and foster economic growth. This research employs the Spatial Durbin Model to investigate the spatial spillover effects of advancements in artificial intelligence (AI) technology on EE across 278 Chinese cities. The analysis reveals several key findings: first, the advancement of AI technology significantly enhances urban EE and generates a positive spatial spillover effect across different spatial weight matrices; second, there is a nonlinear, inverted U-shaped relationship between AI levels and urban EE; third, industrial structure upgrades play a significant moderating role in the impact of AI technology on urban EE. These insights not only illuminate the complex role of AI in improving regional EE but also provide critical recommendations for policymakers aiming to enhance urban EE and achieve sustainable development goals.

Attenuative Unified U-Net with Conditional PatchMatch Algorithm for Edge Preserving Salient Object Detection

The rise of Deep Neural Networks (DNNs) has significantly boosted salient object detection in computer vision tasks. However, downsampling methods like striding and pooling often introduce bluish artifacts near edges, hindering detection accuracy. To address this, the "Attenuative Unified U-Net with Conditional PatchMatch Algorithm" is proposed. The method employs Gaussian smoothing for noise reduction and depth refinement in preprocessing. In existing methods, the Edge-preserving salient object detection struggles with cluttered backgrounds and connected objects, like a bird on a rock, making it difficult to accurately distinguish edges and salient regions due to shared boundaries. Hence, an Attenuative Unified Backpropagated Entropy UNet is proposed, which integrates an Attention Mechanism that enhance feature map spatial weight assignment, emphasizing features or regions that are judged most relevant for edge and salient region detection. Then, the Cascaded Laplace pyramid is incorporated into the Unified U-Net’s design for multi-scale information processing, capturing contextual details effectively. The Backpropagated Entropy Loss Function is then created to ensure accurate and confident fused image output. The depth map, edge map, and salient area map are combined in the U-Net’s final output layer to create an overall fused image. Next, to addresses depth discontinuity problem a noteworthy novel idea the Conditional PatchMatch Random Field Algorithm (CPMRF), which combines PatchMatch efficiency and CRFs’ contextual modeling. PatchMatch iteratively propagates matches from neighboring patches to find similar patches in the remaining portion of the image and Conditional Random Field (CRF) is the next step, which improves the PatchMatch results by taking into account the connections between the matched patches and their neighboring areas. Hence, the experimental outcomes of the proposed model effectively show the improved detection of edge in salient object detection with better accuracy, precision, recall, MaxF, and F1 score with minimized MAE.

Spatio-Temporal Model to Forecast COVID-19 Confirmed Cases in High-Density Areas of Malaysia

The coronavirus 2019 disease has spread across the world. The number of coronaviruses 2019 (COVID-19) cases throughout Malaysia is high in the densely populated state of Selangor. In assisting the early preventive measures, this study utilises time series methods to model and forecast the number of daily positive cases in three Selangor districts: Petaling, Hulu Langat, and Klang. Specifically, the study compares the effectiveness of the Autoregressive Integrated Moving Average (ARIMA), a univariate model and the Generalized Space-Time autoregressive integrated (GSTARI), a multivariate model. For the GSTARI model, uniform and inverse distance weights represent the relationship between locations. The analysed data are from January to August 2021, and the lowest root mean square error (RMSE) is chosen as the best model. The results show GSTARI (1,1) with both spatial weights outperformed ARIMA (0,1,1) in Petaling and Klang but not in Hulu Langat. However, the average RMSE values show that the most accurate and effective for forecasting the number of daily confirmed positive cases in Selangor is using GSTARI. In conclusion, by utilising advanced time series methods such as spatial analysis, this study provides important insights into forecasting trends of infectious diseases like COVID-19 and can help in early preventive measures.

Adaptive content-aware spatial regularized correlation filter tracking algorithm

In order to solve the annoying boundary effects in correlation filter (CF) trackers induced by cyclic shift when sampling training patches, and improve the tracking performance, an adaptive content aware spatially regularized correlation filter (ACSRCF) is proposed. Firstly, real negative samples are generated from the background area around the target object, so as to alleviate the filter degradation by the fake negative samples induced from the circularly shifted object patches. Secondly, the locality sensitive histogram (LSH) based foreground feature is extracted and incorporated with the spatial regularization weight which is updated adaptively according to the varied object-oriented appearances. Thereafter, the CF model is optimized using the alternative direction method of multipliers (ADMM) in which the model is decomposed into two sub-problems and the LSH-based features are used in iteration for obtaining the optimal solutions. Finally, the proposed method is evaluated on 5 public benchmarks. The experimental results show that the accuracy and success rate scores of our method on OTB 50 dataset are 90.3%and 66.1%, respectively, exceeding the other CF trackers .The data on the OTB100 dataset is 92.2%and 69.2%, and the accuracy first ranks among all the trackers, while the success rate is ahead of other CF trackers.

An approach for constructing spatially paired pseudo repeat-sales housing price indices in China

AbstractConstructing a reliable housing price index is crucial for accurately reflecting housing price dynamics and enhancing transparency in the housing market. However, existing methods for constructing housing price indices often confront many challenges, such as omitted variable issues in the hedonic model and constrained samples used in the repeat-sales model. To address these challenges, this study identifies a spatially paired relationship between complexes and develops a Spatially Paired Pseudo Repeat-Sales model to construct the housing price index. This approach offers two significant advantages: first, it enlarges the sample size used in the repeat-sales model at least 1.8 times; second, it effectively estimates the effects of spatial dependency and physical housing factors on prices while mitigating the impacts of unobservable factors through differentiation. The findings of this paper suggest that using the spatially paired pseudo repeat-sales model can significantly improve the estimation of housing price volatility, by approximately 13%. Moreover, the constructed housing price index model demonstrates significant robustness, even when the spatial weight settings are altered. This research provides convincing evidence of improved housing market transparency for stakeholders, including governments, institutional developers, and individual investors. Additionally, the constructed model can inform other similar research in housing price index construction by providing a spatially pairing perspective on housing complexes.

The generalized STAR modelling with three-dimensional of spatial weight matrix in predicting the Indonesia peatland’s water level

The release rate of CO2 gas can be influenced by peatlands’ physical properties, such as water level and soil moisture, and rainfall. To anticipate the unstable condition which is when the peatland emit more carbon, we developed the Generalized Space Time Autoregressive (GSTAR) model in predicting these physical properties for the following weeks. As the innovation in modelling, the spatial weight matrix was based on three-dimensional coordinates with a modification on the height factor. The data we used are real-time data of water level on the peatlands in Pulang Pisau Regency, Central Kalimantan Province from 20 February 2021 to 18 March 2023. We then used Ordinary Kriging interpolation on the prediction results to create contour maps on different dates. There were empty data on several dates, especially from 24 March until 3 August 2022. To fill the empty data, we used linear interpolation and then we added white noise to the interpolation results. From the data, the water level has a downward trend pattern from around November to September and an upward trend pattern from October to November. Furthermore, we found that the best model for water level was GSTAR (2;0.1) with a modified matrix a=0.1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$a=0.1$$\\end{document} and b=1.1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$b=1.1$$\\end{document}. Based on the predicted water level, there is a risk of changes in the properties of the peatlands in several areas in Pulang Pisau Regency.

The Spatial Spillover Effects of Transportation Infrastructure on Regional Economic Growth—An Empirical Study at the Provincial Level in China

This study examines the spatial spillover effects of transportation infrastructure on regional economic growth, utilizing panel data from 31 provincial-level administrative divisions in China from 2003 to 2022. Using the spatial Durbin model (SDM) and three distinct spatial weight matrices—0–1 adjacency, spatial economic–geographical nested, and GDP-based economic distance matrices—this study comprehensively analyzes the multifaceted impacts of transportation infrastructure. The results show that transportation infrastructure significantly promotes economic growth in both local and neighboring regions across all spatial weight matrices. The total effect is most pronounced in geographically proximate regions, with a coefficient of 7.845 (p < 0.01). Regions with similar economic development levels also show strong collaborative effects, with a coefficient of 2.074 (p < 0.01), although the marginal effect of transportation infrastructure diminishes. Furthermore, adjustments in industrial structure and innovation inputs demonstrate a short-term inhibitory effect on economic growth, highlighting the need for synchronized development of transportation infrastructure alongside industrial and innovation policies. This study incorporates multi-dimensional spatial weight matrices to systematically reveal the direct and indirect impacts of transportation infrastructure on regional economies, providing essential empirical support for regional coordination and infrastructure investment policies. The findings offer valuable insights for infrastructure planning in other regions, particularly in formulating policies that promote cross-regional economic cooperation and optimize resource allocation.