Analysis Of Spatio-temporal Data Research Articles

Collective variable discovery in the age of machine learning: reality, hype and everything in between.

Understanding the kinetics and thermodynamics profile of biomolecules is necessary to understand their functional roles which has a major impact in mechanism driven drug discovery. Molecular dynamics simulation has been routinely used to understand conformational dynamics and molecular recognition in biomolecules. Statistical analysis of high-dimensional spatiotemporal data generated from molecular dynamics simulation requires identification of a few low-dimensional variables which can describe the essential dynamics of a system without significant loss of information. In physical chemistry, these low-dimensional variables are often called collective variables. Collective variables are used to generate reduced representations of free energy surfaces and calculate transition probabilities between different metastable basins. However the choice of collective variables is not trivial for complex systems. Collective variables range from geometric criteria such as distances and dihedral angles to abstract ones such as weighted linear combinations of multiple geometric variables. The advent of machine learning algorithms led to increasing use of abstract collective variables to represent biomolecular dynamics. In this review, I will highlight several nuances of commonly used collective variables ranging from geometric to abstract ones. Further, I will put forward some cases where machine learning based collective variables were used to describe simple systems which in principle could have been described by geometric ones. Finally, I will put forward my thoughts on artificial general intelligence and how it can be used to discover and predict collective variables from spatiotemporal data generated by molecular dynamics simulations.

Design of an AI Health Risk Assessment System for Dietary Hygiene of Key Groups Based on IoT Wearable Devices

Population Spatio-temporal big data mining and analysis techniques have been applied to risk assessment of disease transmission, which can describe disease transmission pathways and high-risk areas in fine detail. Based on spatial statistical analysis and artificial intelligence technology, this study seeks to break through the previous risk warning model of a single data source from medical institutions in the era of small data and designs an AI health risk assessment system for the dietary hygiene of key populations. The system is designed to collect multi-source Spatio-temporal big data consisting of urban population positioning, a sanitary inspection of restaurant premises, foodborne disease cases in medical institutions, and environmental monitoring. Spatial location attributes are assigned to the monitoring data, and food and multi-source data are fused across borders. Through the Internet of Things (IoT) technology, the system is designed with an IoT system consisting of sensors for automatic monitoring and wearable devices for real-time warning. Based on the spatial and artificial intelligence models, the system designs personalized and real-time early warning information for critical populations to prevent dietary health risks and provide scientific basis and support for public health departments to prevent foodborne diseases.

A Comparison of Spatiotemporal Visualizations for 3D Urban Analytics.

Recent technological innovations have led to an increase in the availability of 3D urban data, such as shadow, noise, solar potential, and earthquake simulations. These spatiotemporal datasets create opportunities for new visualizations to engage experts from different domains to study the dynamic behavior of urban spaces in this under explored dimension. However, designing 3D spatiotemporal urban visualizations is challenging, as it requires visual strategies to support analysis of time-varying data referent to the city geometry. Although different visual strategies have been used in 3D urban visual analytics, the question of how effective these visual designs are at supporting spatiotemporal analysis on building surfaces remains open. To investigate this, in this paper we first contribute a series of analytical tasks elicited after interviews with practitioners from three urban domains. We also contribute a quantitative user study comparing the effectiveness of four representative visual designs used to visualize 3D spatiotemporal urban data: spatial juxtaposition, temporal juxtaposition, linked view, and embedded view. Participants performed a series of tasks that required them to identify extreme values on building surfaces over time. Tasks varied in granularity for both space and time dimensions. Our results demonstrate that participants were more accurate using plot-based visualizations (linked view, embedded view) but faster using color-coded visualizations (spatial juxtaposition, temporal juxtaposition). Our results also show that, with increasing task complexity, plot-based visualizations perform better in preserving efficiency (time, accuracy) compared to color-coded visualizations. Based on our findings, we present a set of takeaways with design recommendations for 3D spatiotemporal urban visualizations for researchers and practitioners. Lastly, we report on a series of interviews with four practitioners, and their feedback and suggestions for further work on the visualizations to support 3D spatiotemporal urban data analysis.

A new combination of Hankel and sparsity-promoting dynamic mode decompositions and its application to the prediction of plasma turbulence

A new combined use of dynamic mode decomposition algorithms is proposed, which is suitable for the analysis of spatiotemporal data from experiments with few observation points, unlike computational fluid dynamics with many observation points. The method was applied to our data from a plasma turbulence experiment. As a result, we succeeded in constructing a quite accurate model for our training data and it made progress in predictive performance as well. In addition, modal patterns from the longer-term analysis help to understand the underlying mechanism more clearly, which is demonstrated in the case of plasma streamer structure. This method is expected to be a powerful tool for the data-driven construction of a reduced-order model and a predictor in plasma turbulence research and also any nonlinear dynamics researches of other applied physics fields.

Spatial and spatio-temporal distribution of women living with HIV mortality in Porto Alegre, Brazil, from 2007 to 2017.

ABSTRACTOBJETIVE:To present some factors related to the mortality rates of WLHIV in the city of Porto Alegre-RS.METHODS:This is a spatial and spatio-temporal analysis of ecological data about all women monitored by the health care services for the vertical transmission (VT) of HIV, between 2007 and 2017, residing in the city that died during the period. The units of analysis were the 17 sanitary districts of the city. The dependent variable was the mortality rate. The independent territorial variables were the indicators of vulnerability to poverty, women householder proportion, lack of infrastructure, HDI, and GINI index. Still, the individual data collected were: age, race/color, level of education, and period since the HIV diagnosis. The analyses used SPSS 20.0, and QGIS 218.15.RESULTS:Regions with higher vulnerability to poverty and precarious local infrastructure registered higher WLHIV mortality rates, especially black/”pardo” women in fertile age with low education. The regions with most women householders presented a risk of mortality seven times higher. The population with vulnerability to poverty presented the same result.CONCLUSIONS:Regions with critical indicators of vulnerability presented higher mortality rates of WLHIV, which demonstrates social inequalities’ impact for these women.

The Societal Echo of Severe Weather Events: Ambient Geospatial Information (AGI) on a Storm Event

The given article focuses on the benefit of harvested Ambient Geographic Information (AGI) as complementary data sources for severe weather events and provides methodical approaches for the spatio-temporal analysis of such data. The perceptions and awareness of Twitter users posting about severe weather patterns were explored as there were aspects not documented by official damage reports or derived from official weather data. We analysed Tweets regarding the severe storm event Friederike to map their spatio-temporal patterns. More than 50% of the retrieved >23.000 tweets were geocoded by applying supervised information retrievals, text mining, and geospatial analysis methods. Complementary, central topics were clustered and linked to official weather data for cross-evaluation. The data confirmed (1) a scale-dependent relationship between the wind speed and the societal echo. In addition, the study proved that (2) reporting activity is moderated by population distribution. An in-depth analysis of the crowds’ central topic clusters in response to the storm Friederike (3) revealed a plausible sequence of dominant communication contents during the severe weather event. In particular, the merge of the studied AGI and other environmental datasets at different spatio-temporal scales shows how such user-generated content can be a useful complementary data source to study severe weather events and the ensuing societal echo.

Spatiotemporal Pattern and Driving Factors of Urban Sprawl in China

Urban sprawl is a complex phenomenon related to abnormal urbanization, and it has become a key issue of global concern. This study aimed to measure urban sprawl in China and explore its spatiotemporal patterns and driving factors. Based on 343 Chinese cities at the prefecture level and above, remote sensing-derived data from 2000 to 2017 were used to calculate the urban sprawl index (USI). The evolutionary trend and spatiotemporal pattern of urban sprawl in China were then analyzed using trend analysis and exploratory spatiotemporal data analysis, and Geodetector was applied to investigate the factors driving the changes. The results show the following. ① Moderate or high urban sprawl development occurred in China from 2000 to 2017. In terms of spatial distribution, the USI was high in northwest China and low in southeast China. ② The local spatial stability of the USI gradually decreased from southeast to northwest and northeast. USI had strong spatial dependence. No significant spatiotemporal transitions in urban sprawl were observed, and the spatial pattern was stable with strong spatial cohesion. ③ The gross regional product (GRP) of the tertiary industry, the total GRP, and investment in real estate development have been the most important factors affecting sprawl in cities at the prefecture level and above in China.

Single feature spatio-temporal architecture for EEG Based cognitive load assessment.

The study of electroencephalography (EEG) data for cognitive load analysis plays an important role in identification of stress-inducing tasks. This can be useful in applications such as optimal work allocation, increasing efficiency in the workplace and ensuring safety in difficult work environments. In order for such systems to be realistically deployable, easy acquisition and processing of the data on a wearable device is imperative. Current techniques primarily perform offline processing to analyse a multi-channel EEG to make a post facto assessment. This work focusses on building a new deep learning architecture that performs a single feature based spatio-temporal analysis of EEG data. This is achieved by creating a brain topographic map based on a single feature followed by spatio-temporal analysis using the developed network architecture. Data from two cognitive load experiments on the Physionet EEGMAT dataset were used to validate the performance. The network achieves an accuracy of 98.3% which is better than similar state-of-the-art approaches. Moreover, the proposed approach facilitates analysis of the spatial propagation of a signal, which is not possible through conventional EEG signal representations.

Spatiotemporal variability analysis of air pollution data from IoT based participatory sensing

Spatiotemporal variability analysis of air pollution data from IoT based participatory sensing

Life expectancy and risk of death in 6791 communities in England from 2002 to 2019: high-resolution spatiotemporal analysis of civil registration data

SummaryBackgroundHigh-resolution data for how mortality and longevity have changed in England, UK are scarce. We aimed to estimate trends from 2002 to 2019 in life expectancy and probabilities of death at different ages for all 6791 middle-layer super output areas (MSOAs) in England.MethodsWe performed a high-resolution spatiotemporal analysis of civil registration data from the UK Small Area Health Statistics Unit research database using de-identified data for all deaths in England from 2002 to 2019, with information on age, sex, and MSOA of residence, and population counts by age, sex, and MSOA. We used a Bayesian hierarchical model to obtain estimates of age-specific death rates by sharing information across age groups, MSOAs, and years. We used life table methods to calculate life expectancy at birth and probabilities of death in different ages by sex and MSOA.FindingsIn 2002–06 and 2006–10, all but a few (0–1%) MSOAs had a life expectancy increase for female and male sexes. In 2010–14, female life expectancy decreased in 351 (5·2%) of 6791 MSOAs. By 2014–19, the number of MSOAs with declining life expectancy was 1270 (18·7%) for women and 784 (11·5%) for men. The life expectancy increase from 2002 to 2019 was smaller in MSOAs where life expectancy had been lower in 2002 (mostly northern urban MSOAs), and larger in MSOAs where life expectancy had been higher in 2002 (mostly MSOAs in and around London). As a result of these trends, the gap between the first and 99th percentiles of MSOA life expectancy for women increased from 10·7 years (95% credible interval 10·4–10·9) in 2002 to reach 14·2 years (13·9–14·5) in 2019, and for men increased from 11·5 years (11·3–11·7) in 2002 to 13·6 years (13·4–13·9) in 2019.InterpretationIn the decade before the COVID-19 pandemic, life expectancy declined in increasing numbers of communities in England. To ensure that this trend does not continue or worsen, there is a need for pro-equity economic and social policies, and greater investment in public health and health care throughout the entire country.FundingWellcome Trust, Imperial College London, Medical Research Council, Health Data Research UK, and National Institutes of Health Research.

Ensemble machine learning methods for spatio-temporal data analysis of plant and ratoon sugarcane

Recent technological enhancements in the field of information technology and statistical techniques allowed the sophisticated and reliable analysis based on machine learning methods. A number of machine learning data analytical tools may be exploited for the classification and regression problems. These tools and techniques can be effectively used for the highly data-intensive operations such as agricultural and meteorological applications, bioinformatics and stock market analysis based on the daily prices of the market. Machine learning ensemble methods such as Decision Tree (C5.0), Classification and Regression (CART), Gradient Boosting Machine (GBM) and Random Forest (RF) has been investigated in the proposed work. The proposed work demonstrates that temporal variations in the spectral data and computational efficiency of machine learning methods may be effectively used for the discrimination of types of sugarcane. The discrimination has been considered as a binary classification problem to segregate ratoon from plantation sugarcane. Variable importance selection based on Mean Decrease in Accuracy (MDA) and Mean Decrease in Gini (MDG) have been used to create the appropriate dataset for the classification. The performance of the binary classification model based on RF is the best in all the possible combination of input images. Feature selection based on MDA and MDG measures of RF is also important for the dimensionality reduction. It has been observed that RF model performed best with 97% accuracy, whereas the performance of GBM method is the lowest. Binary classification based on the remotely sensed data can be effectively handled using random forest method.

Novel Intelligent Spatiotemporal Grid Earthquake Early-Warning Model

The integration analysis of multi-type geospatial information poses challenges to existing spatiotemporal data organization models and analysis models based on deep learning. For earthquake early warning, this study proposes a novel intelligent spatiotemporal grid model based on GeoSOT (SGMG-EEW) for feature fusion of multi-type geospatial data. This model includes a seismic grid sample model (SGSM) and a spatiotemporal grid model based on a three-dimensional group convolution neural network (3DGCNN-SGM). The SGSM solves the problem concerning that the layers of different data types cannot form an ensemble with a consistent data structure and transforms the grid representation of data into grid samples for deep learning. The 3DGCNN-SGM is the first application of group convolution in the deep learning of multi-source geographic information data. It avoids direct superposition calculation of data between different layers, which may negatively affect the deep learning analysis model results. In this study, taking the atmospheric temperature anomaly and historical earthquake precursory data from Japan as an example, an earthquake early warning verification experiment was conducted based on the proposed SGMG-EEW. Five groups of control experiments were designed, namely with the use of atmospheric temperature anomaly data only, use of historical earthquake data only, a non-group convolution control group, a support vector machine control group, and a seismic statistical analysis control group. The results showed that the proposed SGSM is not only compatible with the expression of a single type of spatiotemporal data but can also support multiple types of spatiotemporal data, forming a deep-learning-oriented data structure. Compared with the traditional deep learning model, the proposed 3DGCNN-SGM is more suitable for the integration analysis of multiple types of spatiotemporal data.

Spatio-temporal analysis of rainfall data in Kuala Krai Kelantan

This paper interpreted spatio-temporally the relationship between event of weather activities and flooding in Kuala Krai Kelantan. During the Kelantan big yellow flood event in December 2014, Kuala Krai was one of the worst affected area with the rarity of the return period approximately 1 in 1000 years. Many say this is due to the unusual occurrence of extreme rainfall. Therefore, this research work on spatio-temporal analysis of the time series rainfall data in Kuala Krai Kelantan, to describe and determine the behaviour and pattern of the data. The data on the monthly amount of rainfall between (2013-2019), were collected from Department Irrigation and Drainage (DID). The main aim of this study is to statistically determine whether it is true the flooding in Kuala Krai Kelantan on 2014 is because of heavy rainfall. The collected rainfall data had been spatially analysed using ArcGIS to compare the distribution of rainfall from year 2013 to 2019. Then, the trend pattern of the data had been determined using Mann Kendall Test and Sen’s slope Test. From those analysis it can be concluded that the huge amount of rainfall intensity is the major factor that contribute the extreme flood event in Kuala Krai Kelantan on December 2014.

Understanding spatial propagation using metric geometry with application to the spread of COVID-19 in the United States

This paper introduces a novel approach to spatio-temporal data analysis using metric geometry to study the propagation of COVID-19 across the United States. Using a geodesic Wasserstein metric, we analyse discrepancies between the density functions of new case counts on any given day, incorporating the geographic spread of cases. First, we apply this to identify the periods during which the changes in the geographic distribution of COVID-19 were most profound. The greatest shift occurred between May and June of 2020, when COVID-19 shifted from mostly dominating the Northeastern states to a wider distribution across the country. We support our findings with a new measure of the extent of geodesic variance of a distribution, demonstrating that the geographic imprint of COVID-19 was most concentrated in May 2020. Next, we investigate whether the epidemic exhibited meaningful patterns of spatial reversion, where similar geographic distributions return later. We identify broad similarity between the spread of COVID-19 across the US between the second and third waves, and to a lesser extent, the reemergence of the first wave's Northeastern dominance closer to the present day. This methodology could provide new insights for analysts to monitor the dynamical spread of epidemics and enable regional policymakers to protect their localities. More broadly, the framework we introduce could be applied to a variety of problems evolving over space and time.

Spatiotemporal representation learning for rescue route selection: An optimized regularization based method

Abstract Emergency medical services (EMS) are emergency services that provide urgent pre-hospital treatment for serious illness and injuries. However, in most countries, EMS is faced with the problem of untimely emergency response. In this paper, we develop an Optimized Regularization based framework (OpRe-RRS) by optimizing the Rescue Route Selection problem to increase the rescue speed. Specifically, through the analysis of spatio-temporal data, we predict the ranking of road priority and select the rescue route for ambulances to lift speed. Along this line, we match the GPS data of ambulances to the correct road section through a map matching algorithm. Then, we extract different features from three perspectives: (i) basic features, (ii) POI features and (iii) traffic features. To effectively exploit the roads similarity, we develop a loss function with regularization to solve this prediction problem. Finally, experiments on real-world data demonstrate that our method can effectively reduce rescue time.

Identifying spatiotemporal transit deserts in Seoul, South Korea

Transit deserts can result from the inequitable distribution of resources and services, and people living in transit deserts have limited access to transportation system. The aim of this study was to perform spatiotemporal data analysis to identify transit desert areas in Seoul in three steps. First, the transit gap between peak and off-peak hours is evaluated and various spatial changes in each temporal transit desert area are identified. Second, a spatial analysis is conducted to identify transit desert and transit oasis areas that emerge during peak hours. Lastly, an independent T-test is conducted to identify how the socio-economic characteristics of transit deserts and transit oases are statistically different. Our analysis show that, transit deserts changed across space and over the time in Seoul. Furthermore, transit deserts in general appear to be associated with socio-economically vulnerable residential areas.

Spatio-temporal analysis of yield and weather data for defining site-specific crop management zones

Spatio-temporal analysis of yield and weather data for defining site-specific crop management zones

MDST-DBSCAN: A Density-Based Clustering Method for Multidimensional Spatiotemporal Data

The increasing use of mobile devices and the growing popularity of location-based ser-vices have generated massive spatiotemporal data over the last several years. While it provides new opportunities to enhance our understanding of various urban dynamics, it poses challenges at the same time due to the complex structure and large-volume characteristic of the spatiotemporal data. To facilitate the process and analysis of such spatiotemporal data, various data mining and clustering methods have been proposed, but there still needs to develop a more flexible and computationally efficient method. The purpose of this paper is to present a clustering method that can work with large-scale, multidimensional spatiotemporal data in a reliable and efficient manner. The proposed method, called MDST-DBSCAN, is applied to idealized patterns and a real data set, and the results from both examples demonstrate that it can identify clusters accurately within a reasonable amount of time. MDST-DBSCAN performs well on both spatial and spatiotemporal data, and it can be particularly useful for exploring massive spatiotemporal data, such as detailed real estate transactions data in Seoul, Korea.

Research on The Effectiveness of Trajectory Similarity Measurement Algorithm

Under the background of big data era, massive trajectory data is constantly generated, which contains great value. The analysis and mining of spatiotemporal trajectory data is a research hotspot of spatial data, including trajectory retrieval, trajectory classification etc. In the process of analysis and mining, the similarity measurement between different trajectories is a key problem. Considering the amount of data, computational complexity, noise and other factors, different metrics need to be selected in different situations. In order to understand the performance of different similarity measurement algorithms, this paper selects the Longest Common Sub-Sequence Algorithm (LCSS), Fréchet Distance Algorithm and One Way Distance Algorithm (OWD) among the three kinds of trajectory similarity measurement algorithms and they were used for comparison. Experimental results show that LCSS algorithm can effectively resist the interference of noise points, Fréchet Distance Algorithm has strong robustness, and OWD Algorithm has low time complexity and short execution time.

Linear-Cost Covariance Functions for Gaussian Random Fields

Gaussian random fields (GRF) are a fundamental stochastic model for spatiotemporal data analysis. An essential ingredient of GRF is the covariance function that characterizes the joint Gaussian distribution of the field. Commonly used covariance functions give rise to fully dense and unstructured covariance matrices, for which required calculations are notoriously expensive to carry out for large data. In this work, we propose a construction of covariance functions that result in matrices with a hierarchical structure. Empowered by matrix algorithms that scale linearly with the matrix dimension, the hierarchical structure is proved to be efficient for a variety of random field computations, including sampling, kriging, and likelihood evaluation. Specifically, with n scattered sites, sampling and likelihood evaluation has an O(n) cost and kriging has an cost after preprocessing, particularly favorable for the kriging of an extremely large number of sites (e.g., predicting on more sites than observed). We demonstrate comprehensive numerical experiments to show the use of the constructed covariance functions and their appealing computation time. Numerical examples on a laptop include simulated data of size up to one million, as well as a climate data product with over two million observations.