Spatial Correlation Characteristics Research Articles

Toward dual carbon targets: Spatial correlation on comprehensive carbon emission index in urban agglomerations based on a new evaluation model

China is confronted with substantial pressure to mitigate its carbon emissions. Urban agglomerations assume a pivotal role in the attainment of carbon peaking and carbon neutrality. This study constructed a carbon emission evaluation model from the perspectives of total quantity, intensity, efficiency, population, and land. A modified gravity model and social network analysis method was used to analyze the spatial correlation characteristics of six urban agglomerations, clarified their carbon emission spillover effects, and explored their influencing factors using the quadratic assignment procedure method. The results are as follows. (1) The carbon emission correlations in the Yangtze River Delta, Pearl River Delta, and Chengdu-Chongqing urban agglomerations increased, while Beijing-Tianjin-Hebei, Central Plains, and Middle Reaches of Yangtze River urban agglomerations decreased. (2) From a macro perspective, the Yangtze River Delta and Pearl River Delta urban agglomerations were at the core of the network, and the “bridging” role of the Middle Reaches of Yangtze River urban agglomeration was evident. From a micro perspective, the cities in the middle of urban agglomerations were more likely to become network cores. (3) Spillover effects between plates were present in the correlation network, with a gradual balance between the reception and spillover relationships. Most urban agglomerations exhibited an uneven distribution of community correlation capacity. (4) Geographic adjacency and urbanization level significantly promoted carbon emission correlation, although the direction and magnitude of other factors’ influence varied. The findings contribute to the implementation of low-carbon planning, carbon reduction strategies and regional sustainable development.

Study on spatial and temporal correlation characteristics for RIS-aided macrocell high-speed railway propagation systems

Study on spatial and temporal correlation characteristics for RIS-aided macrocell high-speed railway propagation systems

Analysis of the Spatial Correlation Network and Driving Mechanism of China’s Transportation Carbon Emission Intensity

From 2008 to 2021, this study analyzed the spatial correlation characteristics between provincial transportation carbon emission intensity and explored ways to reduce transportation carbon emissions. This study used the modified gravity model, social network analysis (SNA) method, and temporal exponential random graph model (TERGM) to analyze the spatial correlation network evolution characteristics and driving mechanism of China’s transportation carbon emission intensity. This study found that China’s transportation carbon emission intensity and spatial correlation network have unbalanced characteristics. The spatial correlation network of transportation carbon emission intensity revealed that Shanghai, Beijing, Tianjin, Guangdong, Fujian, and other provinces were at the center of the network, with significant intermediary effects. The spatial correlation of transportation carbon emission intensity was divided into four functional plates: “two-way spillover”, “net benefit”, “broker”, and “net spillover”. The “net benefit” plate was mainly located in developed regions, and the “net spillover” plate was primarily located in underdeveloped regions. Endogenous structural and exogenous mechanism variables were the main factors affecting the evolution of the spatial correlation network of provincial transportation carbon emission intensity.

A transportation Revitalization index prediction model based on Spatial-Temporal attention mechanism

The global outbreak of COVID-19 has had a substantial impact on various sectors worldwide, including the economy, healthcare, entertainment, policy formulation, and international relations, with the transportation industry being particularly hard-hit. To curb the widespread transmission of the virus, many regions globally have implemented policies and measures to restrict transportation. These actions not only directly affect the transportation industry but also further impose a severe impact on the economy and societal development of various areas. In this context, the Transportation Revitalization Index (TRI) becomes particularly important. It can evaluate the degree of recovery of city traffic conditions after the pandemic, and accurate prediction of TRI can help governments and decision-makers respond more precisely to the challenges that the pandemic brings to the transportation industry. However, existing research primarily focuses on the direct correlation between TRI change data and COVID-19 pandemic data, without fully considering the dynamic spatial correlation features and time dependency features that affect the nonlinear changes of TRI. In light of the above situation, this study proposes a Deep Spatial-Temporal prediction model based on the Attention Mechanism (DeepST-AM). The DeepST-AM deeply integrates historical TRI data with multivariate pandemic information and uses a spatial–temporal attention mechanism to capture the deep and complex spatial–temporal information of urban data. To more accurately capture the long-term complex features of TRI data, this paper designs a Gaussian temporal convolution model dedicated to TRI data. To validate the effectiveness of DeepST-AM, researchers used real data from 29 core cities in China as samples and compared the performance of DeepST-AM with existing multiple methods on TRI prediction tasks. The experimental results showed that compared to other methods, the DeepST-AM proposed in this paper has a significant advantage in the long-term prediction tasks of TRI in terms of performance evaluation, indicator prediction, etc. In summary, this research provides a more accurate and comprehensive prediction model for the traffic recovery status after the pandemic, hoping to provide strong support for future decisions.

Multidimensional measurement of the High-Quality development of city Clusters: Dynamic Evolution, regional differences and trend forecasting--based on the basic connotation of Chinese-style modernization

Chinese-style modernization has led to new requirements for city clusters strategies, which is highly important for the high-quality development (HQD) of city clusters and new urbanization. Based on the basic connotation of Chinese-style modernization, an evaluation index system for the HQD of city clusters is constructed from five dimensions, namely, demographic advantages, coordinated regional development, material and cultural-ethical advancement, ecological sustainability, and opening-up. The HQD of 19 city clusters was measured from 2011 to 2021 using the entropy weight-CRITIC method, and the dynamic evolution, spatial correlation and long-term trend were analyzed. The study revealed that (1) the overall HQD of Chinese city clusters has shown continuous growth, and the spatial distribution of the gradient of HQD in the 'East, Center and West' has decreased, but the spatial pattern of 'South High and North Low' has further emerged. (2) The overall and intra-regional differences in the HQD of city clusters gradually narrowed, while the differences between city clusters remained significant. (3) The HQD of city clusters shows obvious positive spatial correlation and obvious spatial agglomeration characteristics, with high-value agglomerations mostly in mature-stage city clusters along the east coast. (4) There is an obvious 'club convergence' phenomenon in the HQD of city clusters; the higher the HQD of neighboring regions is, the greater the probability of upward HQD of city clusters, and the higher the quality of Chinese city clusters shows an upward trend in the long run.

The Impacts of Water Ecological Carrying Capacity on Green Total Factor Productivity: The Case of Chemical Industry in Jiangsu, China

The chemical industry is not only a crucial sector of national economy, but also a significant consumer of water resources and a major initiator of water pollution. The sustainable development of this sector is intricately linked to the regional water ecological carrying capacity (WECC). Based on SBM-DEA and Global Moran’s I, the green total factor productivity (GTFP) and spatial correlation characteristics of the chemical industry in 13 cities within China’s chemical agglomeration region in Jiangsu Province were estimated from 2015 to 2019. By combining the WECC results, the Tobit model was employed to reveal the driving factors of WECC in optimizing GTFP. The results indicated that the regional WECC in southern Jiangsu was increasing compared with that in northern Jiangsu, which promoted the growth of GTFP. WECC has been a positive radiation-driven effect since 2017, and the optimization of the various subsystems of WECC has had a different impact on GTFP. For the sustainable development of Jiangsu’s chemical industry, effective water resource policies should be formulated by the government, while enterprises need to pursue sustained structural adjustments.

Construction and evolutionary factors of spatial correlation network of China's provincial tourism resource conversion efficiency

Research objectiveTo explore the spatial correlation network characteristics and formation mechanisms of tourism resource conversion efficiency, and provide reference for the collaborative improvement of tourism resource conversion efficiency at the provincial level in China. Research methodsNon parametric SBM efficiency measurement method and social network analysis method. Research hypothesis: The spatial network correlation characteristics of tourism resource conversion efficiency are obvious, and regional connections are close. Research findings(i) during the research period, the spatial connection strength of China's tourism resource conversion efficiency continued to increase and the spatial network structure of tourism resource conversion efficiency tended to become more complex and significantly more stable. (ii) A spatially linked network with a stable tourism resource conversion efficiency structure formed in China. The number of network relations and density of the network fluctuated and increased, while the network efficiency continued to decrease; however, a strong small-world nature was observed. (iii) The economic development level difference matrix, tourism industry agglomeration difference matrix, human capital difference matrix, and marketization degree difference matrix significantly and positively affected spatial association relationship establishment, while the provincial adjacency matrix significantly and negatively affected such relationships.

Research on Dynamic Graphic Features in Digital Media Interfaces

In digital media interfaces, dynamic graphics integrate elements of animation design, graphic design, andcinematic language, presenting in various forms and demonstrating significant inclusivity. From the perspective of visual cognition, by capturing dynamic graphics within the interface, three-dimensional information such as time and space is acquired, and the cognition process exhibits characteristics of spatial and temporal correlation. In terms of information cognition, dynamic representation fragments information, resulting in a sense of discontinuity and intermittent memory. The efficiency of information cognition and transmission is enhanced through the coordination of audio, video, and other elements. In aesthetic perception, with the rise of Internet culture, people’s aesthetic perceptions towards dynamic graphic design have evolved, showcasing a generalization of form and the instantaneous nature of content. Technically, the complexity of design and the diversity of applications have established dynamic graphics as a typical design style label in digital media interfaces.

Distribution and Change Characteristics of Ecosystem Services in Highly Urbanized Areas along Gradients of Human Activity Intensity: A Case Study of Shenzhen City, China

Comprehensively and objectively revealing the spatial relationship between ecosystem services (ESs) and human activity intensity (HAI) is vital for achieving sustainable development goals. However, existing studies still have an incomplete understanding of how ESs change with HAI gradients. Therefore, taking Shenzhen City, China, as an example region experiencing rapid urbanization, the distribution of ESs and HAI in 2010 and 2020 were quantified using the InVEST model and the human footprint index method; at the same time, the gradient perspective was introduced and the spatial and temporal correlation characteristics of ESs along 10 HAI gradient bands, from weak to strong, were captured by applying multiscale geographically weighted regression (MGWR) and the bivariate spatial autocorrelation model. The findings showed that (1) the HAI demonstrated an increasing trend (20.63 (2010) and 23.36 (2020)), and the area with high values of HAI (the 10th gradient band) was distributed in the western part of the study area; meanwhile, the area with low HAI values (the 1st gradient band) was more distributed in the eastern part of the study area. (2) On the whole, the average levels of water conservation, soil conservation, carbon storage, and habitat quality decreased from 2010 to 2020; the spatial distribution characteristics of these parameters were similar. (3) In general, ESs were negatively correlated with HAI, and the negative correlation ratio was more than 65%. At the same time, the spatial and temporal correlations between ES patterns and HAI under different gradient bands were significant. These findings can effectively alleviate the pressure on the ecosystem caused by human activities, which is of great significance for the sustainable development of highly urbanized regions.

Ultra-short-term operation situation prediction method of active distribution network based on convolutional neural network long short term memory

The large-scale and high-permeability access of distributed generations (DGs) is making the distribution networks develop into active distribution networks (ADNs). The increasing complexity of the structure of ADNs also increases the vulnerabilities for cyberattacks. To accurately predict the operation situation of ADNs no matter whether cyberattacks occurred, this paper proposes an ultra-short-term operation situation prediction method of ADNs based on CNN-LSTM. Firstly, an ADNs situation prediction index system is established, which can comprehensively evaluate the future operation situation of ADNs from different perspectives. Secondly, a multi-feature data reconstruction method based on the time sliding window algorithm is proposed, which is utilized for constructing 2-dimensional matrix and as input datasets for multiple independent CNN-LSTM models to predict each situation prediction index. Then, there are 8 independent CNN-LSTM models shared same input matrix to predict 8 ADNs situation prediction index value without interfering with each other. Among them, CNN is used to extract the spatial correlation feature vectors of ADNs historical operation data and meteorological factor data in ultra-short term, which are reconstructed in time series and used as the input data of LSTM. LSTM is used to extract long-term historical temporal relationship to obtain ADNs operation situation prediction index value. Finally, we utilize the fuzzy analytic hierarchy process to calculate the future operation situation of ultra-short-term ADNs. Taking a real ADNs with 33-node as an example, we compared our proposed methodology to other existing excellent machine learning-based models, the result demonstrates that our proposed prediction method exhibits outstanding performance in time consumption and prediction accuracy.

Multi-residual 2D network integrating spatial correlation for whole heart segmentation

Whole heart segmentation (WHS) has significant clinical value for cardiac anatomy, modeling, and analysis of cardiac function. This study aims to address the WHS accuracy on cardiac CT images, as well as the fast inference speed and low graphics processing unit (GPU) memory consumption required by practical clinical applications. Thus, we propose a multi-residual two-dimensional (2D) network integrating spatial correlation for WHS. The network performs slice-by-slice segmentation on three-dimensional cardiac CT images in a 2D encoder–decoder manner. In the network, a convolutional long short-term memory skip connection module is designed to perform spatial correlation feature extraction on the feature maps at different resolutions extracted by the sub-modules of the pre-trained ResNet-based encoder. Moreover, a decoder based on the multi-residual module is designed to analyze the extracted features from the perspectives of multi-scale and channel attention, thereby accurately delineating the various substructures of the heart. The proposed method is verified on a dataset of the multi-modality WHS challenge, an in-house WHS dataset, and a dataset of the abdominal organ segmentation challenge. The dice, Jaccard, average symmetric surface distance, Hausdorff distance, inference time, and maximum GPU memory of the WHS are 0.914, 0.843, 1.066 mm, 15.778 mm, 9.535 s, and 1905 MB, respectively. The proposed network has high accuracy, fast inference speed, minimal GPU memory consumption, strong robustness, and good generalization. It can be deployed to clinical practical applications for WHS and can be effectively extended and applied to other multi-organ segmentation fields. The source code is publicly available at https://github.com/nancy1984yan/MultiResNet-SC.

Land use data can improve the accuracy of carbon emission spatial inversion model

AbstractInvestigating the spatial distribution and correlation characteristics of carbon emissions would be conducive to the policy formulation for precise carbon emission spatial reduction. Firstly, a new carbon emission spatial inversion model was developed, incorporating nighttime light data and land use data. After verifying the validity and accuracy of the inversion results, the continuous carbon emission spatial data in the Beijing‐Tianjin‐Hebei Urban Agglomeration (BTHUA) were acquired from 2000 to 2019. Then, the spatial distribution and correlation characteristics were further analyzed in the BTHUA. Finally, policy recommendations were proposed for carbon emission reduction and urban sustainable development. The results showed that the built model can improve the accuracy of the carbon emission spatial inversion data. The carbon emissions were low in the northwest and high in the southeast of the BTHUA, with a noticeable expansion of the high carbon emission contiguous areas around Beijing, Tianjin, Shijiazhuang, and other prefecture‐level cities, which was consistent with the socioeconomic development pattern. The center of gravity of carbon emissions moved to the southeast, showing a relatively stable distribution. The spatial correlation degree of carbon emissions among cities gradually increased, with Beijing and Tianjin playing a prominent role. As a scientific tool, the spatial inversion model helps to produce more accurate spatial data. The results and conclusions can provide useful and scientific references for spatial analysis and regulation strategies of regional carbon emission reduction.

Can Green Credit Improve the Innovation of Enterprise Green Technology: Evidence from 271 Cities in China

With the promotion of the “carbon neutrality” and “carbon peak” initiatives, green credit plays an important role in helping enterprises to change their high-pollution, high-energy-consumption production methods and establishing a sound green, low-carbon, and circular economic system. This study used spatial correlation analysis and a fixed effects SDM model to examine the spatiotemporal and causal relationship between green credit levels and enterprise green technology innovation in 271 prefecture level cities in China from 2013 to 2021. It found that (1) green credit and green technology innovation levels are both highest in the eastern region, followed by the central region, and exhibit spatial correlation characteristics. The main types of agglomeration are high–high and low–low agglomeration. (2) Green credit has a significant enhancing effect on green technology innovation in enterprises, and this conclusion still holds after robustness and endogeneity tests. (3) There is significant regional heterogeneity in the impact of green credit on green technology innovation, mainly concentrated in the central and western regions. (4) Green credit can significantly increase enterprise R&D investment and enhance the level of green technology innovation through this channel. Finally, some policy implications are provided to the decision-making departments that can be used for reference.

Exploring the coupling coordination relationship of water resources, socio-economy and eco-environment in China

Water resources (W), socio-economy (S), and eco-environment (E) have incredibly intricate linkages of interaction, and the coordination of them is crucial to the long-term sustainability of a nation. Thus, we considered “water resources, socio-economy, and eco-environment” (W-S-E) as a composite system and constructed an evaluation model to quantitatively analyze the coupling coordination degree (CCD) of W-S-E system in China from 2011 to 2020. Then, the spatial correlation characteristics were analyzed by using spatial autocorrelation method. To analyze the time evolution patterns of the W-S-E system, this paper divided the stages from the perspective of clustering, which is more scientific and interpretable than the CCD fixed-value division. We found that: (1) W subsystem, S subsystem and E subsystem were closely connected and its CCD was enhanced with relatively higher growth rates in the development of S subsystem but slower growth rates in the W subsystem. (2) The CCD of W-S-E system had spatial correlation. The areas with low CCD were concentrated in the west of China, forming poor coordinated development phenomena. Conversely, most of provinces had relatively high CCD in the east of China with the coastal region playing radiative driving function. (3) The temporal change of W-S-E system followed four transforming patterns including “policy-oriented type”, “resource problems constraint type”, “socio-economy leading type”, and “special location controlling type”. Furthermore, we also put forward some advice and policy suggestions. The findings provide research basis and guidance for the sustainable and coordinated development of water, society and ecology.

Hyperspectral Image Shadow Enhancement Using Three-Dimensional Dynamic Stochastic Resonance and Classification Based on ResNet

Classification is an important means of extracting rich information from hyperspectral images (HSIs). However, many HSIs contain shadowed areas, where noise severely affects the extraction of useful information. General noise removal may lead to loss of spatial correlation and spectral features. In contrast, dynamic stochastic resonance (DSR) converts noise into capability that enhances the signal in a way that better preserves the image’s original information. Nevertheless, current one-dimensional and 2D DSR methods fail to fully utilize the tensor properties of hyperspectral data and preserve the complete spectral features. Therefore, a hexa-directional differential format is derived in this paper to solve the system’s output, and the iterative equation for HSI shadow enhancement is obtained, enabling 3D parallel processing of HSI spatial–spectral information. Meanwhile, internal parameters are adjusted to achieve optimal resonance. Furthermore, the residual neural network 152 model embedded with the convolutional block attention module is proposed to diminish information redundancy and leverage data concealed within shadow areas. Experimental results on a real-world HSI demonstrate the potential performance of 3D DSR in enhancing weak signals in HSI shadow regions and the proposed approach’s effectiveness in improving classification.

Dynamic Analysis of Regional Integration Development: Comprehensive Evaluation, Evolutionary Trend, and Driving Factors

Regional integration, as an essential measurement for solving unbalanced and uncoordinated regional development, plays an important role in achieving regional sustainable development. In this study, we aimed to construct a systematic research framework to facilitate the development of regional integration. Using 31 prefecture-level cities in the urban agglomeration in the Middle Reaches of the Yangtze River (MYR-UA) as case sites, this study applied box plots, kernel density estimation, GIS visualization tools, Markov chains, and geographic detectors to reveal the dynamic spatiotemporal evolution and factors influencing regional integration from 2009 to 2018. The results indicate that the level of regional integration and its subsystem development is suboptimal in MYR-UA; the temporal characteristic shows an upward fluctuating trend, and the spatial distribution shows remarkable spatial correlation and clustering characteristics. Additionally, we found that the level of regional integration development in MYR-UA has both “path dependence” and “self-locking” effects, and the spatial lag type has a crucial impact on the degree of regional transfer stability. The dominant factors affecting regional integration development include the GDP per capita, economic openness, industrial structure, proportion of education expenditure in fiscal expenditure, urbanization rate, proportion of environmental investment in fiscal expenditure, population density, capital flow, information flow, and technology flow. Finally, based on the findings of this study, policy recommendations for promoting regional integration are proposed.

Construction of Social Resilience Assessment System after Floods in the New Era

Abstract This paper constructs an assessment framework through theoretical research and literature study, determines the assessment indicators using the systematic review method, and forms a final assessment system of social resilience after flooding based on the correlation test. On this basis, the index weights were determined using the comprehensive assignment method, and the social resilience index was calculated using multi-criteria optimization and compromise solutions methods. The spatiotemporal evolution trend and spatial correlation characteristics of post-flood social resilience were explored by combining mathematical statistical methods, geographic information technology, and spatial measurement models. The temporal evolution characteristics of different dimensions of social resilience during the period 2012–2021 show that the social resilience index declined steeply in 2012, reached a maximum value of 0.316 in 2018, then gradually decreased to 0.305 in 2020, and recovered to 0.312 in 2021, with an overall increase of 5.05%. Assessing the social resilience of 17 cities under the jurisdiction of Henan Province, overall, the ability of the social system to cope with heavy rainfall and flooding disasters in 10 cities showed an increasing trend, and 7 towns showed a decreasing trend.The social resilience of Zhengzhou City under heavy rainfall and flooding disasters in 2017–2021 showed a trend of decreasing and increasing, with a composite index fit of 0.885, 0.893, 0.806, 0.893, 0.806, 0.824, 0.861.This paper constructs a social resilience assessment system after flooding to provide some reference for central cities to cope with extreme weather.

Spatiotemporal prediction of carbon emissions using a hybrid deep learning model considering temporal and spatial correlations

Accurate prediction of carbon emissions plays a crucial role in enabling government decision-makers to formulate appropriate policies and plan necessary response measures in a timely manner. This study explored the spatiotemporal prediction methods for carbon emissions from temporal and spatial correlation perspectives. Specifically, a deep learning-based hybrid prediction framework for carbon emissions was developed. It includes three sequentially linked modules: gated recurrent units for modelling temporal correlation features, graph convolutional networks for modelling spatial correlation features and spatiotemporal prediction. The proposed model enables one- and multi-step spatiotemporal prediction of carbon emissions. The monthly Open-source Data Inventory for Anthropogenic CO2 data for three major urban agglomerations in China were utilised to assess the performance of our model. Results indicate that our model outperforms the baseline models in terms of predictive accuracy for single- and multi-step spatiotemporal predictions. Additionally, our model demonstrates good generalisation through further application experiments.

A novel spatial electric load forecasting method based on LDTW and GCN

AbstractSpatial power load forecasting is crucial for power grid planning, generation planning, dispatching, efficient power utilization, and sustainable development. The integration of new energy sources and electric vehicles has significantly altered grid loads, increasing the complexity of spatial load forecasting. However, existing techniques fail to fully consider the temporal and spatial correlation characteristics of data, leading to challenges in data identification and summarization. This reduces load forecasting accuracy and prolongs prediction time. To address these issues, a spatial electric load forecasting method based on improved scale limited dynamic time warping (LDTW) and graph convolutional network (GCN) are proposed. Firstly, the improved scale LDTW is used to improve the clustering effect of K‐Mediods++, refine the type of load data, and make the subsequent model training more targeted. Secondly, the interconnections and distances of substations in a real network structure is used to build a graph model to capture the power load distribution. Finally, based on the clustering results and the graph model, GCN‐LSTM is used to construct the spatio‐temporal forecasting algorithm. The proposed algorithm is tested using load data from a region in Shanghai and compared with other advanced algorithms. Results show that the algorithm achieves higher prediction accuracy and efficiency.

Spatial correlation-based machine learning framework for evaluating shale gas production potential: A case study in southern Sichuan Basin, China

Assessment of production potential and prediction of sweet spots in unexploited shale gas wells are crucial technologies for achieving a high success rate in drilling. Most existing methods are only applicable for yield forecasting of shale gas wells with known geological and drilling/completion factors after production. In addition, the shale gas reservoir in the Longmaxi Formation in the southern Sichuan Basin of China is characterized by low porosity, low permeability, and diverse gas reservoir states. Thus, forecasting production from unexploited wells and predicting the exact location of the sweet spot under complex geological conditions have become challenging topic for both academia and industry. According to the first law of geography, shale gas wells that are closer in space have more similar geologic features. Based on this foundation, a machine-learning prediction model based on spatial correlation (SC-MLPM) is proposed for evaluating potential production of shale gas wells in the Changning play located in Longmaxi Formation in the southern Sichuan basin, China. Specifically, an improved K-nearest neighbor algorithm (SC-KNN) based on the spatial correlation characteristics of the exploited wells is designed to estimate the relevant geological factors of the unexploited wells in the same area. In addition, an extreme gradient lifting model based on Huber loss function (Hu-XGB) is developed to predict the potential production of unexploited shale gas wells, and then the shale gas sweet spot area in the research area is predicted quickly and accurately. The experimental results on 88 shale gas wells from Changning play show that the mean relative error of the prediction results of the proposed method is 9.8%. Furthermore, the results also determine that the sweet spots of shale gas wells in the research area are mainly developed in the northwest and northeast directions, and gradually become worse in the southeast direction. Eventually, experimental results for the Fox Creek play in Canada show that the proposed model obtains better predictive performance as the number of gas wells increases, and also verifies the generalizability. This work provides a basis for the efficient development of the research area.