Cities Of Henan Province Research Articles

Research on the evaluation of emergency management capability for urban public health emergencies under the perspective of resilience—a case study of Henan Province, China

With the rapid development of the economy and society, the likelihood of sudden public health emergencies in urban areas continues to rise. In particular, major infectious diseases that have gained global attention, such as the SARS virus, H1N1 influenza, Ebola outbreak, and COVID-19 pandemic, have presented significant challenges to urban emergency management systems. Evaluating emergency management capability is a fundamental requirement for developing emergency response capacity. To this end, this study combines the theory of resilience with the theory of full-process equilibrium emergency management, selects 31 evaluation indicators from six key aspects: preparedness, forewarning, mitigation, disposal, recovery, and learning. The indicator weights are determined using the AHP-Entropy Weight Method, and a TOPSIS model is constructed to assess the emergency management capability of urban public health emergencies. The model’s applicability is validated by examining 18 cities in Henan Province. The findings suggest that Jiaozuo, Hebi, Zhengzhou, and Luohe possess relatively robust emergency management capabilities for sudden public health incidents, whereas Kaifeng, Pingdingshan, and Shangqiu exhibit weaker capabilities.

Research on Spatial Pattern and Accessibility of Traditional Villages-Taking Henan Province as an Example

Abstract. Chinese culture has a long history. Traditional villages carry the breath of history. The great cultural attraction of traditional villages to people and the implementation of rural revitalization policies, it makes the attention to traditional villages gathered. Henan Province has a deep cultural heritage, he has many traditional villages, widely distributed. Therefore, it is particularly important to study the spatial pattern and accessibility of national-level traditional villages in Henan Province. This study takes 275 national-level traditional villages in Henan Province as research objects, using GIS analysis with accessibility to study the spatial pattern of traditional villages in Henan Province and to demonstrate the accessibility of traditional villages in prefectural-level cities in Henan Province at the municipal scale. Studies have shown that the spatial pattern and accessibility of the distribution of traditional villages in Henan Province are closely related to many factors (transportation road network, distance from the central city, etc.). The accessibility values of traditional villages in each prefecture-level city vary greatly, indicating that there are obvious differences in the accessibility of traditional villages in Henan Province. It intuitively reflects the spatial distribution and accessibility of traditional villages in Henan Province, with a view to providing a reference for the tourism development of traditional villages. Providing an analytical basis for promoting the optimal allocation of traditional village resources.

A multi-index comprehensive evaluation method for assessing the water use balance between economic society and ecology considering efficiency-development-health-harmony.

Quantitative assessment of the water use balance between economic society and ecology (EEWB) is the basis for coordinating the competitive relationship of water use between human activity and ecological requirements and. It is of great significance for optimizing the water resources carrying capacity and achieving a healthy regional water balance. Based on the concept of harmonious balance, this paper puts forward the definition and connotation of EEWB regarding the competition in water use between economic society and ecology. And, a novel framework for assessing the EEWB is proposed. It has four aspects relating to water resources, economic society, ecology, and human-water relationship. Linked to these aspects the Data Envelopment Analysis (DEA) technique, Water Ecological Footprint (WEF) model, InVEST model and indicators system of human-water relationship are used to establish a water resources efficiency index (IEEWB-W), economic society high-quality development index (IEEWB-ES), ecology health index (IEEWB-E), harmony index of human-water relationship (IEEWB-H). The four indices were then integrated into the water use balance between economic society and ecology index (IEEWB) with Euclidean distance, thus forming the EEWB quantification method system. Finally, the temporal and spatial characteristics of EEWB during 2010-2022 was diagnosed in Henan Province and cities of China. Results reveal that: (1) The water resources utilization efficiency exhibit a changing trend of initial decrease followed by subsequent increase; (2) Southern cities in Henan Province have a higher economic society development level compared to northern cities; (3) IEEWB-E in Henan Province is below 0.60, indicating that the regional ecology health remains consistently vulnerable; (4) IEEWB-H in Henan Province shows an increasing trend, indicating that a gradual improvement and overall upward development in the human-water relationship; (5) IEEWB multi-year average was within [0.53, 0.65] in Henan Province, indicating a state of Proximity imbalance. The low level of ecological health is the primary influencing factor. These findings will contribute to a better understanding of the water use balance between economic society and ecology and provide scientific reference for achieving a healthy regional water balance.

Study on the Level Measurement and Spatial Distribution of Comprehensive Competitiveness of Logistics Industry in Henan Province

This paper takes the 18 cities in Henan Province as the research object, combining their relevant data in 2022, and conducts a comparative study on the comprehensive competitiveness indicators of logistics industry in Henan Province through factor analysis method. Starting from the three dimensions of infrastructure level, economic benefits, and development scale, this paper explores the level of comprehensive competitiveness of logistics industry in Henan Province and explores the spatial distribution characteristics of comprehensive competitiveness through spatial trend analysis and natural breakpoint method. And it puts forward corresponding improvement strategies.

Relationship Between Land Use Transformation and Ecosystem Service Value in the Process of Urban–Rural Integration: An Empirical Study of 17 Prefecture-Level Cities in Henan Province, China

Urban–rural integration, which aims to balance economic growth with sustainable land use, is becoming an increasingly critical strategy for regional development. This study provides crucial insights into the relationship between land use changes and ecosystem service values (ESVs) in rapidly urbanizing areas by analyzing the urban–rural integration process in Henan Province, a typical agricultural province in China. This research investigated the relationship between land use transformation and ESVs in Henan Province, China, from 1990 to 2020. Utilizing land use data and employing the equivalent factor method and elasticity model, we analyzed shifts in land use and their impacts on ecosystem services across 17 prefecture-level cities. Results indicated a gradual improvement in the urban–rural integration development index of Henan Province, particularly after 2000, but with notable disparities among cities. Zhengzhou, the provincial capital, consistently demonstrated high urban–rural integration development index (URII) values, influencing the integration efforts of neighboring cities. Conversely, peripheral cities exhibited lower integration indices. Notable shifts in land use patterns characterized by diverse transfer dynamics distinctively influenced ESVs across regions. Urban sprawl initially exerted substantial impacts on ecosystem services and stabilized over time. Suburbanization impacts peaked in the early and middle stages, while agricultural intensification initially affected ecosystem services, but their effects diminished with increased efficiency. Ecological restoration efforts consistently enhanced ESVs. The findings contribute to a more comprehensive understanding of the dynamic interactions between land use transitions and ecosystem services in the context of urban–rural integration.

Novel Framework for Exploring Human–Water Symbiosis Relationship: Analysis, Quantification, Discrimination, and Attribution

There is an interdependent symbiotic relationship between humans and water; scientific and effective assessment of the human–water symbiosis relationship is of great significance for the promotion of sustainable development. This study developed a novel framework of the human–water symbiosis relationship under an integrated perspective, which included theoretical interpretation, quantitative assessment, pattern discrimination, and an attribution analysis. Based on the symbiosis theory, the theoretical analysis of the human–water relationship was carried out to analyze the three basic elements of the human–water system, and then the evaluation index system of the human–water symbiosis system was constructed to quantitatively assess the development level of the human system and the water system. The Lotka–Volterra model was used to identify the symbiotic pattern, and the human–water symbiosis index was calculated to characterize the health state of the human–water symbiosis system. The main influencing factors of the human–water symbiosis system were further identified through an attribution analysis. Finally, a case study was carried out with 18 cities in Henan Province. Results reveal that (a) the proposed method can effectively realize the quantitative characterization of the human–water symbiosis relationship, with good applicability and obvious advantages; (b) the human–water symbiosis pattern of cities in Henan Province is dominated by the “human system parasitizes water system (H+W−)” pattern, and more attention should be paid to the water system in the subsequent development of it; and (c) the main factors influencing the human system, the water system, and the human–water symbiosis system are the research and development (R&D) personnel equivalent full-time (H7), per capita water resources (W1), and proportion of water conservancy and ecological water conservancy construction investment (W6), respectively. The findings can provide theoretical and methodological support for the study of the human–water symbiosis relationship and sustainable development in other regions.

An Application of The Theory of Planned Behaviour: Factors Influencing Parental Decision on Children Involvment in Out-Of-School Music Education

In China's music education and training industry, the exploration of parents' and children's educational decisions on the demand side of the market is crucial to the healthy functioning of the music education market. The current study applies TPB theory and modelling to investigate the factors influencing parental decision-making in children's out-of-school music education participation. The study was conducted in Henan Province, China, with a sample of 650 parents from 21 music education institutions in seven cities in Henan Province. The results of data analyses showed that parental ATT, SN, and PBC all had significant positive effects on PI. PBC directly affected PD, while PI was the most significant influence on PD.

Coupling Coordination Degree of Land, Ecology, and Food and Its Influencing Factors in Henan Province

Studying the spatiotemporal evolution characteristics of the coupling coordination of the land–ecology–food system (LEF) aids in promoting green agricultural development and regional resource management. This study enriches food indicators under the dietary structure and uses the coupling coordination degree model to analyze the coupling coordination relationship among the LEF of 18 cities in Henan Province from 2011 to 2020. The gray relational degree model is used to investigate the main influencing factors determining the synergistic development of the system. The results show that the comprehensive development index of the LEF in Henan Province ranges between 0.4 and 0.6. The overall comprehensive evaluation index of various cities is ranked as Southern Henan > Eastern Henan > Central Henan > Northern Henan > Western Henan, with the greatest fluctuation observed in the food subsystem. During the study period, the coupling degree of Henan’s LEF ranged from 0.277 to 0.996, indicating stages from low- to high-level coupling. The coupling coordination degree ranged from 0.338 to 0.775, generally bordering on imbalance and barely coordinated. The impact of each subsystem evaluation index on the system’s coupling coordination degree can be ranked as food subsystem > ecology subsystem > land subsystem, with the correlation degree of internal indicators of the food and ecology subsystems with the system’s coupling coordination degree being over 85%, emphasizing the importance of strict management. In summary, the coupling coordination of the LEF system in Henan Province urgently needs to be improved; especially, the coordination of the agricultural system is particularly important. Clarifying the spatiotemporal pattern of the LEF coupling and its coordination can provide a scientific basis for the coordinated development of land use, agricultural ecology, and grain production in Henan Province.

Evaluation and Spatial–Temporal Pattern Evolution of Synergy Degree of Emergency Management for Urban Flood Disasters from the Perspective of Sustainable Development—The Case of Henan, China

The management of urban flood disasters is a systematic engineering project that requires a great amount of manpower, material resources, and financial resources, and the interaction and coordination degrees of various elements in the system deeply affect the efficiency of the final governance. According to the theories of synergy, composite systems, and sustainable development, this research first established an evaluation index system to determine the synergy degree of urban flood disaster emergency management from the four dimensions of prevention and preparation, monitoring and early warning, response and rescue, and recovery and reconstruction. Then, the synergy degree was explored by using the developed composite system synergy degree model on the basis of the panel data of 18 prefecture-level cities in Henan Province from 2013 to 2021, and synergy level change characteristics were analyzed from the perspectives of time and space. Finally, the obstacle degree model was applied to explore the obstacle factors affecting synergy degree development. The results showed that the overall level of the urban flood disaster emergency management coordination degree in Henan Province was relatively low, and there were significant differences in synergy among cities. Among them, 12 cities presented mild synergy, and 6 cities showed mild nonsynergy. The spatial correlation of the synergy degree was not stable, which revealed a lack of mature coordination mechanisms for flood disaster emergency management among cities. The analysis of obstacle factors showed that recovery and reconstruction subsystems were the main obstacle systems that affected the synergy degree.

Evaluation and Regional Differences of Urban Green Development in Henan Province

As an extension of ecological concepts, urban green development has gradually become a new bridge for various countries or regions to achieve sustainable development. Based on the panel data of 17 cities in Henan Province, China from 2007 to 2022, this article uses the entropy method to measure the green development level of cities in Henan Province, and uses the Dagum Gini coefficient method to analyze the green development differences between cities. The results show that: first, urban green development in Henan Province is generally at a lower-middle level and tends to be balanced. Second, there are obvious regional gaps in urban green development in Henan Province. Third, inter-regional disparity is the main reason for the differential distribution of urban green development levels in Henan Province. In order to promote the improvement of urban green level and narrow the spatial development gap in Henan Province, this study puts forward corresponding policy suggestions from the aspects of green investment, green technology innovation, industrial structure upgrading and green life. This also provides reference for other less developed regions in China to achieve balanced urban green development.

Influencing factors of hypertension and diabetes care cascade: a qualitative study

Objective: Employing the cascade care model, this qualitative study explores determinants influencing the cascading care stages of hypertension and diabetes by interviewing various stakeholders. Methods: In July 2023, purposive sampling was employed to recruit participants from Gongyi and Wugang cities in Henan Province, and Linqu County in Weifang City, Shandong Province. Semi-structured in-depth interviews were conducted with representatives of policymakers, healthcare institution managers, providers, and patients with hypertension and diabetes.And thematic analysis was performed using both inductive and deductive approaches. Results: A total of 82 individuals were interviewed, with an age range of (53.8±12.0) years, among which 48 (58.5%) were male; including 5 policymakers, 10 institutional managers, 20 healthcare providers, and 47 patients with hypertension and diabetes. The study identified both barriers and facilitating factors at the patient, healthcare provider, and system levels across various stages: awareness, screening, diagnosis, treatment, long-term management, and control of hypertension and diabetes. Conclusion: By delineating and analyzing the barriers and facilitators at each stage of hypertension and diabetes care, this study lays the groundwork for the development of effective, feasible, and sustainable implementation pathways, with significant implications for the enhanced management of hypertension and diabetes in China.

Inventory and Distribution Characteristics of Carbon Emissions from Agricultural Sources in Henan Province from 2011 to 2020

Agriculture is an important part of Henan's economic development, and agricultural production is also an important source of greenhouse gas emissions. In this paper, the activity level data of agricultural carbon emissions in 18 cities in Henan Province were collected. Based on the calculation method provided by the Guidelines for Compiling Provincial Greenhouse Gas Inventories and referring to the 2006 IPCC Guidelines for National Greenhouse Gas Inventories, agricultural CO2, CH4 and N2O emissions were carefully estimated. An agricultural greenhouse gas inventory was compiled for Henan Province from 2011 to 2020. Then, based on the spatial distribution and emission intensity, the carbon emissions of each city in Henan Province in 2019 were further analyzed. The results show that carbon emissions decreased from 57,603,500 tons in 2011 to 44,517,300 tons in 2020, with an average annual decrease rate of about 2.66%. The total agricultural carbon emissions in Henan showed a downward trend, and agricultural land was the dominant factor of carbon emissions, accounting for about 47% of the total carbon emissions over the years.

Molecular characterization of Cryptosporidium spp. and Giardia duodenalis in pet cats in Henan Province, central China

Cryptosporidium spp. and G. duodenalis often infect humans, cats, and other mammals, causing diarrhea and being responsible for numerous outbreaks of waterborne and foodborne infections worldwide. The rapid increase in the number of pet cats poses a substantial public health risk. However, there were few reports about the infection of Cryptosporidium spp. and G. duodenalis infections in pet cats in Henan Province, central China. Thus, to understand the prevalence and genetic distribution of Cryptosporidium spp. and G. duodenalis in pet cats, and to evaluate the zoonotic potential, possible transmission routes and public health implications of isolates, fecal samples (n = 898) were randomly collected from pet cats in 11 cities in Henan Province, central China. Nested PCR based on the SSU rRNA gene and bg gene was used to the prevalence of Cryptosporidium spp. and G. duodenalis, respectively. The prevalence was 0.8 % (7/898) and 2.0 % (18/898) for Cryptosporidium spp. and G. duodenalis respectively. Additionally, the Cryptosporidium spp. positive isolates were identified as C. parvum subtype IIdA19G1 by gp60 gene. In the present study, the IIdA19G1 subtype was discovered in pet cats for the first time in China, enriching the information on the host type and geographical distribution of Cryptosporidium spp. in China. For G. duodenalis, a total of 18 G. duodenalis positive samples were identified, belonging to four assemblages: a zoonotic assemblage A1 (4/898), three host-specific assemblages C (8/898), D (5/898), and F (1/898). Interestingly, we found that pet cats infected with Cryptosporidium spp. and G. duodenalis are more likely to experience emaciation symptoms compared to the negative group. More importantly, the prevalence of Cryptosporidium spp. and G. duodenalis detected in the present study were low, but the subtype IIdA19G1 of Cryptosporidium spp. and the assemblages A1, C, D, and F of G. duodenalis have the potential for zoonotic transmission. Thus, we should focus on preventing and controlling the risk of cross-species transmission that may occur in pet cats in Henan Province.

Exploration of detection methods for free silica with different crystal forms in dust

Objective: To investigate the differences and applicability of free silica detection methods of different crystal forms in dust, and to provide a basis for the selection of various methods. Methods: From December 2021 to June 2022, dust samples from 20 enterprises in different industries in 18 cities in Henan Province were randomly selected as the investigation objects. X-ray diffraction (XRD) method was used to analyze the samples and classify the samples. Based on GBZ/T 192.4-2007 "Determination of Dust in the Air of Workplace-Part 4: Content of Free Silica in Dust", pyrophosphate method and infrared spectrophotometry were used for quantitative determination. The measured results were analyzed by paired sample t test to evaluate the advantages and disadvantages of the two methods and their applicable scope. Results: The XRD results of 20 dust samples could be divided into α, β, γ crystal types and the mixed type of α and γ. There was no significant difference between pyrophosphate method and infrared spectrophotometry (P=0.180). The pyrophosphate method results of β, γ and α, γ mixed crystalline free silica were significantly higher than those of infrared spectrophotometry, and the difference was statistically significant (P<0.001) . Conclusion: Pyrophosphate method and infrared spectrophotometry are suitable for α-type free silica, while pyrophosphate method is suitable for β, γ and α, γ mixed crystalline free silica.

A STUDY OF THE IMPACT OF DIGITAL INCLUSIVE FINANCE ON THE REAL ECONOMY: EVIDENCE FROM CHINA

With the rapid development of digital technology, digital inclusive finance has become an important force for promoting the development of the real economy. Based on an in-depth analysis of the relationship between digital inclusive finance and the development of the real economy, this paper takes Henan Province as an example. Based on the Digital Inclusive Finance Index and the Henan Statistical Yearbook, panel data on 17 prefectural-level cities in Henan Province for the period of 2012-2021 are used to carry out a basic regression analysis of various dimensions by using the fixed effect model, and the promotion effect of digital inclusive finance on the development of the real economy and different dimensions of digital inclusive finance on the promotion of real economic development are drawn. The paper finally used the quantile regression method to carry out a heterogeneity test and concluded that the promotion effect of digital inclusive finance is more significant in regions with lower levels of economic development. Therefore, to better promote the development of the real economy, Henan Province should strengthen the construction of a digital inclusive financial system, emphasize scientific and technological innovation, and use digital inclusive finance to guide rural migrants to return to their hometowns for development.

Spatio-temporal evolution and driving factors of new urbanization in central China based on multi-source data.

Urbanization is an inevitable outcome of the development of human society to a certain stage, and it is also an irreversible pattern of the concentration degree of human society. Based on multi-source data such as remote sensing images, ecological environment and socio-economic data, the evaluation index system of new urbanization is constructed from multi-dimensions of population, economy, society, space and ecology. To explore the spatio temporal evolution and driving factors of urbanization in 80 prefecture-level cities in central China from 2013 to 2021 by using entropy method, spatial autocorrelation model and geographic detector. The results show that: (1) The level of new urbanization continues to grow, with the average value rising from 0.1562 in 2013 to 0.2557 in 2021, and the regional differences are obvious, forming a circle structure with Wuhan, Zhengzhou and other provincial capitals as the center and weakening radiation to surrounding cities. (2) The agglomeration of ecological urbanization is significant, and the agglomeration trend is gradually enhanced. The high-high agglomeration areas tend to Xinzhou City, most prefecture-level cities in Hubei Province and some prefecture-level cities in Southern Hunan Province, while the low-low agglomeration areas tend to Changzhi City, most prefecture level cities in Henan Province and some prefecture-level cities in Northern Anhui Province. (3) The night light index, total retail sales of consumer goods, investment in fixed assets, proportion of built-up areas and urban economic density are the main driving factors affecting the level of new urbanization. (4) The interaction of driving factors shows double factor enhancement and nonlinear enhancement effects.

Seroepidemiological analysis of hepatitis B virus infection among adolescents aged 0-14 years in Henan Province and preliminary evaluation of the effectiveness of childhood hepatitis B vaccine immunization program

Objective: To analyze the seroepidemiological characteristics of hepatitis B virus (HBV) infection among adolescents aged 0-14 years in Henan Province and to evaluate the effectiveness of the childhood hepatitis B vaccine (HepB) immunization program. Methods: From September 2021 to March 2022, a total of 4 883 adolescents aged 0-14 years were selected from 25 villages or communities of 18 provincial-level cities in Henan Province by using the multi-stage random cluster sampling method. Demographic data were collected through questionnaires. The 3 ml of blood samples were collected from individuals aged 0-4 years and 5 ml of blood samples were collected from individuals aged 5-14 years to test HBsAg, HBcAb and HBsAb. Data on vaccination were collected through Henan Provincial Immunization Information System and hepatitis B cases in Henan Province were collected through China Infectious Disease Reporting System. The effectiveness of the childhood HepB immunization program was analyzed. Results: The average age of 4 883 subjects was (7.32±2.81) years old. The positive rates of HBsAg and HBcAb were 0.1% (7/4 883) and 1.0% (50/4 883), and the population standardized rates were 0.3% and 1.7%. In 2002, the positive rate of HBsAg among adolescents aged 0-14 years in Henan Province was 3.39%. Compared with that in 2002, the number of chronic HBV infections among adolescents in Henan Province in 2022 decreased by about 0.7 million. In 2002, the vaccination rate of newborns who completed all three doses of vaccine was 6.26%. In 2003, the vaccination rate of the hepatitis B vaccine rose rapidly, reaching 90% in 2013 for the first time. After 2014, the vaccination rate in Henan Province continued to remain above 95%. The proportion of cases among children aged 1-4 years in clinical reports decreased from 0.43% (1 108/256 566) in 2006 to 0.01% (78/80 655) in 2021. The proportion of cases among adolescents aged 5-19 years decreased from 18.21% (46 710/256 566) in 2006 to 1.1% (827/80 655) in 2021. Conclusions: From 2002 to 2022, the positive rate of HBsAg among adolescents aged 0-14 years has decreased significantly in Henan Province. The effectiveness of the HepB immunization program for children is good.

Spatial-temporal evolution law analysis of resource and environment carrying capacity based on game theory combination weighting and GMD-GRA-TOPSIS model. Evidence from 18 cities in Henan Province, China

In the backdrop of the high-quality growth of China's Yellow River Basin (YRB), Henan Province as a significant resource, population, economic, and grain-producing province, the contradiction between the finite availability of natural resource supply and ecological environmental capacity and the socioeconomic development has become more and more prominent, which significantly restricts the healthy sustainable development of Henan Province. Thus, it is essential to precisely assess the Resource and Environmental Carrying Capacity (RECC) for Henan Province and control the scale of cities within the regulating capacity of the ecological and resource system. Therefore, based on the evaluation system composed of natural resources, ecological environment and socioeconomic subsystems, the method of substitutability of indicator information is applied to screen the indicator system. Determine the integrated weight value of each indicator based on the Ordinal Relationship-Entropy Weight-Game Theory model. To identify the spatial-temporal progression law of RECC in 18 cities in the province of Henan from 2005 to 2020 and to forecast the development trend of RECC in each city from 2021 to 2026, the GMD-GRA-TOPSIS-Holt model was constructed. The research findings show that (1) the development of RECC in Henan Province is divided into two periods: the period of slow development (2005–2011) and the period of rapid enhancement (2012–2020). Shangqiu (SQ) and Puyang (PY) were the two cities with the largest and smallest increases in the province, with a difference of up to 51.59%. (2) There are significant regional differences in the RECC and the subsystem carrying capacity in Henan Province. Except for the resource subsystem, the carrying capacity levels of the remaining three systems are improving, and the differences among cities are gradually decreasing. (3) The vitality and strength of the future development of RECC in Henan Province will continue to increase, characterised by “accelerated advancement in the early stage and steady improvement in the later stage.” Overall, this paper provides a theoretical basis for the scientific understanding of RECC in the cities of Henan Province and a scientific basis for optimising the allocation of resources and environmental capacity. Furthermore, the evaluation model constructed in this paper expands the space of theoretical application and has a popularisation value.

Long-Term Prediction of Particulate Matter2.5 Concentration with Modal Autoformer Based on Fusion Modal Decomposition Algorithm

To overcome the limitations of long-term prediction of PM2.5 concentration, a multi-factor information flow causality analysis method is used to screen suitable meteorological and air pollutant-related factors and concatenate them with a PM2.5 sequence as the dataset. A modal decomposition algorithm is used as a module to be integrated into the autoformer (transformer improved with autocorrelation mechanism) model to improve it, and the modal autoformer (empirical modal decomposition combined with autoformer) is proposed. The constructed model decomposes the sequence into several components by using the modal decomposition module and uses the self-correlation mechanism and decomposition structure to decompose and extract features of different components at the time-feature level. Based on the matching method, the model is adjusted for different component features to improve the long-term prediction effect. The model is applied to three cities in Henan Province, Zhengzhou, Luoyang, and Zhumadian, as examples for experiments, and gated neural unit (GRU), informer, autoformer, and modal GRU (empirical modal decomposition combined with GRU model) are constructed for comparative verification. The results show that the modal autoformer can better cope with the complex characteristics of long-term prediction of the PM2.5 time series, has strong spatial adaptability and that its various indicators are optimal for the three cities, with R2 values being all above 0.96, where the highest is 0.987 in Zhengzhou; MAPE (Mean absolute percentage error) values all being less than 10, where the best is 7.602 in Zhumadian; and MAE (Mean absolute error) values all being less than 4. The prediction effect is stable enough, showing its feasibility and adaptability in long-term prediction.

Histogram matching-based semantic segmentation model for crop classification with Sentinel-2 satellite imagery

ABSTRACT Accurate and near-real-time crop mapping from satellite imagery is crucial for agricultural monitoring. However, the seasonal nature of crops makes it challenging to rely on traditional machine learning methods and previous samples generated within specific domains. In this study, we improved the histogram matching method for color correction of multi-temporal images and tested the performance and prediction classification accuracy of three semantic segmentation models based on weak samples. Classification experiments were conducted for nine categories in two cities in Henan province from 2019 to 2022 using 10 m resolution Sentinel-2 images with different feature selection schemes. We trained the models using classified and recorrected results in four selected sites in 2019 and 2020, and designed experiments to assess the performance of the improved histogram matching method and verify the transferability of semantic segmentation models across regions and years. The experimental results showed that the UNet++ model with feature selection and improved histogram matching methods outperformed other models, such as DeepLab V3+ and UNet, in crop classification transfer cases, with better model performance and higher classification accuracy. The UNet++ model without training samples achieved optimal overall accuracy, Kappa coefficient, and mean F1-score values from 2019 to 2022, exceeding 87%, 82%, and 65%, respectively. Moreover, the representative error of weak samples and prediction classification results were analyzed to improve the model robustness. As an application of transfer-learning in crop mapping, the proposed model effectively addressed the classification problem of multispectral satellite imagery with missing labels.