Feedback information concerning automotive quality often suffers from significant delays, making online consumer complaints an invaluable real-time source of information for monitoring and assessing product quality. Given that the frequency of online complaints is influenced by numerous factors, such as automobile quality, sales, Internet development, and public awareness of rights protection, it exhibits significant auto-correlation and dynamics. However, the existing modeling methods have been proven to be unreliable in practical applications, because they often assume that in-control (IC) processes remain static and employ models with fixed parameters. To this end, a dynamic modeling framework that integrates generalized linear regression with an integer-valued auto-regressive (INAR) state space model is proposed to capture the evolving nature of the process. Then, a procedure combining the Extended Kalman Smoothing (EKS) with the Expectation Maximization (EM) algorithm, referred to as EM-EKS, is used to estimate the model parameters. Furthermore, for online monitoring of any upward shifts in the number of complaints, a control chart (denoted as SDC-INAR(1)-G) with one-step-ahead forecasting value as the plotting statistic is constructed. Simulation studies show that the proposed SDC-INAR(1)-G method consistently exhibits much better performance than three benchmark approaches in different scenarios. Finally, the proposed SDC-INAR(1)-G method is applied to monitor online complaints of the Volkswagen Sagitar, focusing on two specific cases: the stationary process of “brake abnormal noise” and the non-stationary process of “transmission abnormal noise.” The results further demonstrate that the SDC-INAR(1)-G method outperforms the static approaches in both cases. The state-space framework and adaptive EM-EKS parameter estimation of the proposed SDC-INAR(1)-G method ensure robust sensitivities to different shifts, offering reliable monitoring for both stationary and non-stationary data, at the same time, remaining computationally efficient for real-world applications.

Rapid urbanization and industrialization promote economic growth as well as bring carbon emissions, which seriously threaten the eco-environment and socioeconomic sustainable development. Facing increasing resource constraints, improving carbon emissions efficiency (CEE) is conducive to promote coordinated development of economy and environmental protection. In recent years, regional economic integration (REI) has rapidly developed. It can not only promote factors flow between regions but also achieve industrial and economic agglomeration. However, few studies have been reported in the literature about the relationship between the REI and CEE. In this study, we first illustrate how the REI influences CEE in theory, then take the Yangtze River Delta (YRD) as a case study to conduct empirical research. The results show that (1) the overall CEE value in the YRD has exhibited an upward trend from 2000 to 2020, and its spatial distribution has revealed a significant auto-correlation pattern. (2) On the whole, the REI act a noteworthy positive impact on CEE. When considering types of cities, it is found to have significant positive impacts for the CEE in economically developed cities, while it exhibits a negative impact in the less-developed ones. (3) Upgrading industrial structure and increasing per capita GDP can promote the CEE, but hinder its growth in surrounding areas. Our findings suggest that the government should formulate a unified overall plan to facilitate REI development and establish a modern industrial system of clean and low-carbon to promote regional sustainable development.

Spatial variation and controls of soil microbial necromass carbon in a tropical montane rainforest

The study of the spatiotemporal evolution of landscape ecological hazard and human and natural influences is essential for conservative management and regional sustainable development. This study applied a landscape pattern analysis method and geodetector to multi-source data for 2000, 2010, and 2020 to analyze changes in and drivers of landscape ecological hazard in Laos. The results indicated that: (1) There were more prominent changes in landscape types in Laos. Forest area decreased, whereas the areas of other landscape types increased. There was an overall steady change in the landscape patterns of Laos. Besides for significant changes in the artificial surface landscape index, landscape indices remained stable; (2) The cumulative high and extreme ecological hazard areas increased by 1,947.81 km2, whereas the cumulative areas of low and minimal ecological hazard decreased by 8,461.8 km2. Areas of low and moderate ecological hazard accounted for > 85% of the total area. Areas of low ecological hazard were mainly in the northwest and southeast. The area of high ecological hazard was concentrated in the central and northeastern regions. The distributions of different landscape ecological hazards in Laos during the study period were similar, with general patterns of decreasing hazard from north to south; (3) A positive Moran’s I of landscape ecological hazard in Laos was obtained. While the agglomeration effect was pronounced, it decreased over time, resulting in a weakening in spatial autocorrelation. A significant positive autocorrelation was observed in the spatial distribution of landscape ecological hazard in the study area. Agglomerated areas of high and low ecological hazard were mainly concentrated in the northeast and southeast, respectively; (4) The spatiotemporal evolution of landscape ecological hazard in Laos over the last 20 years could be attributed to interactions between natural and anthropogenic influences. Natural influences were a significant driver of changes to landscape ecological hazard in Laos, with annual precipitation and average temperature being the most significant. Anthropogenic influences, including socioeconomic factors and regional accessibility, significantly impacted local ecological deterioration in Laos.

Quantitatively measuring rural digitalization performance and development sustainability, identifying their key influencing factors and figuring out their driving mechanisms are of great value to policy design for rural revitalization and management. This paper analyzed the sustainable development degree, spatial patterns, and influencing factors of rural digitization in Hunan Province, China, based on a combination of PSR, TOPSIS, ESDA, GWR and GeoDetector, in an attempt to provide a basis for the planning and policy design of rural management. The sustainability and construction performance of rural digitalization in Hunan were characterized by significant spatial inequality and positive autocorrelation, with coefficients of variation of 0.33 and 0.24, and Moran’s I values of 0.29 and 0.34, respectively. The rural digitalization in Hunan showed significant non-equilibrium across different dimensions and brought forward diversified combination patterns, including single dimensional leadership, dual dimensional leadership, three-dimensional leadership, and all-round development. The pattern dual dimensional leadership, especially PS (pressure + state), was dominant in the sustainability of rural digitalization, compared to the pattern single dimensional leadership dominant in the construction performance, especially I (rural infra-structure digitalization), IL (rural infrastructure + life digitalization), IG (rural infrastructure + governance digitalization). The sustainability and construction performance of rural digitalization in Hunan were subject to a complex driving mechanism, with different factors differing significantly in their action nature, force, spatial effects and interactions. Notably, economic development (gross domestic product) is a positive key factor, while government intervention capacity (fiscal self-sufficiency rate) is an important factor, and natural environment (relief amplitude) is a mixed auxiliary factor (both positive and negative). Factor interactions were mainly characterized by nonlinear enhancement and a large number of super factor pairs. Therefore, the policy design should take into account both localized and differentiated management; and also emphasize enhanced cooperation with adjacent counties and synergistic management. It is suggested to divide Hunan into four planning zonings of leading, potential, warning and general zone, and design the spatial policies for each of them according to the driving mechanism, so as to develop a more reasonable and practical combination of development projects and management policies.

Drought is a hazardous natural disaster that can negatively affect the environment, water resources, agriculture, and the economy. Precise drought forecasting and trend assessment are essential for water management to reduce the detrimental effects of drought. However, some existing drought modeling techniques have limitations that hinder precise forecasting, necessitating the exploration of suitable approaches. This study examines two forecasting models, Long Short-Term Memory (LSTM) and a hybrid model integrating regularized extreme learning machine and Snake algorithm, to forecast hydrological droughts for one to six months in advance. Using the Multivariate Standardized Streamflow Index (MSSI) computed from 58 years of streamflow data for two drier Malaysian stations, the models forecast droughts and were compared to classical models such as gradient boosting regression and K-nearest model for validation purposes. The RELM-SO model outperformed other models for forecasting one month ahead at station S1, with lower root mean square error (RMSE = 0.1453), mean absolute error (MAE = 0.1164), and a higher Nash-Sutcliffe efficiency index (NSE = 0.9012) and Willmott index (WI = 0.9966). Similarly, at station S2, the hybrid model had lower (RMSE = 0.1211 and MAE = 0.0909), and higher (NSE = 0.8941 and WI = 0.9960), indicating improved accuracy compared to comparable models. Due to significant autocorrelation in the drought data, traditional statistical metrics may be inadequate for selecting the optimal model. Therefore, this study introduced a novel parameter to evaluate the model's effectiveness in accurately capturing the turning points in the data. Accordingly, the hybrid model significantly improved forecast accuracy from 19.32 % to 21.52 % when compared with LSTM. Besides, the reliability analysis showed that the hybrid model was the most accurate for providing long-term forecasts. Additionally, innovative trend analysis, an effective method, was used to analyze hydrological drought trends. The study revealed that October, November, and December experienced higher occurrences of drought than other months. This research advances accurate drought forecasting and trend assessment, providing valuable insights for water management and decision-making in drought-prone regions.

SAC-ConvLSTM: A novel spatio-temporal deep learning-based approach for a short term power load forecasting

Understanding the relationship between commodity prices is paramount for investors, policymakers, and industries reliant on these markets. This study delves into the intricate dynamics between coconut oil and crude oil prices using a Vector Error Correction Model (VECM). The VECM approach allows for exploring these commodities' short-term adjustments and long-term equilibrium relationships. The analysis reveals that while there may not be a strong long-term interdependence between coconut oil and crude oil prices, robust short-term adjustment mechanisms exist. The cointegration rank two (2) highlights the presence of two cointegrating vectors, indicating a stable equilibrium relationship. The alpha and beta coefficients shed light on the speed and direction of adjustments, emphasizing how the system corrects deviations from the equilibrium relationship. Various model selection criteria, including the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), validate the VECM's efficacy in capturing the complexities of these markets while maintaining model simplicity. Moreover, significant error correction terms emphasize the system's self-correcting nature, ensuring long-term stability. Interpreting the coefficients of the lagged terms reveals short-term dynamics, showcasing how coconut oil and crude oil prices mutually influence and respond to changes in one another. The absence of significant autocorrelation in the model's residuals validates the model's accuracy in capturing underlying dynamics.

BackgroundThe city of Port-au-Prince, Haiti, is experiencing an epidemic of firearm injuries which has resulted in high burdens of morbidity and mortality. Despite this, little scientific literature exists on the topic. Geospatial research could inform stakeholders and aid in the response to the current firearm injury epidemic. However, traditional small-area geospatial methods are difficult to implement in Port-au-Prince, as the area has limited mapping penetration. Objectives of this study were to evaluate the feasibility of geospatial analysis in Port-au-Prince, to seek to understand specific limitations to geospatial research in this context, and to explore the geospatial epidemiology of firearm injuries in patients presenting to the largest public hospital in Port-au-Prince.ResultsTo overcome limited mapping penetration, multiple data sources were combined. Boundaries of informally developed neighborhoods were estimated from the crowd-sourced platform OpenStreetMap using Thiessen polygons. Population counts were obtained from previously published satellite-derived estimates and aggregated to the neighborhood level. Cases of firearm injuries presenting to the largest public hospital in Port-au-Prince from November 22nd, 2019, through December 31st, 2020, were geocoded and aggregated to the neighborhood level. Cluster analysis was performed using Global Moran’s I testing, local Moran’s I testing, and the SaTScan software. Results demonstrated significant geospatial autocorrelation in the risk of firearm injury within the city. Cluster analysis identified areas of the city with the highest burden of firearm injuries.ConclusionsBy utilizing novel methodology in neighborhood estimation and combining multiple data sources, geospatial research was able to be conducted in Port-au-Prince. Geospatial clusters of firearm injuries were identified, and neighborhood level relative-risk estimates were obtained. While access to neighborhoods experiencing the largest burden of firearm injuries remains restricted, these geospatial methods could continue to inform stakeholder response to the growing burden of firearm injuries in Port-au-Prince.

Cultivated land quality (CLQ) is at the core of the trinity protection of cultivated land in China. Scientific evaluation of CLQ and identification of its obstacle factors are the foundation for the construction and improvement of the quality of cultivated land. The main objective of this study was to evaluate CLQ and identify its obstacle factors, and Quzhou County, an intensive agricultural region in the North China Plain (NCP), was selected as a case study. The evaluation index system of CLQ was constructed based on five dimensions, including climate condition, topographic characteristic, soil property, farming status, and environmental condition, by analyzing the logical evolution of elements, processes, functions, and quality of cultivated land. A methodological system based on the Weighted Summation Method (WSM) and the “1 + X” model was developed to evaluate the CLQ. Then, the obstacle diagnosis model constructed based on the Cask Law and relevant academic studies was used to identify the obstacle factors of CLQ. The results showed that the proportion of high-, medium-, and low-quality cultivated land in Quzhou County was 36.19%, 33.60%, and 30.21%, respectively, and the average grade of CLQ was 2.97, which was considered to be at a medium level. Moran’s I of global spatial autocorrelation in Quzhou County was 0.8782, indicating a significant positive autocorrelation of the cultivated land quality index (CLQI). The main obstacle factors of CLQ in Quzhou County were soil profile constitution, irrigation guarantee rate, groundwater depth, and soil microbial biomass carbon. Therefore, based on the stable and dynamic characteristics of the obstacle factors, suggestions were provided to improve the quality of cultivated land in terms of strengthening the consolidation of cultivated land, transforming the concept of agricultural fertilization, and carrying out cultivated land recuperation. This study provides a new perspective on the cognition, evaluation, and identification of obstacle factors of CLQ, and the findings of this study can provide a reference for the consolidation and improvement of CLQ in the NCP.

<p><big>This paper investigates the degree of inflation persistence across regions in Portugal by analyzing the Consumer Price Index (CPI) growth rates for NUTS II regions. The study employs the Augmented Dickey-Fuller (ADF) test to determine whether the CPI data for Portugal is stationary or non-stationary. The results of the ADF test reveal that the IPC data for Portugal is non-stationary, indicating that inflation exhibits persistence in the long run. The study further assesses the persistence of inflation by estimating an autoregressive integrated moving average (ARIMA) model for each region. The Ljung-Box test is used to test for autocorrelation in the time series data, and the Hurst exponent is calculated to evaluate the presence of long-term memory in the time series data. The study finds that there is significant autocorrelation in the time series data for all regions, supporting the presence of persistence in inflation at the regional level in Portugal. The Hurst exponent also shows that the time series data for each region exhibits a high degree of persistence in inflation. Finally, the study applies the ARIMA model to each CPI division's data and uses the Ljung-Box test to test for autocorrelation in the time series data. The results show that some CPI divisions exhibited higher levels of persistence compared to others. For example, the "Housing, water, electricity, gas and other fuels" division exhibited high persistence, while the "Communication" division exhibited low persistence. This study contributes to the existing literature by exploring regional inflation persistence in Portugal and its implications for policymaking. The results provide insights into the inflation persistence patterns across regional levels in Portugal, by emphasizing the need to consider regional differences in inflation dynamics when formulating effective policy interventions. Understanding the persistence of inflation is crucial for policymakers to ensure price stability and sustainable economic growth.</big></p>

The Jinsha River basin, full of hydropower resources, is the largest hydropower energy base in China. From 2005 to 2018, four giant cascade hydropower stations (Wudongde, Baihetan, Xiluodu, and Xiangjiaba) were built along the Jinsha River. The reservoir area of four hydropower stations involves 26 counties (districts). The ecological environment of the reservoir area has a close relationship with hydropower projects, and ecosystem service value is an important standard to measure the quality of the ecological environment. Taking the reservoir area formed by four cascade hydropower stations in Jinsha River (Jinsha River Reservoir Area, JRRA) as the research object, the essay analyzed the spatial and temporal pattern of ecosystem service value in the reservoir area in 2005, 2010, 2015, and 2018. The results showed that (1) The ecosystem service value of JRRA reached 94 billion yuan in 2018, and the forestland took the largest proportion of ecosystem service value, accounting for 46.93%, followed by grassland, water area, cropland, and unused land. (2) From 2005 to 2018, the total ecosystem service value in JRRA increased by 3.374 billion yuan, and the spatial pattern of ecosystem service value showed a spatial distribution characteristic of high in the middle and low on both sides, and the spatial distribution had significant positive autocorrelation. (3) Because the area of water increased a lot, the ecosystem service value of JRRA showed a trend of overall increase which mainly occurred in the 3-km buffer zone along the river. The results further proved that the implementation of hydropower projects could improve the ecosystem service function in the reservoir area and provide technical support for the sustainable utilization of land resources and ecological compensation in the reservoir area.

This paper presents an analysis of the area, production and productivity of groundnut in Rajasthan over the last thirty years and a forecast of these variables using the auto regressing integrated moving average (ARIMA) model. Descriptive statistics show that there was a large fluctuation in the lowest and maximum values of area, production, and productivity of groundnut in Rajasthan over the period of last thirty years. The ARIMA model was used to forecast the area, production, and productivity of groundnut in Rajasthan. The parameter estimates of the ARIMA model were used to determine the model fit statistics, including the R-squared value, which indicates how well the model fits the data. The Ljung-Box Q Statistics and the corresponding Sig. indicate that there is no significant autocorrelation in the residuals of the model. Finally, forecasts for 2021, 2022, 2023, 2024, and 2025 are presented, along with their corresponding upper and lower confidence limits. The results indicate that there is a considerable upward trend in area, production, and productivity of groundnut in Rajasthan over the last thirty years. The ARIMA model was found to be successful in forecasting the area, production, and productivity of ground. The findings of this paper can help in the formulation of better policies for groundnut production in Rajasthan.

The Yellow River beach area is the basic component of the Yellow River Basin. Promoting the comprehensive improvement and high-quality development of the Yellow River beach area is an important guarantee of the long-term stability of the Yellow River and an important part of promoting the high-quality development and ecological protection of the Yellow River Basin. In this paper, four new indexes (flood risk intensity index, accessibility index, biological abundance index, and remote sensing ecological index) were extracted from geospatial data and remote sensing images, and a quantitative evaluation model (Ecology-Economy -Society-Flood, EESF) for the development of the Yellow River beach area were constructed based on social statistics, such as flood control and control in the beach area. The coordinated development level of the Yellow River beach area was evaluated by combining the “CRITIC–entropy weight method” and “‘single index quantification–multi-index synthesis–multi-criteria integration’ (SMI-P)—coordination degree model” methods. The spatial autocorrelation model was used to analyze the spatial distribution characteristics of the coordinated development level, and the global sensitivity and uncertainty analysis (GSUA) was carried out for the sensitivity and uncertainty of the parameters. Taking the Yellow River beach area in Shandong Province in 2009 and 2019 as the study object, the research results showed that during this period, the coordinated development level of the Yellow River beach area in Shandong Province showed a gradual upward trend, from 0.344 to 0.580, reaching a basic coordinated state; the overall coordinated development level of the beach area showed significant autocorrelation and small spatial heterogeneity. Grain production was the most sensitive parameter in the coordinated development model of the beach area. The beach area should rationally develop and utilize agricultural resources and promote the integration of ecological industries.

In many applications, e.g. fault diagnostics and optimized control of supermarket refrigeration systems, it is important to determine the heat demand of the cabinets. This can easily be achieved by measuring the mass flow through each cabinet, however that is expensive and not feasible in large-scale deployments. Therefore it is important to be able to estimate the valve sizes from the monitoring data, which is typically measured. The valve size is measured by an area, which can be used to calculate mass flow through the valve — this estimated value is referred to as the valve constant. A novel method for estimating the cabinet evaporator valve constants is proposed in the present paper. It is demonstrated using monitoring data from a refrigeration system in a supermarket in Otterup (Denmark), consisting of data sampled at a one-minute sampling rate, however it is shown that a sampling time of around 10–20 min is adequate for the method. Through thermodynamic analysis of a two stage CO2 refrigeration system, a linear regression model for estimating valve constants is developed using time series data. The linear regression requires that transient dynamics are not present in the data, which depends on multiple factors e.g. the sampling time. If dynamics are not modelled it can be detected by a significant auto-correlation of the residuals. In order to include the dynamics in the model, an Auto-Regressive Moving Average model with eXogenous variables (ARMAX) is applied, and it is shown how it effectively eliminates the auto-correlation and provides less bias and higher accuracy of the estimates. Furthermore, it is shown that the sample time has a huge impact on the estimates. Thus, a method for selecting the optimal sampling time is introduced. It works individually for each of the evaporators, by exploring their respective frequency spectrum. That way, a reliable estimate of the actual valve constant can be achieved for each evaporator in the system and it is shown that sampling times above 10 min are optimal for the analysed systems.

Exploratory Spatio-Temporal Data Analysis (ESTDA) of Dengue and its association with climatic, environmental, and sociodemographic factors in Punjab, India

Ants combine systematic meandering and correlated random walks when searching for unknown resources

High concentration of surface ozone (O3) will cause health risks to people. In order to analyze the spatiotemporal characteristics of O3 and assess O3 exposure and health risks for different age groups in China, we applied multiple methods including standard deviation ellipse, spatial autocorrelation, and exposure-response functions. Results show that O3 concentrations increased in 64.5% of areas in China from 2013 to 2018. The central plain urban agglomeration (CPU), Beijing-Tianjin-Hebei (BTH), and Yangtze River Delta (YRD) witnessed the greatest incremental rates of O3 by 16.7%, 14.3%, and 13.1%. Spatially, the trend of O3 shows a significant positive autocorrelation, and high trend values primarily in central and east China. The proportion of the total population exposed to high O3 (above 160μg/m3) increased annually. Compared to 2013, the proportion of the young, adult, and old populations exposed to high O3 increased to different extents in 2018 by 26.8%, 29.6%, and 27.2%, respectively. The extent of population exposure risk areas in China expanded in size, particularly in north and east China. The total premature respiratory mortalities attributable to long-term O3 exposure in six urban agglomerations were about 177,000 in 2018 which has increased by 16.4% compared to that in 2013. Among different age groups, old people are more vulnerable to O3 pollution, so we need to strengthen their relevant health protection of them.

We examine Bitcoin returns’ statistical properties and check whether these properties are consistent with the well-known stylized facts of asset returns for the period from January 2019 to May 2022. We find that Bitcoin exhibits price behaviors that correspond well to all the stylized facts of asset returns examined in the analyses. We also examine the returns of Tesla stock, NASDAQ index, and S&P500 index for comparison and find that they generally conform to the stylized facts examined. However, Tesla stock does not exhibit an asymmetric volatility feature, and the two indices show significant autocorrelations in low order time lags, which are inconsistent with the well-known stylized facts of asset returns. Based on these findings, we discuss the possible implications of cryptoassets for asset allocation processes. Cryptoassets provide some potential utilities for asset allocations, but only with several simultaneous limitations.

The Mann–Kendall (MK) test was widely used to detect significant trends in hydrologic and climate time series (HCTS), but it cannot deal with significant autocorrelations in HCTS. To solve this problem, the modified MK (MMK) test and the over-whitening (OW) operation were successively proposed. However, there are still limitations for these two methods, especially for the OW operation. When an HCTS has unknown interaction scenarios of trends and autocorrelations, it is obviously unclear which of these two methods will perform better in the trend test. Additionally, the trend test is always accompanied by an autocorrelations test. In the dual test, it is also unknown how the significance level affects the accuracy of the trend test. To address these issues, this study first proposes a strategy of adding an outer loop to modify the OW-operation-based trend test. Then, two simulation experiments are designed to evaluate the performances of MMK-test-based and OW-operation-based methods, and the influence of the significance level on the trend test is analyzed. Moreover, six HCTSs in the Huaihe River basin are taken as examples to examine the consistence and difference of trend test results of these two methods. Results show that: (1) previous OW operations still have the risk of misjudging trends in the presence of significant autocorrelations, and the proposed strategy is necessary and effective to modify the OW operation; (2) these two methods are similar in the accuracy of the trend test results, but they may also produce opposite results when determining whether a significant trend is a pseudo trend or not; and (3) at a given significance level α, the accuracy rates of two methods are always less than 1-α, and the accuracy rate of the trend test tends to decrease for short HCTSs and increase for long HCTSs as the significance level decreases. This study would provide a new perspective for the trend test of HCTS based on the MK test.