Spatial Autocorrelation Patterns Research Articles

Machine learning-driven source identification and ecological risk prediction of heavy metal pollution in cultivated soils

To overcome challenges in assessing the impact of environmental factors on heavy metal accumulation in soil due to limited comprehensive data, our study in Yangxin County, Hubei Province, China, analyzed 577 soil samples in combination with extensive big data. We used machine learning techniques, the potential ecological risk index, and the bivariate local Moran’s index (BLMI) to predict Cr, Pb, Cd, As, and Hg concentrations in cultivated soil to assess ecological risks and identify pollution sources. The random forest model was selected for its superior performance among various machine learning models, and results indicated that heavy metal accumulation was substantially influenced by environmental factors such as climate, elevation, industrial activities, soil properties, railways, and population. Our ecological risk assessment highlighted areas of concern, where Cd and Hg were identified as the primary threats. BLMI was used to analyze spatial clustering and autocorrelation patterns between ecological risk and environmental factors, pinpointing areas that require targeted interventions. Additionally, redundancy analysis revealed the dynamics of heavy metal transfer to crops. This detailed approach mapped the spatial distribution of heavy metals, highlighted the ecological risks, identified their sources, and provided essential data for effective land management and pollution mitigation.

Dengue fever mapping in Bangladesh: A spatial modeling approach

AbstractBackgroundEpidemics of the dengue virus can trigger widespread morbidity and mortality along with no specific treatment. Examining the spatial autocorrelation and variability of dengue prevalence throughout Bangladesh's 64 districts was the focus of this study.MethodsThe spatial autocorrelation is evaluated with the help of Moran and Geary . Local Moran was used to detect hotspots and cold spots, whereas local Getis Ord G was used to identify only spatial hotspots. The spatial heterogeneity has been detected using various conventional and spatial models, including the Poisson‐Gamma model, the Poisson‐Lognormal Model, the Conditional Autoregressive (CAR) model, the Convolution model, and the BYM2 model, respectively. These models are implemented using Gibbs sampling and other Bayesian hierarchical approaches to analyze the posterior distribution effectively, enabling inference within a Bayesian context.ResultsThe study's findings show that Moran and Geary analysis provides a substantial clustering pattern of positive spatial autocorrelation of dengue fever (DF) rates between surrounding districts at a 90% confidence interval. The Local Indicators of Spatial Autocorrelation cluster mapped spatial clusters and outliers based on prevalence rates, while the local Getis‐Ord G displayed a thorough breakdown of high or low rates, omitting outliers. Although Chattogram had the most dengue cases (15,752), Khulna district had a higher prevalence rate (133.636) than Chattogram (104.796). The BYM2 model, determined to be well‐fitted based on the lowest Deviance Information Criterion value (527.340), explains a significant association between spatial heterogeneity and prevalence rates.ConclusionThis research pinpoints the district with the highest prevalence rate for dengue and the neighboring districts that also have high risk, allowing government agencies and communities to take the necessary precautions to mollify the risk effect of DF.

Assessing the environmental factors affecting the sustainability of Aini Falaj system.

This study investigates the spatial distribution patterns and environmental factors influencing the Aini Falaj system in a specific study area. The research findings are presented through the lens of the following four categories: collinearity diagnostics, spatial autocorrelation analysis, kernel density (KD) findings, and multivariate geographically weighted regression (MGWR) analysis. The collinearity diagnostics were applied to examine the interrelationships among 18 independent environmental variables. The results indicate the absence of significant multicollinearity concerns, with most variables showing values below the critical threshold of five for variance inflation factors (VIFs). The selected variables indicate minimal intercorrelation, suggesting that researchers should be confident utilizing them in subsequent modelling or regression analyses. A spatial autocorrelation analysis using Moran's Index revealed positive spatial autocorrelation and significant clustering patterns in the distribution of live and non-functional Aini Falajs. High concentrations of live or dead Falajs tended to be surrounded by neighbouring areas with similar characteristics. These findings provide insights into the ecological preferences and habitat associations of Aini Falajs, thereby aiding conservation strategies and targeted studies. The kernel density (KD) analysis depicted distribution patterns of live and dry Aini Falajs through hotspots and cold spots. Specific regions exhibited high-density areas of live Falajs, indicating favourable environmental conditions or historical factors contributing to their concentrated distribution. Identifying these high-density zones can enhance our understanding of the spatial patterns and potential factors influencing the prevalence and sustainability of Aini Falajs. The multivariate geographically weighted regression (MGWR) models revealed strong associations between the live or dead status of Aini Falajs and environmental factors. The precipitation, topographic wetness index (TWI), aspect and slope exerted positive impacts on the live status, while evaporation, solar radiation, distance to drains and drain density exerted negative influences. Similar associations were observed for the dead status, emphasising the importance of controlling evaporation, shading mechanisms, proper drainage planning and sustainable land-use practices. This study provides valuable insights into the spatial distributions and factors influencing the live and dead status of Aini Falajs, thereby contributing to our understanding of their ecological dynamics and guiding conservation efforts and management strategies.

Towards Understanding the Microepidemiology of Lymphatic Filariasis at the Community Level in Ghana.

Studies on the distribution of lymphatic filariasis (LF) have mostly focused on reporting prevalence at the community level and distribution at the district levels. Understanding the distribution patterns at community levels may help in designing surveillance strategies. This study aimed to characterize the spatial distribution of LF infections in four hotspot communities in Ghana. The research, involving 252 participants, collected demographic data, mass drug administration (MDA) information, household GPS coordinates, and antigen detection test results. The LF prevalence varied significantly among the communities, with Asemda having the highest (33.33%) and Mempeasem having the lowest (4.44%). Females had lower odds of infection than males (OR = 2.67, p = 0.003 CI: 1.39-5.13). Spatial analysis using kernel density, Anselin Local Moran's, Getis-Ord Gi models, Ordinary Least Squares, and Geographic Weighted Regression revealed mixed patterns of spatial autocorrelation. This study identified LF hotspots, indicating clusters of high or low prevalence with some areas showing disparities between MDA coverage and LF positivity rates. Despite these hotspots, the overall distribution of LF appeared random, suggesting the importance of purposeful sampling in surveillance activities. These findings contribute valuable insights into the micro-epidemiology of LF, emphasizing the need for community-specific investigations to understand the factors influencing the effectiveness of MDA programs in controlling filarial infections. The study highlights the importance of refining surveillance strategies based on community-level distribution patterns.

Investigating the nexus between energy, socio-economic factors and environmental pollution: A geo-spatial multi regression approach

The Yellow River Basin (YRB) and Yangtze River Basin (YZRB) stand as pivotal regions in China, holding paramount importance in both economic development and environmental security. However, the rapid pace of climate change and extensive human activities have dramatically reshaped these areas, leading to substantial alterations in natural landscapes and urban ecosystems. To ensure sustainable socio-economic growth, a profound understanding of the intricate interplay between socioeconomic factors and the emission of fine particulate matter (FPM) is imperative, along with an exploration of the underlying mechanisms governing these relationships. n this comprehensive study, we conducted spatial autocorrelation and spatial panel regression analyses, leveraging panel data encompassing the years from 2002 to 2021, derived from provincial-level administrative units within the YZRB and YRB. By adopting a holistic approach that considers comprehensive features and spatial effects, our research contributes substantively to the existing literature concerning the YZRB and YRB areas. Our analysis unveiled a notable decline in pollutant emissions over the course of the study period, yet it became evident that socioeconomic and energy-related factors continued to exert significant influence on FPM levels. Furthermore, we identified pronounced positive spatial autocorrelations in FPM emissions, suggesting a need for regionally tailored environmental management strategies. Employing various statistical tests, we rigorously examined the spatial autocorrelation patterns among the regions. Results from our random effect regression model and Geographically Weighted Regression (GWR) approach underscored the significant impact of socioeconomic and natural factors on FPM concentrations. Importantly, the magnitudes of these impacts exhibited variations contingent upon the specific river basin type. Within the YZRB, our findings emphasize the relevance of urbanization metrics, such as urban population, urban green space, Gross Domestic Product (GDP), and economic spending, which displayed positive and statistically significant relationships with FPM concentrations. Conversely, in the YRB, the utilization of energy resources and natural assets emerged as pivotal determinants.

Spatial pattern of China's rural digital economy based on subjective-Objective evaluation: Evidence from 2085 counties.

The rural digital economy plays an essential role in China's industrial upgrading, transformation, and urban-rural integration. To determine the state of China's rural digital economy, we constructed a county-level evaluation system using the subjective-objective evaluation method and calculated the digital economic levels of 2085 counties. Then, we analyzed the spatial distribution characteristics, spatial autocorrelation pattern, spatial disequilibrium degree, and spatial driving force of the rural digital economy at the county level using spatial analysis technology and a self-organizing feature mapping model. The results are as follows: 1) Compared with the real economy, the agglomeration effect of the digital economy was more obvious, and the economic gradient was more significant. Specifically, the dense high-value regions formed a continuous belt on the eastern coast from the Beijing-Tianjin area to the Pearl River Delta, opposite the dense low-value regions in the west. 2) There were significant differences in the rural digital economy within cities or provinces. Intraregional differences were not necessarily linked to the overall digital economy level because central and northeastern China presented a more balanced rural digital economy. 3) Digital network performance, e-commerce level, and economic vitality were identified as the core factors influencing the rural digital economy.

Spatiotemporal variations and spillover effects of regional water resources metabolism efficiency with heterogeneous resource endowments

Abstract Scientific evaluation of water resources metabolism efficiency (WME) has essential theoretical and practical value for regional water resources security and sustainable utilization. Based on the framework of the water resources metabolism process and construction of the indicator system of WME, the spatiotemporal variations of WME were analyzed using the weighted summation method in the Eastern, Central, and Western regions of China during the period from 1990 to 2020 with heterogeneous resource endowments. The exploratory spatial data analysis (ESDA) and spatial Durbin model were applied to analyze the spatial autocorrelation patterns and reveal spillovers of the WME. The results show that (1) The WME increased at different speeds in the Eastern, Central, and Western regions from 1990 to 2020 with heterogeneous resource endowment, and the spatial variation of WME in the Eastern and Central regions was significantly higher than in the Western regions. (2) The WME had significant spatial autocorrelation except in 2015, indicating obvious spatial agglomeration characteristics and spatial heterogeneity simultaneously. (3) The spatial spillover effects analysis indicated that the waste virtual recycling use ratio, the ratio of output virtual water and input virtual water, and industrial water ratio were the primary factors influencing WME.

The dynamic impact of digital economy on the green development of traditional manufacturing industry: Evidence from China

The traditional manufacturing industry is China’s second-largest source of carbon emissions, and the successful completion of dual carbon target depend on the traditional manufacturing industry’s ability to reduce emissions. This paper constructs the evaluation index system to analyze the driving factors and green coupling level of the digital economy enabling the green development of traditional manufacturing industry from three aspects: industry digitalization capacity, socio-economic benefits capacity and ecological resources carrying capacity based on the theory of social shaping of technology. From the perspective of regional economic development, this paper constructs the spatial Durbin model and threshold regression model to analyze the mediation effect and spatial spillover mechanism of the digital economy empowering the green development of traditional manufacturing industry. Based on the panel data of 30 provinces in China from 2012 to 2020, the empirical analysis show that digital economy has the positive impact on the green development of traditional manufacturing industry through the digital innovation, industrial upgrading and human capital. At same time, the digital economy has a positive spatial autocorrelation pattern of the green development of traditional manufacturing industries with “high in the eastern and low in the western of China” from the global Moran index. Through the policy test of carbon-trading pilot programs by the difference-in-differences model, the digital economy has a non-linear impact on the intensive production of traditional manufacturing industry, which green finance activate the new impetus of market and the data element resources enhance industrial coordination development.

Data augmentation for bias correction in mapping PM2.5 based on satellite retrievals and ground observations

As most air quality monitoring sites are in urban areas worldwide, machine learning models may produce substantial estimation bias in rural areas when deriving spatiotemporal distributions of air pollutants. The bias stems from the issue of dataset shift, as the density distributions of predictor variables differ greatly between urban and rural areas. We propose a data-augmentation approach based on the multiple imputation by chained equations (MICE-DA) to remedy the dataset shift problem. Compared with the benchmark models, MICE-DA exhibits superior predictive performance in deriving the spatiotemporal distributions of hourly PM2.5 in the megacity (Chengdu) at the foot of the Tibetan Plateau, especially for correcting the estimation bias, with the mean bias decreasing from –3.4 µg/m3 to –1.6 µg/m3. As a complement to the holdout validation, the semi-variance results show that MICE-DA decently preserves the spatial autocorrelation pattern of PM2.5 over the study area. The essence of MICE-DA is strengthening the correlation between PM2.5 and aerosol optical depth (AOD) during the data augmentation. Consequently, the importance of AOD is largely enhanced for predicting PM2.5, and the summed relative importance value of the two satellite-retrieved AOD variables increases from 5.5% to 18.4%. This study resolved the puzzle that AOD exhibited relatively lower importance in local or regional studies. The results of this study can advance the utilization of satellite remote sensing in modeling air quality while drawing more attention to the common dataset shift problem in data-driven environmental research.

Effects of Forest Fragmentation on Connectivity and Genetic Diversity in an Endemic and an Invasive Rodent in Northwestern Madagascar.

Habitat loss and fragmentation are of concern to conservation biologists worldwide. However, not all organisms are affected equally by these processes; thus, it is important to study the effects of living in fragmented habitats on species that differ in lifestyle and habitat requirements. In this study, we examined the dispersal and connectivity patterns of rodents, one endemic (Eliurus myoxinus) and one invasive (Rattus rattus), in two landscapes containing forest fragments and adjacent continuous forest patches in northwestern Madagascar. We generated genetic (RADseq) data for 66 E. myoxinus and 81 R. rattus individuals to evaluate differences in genetic diversity as well as inbreeding and connectivity in two landscapes. We found higher levels of inbreeding and lower levels of genetic diversity in E. myoxinus compared with R. rattus. We observed related dyads both within and between habitat patches and positive spatial autocorrelation at lower distance classes for both species, with a stronger pattern of spatial autocorrelation in R. rattus. Across each site, we identified contrasting migration rates for each species, but these did not correspond to habitat-matrix dichotomies. The relatively low genetic diversity in the endemic E. myoxinus suggests ecological constraints that require further investigation.

Key epidemiological indicators and spatial autocorrelation patterns across five waves of COVID-19 in Catalonia

This research studies the evolution of COVID-19 crude incident rates, effective reproduction number R(t) and their relationship with incidence spatial autocorrelation patterns in the 19 months following the disease outbreak in Catalonia (Spain). A cross-sectional ecological panel design based on n = 371 health-care geographical units is used. Five general outbreaks are described, systematically preceded by generalized values of R(t) > 1 in the two previous weeks. No clear regularities concerning possible initial focus appear when comparing waves. As for autocorrelation, we identify a wave’s baseline pattern in which global Moran’s I increases rapidly in the first weeks of the outbreak to descend later. However, some waves significantly depart from the baseline. In the simulations, both baseline pattern and departures can be reproduced when measures aimed at reducing mobility and virus transmissibility are introduced. Spatial autocorrelation is inherently contingent on the outbreak phase and is also substantially modified by external interventions affecting human behavior.

Spatial pattern and heterogeneity of chronic respiratory diseases and relationship to socio-demographic factors in Thailand in the period 2016 to 2019.

Chronic respiratory diseases (CRDs) constitute 4% of the global disease burden and cause 4 million deaths annually. This cross-sectional study used QGIS and GeoDa to explore the spatial pattern and heterogeneity of CRDs morbidity and spatial autocorrelation between socio-demographic factors and CRDs in Thailand from 2016 to 2019. We found an annual, positive, spatial autocorrelation (Moran's I >0.66, p<0.001) showing a strong clustered distribution. The local indicators of spatial association (LISA) identified hotspots mostly in the northern region, while coldspots were mostly seen in the central and north-eastern regions throughout the study period. Of the socio-demographic factors, the density of population, households, vehicles, factories and agricultural areas, correlated with the CRD morbidity rate, with statistically significant negative spatial autocorrelations and coldspots in the north-eastern and central areas (except for agricultural land) and two hotspots between farm household density and CRD in the southern region in 2019. This study identified vulnerable provinces with high risk of CRDs and can guide prioritization of resource allocation and provide target interventions for policy makers.

Assessing the progress and spatial patterns of sustainable eco-environmental development based on the 2030 Agenda for SDGs in China

ABSTRACT The eco-environment is fundamental for human survival and development. To gain insight into Chinese eco-environmental challenges, a scientific and quantifying assessment of sustainable eco-environmental development (SED) is essential and can guide policy development and implementation. However, systematic methods for assessing progress towards achieving SED are lacking based on the 2030 Agenda for the Sustainable Development Goals (SDGs). Therefore, we developed a systematic method to quantify SED progress at the provincial level in China. In the proposed method, the SED indicator framework was developed to align with the global indicator framework (GIF), adopting clear statistical definitions for each indicator and the criteria of data selection at provincial levels in China. A four-level method of identifying the upper and lower bounds of the indicator values was proposed to normalise them to a standard scale of 0–100. The SED index and three composite indices were aggregated by the arithmetic means of the individual scores for assessing overall SED progress. A spatial autocorrelation analysis was used to explore the spatial patterns of the SED index scores. The results showed that all provinces except Shandong and Hebei had relatively good performances in achieving SED. Most provinces performed better in terms of the water area eco-environment than they do in terms of the air and terrestrial eco-environments. In addition, some provinces showed a positive spatial autocorrelation pattern on the SED index scores, and the high-value (low-value) aggregation regions were mainly concentrated in Western (East) China. These results provide a richer understanding of the challenges for SED faced by each province in China.

Evaluating urban environment quality (UEQ) for Class-I Indian city: an integrated RS-GIS based exploratory spatial analysis

Urban environmental quality consisting of ecological, physical, and socio-economic components, often deteriorates due to rapid urbanization. Therefore, using Remote sensing and GIS environment, a composite measure is applied to quantify the spatial heterogeneity of urban environmental quality for the Class-1 Indian city (Siliguri). In this study, the Urban Environmental Quality Index was constructed using 15 indicators and three interconnected dimensions (eco-environment, landscape and built-up, and socio-economy). The three domains and Urban Environmental Quality Index were computed utilizing Principal Component Analysis with average aggregation techniques. Exploratory Spatial Data Analysis includes Moran’s I and Local indicator of spatial auto-correlation, were used to leverage the information of spatial clusters, spatial heterogeneity, and outliers based on the Urban Environmental Quality Index. The results show that Siliguri’s northern, north-western, and southern parts experience good environmental quality. The effectiveness of the employed model was checked using R2 (0.832), providing a good fit for the model. Moreover, the spatial pattern of urban environmental quality and the constructed domains (except socio-economy) revealed that the Low-Low values were predominantly clustered in the city centre, while High-High patterns are concentrated towards the periphery. Also, the value of Moran’s I indicated the existence of spatial autocorrelation and non-randomness pattern in Siliguri City. The results obtained from the analysis indicate spatial heterogeneity and spatial differentiation across the study area. The study’s outcome is relevant for urban planning, frequent monitoring of urban environmental quality, urban governance, and the well-being of urban inhabitants for a sustainable urban space.

Precipitation interpolation, autocorrelation, and predicting spatiotemporal variation in runoff in data sparse regions: Application to Panama

Study regionPanama faces seasonal floods and droughts, and rising freshwater demand for domestic consumption, hydropower, and the operation of the Panama Canal. A process-based hydrological model of the country would complement the existing national water security plan as a scenario planning tool. Study focusIn Panama, as in much of the Global South, sufficient observed data do not exist for all watersheds to calibrate complex hydrological models. Understanding and improving the performance of uncalibrated hydrological models could greatly expand their utility in such regions. In this study, we build and validate an uncalibrated Soil and Water Assessment Tool (SWAT) model for Panama. We extend the default precipitation submodel and demonstrate the importance of accounting for spatial autocorrelation patterns in precipitation inputs: we found large improvements over the default model, not only for monthly means (NSE = 0.88, from 0.69 for default SWAT), but especially for standard deviations (NSE = 0.59, from 0.27) and maxima (NSE = 0.51, from 0.21) of discharge across locations and months. New hydrological insights for regionWe found a strong seasonal trend and regional differences in the spatial autocorrelation of rainfall, suggesting that this phenomenon should not be modeled statically. The resulting precipitation and hydrology models provide important baseline information for Panama, especially on variability and extremes, and could serve as a template for other regions with limited data.

How well does digital soil mapping represent soil geography? An investigation from the USA

Abstract. We present methods to evaluate the spatial patterns of the geographic distribution of soil properties in the USA, as shown in gridded maps produced by digital soil mapping (DSM) at global (SoilGrids v2), national (Soil Properties and Class 100 m Grids of the USA), and regional (POLARIS soil properties) scales and compare them to spatial patterns known from detailed field surveys (gNATSGO and gSSURGO). The methods are illustrated with an example, i.e. topsoil pH for an area in central New York state. A companion report examines other areas, soil properties, and depth intervals. A set of R Markdown scripts is referenced so that readers can apply the analysis for areas of their interest. For the test case, we discover and discuss substantial discrepancies between DSM products and large differences between the DSM products and legacy field surveys. These differences are in whole-map statistics, visually identifiable landscape features, level of detail, range and strength of spatial autocorrelation, landscape metrics (Shannon diversity and evenness, shape, aggregation, mean fractal dimension, and co-occurrence vectors), and spatial patterns of property maps classified by histogram equalization. Histograms and variogram analysis revealed the smoothing effect of machine learning models. Property class maps made by histogram equalization were substantially different, but there was no consistent trend in their landscape metrics. The model using only national points and covariates was not substantially different from the global model and, in some cases, introduced artefacts from a lithology covariate. Uncertainty (5 %–95 % confidence intervals) provided by SoilGrids and POLARIS were unrealistically wide compared to gNATSGO/gSSURGO low and high estimated values and show substantially different spatial patterns. We discuss the potential use of the DSM products as a (partial) replacement for field-based soil surveys. There is no substitute for actually examining and interpreting the soil–landscape relation, but despite the issues revealed in this study, DSM can be an important aid to the soil surveyor.

Spatial autocorrelation signatures of ecological determinants on plant community characteristics in high Andean wetlands

Understanding how biological communities are shaped is a central tenet of community ecology. Recent evidence highlights the potential of decoupling diversity spatial autocorrelation into its positive and negative components to reveal community assembly processes that would otherwise remain undetected, as well as to improve understanding of their impacts on different facets of diversity. Yet, such approaches have only been implemented to investigate the effects of a few assembly drivers on a small number of diversity components. Here, we used high Andean wetland plant communities over a strong latitudinal gradient to investigate the effects of various ecological factors on spatial autocorrelation patterns of nine community metrics with different informative values, including measures of richness, dominance, evenness and beta-diversity. By combining Moran’s Eigenvector Maps, partial least squares structural equation modeling, and regression analyses, we revealed two groups of community parameters presenting contrasting spatial patterns due to specific sensitivities to ecological factors. While environmental variation and wetland connectivity increased positive spatial autocorrelation in richness and dominance-related parameters, species co-occurrence promoted negative spatial autocorrelation in evenness-related parameters. These results offer new insights regarding both how ecological processes affect species assembly, as well as the information captured by classical taxonomic parameters.

An Improved Gray Neural Network Method to Optimize Spatial and Temporal Characteristics Analysis of Land-Use Change.

In this article, the principles of the gray model and BP neural network model are analyzed, and the characteristics of land-use change and spatial and temporal distribution are studied in-depth, and at the same time, to explore the influence of land-use change on ESV, the relationship between the two is analyzed using gray correlation degree, and a mathematical model is constructed to maximize the benefits of the regional system, coupling economic and ecological benefits, combined with Geo SOS-FLUS model to achieve the optimization of land use. This article constructs a combined prediction model of a gray neural network. The gray differential equation parameters correspond to the weights and thresholds of the neural network, and the optimized parameters are determined by training the neural network to make it stable. Then the training results of the BP neural network are fitted with the results obtained from the gray GM (1.1) model. Finally, the prediction results of the three models, gray GM (1.1), BP God Meridian, and gray neural network model, are compared and analyzed. The global spatial autocorrelation and local spatial aggregation patterns of regional soil erosion and its erosion factors are analyzed using the Exploratory Spatial Data Analysis (ESDA) method in spatial measurement theory.

Improving estimation of urban land cover fractions with rigorous spatial endmember modeling

The spatial information has been widely utilized in Spectral Mixture Analysis (SMA) studies over the years. However, the spatial autocorrelation, as a prerequisite of these studies, was seldomly examined. In the complex urban systems, it remains largely unknown whether and how land cover spectra at different locations are spatially autocorrelated and to which extent spatial autocorrelation can explain the great spectral variability. This study proposed an SMA method with Spatial Endmember Modeling (SEMSMA) to improve the fraction estimation of major urban land cover types. SEMSMA used the Incremental Spatial Autocorrelation (ISA) analysis to quantify spatial autocorrelation patterns in broadband reflectance. With the patterns, SEMSMA predicted endmember signatures that incorporated both spatial (location-oriented) and non-spatial spectral variability via the Restricted Maximum Likelihood-Empirical Best Linear Unbiased Predictor (REML-EBLUP) and Monte Carlo sampling. The spectral variabilities were then addressed in pixel unmixing by an iterative mixture analysis method. Results of ISA demonstrated diverse spatial autocorrelation patterns in reflectance of urban land covers. These patterns can be related to the pathways that spatial processes acted on land cover properties. The predicted endmember signatures explained most of the spectral variability for all land cover types. Subpixel fraction estimates showed that SEMSMA outperformed multiple endmember SMA (MESMA) and spatially adaptive SMA (SASMA), based on the root mean square error (0.04–0.15), the mean absolute error (0.01–0.09), and the Systematic Error (SE) (−80.00–0.01). The low SE of SEMSMA revealed unbiased estimation of land cover fractions. Results of this study underscored the necessity of spatial autocorrelation examination and the advantage of rigorous spatial endmember modeling when incorporating spatial information into SMA.

Spatial autocorrelation patterns among US commercial banks: before, during and after the subprime mortgage crisis

ABSTRACT We study patterns of spatial autocorrelations of four customary performance measures (return on asset, return on equity, net interest margin, and loan loss reserves to total assets) among 49 commercial banks spread in the continental US from the first quarter of 2000 until the fourth quarter of 2010, before and after the subprime mortgage crisis. We use Moran’s I, Geary’s C, and Conley’s one-metric and two-metric spatial autocorrelation methodologies and discover mostly positive (negative) spatial autocorrelations before (during and after) the US subprime mortgage crisis. We also identify the unique influences of size and risk management practices in these commercial banks on the spatial autocorrelations within the two tested periods. Our findings suggest that among many US commercial banks, unifying economic features were more dominant before the crisis, but they were gradually replaced with dividing economic elements during and after this major financial calamity. Our robust evidence aim to highlight the influence of physical distances among commercial banks on their routine operations.