Spatial Time Series Research Articles

Spatiotemporal evolution of global long-term patterns of soil moisture

Surface soil moisture (SM) is essential for existence of biotic lifeform and geophysical processes. However, with increasing global warming due to climatic changes, its spatiotemporal evolution is uncertain and largely unknown. In this study we detected long-term (40 years; 1981–2020) SM patterns of global vegetated areas through spatial timeseries clustering using the state-of-the-art ERA5-Land dataset. In addition, we also analyzed long-term patterns of precipitation (P), evapotranspiration (bare soil evaporation (BSe) and vegetation transpiration (VT)), and normalized difference vegetation index (NDVI). Our results indicate that surface SM (0–7 cm depth) of about 48 % and 9 % of the global vegetated area is showing drying and wetting pattern over the past 40 years, respectively. The detected soil drying, and wetting patterns were largely consistent across different soil depth, with 90 % and 80 % pattern similarity of surface soil layer with 2nd soil layer (7–28 cm) and 3rd soil layer (28–100 cm), respectively. About 80 % of areas with drying soil pattern also showed increasing evapotranspiration and/or decreasing precipitation. Specifically, decreasing P, increasing BSe and VT pattern were detected for 11 % of the soil drying pattern area. Similarly, increasing BSe and VT pattern, only decreasing P and only increasing VT pattern were detected for 17 %, 25 % and 12 % of soil drying areas, respectively. Both decreasing precipitation and increasing evapotranspiration patterns showed about 40 % similarity with decreasing soil moisture patterns. Across different landcover types, broadleaved forests, and cropland areas showed largest drying pattern. Under the future global warming scenario, the global soil water is expected to decrease as evapotranspiration would increase with inconsistent trend of global precipitation change. Our findings are of utmost importance for global soil water resource conservation and management.

Evaluation of ERA5 and ERA5-Land reanalysis precipitation datasets over Spain (1951–2020)

Reanalysis precipitation estimates are widely used in the fields of meteorology and hydrology because they can provide physical, spatial, and temporal coherent long time series at a global scale. Nevertheless, as a pre-requisite for many applications their performance needs to be assessed. The objective of this study was to evaluate the European Centre for Medium-Range Weather Forecasts (ECMWF) latest fifth-generation reanalysis precipitation products, i.e., ERA5 and ERA5-Land, at country scale in Spain. For doing so, we compared it against a high-resolution precipitation product of the Spanish Meteorological Agency which spans approximately 70 years (1951–2020). A comprehensive assessment (continuous, categorical, probability distribution function (pdf), spatial pattern, and temporal trend) was performed in order to ascertain the quality of the reanalysis products. Results of the analysis revealed a general agreement between observations and ERA5-Land/ERA5 estimates: spearman correlation values between 0.5 and 0.9, Root Mean Square Error (RMSE) mostly between 2 and 8 mm/d and Kling Gupta Efficiency (KGE) values >0.4. Categorical assessment additionally indicated a good performance (Heiken Skill score (HSS) score, also known as kappa, between 0.4 and 0.8). Nevertheless, performance was found to be dependent on the climatic region, precipitation intensity and orography. Correlation revealed a north-west (higher values) south-east (lower values) spatial gradient while relative bias (RBIAS) and RMSE spatial patterns were positively correlated with slope (ρ = 0.41/0.35, 0.69/0.70, respectively). In addition, as indicated by the categorical analysis, along the Mediterranean coast a wet bias (i.e., overestimation of days with precipitation) was found. Reanalysis detection capacity (kappa) shown a negative correlation with the slope (ρ = −0.29/−0.34). Worst model performance is obtained during summer months, with a generalized overestimation. The pdf assessment revealed that the ERA5-Land/ERA5 tended to overestimate light (≥1 and < 5 mm/day), and moderate (≥5 and < 20 mm/day) precipitation categories while underestimating the heavy (≥20 and < 40 mm/day) and violent (≥40 mm/day) categories. Moderate precipitation provided the best detection capacity, as indicated by the precipitation-intensity analysis. ERA5-Land/ERA5 showed a good capacity to reproduce the spatial patterns and temporal trends of the observations. ERA5-Land and ERA5, with a different spatial resolution, performed very similar in all the analysis considered. Mediterranean and northern coast were highlighted as the most critical for reanalysis modelling purposes because of its performance.

Applicability Assessment of a Spatiotemporal Geostatistical Fusion Model for Disaster Monitoring: Two Cases of Flood and Wildfire

A spatial time series geostatistical deconvolution/fusion model (STGDFM), as one of spatiotemporal data fusion model, combines Dense time series data with a Coarse-scale (i.e., DC data) and Sparse time series data with a Fine-scale (i.e., SF data) to generate Synthetic Dense time series data with a Fine-scale (i.e., SDF data). Specifically, STGDFM uses a geostatistics-based spatial time series modeling to capture the temporal trends included in time series DC data. This study evaluated the prediction performance of STGDFM for abrupt changes in reflectance due to disasters in spatiotemporal data fusion, and a spatial and temporal adaptive reflectance fusion model (STARFM) and an enhanced STARFM (ESTARFM) were selected as comparative models. For the applicability assessment, flood and wildfire were selected as case studies. In the case of flood, MODIS-like data (240 m) with spatial resolution converted from Landsat data and Landsat data (30 m) were used as DC and SF data, respectively. In the case of wildfire, MODIS and Landsat data were used as DC and SF data, respectively. The case study results showed that among the three spatiotemporal fusion models, STGDFM presented the best prediction performance with 0.894 to 0.979 at the structure similarity and 0.760 to 0.872 at the R-squared values in the flood- and wildfire-affected areas. Unlike STARFM and ESTARFM that adopt the assumptions for reflectance changes, STGDFM combines the temporal trends using time series DC data. Therefore, STGDFM could capture the abrupt changes in reflectance due to the flood and wildfire. These results indicate that STGDFM can be used for cases where satellite images of appropriate temporal and spatial resolution are difficult to acquire for disaster monitoring.

Developing DPSIR Framework for Managing Climate Change in Urban Areas: A Case Study in Jakarta, Indonesia

From an environmentally conscious and ecological perspective, the sustainability of cities within the effects of climate change are closely related to the wise use of resources and modifications in the ecological status of the environment. In terms of the ecological environment, the sustainability of smart cities entails meeting present and future societal demands for the environment of the water, land, and air, among others. Environmental and the ecological concerns that arise from rapid climate change and monetary developments are shown in the inconsistency between ecological assets, environmental pollution, and the destruction of nature. In this study, the authors aim to develop a strategy to deal with climate change in urban areas using Remote Sensing and the Driver-Pressure-State-Impact-Response (DPSIR) Framework with a case study in Jakarta Smart City. The DPSIR framework, which will be developed and implemented in the city of Jakarta, is a smarter and more sustainable framework that is evaluated through a systematic evaluation of sustainability with quantitative research using the entropy weight method and Partial Least Square-Structural Equation Modeling (PLS-SEM). These methods evaluate 58 representative elements of environments at the urban level, including the shortcomings of earlier research such as data availability, spatial and temporal constraints, and several related ecological indicators, such as soil pH, wind speed, air quality index as well as land changes in the spatial (spatiotemporal) time series. The results of the study show that in the metropolitan city of Jakarta, the Drivers that are related to climate change are the rate of population growth and the rate of industrial growth which, although increases people’s income and GRDP in Jakarta; it also creates Pressures, namely an increase in the amount of water consumption and in the amount of wastewater. Based on these pressures, the environmental conditions (State) of Jakarta city have undergone several environmental changes, such as loss of water supply, changes in wind speed, changes in rainfall, and increasing concentrations of the Air Pollutant Standard Index. The Impact of these three elements resulted in the increase in household and industrial water consumption, an increase in annual electricity consumption, and deteriorating air quality. Hence, the Response to these four interrelated causal variables is that the Jakarta Provincial Government must increase annual funds for the construction of urban community facilities, increase the production capacity of clean water supply, build environment-friendly wastewater treatment facilities, increase the capacity of waste processing infrastructure and transportation fleets, and educate people to use water wisely to reduce the level of water use.

Deep learning models to map an agricultural expansion area with MODIS and Sentinel-2 time series images

Mapping changing land use and land cover (LULC) is important for land management and environment analysis. We tried to build deep learning models to classify LULC over time at an agricultural expansion area in Matopiba region, Brazil with MCD43A4 V006 moderate resolution imaging spectroradiometer (MODIS), and Sentinel-2 multispectral instrument (MSI) time series data. We collected time series MODIS data and Sentinel-2 A/B MSI data from 2015 to 2020 and prepared small patches with containing blue, green, red, near-infrared, and shortwave-infrared-1 bands as features. Then the both datasets were used to build and train the convolutional neural network (CNN) model, the CNN gate recurrent unit (CNN-GRU) model, and the CNN long short-term memory (CNN-LSTM) model, respectively. We evaluated these three trained models with ground truth data, and the CNN-LSTM model (overall accuracy: 91.29% from MODIS data and 89.47% from Sentinel-2 data) was better than the CNN-GRU model (overall accuracy: 89.19% from MODIS data and 88.61% from Sentinel-2 data) and the CNN model (overall accuracy: 89.17% from MODIS data and 86.02% from Sentinel-2 data). Our results also showed that the accuracy from cropland and savanna classes were higher than grassland and forest classes in all three models. These two classes generated from the CNN-LSTM model performed better than the other two deep learning models. The results from these two datasets indicated that the methods were reliable for both coarse and medium spatial resolution satellite images and time series remote sensing images worked better than single image for classification problems when considering LULC change over time. The results also provided an alternative way to prepare input data from satellite images for deep learning models. Furthermore, the classification results of the whole agricultural expansion area were reasonable and it can be used as an additional dataset for further environmental analysis at a regional scale.

Multivariate and spatio-temporal groundwater pollution risk assessment: A new long-time serial groundwater environmental impact assessment system

Groundwater pollution risk assessment is an important part of environmental assessment. Although it has been developed for many years, there has not yet been a multi-dimensional method that takes into account long time series and spatial factors. We proposed a new method combines the advantages of remote sensing cloud computing, long-term groundwater modeling simulation and GIS technology to solve it efficiently. A coastal industrial park in Hainan was used as the study area. The depth of groundwater level, rainfall, topography and geomorphology, soil moisture, pollution source, pollution toxicity and other more than 10 parameters were used as the indexes. A comprehensive model with remote sensing cloud computing, DRASTIC model and Modflow + MT3DMS was established to assess the pollution risk from 2014 to 2021. The multi-year results indicated that the risk assessment of groundwater pollution was usually on the vertical coastal direction, and the risk increased from far away to near coast. With the discharge of pollutants in the industrial park, the pollution risk in the area 5 km away from the centre increased year by year until it became stable in 2019, and the risk in the centre of the park reached 1 level, covered an area of up to 145400 square metres, accounted for 0.012% of the whole study area. The assessment results in 2020 and 2021 fluctuate slightly compared with those in 2019. Therefore, in terms of groundwater resource protection and resource management, it is necessary to focus on the detection of pollution in the coastal zone and the pollution within 5 km of the centre to strictly control pollution discharge. In this study, the comprehensive assessment includes surface indicators, subsurface indicators, and pollutant indicators. Finally, we achieve a multivariate, spatial and long time series groundwater pollution risk assessment system, which is a new groundwater environmental impact assessment (GEIA) system.

The impact of tourism development on the changes of the household economy in ciwidey tourism area, bandung regency, west java

Ciwidey Tourism Area is a tourism destination in the Province of West Java which has a rapid development. In 2007, the provincial government officially declared the area as the agropolitan region. It stimulated the fundamental impact on the household economy in the area. This study aims to elaborate on the spatial pattern of household economy alteration due to tourism penetration. It is a descriptive stud y that relies on primary data that comes from field observation and questionnaire - interview with local people. The study exercises spatial dan time series analysis to analyze the change of occupation and income of households between before and after the year 2007. The results showed that the development of tourism is situated at a distance of 2.5 km-5 km outside the core of the tourism area. It was marked by the development of tourism objects, tourism attractions, and secondary facilities. Such development resulted in changes in the type of household economy, from both the “unemployed” and “agricultural” to the “tourism” households. This change in household types was followed by an increase in population income, mostly around the tourism core.

Impact of Driving Behavior on Commuter’s Comfort During Cab Rides: Towards a New Perspective of Driver Rating

Commuter comfort in cab rides affects driver rating as well as the reputation of ride-hailing firms like Uber/Lyft. Existing research has revealed that commuter comfort not only varies at a personalized level but also is perceived differently on different trips for the same commuter. Furthermore, there are several factors, including driving behavior and driving environment, affecting the perception of comfort. Automatically extracting the perceived comfort level of a commuter due to the impact of the driving behavior is crucial for a timely feedback to the drivers, which can help them to meet the commuter’s satisfaction. In light of this, we surveyed around 200 commuters who usually take such cab rides and obtained a set of features that impact comfort during cab rides. Following this, we develop a system Ridergo which collects smartphone sensor data from a commuter, extracts the spatial time series feature from the data, and then computes the level of commuter comfort on a five-point scale with respect to the driving. Ridergo uses a Hierarchical Temporal Memory model-based approach to observe anomalies in the feature distribution and then trains a multi-task learning-based neural network model to obtain the comfort level of the commuter at a personalized level. The model also intelligently queries the commuter to add new data points to the available dataset and, in turn, improve itself over periodic training. Evaluation of Ridergo on 30 participants shows that the system could provide efficient comfort score with high accuracy when the driving impacts the perceived comfort.

Vorticity in the Wake of Palau from Lagrangian Surface Drifters

Abstract Wake eddies are important to physical oceanographers because they tend to dominate current variability in the lee of islands. However, their generation and evolution has been difficult to study due to their intermittency. In this study, 2 years of observations from Surface Velocity Program (SVP) drifters are used to calculate relative vorticity (ζ) and diffusivity (κ) in the wake generated by westward flow past the archipelago of Palau. Over 2 years, 19 clusters of five SVP drifters ∼5 km in scale were released from the north end of the archipelago. Out of these, 15 were entrained in the wake. We compare estimates of ζ from both velocity spatial gradients (least squares fitting) and velocity time series (wavelet analysis). Drifters in the wake were entrained in either energetic submesoscale eddies with initial ζ up to 6f, or island-scale recirculation and large-scale lateral shear with ζ ∼ 0.1f. Here f is the local Coriolis frequency. Mean wake vorticity is initially 1.5f but decreases inversely with time (t), while mean cluster scale (L) increases as L ∝ t. Kinetic energy measured by the drifters is comparatively constant. This suggests ζ is predominantly a function of scale, confirmed by binning enstrophy (ζ2) by inverse scale. We find κ ∝ L4/3 and upper and lower bounds for L(t) are given by t3/2 and t1/2, respectively. These trends are predicted by a model of dispersion due to lateral shear. We argue the observed time dependence of cluster scale and vorticity suggest island-scale shear controls eddy growth in the wake of Palau.

AgriMine: A Deep Learning integrated Spatio-temporal analytics framework for diagnosing nationwide agricultural issues using farmers’ helpline data

In the current scenario, exploring new means to gain accurate information regarding agriculture-related problems is the need of the hour. In this direction, we propose a multi-stage framework to perform spatial mapping and time series analysis on more than 26 million farmers’ helpline call-log records, made available by the Ministry of Agriculture & Farmers’ Welfare, Government of India. The proposed spatial analysis framework delivers hidden patterns regarding the crop-wise density of farmers calling for help from various regions of the country. Furthermore, the proposed step-plot concept gives insights into the time span of the problems in the agriculture sector. Additionally, the proposed framework explores the potential of high-end forecasting models, including five Deep Learning-based models to predict the topic-wise demand for help (number of query calls) by the producers of the target regions. To elaborate on the utility of the presented work, the article outlines two case studies corresponding to policy recommendations regarding agriculture extension and other related domains using AgriMine.

The Interplay between Spatial Urban Expansion and Morphologic Landscapes East of Cairo, Egypt Using Time Series Satellite Imagery

This study aims to monitor the magnitudes, rates, and directions of spatial urban expansions east of Cairo and their interactions with the initial morphologic landscapes. The approach relies on using CORONA satellite images acquired in 1969 with fine spatial resolution and time series images of Landsat and ASTER from 1984 to 2020. The CORONA images enable retrieval of the initial morphologic components, whereas the Landsat and ASTER images enable the spatial urban expansions to be mapped. The magnitudes of spatial urban expansions have been massive, in the order of 165 km2. These expansions have occurred through four main temporal phases with different spatial extents, rates, and directions in response to common urban policies and socioeconomic settings. Assessing the interactions between urban expansions and the morphology of watersheds in the study area indicates that the directions of urban expansion have been opposite to the geospatial orientations of the watersheds. In addition, significant urban areas in the order of ~8 km2 are under the direct threat of flash floods because they are misplaced within the valley floors of the studied watersheds. The study concludes that successful spatial urban expansion should consider the morphologic characteristics of the initial landscape for the purpose of maximizing interests and avoiding or reducing potential hazards against urban settlements.

DEVELOPING GEOGRAPHICALLY WEIGHTED PANEL REGRESSION MODEL FOR SPATIO-TEMPORAL ANALYSIS OF COVID-19 POSITIVE CASES IN KALIMANTAN, INDONESIA

This article describes spatial-temporal analysis using the innovation of developing a Geographically Weighted Panel Regression model with a distance weighting function that includes the interaction between spatial and time aspects (GWPR-st). The method is a local regression technique that provides a parameter model that varies in each location through cross-sectional and time-series data observation units. This study develops a new model in spatial statistics and offers new methodologies in Geographic Models and Geographic Information Systems (GIS). This study aims to determine the factors that influence the increase in positive cases and map the spread of COVID-19 on the Kalimantan Regency/City Scale. The model applied in this study involves geographic weighting functions, including the Gaussian kernel, Bisquare kernel, and tricube kernel, which spatial interactions and time series have modified. This study uses national COVID-19 data from 56 regencies/cities until August 2021. According to the research results, the developed model with the geographic weighting of the Bisquare kernel function was considered the most acceptable method. The developed model, which is deemed capable of information the most substantial influence on the number of COVID-19 cases in Kalimantan, is health services, such as a shortage of doctors, number of hospitals, number of community health centers, and number of tuberculosis cases. The study results provide the local governments with decision-making recommendations for overcoming the COVID-19 problems in their regions.

Preliminary Application of Space-Based Remote Sensing and Geospatial Technology for Investigation on the Geo-Environmental Consequences of Cyclone Aila 2009 in the NW Bangladesh

Climate change phenomena have become a great concern in the context of global change and increased frequency and magnitude of natural disasters throughout the world in the recent time. Natural disasters like floods, cyclones, storm surges etc. often cause significant losses of life, large-scale economic and social impacts, and considerable environmental damages. This paper dealt with study on the overall methodological development to investigate the consequences of climate change extremities particularly, the after effects of cyclone using Remote Sensing (RS) and Geographic Information System (GIS) technology. In this connection, individual functional components have been investigated, tested and verified. Time series multi-sensor satellite data particularly of Landsat, World view (from Google origin) have been utilized to infer information on the consequences of Cyclone Aila 2009 hitting part of southwestern Bangladesh as a test case under the present study. Information retrieval mechanism utilized is based on specially designed methodological framework using satellite-based RS technology along with GIS. Developed technical approach consists of a three-fold components – (i) Establishment of input foundation layer with high spatial details to support characterization, recognition and identification of important surface features using high resolution satellite data; (ii) Effective operational procedure to process, analyze, interpret and finally to archive the retrieved information; (iii) Functional computations were made using spatial modeler language (SML) programming environment under ERDAS Imagine image processing software. Satellite image processing, analysis operation together with image-based spectral characterization of surface features under different stressing conditions etc. have been exercised to derive useful surface information. Specially designed geospatial database has been established in GIS using ArcInfo professional software. Varieties of geospatial data from diverse sources have been incorporated categorically as column-based attributes in GIS. Dual spatial data layers have been generated in GIS for two different dates representing the pre-cyclone and post-cyclone time sequences utilizing appropriate high spatial resolution satellite images. Finally, a geospatial image-based combinational technique has been utilized employing high temporal and moderate spatial resolution time series satellite data with low temporal and high spatial resolution satellite data. Such an operation results in an improved spatial and temporal resolution of output products enabling capture of dynamics of surface features in the spatiotemporal domain providing more precision and details in the output. This study has been supplemented with necessary Ground Position System (GPS)-based ground truthing, selected field data collection and field-based group discussions outcomes.

Sustainable Development Goals and childhood measles vaccination in Ekiti State, Nigeria: Results from spatial and interrupted time series analyses

Measles remains an important cause of childhood mortality in many resource-limited countries. With Sustainable Development Goals (SDG), there has been increasing emphasis on measles vaccination as a key strategy to remarkably improve child survival. While progress has been made towards measles vaccination coverage due to SDG in some settings, there has been no prior study evaluating its impact in Nigeria. To assess the effectiveness of SDG policy implementation on measles vaccination coverage, we examined the changes in first dose of measles vaccination coverage rates among children aged 9–15 months following the implementation of SDG, and changes in spatial patterns of measles vaccination from 2014 to 2019 in Ekiti State, Southwest Nigeria. Using state and local government area-level District Health Information data from January 2014 to December 2019, we conducted interrupted time series (ITS) and spatiotemporal analyses. The ITS evaluated the immediate and continuous effects of SDG policy implementation on the monthly childhood measles vaccination coverage by comparing longitudinal changes in rates between pre-intervention period (January 2014-December 2015) and during-intervention period (January 2016-December 2019). The low and high coverage clusters across the years were detected with spatial cluster analysis. The average state-level measles vaccination coverage rates from 2014 to 2019 was 70.67%. In 2019, coverage rate was 49%—a 35.53% decline from 76% in 2014 and a state-level gap of 46%. The geographical distribution of measles vaccination varied considerably across the local government areas from 2014 to 2019. There was an initial acceleration of vaccination rates (β^ = 24.07, p-value = 0.012), but a significant decrease in coverage rates after implementation of SDG policy in Ekiti State (β^ = −1.08, p-value < 0.001). No local government area had accelerated monthly coverage rates following SDG-implementation. Evidence suggests immediate acceleration in coverage rates which could not be sustained during SDG-era and calls for a rethink measles immunization coverage strategy in the state and other resource-limited jurisdictions to ensure vaccination scale-up.

Modeling the Determinants of PM2.5 in China Considering the Localized Spatiotemporal Effects: A Multiscale Geographically Weighted Regression Method

Many studies have identified the influences of PM2.5. However, very little research has addressed the spatiotemporal dependence and heterogeneity in the relationships between impact factors and PM2.5. This study firstly utilizes spatial statistics and time series analysis to investigate the spatial and temporal dependence of PM2.5 at the city level in China using a three-year (2015–2017) dataset. Then, a new local regression model, multiscale geographically weighted regression (MGWR), is introduced, based on which we measure the influence of PM2.5. A spatiotemporal lag is constructed and included in MGWR to account for spatiotemporal dependence and spatial heterogeneity simultaneously. Results of MGWR are comprehensively compared with those of ordinary least square (OLS) and geographically weighted regression (GWR). Experimental results show that PM2.5 is autocorrelated in both space and time. Compared with existing approaches, MGWR with a spatiotemporal lag (MGWRL) achieves a higher goodness-of-fit and a more significant effect on eliminating residual spatial autocorrelation. Parameter estimates from MGWR demonstrate significant spatial heterogeneity, which traditional global models fail to detect. Results also indicate the use of MGWR for generating local spatiotemporal dependence evaluations which are conditioned on various covariates rather than being simple descriptions of a pattern. This study offers a more accurate method to model geographic events.

Discovering hidden brain network responses to naturalistic stimuli via tensor component analysis of multi-subject fMRI data

The study of brain network interactions during naturalistic stimuli facilitates a deeper understanding of human brain function. To estimate large-scale brain networks evoked with naturalistic stimuli, a tensor component analysis (TCA) based framework was used to characterize shared spatio-temporal patterns across subjects in a purely data-driven manner. In this framework, a third-order tensor is constructed from the timeseries extracted from all brain regions from a given parcellation, for all participants, with modes of the tensor corresponding to spatial distribution, time series and participants. TCA then reveals spatially and temporally shared components, i.e., evoked networks with the naturalistic stimuli, their time courses of activity and subject loadings of each component. To enhance the reproducibility of the estimation with the adaptive TCA algorithm, a novel spectral clustering method, tensor spectral clustering, was proposed and applied to evaluate the stability of the TCA algorithm. We demonstrated the effectiveness of the proposed framework via simulations and real fMRI data collected during a motor task with a traditional fMRI study design. We also applied the proposed framework to fMRI data collected during passive movie watching to illustrate how reproducible brain networks are evoked by naturalistic movie viewing.

Real‐Time 3‐D Modeling of the Ground Electric Field Due To Space Weather Events. A Concept and Its Validation

AbstractWe present a methodology that allows researchers to simulate in real time the spatiotemporal dynamics of the ground electric field (GEF) in a given 3‐D conductivity model of the Earth based on continuously augmented data on the spatiotemporal evolution of the inducing source. The formalism relies on the factorization of the source by spatial modes (SM) and time series of respective expansion coefficients and exploits precomputed GEF kernels generated by corresponding SM. To validate the formalism, we invoke a high‐resolution 3‐D conductivity model of Fennoscandia and consider a realistic source built using the Spherical Elementary Current Systems (SECS) method as applied to magnetic field data from the International Monitor for Auroral Geomagnetic Effect network of observations. The factorization of the SECS‐recovered source is then performed using the principal component analysis. Eventually, we show that the GEF computation at a given time instant on a 512 × 512 grid requires less than 0.025 s provided that GEF kernels due to pre‐selected SM are computed in advance. Taking the 7–8 September 2017 geomagnetic storm as a space weather event, we show that real‐time high‐resolution 3‐D modeling of the GEF is feasible. This opens a practical opportunity for GEF (and eventually geomagnetically induced currents) nowcasting and forecasting.

DIC-ST: A Hybrid Prediction Framework Based on Causal Structure Learning for Cellular Traffic and Its Application in Urban Computing

The development of technology has strongly affected regional urbanization. With development of mobile communication technology, intelligent devices have become increasingly widely used in people’s lives. The application of big data in urban computing is multidimensional; it has been involved in different fields, such as urban planning, network optimization, intelligent transportation, energy consumption and so on. Data analysis becomes particularly important for wireless networks. In this paper, a method for analyzing cellular traffic data was proposed. Firstly, a method to extract trend components, periodic components and essential components from complex traffic time series was proposed. Secondly, we introduced causality data mining. Different from traditional time series causality analysis, the depth of causal mining was increased. We conducted causality verification on different components of time series and the results showed that the causal relationship between base stations is different in trend component, periodic component and essential component in urban wireless network. This is crucial for urban planning and network management. Thirdly, DIC-ST: a spatial temporal time series prediction based on decomposition and integration system with causal structure learning was proposed by combining GCN. Final results showed that the proposed method significantly improves the accuracy of cellular traffic prediction. At the same time, this method can play a crucial role for urban computing in network management, intelligent transportation, base station siting and energy consumption when combined with remote sensing map information.

Determinants of COVID-19 Vaccinations among a State-Wide Year-Long Surveillance Initiative in a Conservative Southern State.

By the end of 2021, the COVID-19 pandemic resulted in over 54 million cases and more than 800,000 deaths in the United States, and over 350 million cases and more than 5 million deaths worldwide. The uniqueness and gravity of this pandemic have been reflected in the public health guidelines poorly received by a growing subset of the United States population. These poorly received guidelines, including vaccine receipt, are a highly complex psychosocial issue, and have impacted the successful prevention of disease spread. Given the intricate nature of this important barrier, any single statistical analysis methodologically fails to address all convolutions. Therefore, this study utilized different analytical approaches to understand vaccine motivations and population-level trends. With 12,975 surveys from a state-wide year-long surveillance initiative, we performed three robust statistical analyses to evaluate COVID-19 vaccine hesitancy: principal component analysis, survival analysis and spatial time series analysis. The analytic goal was to utilize complementary mathematical approaches to identify overlapping themes of vaccine hesitancy and vaccine trust in a highly conservative US state. The results indicate that vaccine receipt is influenced by the source of information and the population’s trust in the science and approval process behind the vaccines. This multifaceted statistical approach allowed for methodologically rigorous results that public health professionals and policy makers can directly use to improve vaccine interventions.

Embedded Temporal Convolutional Networks for Essential Climate Variables Forecasting.

Forecasting the values of essential climate variables like land surface temperature and soil moisture can play a paramount role in understanding and predicting the impact of climate change. This work concerns the development of a deep learning model for analyzing and predicting spatial time series, considering both satellite derived and model-based data assimilation processes. To that end, we propose the Embedded Temporal Convolutional Network (E-TCN) architecture, which integrates three different networks, namely an encoder network, a temporal convolutional network, and a decoder network. The model accepts as input satellite or assimilation model derived values, such as land surface temperature and soil moisture, with monthly periodicity, going back more than fifteen years. We use our model and compare its results with the state-of-the-art model for spatiotemporal data, the ConvLSTM model. To quantify performance, we explore different cases of spatial resolution, spatial region extension, number of training examples and prediction windows, among others. The proposed approach achieves better performance in terms of prediction accuracy, while using a smaller number of parameters compared to the ConvLSTM model. Although we focus on two specific environmental variables, the method can be readily applied to other variables of interest.