A Poverty Measurement Method Incorporating Spatial Correlation: A Case Study in Yangtze River Economic Belt, China

The UN 2030 Agenda sets poverty eradication as the primary goal of sustainable development. An accurate measurement of poverty is a critical input to the quality and efficiency of poverty alleviation in rural areas. However, poverty, as a geographical phenomenon, inevitably has a spatial correlation. Neglecting the spatial correlation between areas in poverty measurements will hamper efforts to improve the accuracy of poverty identification and to design policies in truly poor areas. To capture this spatial correlation, this paper proposes a new poverty measurement model based on a neural network, namely, the spatial vector deep neural network (SVDNN), which combines the spatial vector neural network model (SVNN) and the deep neural network (DNN). The SVNN was applied to measure spatial correlation, while the DNN used the SVNN output vector and explanatory variables dataset to measure the multidimensional poverty index (MPI). To determine the optimal spatial correlation structure of SVDNN, this paper compares the model performance of the spatial distance matrix, spatial adjacent matrix and spatial weighted adjacent matrix, selecting the optimal performing spatial distance matrix as the input data set of SVNN. Then, the SVDNN model was used for the MPI measurement of the Yangtze River Economic Belt, after which the results were compared with three baseline models of DNN, the back propagation neural network (BPNN), and artificial neural network (ANN). Experiments demonstrate that the SVDNN model can obtain spatial correlation from the spatial distance dataset between counties and its poverty identification accuracy is better than other baseline models. The spatio-temporal characteristics of MPI measured by SVDNN were also highly consistent with the distribution of urban aggregations and national-level poverty counties in the Yangtze River Economic Belt. The SVDNN model proposed in this paper could effectively improve the accuracy of poverty identification, thus reducing the misallocation of resources in tracking and targeting poverty in developing countries.

Measuring Energy Efficiency Performance in China: Does Technological and Environmental Concerns Matter for Energy Efficiency?

Considering the significance of green governance in economic restructuring and the green technology revolution, this study examines the impact of China’s recent green governance policies and their implications in various regions; it also examines new models, methods, and development directions for China’s green governance in the future. Green governance efficiency and spatial patterns have been studied through 2008–2018 data using a three-stage generalized panel Data Envelopment Analysis (DEA) model, spatial autocorrelation model, spatial gravity model, and social network analysis. The study summarizes the status and role of each provincial region in green governance based on the social network of green governance efficiency under the network architecture. It concludes that (1) green governance efficiency in China’s provinces has a U-shaped trend, with non-managerial elements in the external environment masking genuine green governance efficiency. (2) During the study period, the overall efficiency of the industrial system improved. The efficiency of the manufacturing and wastewater stages has been substantially enhanced, but no significant gains were observed in the treatment stages of solid and gas waste. (3) Although China has made progress in enhancing the overall efficiency of its industrial system, there is still potential for improvement. (4) China has established a “three horizontal and two vertical grid-type” green governance spatial correlation structure among the sub-stages of the industrial system, and the radiation impact of major provincial areas would increase overall green governance efficiency.

Multivariate Kalman Filtering for Spatio-Temporal Processes

An increasing interest in models for multivariate spatio-temporal processes has been noted in the last years. Some of these models are very flexible and can capture both marginal and cross spatial associations amongst the components of the multivariate process. In order to contribute to the statistical analysis of these models, this paper deals with the estimation and prediction of multivariate spatio-temporal processes by using multivariate state-space models. In this context, a multivariate spatio-temporal process is represented through the well-known Wold decomposition. Such an approach allows for an easy implementation of the Kalman filter to estimate linear temporal processes exhibiting both short and long range dependencies, together with a spatial correlation structure. We illustrate, through simulation experiments, that our method offers a good balance between statistical efficiency and computational complexity. Finally, we apply the method for the analysis of a bivariate dataset on average daily temperatures and maximum daily solar radiations from 21 meteorological stations located in a portion of south-central Chile.

Adjusting spatial dependence of climate model outputs with cycle-consistent adversarial networks

Climate model outputs are commonly corrected using statistical univariate bias correction methods. Most of the time, those 1d-corrections do not modify the ranks of the time series to be corrected. This implies that biases in the spatial or inter-variable dependences of the simulated variables are not adjusted. Hence, over the last few years, some multivariate bias correction (MBC) methods have been developed to account for inter-variable structures, inter-site ones, or both. As proof-of-concept, we propose to adapt a computer vision technique used for Image-to-Image translation tasks (CycleGAN) for the adjustment of spatial dependence structures of climate model projections. The proposed algorithm, named MBC-CycleGAN, aims to transfer simulated maps (seen as images) with inappropriate spatial dependence structure from climate model outputs to more realistic images with spatial properties similar to the observed ones. For evaluation purposes, the method is applied to adjust maps of temperature and precipitation from climate simulations through two cross-validation approaches. The first one is designed to assess two different post-processing schemes (Perfect Prognosis and Model Output Statistics). The second one assesses the influence of nonstationary properties of climate simulations on the performance of MBC-CycleGAN to adjust spatial dependences. Results are compared against a popular univariate bias correction method, a “quantile-mapping” method, which ignores inter-site dependencies in the correction procedure, and two state-of-the-art multivariate bias correction algorithms aiming to adjust spatial correlation structure. In comparison with these alternatives, the MBC-CycleGAN algorithm reasonably corrects spatial correlations of climate simulations for both temperature and precipitation, encouraging further research on the improvement of this approach for multivariate bias correction of climate model projections.

Assessment of the uncertainty in spatial-correlation models for earthquake ground motion due to station layout and derivation method

The evaluation of the aggregate risks to spatially distributed infrastructures and portfolios of buildings requires quantification of the estimated shaking over a region. To characterize the spatial dependency of ground motion intensity measures (e.g. peak ground acceleration), a common geostatistical tool is the semivariogram. Over the past decades, different fitting approaches have been proposed in the geostatistics literature to fit semivariograms and thus characterize the correlation structure. A theoretically optimal approach has not yet been identified, as it depends on the number of observations and configuration layout. In this article, we investigate estimation methods based on the likelihood function, which, in contrast to classical least-squares methods, straightforwardly define the correlation without needing further steps, such as computing the experimental semivariogram. Our outcomes suggest that maximum-likelihood based approaches may outperform least-squares methods. Indeed, the former provides correlation estimates, that do not depend on the bin size, unlike ordinary and weighted least-squares regressions. In addition, maximum-likelihood methods lead to lower percentage errors and dispersion, independently of both the number of stations and their layout as well as of the underlying spatial correlation structure. Finally, we propose some guidelines to account for spatial correlation uncertainty within seismic hazard and risk assessments. The consideration of such dispersion in regional assessments could lead to more realistic estimations of both the ground motion and corresponding losses.

A method to define the relevant ego-centred spatial scale for the assessment of neighbourhood effects: the example of cardiovascular risk factors

Introduction The neighbourhood in which one lives affects health through complex pathways not yet fully understood. A way to move forward in assessing these pathways direction is to explore the spatial structure of health phenomena to generate hypotheses and examine whether the neighbourhood characteristics are able to explain this spatial structure. We compare the spatial structure of two cardiovascular disease risk factors in three European urban areas, thus assessing if a non-measured neighbourhood effect or spatial processes is present by either modelling the correlation structure at individual level or by estimating the intra-class correlation within administrative units. Methods Data from three independent studies (RECORD, DHS and BaBi), covering each a European urban area, are used. The characteristics of the spatial correlation structure of cardiovascular risk factors (BMI and systolic blood pressure) adjusted for age, sex, educational attainment and income are estimated by fitting an exponential model to the semi-variogram based on the geo-coordinates of places of residence. For comparison purposes, a random effect model is also fitted to estimate the intra-class correlation within administrative units. We then discuss the benefits of modelling the correlation structure to evaluate the presence of unmeasured spatial effects on health. Results BMI and blood pressure are consistently found to be spatially structured across the studies, the spatial correlation structures being stronger for BMI. Eight to 22% of the variability in BMI were spatially structured with radii ranging from 100 to 240 m (range). Only a small part of the correlation of residuals was explained by adjusting for the correlation within administrative units (from 0 to 4 percentage points). Discussion The individual spatial correlation approach provides much stronger evidence of spatial effects than the multilevel approach even for small administrative units. Spatial correlation structure offers new possibilities to assess the relevant spatial scale for health. Stronger correlation structure seen for BMI may be due to neighbourhood socioeconomic conditions and processes like social norms at work in the immediate neighbourhood.

Improved inference for areal unit count data using graph-based optimisation

Spatio-temporal count data relating to a set of non-overlapping areal units are prevalent in many fields, including epidemiology and social science. The spatial autocorrelation inherent in these data is typically modelled by a set of random effects that are assigned a conditional autoregressive prior distribution, which is a special case of a Gaussian Markov random field. The autocorrelation structure implied by this model depends on a binary neighbourhood matrix, where two random effects are assumed to be partially autocorrelated if their areal units share a common border, and are conditionally independent otherwise. This paper proposes a novel graph-based optimisation algorithm for estimating either a static or a temporally varying neighbourhood matrix for the data that better represents its spatial correlation structure, by viewing the areal units as the vertices of a graph and the neighbour relations as the set of edges. The improved estimation performance of our methodology compared to the commonly used border sharing rule is evidenced by simulation, before the method is applied to a new respiratory disease surveillance study in Scotland between 2011 and 2017.

Kriging Method-Based Return Prediction of Waste Electrical and Electronic Equipment in Reverse Logistics

In reverse logistics, the accurate prediction of waste electrical and electronic equipment (WEEE) return amount is of great significance to guide electronic enterprises to formulate a reasonable recycling plan, remanufacturing production plan and inventory plan. However, due to the uncertainty of WEEE return, it is a challenge to accurately predict the WEEE return amount of recycling sites. Differently from the existing research methods aiming at the spatial correlation of the recycling amount of recycling sites, a spatial mathematical model based on Kriging method is proposed by this paper to predict the return amount of WEEE in reverse logistics. Based on the second-order randomness of the return amount, the spatial structure of the return amount of the recycling network is analyzed. According to the principle of unbiased prediction and minimum variance, the Kriging space mathematical model of WEEE return amount is derived, and the calculation process of three variograms is given. The results of Monte Carlo simulation and the case study on J company in Shanghai show that it is effective to utilize the Kriging method-based spatial mathematical model to predict the WEEE return of reverse logistics and analyze the spatial correlation structure of each recycling site. The proposed model can accurately predict the WEEE return amounts of unknown sites as well as those of the whole area through the known site data, which provides a novel analysis method and theoretical basis for the prediction of reverse logistics return amount.

Brain kernel: a new spatial covariance function for fMRI data

A key problem in functional magnetic resonance imaging (fMRI) is to estimate spatial activity patterns from noisy high-dimensional signals. Spatial smoothing provides one approach to regularizing such estimates. However, standard smoothing methods ignore the fact that correlations in neural activity may fall off at different rates in different brain areas, or exhibit discontinuities across anatomical or functional boundaries. Moreover, such methods do not exploit the fact that widely separated brain regions may exhibit strong correlations due to bilateral symmetry or the network organization of brain regions. To capture this non-stationary spatial correlation structure, we introduce the brain kernel, a continuous covariance function for whole-brain activity patterns. We define the brain kernel in terms of a continuous nonlinear mapping from 3D brain coordinates to a latent embedding space, parametrized with a Gaussian process (GP). The brain kernel specifies the prior covariance between voxels as a function of the distance between their locations in embedding space. The GP mapping warps the brain nonlinearly so that highly correlated voxels are close together in latent space, and uncorrelated voxels are far apart. We estimate the brain kernel using resting-state fMRI data, and we develop an exact, scalable inference method based on block coordinate descent to overcome the challenges of high dimensionality (10-100K voxels). Finally, we illustrate the brain kernel's usefulness with applications to brain decoding and factor analysis with multiple task-based fMRI datasets.

Adjusting spatial dependence of climate model outputs with Cycle-Consistent Adversarial Networks

Climate model outputs are commonly corrected using statistical univariate bias correction methods. Most of the time, those 1d-corrections do not modify the ranks of the time series to be corrected. This implies that biases in the spatial or inter-variable dependences of the simulated variables are not adjusted. Hence, over the last few years, some multivariate bias correction (MBC) methods have been developed to account for inter-variable structures, inter-site ones, or both. As proof-of-concept, we propose to adapt a computer vision technique used for Image-to-Image translation tasks (CycleGAN) for the adjustment of spatial dependence structures of climate model projections. The proposed algorithm, named MBC-CycleGAN, aims to transfer simulated maps (seen as images) with inappropriate spatial dependence structure from climate model outputs to more realistic images with spatial properties similar to the observed ones. For evaluation purposes, the method is applied to adjust maps of temperature and precipitation from climate simulations through two cross-validation approaches. The first one is designed to assess two different post-processing schemes (Perfect Prognosis and Model Output Statistics). The second one assesses the influence of nonstationary properties of climate simulations on the performance of MBC-CycleGAN to adjust spatial dependences. Results are compared against a popular univariate bias correction method, a ``quantile-mapping'' method, which ignores inter-site dependencies in the correction procedure, and two state-of-the-art multivariate bias correction algorithms aiming to adjust spatial correlation structure. In comparison with these alternatives, the MBC-CycleGAN algorithm reasonably corrects spatial correlations of climate simulations for both temperature and precipitation, encouraging further research on the improvement of this approach for multivariate bias correction of climate model projections.