Spatio-temporal Datasets Research Articles

Ecosystem Resilience Monitoring and Early Warning Using Earth Observation Data: Challenges and Outlook

AbstractAs the Earth system is exposed to large anthropogenic interferences, it becomes ever more important to assess the resilience of natural systems, i.e., their ability to recover from natural and human-induced perturbations. Several, often related, measures of resilience have been proposed and applied to modeled and observed data, often by different scientific communities. Focusing on terrestrial ecosystems as a key component of the Earth system, we review methods that can detect large perturbations (temporary excursions from a reference state as well as abrupt shifts to a new reference state) in spatio-temporal datasets, estimate the recovery rate after such perturbations, or assess resilience changes indirectly from stationary time series via indicators of critical slowing down. We present here a sequence of ideal methodological steps in the field of resilience science, and argue how to obtain a consistent and multi-faceted view on ecosystem or climate resilience from Earth observation (EO) data. While EO data offers unique potential to study ecosystem resilience globally at high spatial and temporal scale, we emphasize some important limitations, which are associated with the theoretical assumptions behind diagnostic methods and with the measurement process and pre-processing steps of EO data. The latter class of limitations include gaps in time series, the disparity of scales, and issues arising from aggregating time series from multiple sensors. Based on this assessment, we formulate specific recommendations to the EO community in order to improve the observational basis for ecosystem resilience research.

Characterization and low-order representation of the vortex meandering motion in upswept afterbody wakes

Vortex meandering is often characterized by seemingly stochastic motions of the vortex core. An elucidation of the underlying mechanisms of core movement aids not only in characterizing the meandering phenomenon but also forms a starting point to guide flow control techniques. This paper investigates the complex motion of longitudinal vortices behind an abstracted cargo aircraft fuselage. In contrast to wingtip vortices that arise in relative isolation, in this case the large aft region upsweep generates a meandering counter-rotating vortex pair that retains its coherence for long distances downstream. High-resolution spatio-temporal datasets obtained from large-eddy simulation of a cylindrical fuselage with longitudinally aligned axis and a sharp-edged base are used for this purpose. The circulation of each vortex in the pair initially increases immediately after formation and asymptotes to a near constant value downstream. Although the time-mean form of the vortices becomes nearly axisymmetric, the transient disorganized motions include time-local regions of opposite vorticity. The complicated meandering motion is decomposed using proper-orthogonal decomposition (POD) modes as primary building blocks. The first two modes constitute a mutually orthogonal |m|=1 elliptic pair, accounting for about 35% of the total energy; individually these modes account for the displacement of vortex cores along straight lines whose slopes coincide with their respective dipole axes. The wake outside of the immediate vicinity of the base displays low-rank behavior, in that the number of modes required to reproduce the flow to a given degree of accuracy diminishes rapidly. Beyond two fuselage (cylinder) diameters downstream, the two leading POD modes can reconstruct the dominant meandering motion and spatial structure in the LES data with less than 15% error using a suitable loss measure.

A Novel and Efficient Spatio-Temporal Co-location Pattern Mining Algorithm

Colocation pattern mining approaches aim at discovering neighboring relationships of distinct spatial features in geographic and temporal space.With big spatio-temporal dataset, there is large number of patterns often discovered. Then it is of importance to discover meaningful and patterns of interest which come as an aid in applications in use for humans and commercial use. To discover interesting patterns, we present in this article a co-location pattern mining algorithmic framework by considering neighbourhood, clustering, hashing, and mining methods. Neighbourhood relationship describes the closeness between the entities. The results of neighbourhood could be varied by varying the distance threshold. These objects exhibiting neighbouring entities are grouped using clustering technique. Clustering is a classical research approach that produces grouping of the entities. A clustering technique has been presented in the paper for spatio-temporal dimension that offers the advantage of faster grouping based on the neighbourhood relationship. Finally, a hash structure is utilized for faster access and retrieval of patterns. The proposed mining algorithm along with the distance and time threshold efficiently discovers the interesting spatio-temporal patterns and validates the patterns. The experiment conducted shows that the proposed co-location algorithm method yields effective and efficient outcome.

Missing Value Imputation of Wireless Sensor Data for Environmental Monitoring.

Over the past few years, the scale of sensor networks has greatly expanded. This generates extended spatiotemporal datasets, which form a crucial information resource in numerous fields, ranging from sports and healthcare to environmental science and surveillance. Unfortunately, these datasets often contain missing values due to systematic or inadvertent sensor misoperation. This incompleteness hampers the subsequent data analysis, yet addressing these missing observations forms a challenging problem. This is especially the case when both the temporal correlation of timestamps within a single sensor and the spatial correlation between sensors are important. Here, we apply and evaluate 12 imputation methods to complete the missing values in a dataset originating from large-scale environmental monitoring. As part of a large citizen science project, IoT-based microclimate sensors were deployed for six months in 4400 gardens across the region of Flanders, generating 15-min recordings of temperature and soil moisture. Methods based on spatial recovery as well as time-based imputation were evaluated, including Spline Interpolation, MissForest, MICE, MCMC, M-RNN, BRITS, and others. The performance of these imputation methods was evaluated for different proportions of missing data (ranging from 10% to 50%), as well as a realistic missing value scenario. Techniques leveraging the spatial features of the data tend to outperform the time-based methods, with matrix completion techniques providing the best performance. Our results therefore provide a tool to maximize the benefit from costly, large-scale environmental monitoring efforts.

Generative Architecture for Data Imputation in Secure Blockchain-enabled Spatiotemporal Data Management

In the era of big data, one of the most critical challenges is ensuring secure access, retrieval, and sharing of linked spatiotemporal data. To address this challenge, this paper introduces a groundbreaking blockchain-enabled evolutionary indirect feedback graph algorithm for the secure management of interconnected spatiotemporal datasets. The algorithm utilizes a generative neural network model for data imputation, predicting and generating plausible values to improve dataset completeness and integrity. The core architecture utilizes blockchain technology to optimize data retrieval efficiency and uphold robust access control mechanisms. The algorithm incorporates indirect feedback mechanisms, allowing users to provide implicit feedback through their interactions, enhancing the relevance and efficiency of data retrieval. In addition. sophisticated graph-based techniques are used to model intricate relationships between data entities, facilitating seamless data retrieval and sharing in interwoven datasets. The algorithm’s data security approach includes comprehensive access control mechanisms, encryption, and authentication mechanisms, safeguarding data confidentiality and integrity. Extensive evaluations show significant enhancements in retrieval performance and access control precision, making the proposed model a promising solution for the secure management of expansive interconnected spatiotemporal data.

Feature Transportation Improves Graph Neural Networks

Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena that involve feature transportation. In this paper, we propose a novel GNN architecture inspired by Advection-Diffusion-Reaction systems, called ADR-GNN. Advection models feature transportation, while diffusion captures the local smoothing of features, and reaction represents the non-linear transformation between feature channels. We provide an analysis of the qualitative behavior of ADR-GNN, that shows the benefit of combining advection, diffusion, and reaction. To demonstrate its efficacy, we evaluate ADR-GNN on real-world node classification and spatio-temporal datasets, and show that it improves or offers competitive performance compared to state-of-the-art networks.

Mining human periodic behaviors via tensor factorization and entropy.

Understanding human periodic behaviors is crucial in many applications. Existing research has shown the existence of periodicity in human behaviors, but has achieved limited success in leveraging location periodicity and obtaining satisfactory accuracy for oscillations in human periodic behaviors. In this article, we propose the Mobility Intention and Relative Entropy (MIRE) model to address these challenges. We employ tensor decomposition to extract mobility intentions from spatiotemporal datasets, thereby revealing hidden structures in users' historical records. Subsequently, we utilize subsequences associated with the same mobility intention to mine human periodic behaviors. Furthermore, we introduce a novel periodicity detection algorithm based on relative entropy. Our experimental results, conducted on real-world datasets, demonstrate the effectiveness of the MIRE model in accurately uncovering human periodic behaviors. Comparative analysis further reveals that the MIRE model significantly outperforms baseline periodicity detection algorithms.

Forecasting solar irradiation using convolutional long short-term memory and feature selection of data from neighboring locations

The capacity of renewable energy systems, such as photovoltaic farms, has been steadily increasing owing to the continuous depletion of fossil-based energy sources. Information that can be used to optimize the use of renewable energy is required. This work proposes a novel method that uses data from neighboring locations to perform 24 h-ahead solar GHI forecasting. The approach is helpful in supporting the operation of photovoltaic farms, minimizing the need to collect new data on the target location. This work proposes the Convolutional Long Short-term Memory (ConvLSTM) model to maximize the performance using a feature-rich spatiotemporal dataset. The ConvLSTM model uses Hadamard convolutions in its input-to-state transition and state-to-state transition, allowing it to retain better information. The feature selection methods are used to ensure that only the critical subsets of the dataset are used to develop the model. The subsets identified by the feature selection methods are used on Vector Autoregressive, Support Vector Regression, Multilayer Perceptron, Convolutional Neural Network (CNN), CNN-LSTM and ConvLSTM networks. The winning method is compared to related studies using Stacked-LSTM with transfer-learning, attention-based LSTM and Krill-Herd Algorithm – Support vector Regression (KHA-SVR). The resulting coefficients of determination and root-mean-squared errors were statistically evaluated and compared. Ultimately, the proposed ConvLSTM model performed consistently better across all the seasons and feature subsets.

Retrieval of Desert Microwave Land Surface Emissivity Based on Machine Learning Algorithms

Based on the community radiative transfer model, ensemble tree-based random forest algorithm, and extreme gradient boosting tree algorithm, this study established a random forest retrieval model (RF) and an extreme gradient boosting tree retrieval model (XGBoost) for the microwave land surface emissivity by using ERA5 reanalysis data and the observed brightness temperature of 10.65 GHz vertical polarization from FY3C Microwave Radiation Imager-I. In addition, an optimized Bayesian regularized neural network retrieval model (M2_30NN) has also been established on the basis of the original neural network land surface emissivity retrieval model (M1_20NN). The results show that compared with the simulated brightness temperature of the original land surface emissivity, the simulated brightness temperature of the land surface emissivity from each retrieval model is not only significantly improved in the correlation coefficient with the observed brightness temperature (5.92% (M1_20NN), 4.23% (M2_30NN), 14.21% (RF), 13.07% (XGBoost)), but also in the evaluation indexes of root mean square error, mean absolute error and explained variance regression score in the training datasets. Furthermore, in terms of testing datasets and spatiotemporal independence test datasets, the retrieval results of RF and XGBoost models can capture the spatial distribution patterns that are consistent with observations well, and also show great numerical improvement compared with the original model. In general, the XGBoost retrieval model is the best, followed by the RF retrieval model.

Decoding China's anthropogenic typical pollutant discharge patterns: Long-term dynamics and hotspot transitions driven by population, diet, and sanitation

Human activities have led to an alarming increase in pollution, resulting in widespread water contamination. A comprehensive understanding of the quantitative relationship between anthropogenic pollutant discharges and the escalating anthropogenic disturbances and environmental efforts is crucial for effective water quality management. Here we establish a Model for Estimating Anthropogenic pollutaNts diScharges (MEANS) and simulate the long-term dynamics of various types of anthropogenic discharges in China based on an unprecedented spatio-temporal dynamic parameter dataset. Our findings reveal that from 1980 to 2020, anthropogenic discharges exhibited an overall trend of initially increasing and subsequently decreasing, with the peak occurring around 2005. During this period, the dominant pollution sources in China shifted from urban to rural areas, thereby driving the transition of hotspot pollutants from nitrogen to phosphorus in the eastern regions. The most significant drivers of anthropogenic pollutant discharges gradually shifted from population size and dietary structure to wastewater treatment and agricultural factors. Furthermore, we observed that a significant portion of China's regions still exceed the safety thresholds for pollutant discharges, with excessive levels of total phosphorus (TP) being particularly severe. These findings highlight the need for flexible management strategies in the future to address specific pollution levels and hotspots in different regions. Our study underscores the importance of considering the complex interplay between anthropogenic disturbances, environmental efforts, and long-term anthropogenic pollutant discharges for effective water pollution control.

Modified Deep Pattern Classifier on Indonesian Traditional Dance Spatio-Temporal Data

Traditional dances, like those of Indonesia, have complex and unique patterns requiring accurate cultural preservation and documentation classification. However, traditional dance classification methods often rely on manual analysis and subjective judgment, which leads to inconsistencies and limitations. This research explores a modified deep pattern classifier of traditional dance movements in videos, including Gambyong, Remo, and Topeng, using a Convolutional Neural Network (CNN). Evaluation model's performance using a testing spatio-temporal dataset in Indonesian traditional dance videos is performed. The videos are processed through frame-level segmentation, enabling the CNN to capture nuances in posture, footwork, and facial expressions exhibited by dancers. Then, the obtained confusion matrix enables the calculation of performance metrics such as accuracy, precision, sensitivity, and F1-score. The results showcase a high accuracy of 97.5%, indicating the reliable classification of the dataset. Furthermore, future research directions are suggested, including investigating advanced CNN architectures, incorporating temporal information through recurrent neural networks, exploring transfer learning techniques, and integrating user feedback for iterative refinement of the model. The proposed method has the potential to advance dance analysis and find applications in dance education, choreography, and cultural preservation.

ENABLING INTEROPERABILITY OF URBAN BUILDING ENERGY DATA BASED ON OGC API STANDARDS AND CITYGML 3D CITY MODELS

Abstract. This paper presents an investigation into the interoperability of 3D building energy data management, delivery, processing, and visualization via web clients using Open Geospatial Consortium – Application Programming Interface (OGC API) standard-based data models and web interfaces. Specifically, the OGC API – 3D GeoVolumes enable access to 3D city model geometries and semantics on the web, the OGC API – Features support the 2D version of the same geospatial data, the OGC API – Processes are used for CityGML analytics and building energy computation with the SimStadt urban simulation software and the OGC SensorThings API is utilized to manage related spatiotemporal or time-series datasets. The efficacy of this approach has been demonstrated in the OGC Testbed 18 Innovation Program, which highlighted the capacity of OGC API web services to synchronize building energy data and computation results between client and server for the case study of Helsinki, Finland, and Montreal, Canada. The advantages of using OGC API services for 3D building energy data interoperability are discussed, and it is suggested that the use of OGC API be promoted to the general public as well as extended to other domains and on a larger scale in future research.

A lightweight spatiotemporal graph dilated convolutional network for urban sensor state prediction

Spatiotemporal prediction is one attractive research topic in urban computing, which is of great significance to urban planning and management. At present, there are many attempts to predict the spatiotemporal state of systems using various deep learning models. However, most existing models tend to improve prediction accuracy with larger parameter scale and time consumption, but ignoring ease of use in practice. To overcome this question, we propose a lightweight spatiotemporal graph dilated convolutional network called STGDN with satisfactory prediction accuracy and lower model complexity. More specifically, we propose a novel dilated convolution operator and integrate it into traditional causal convolutional networks and graph convolutional networks to greatly improve the efficiency of prediction. The proposed dilated convolution operator can significantly reduce the depth of the model, thereby reducing the parameter scale and improving the computational efficiency of the model. We conducted on multi experiments on three real-world spatiotemporal datasets (traffic dataset, PM2.5 dataset, and temperature dataset) to prove the effectiveness and advantage of our proposed STGDN. The experimental results show that the proposed STGDN model outperforms or achieves comparable prediction accuracy of the existing nine baselines with higher operational efficiency and fewer model parameters. Codes are available at anonymous private link on https://doi.org/10.6084/m9.figshare.23935683.

A real-time wave prediction in directional wave fields: Strategies for accurate continuous prediction in time

Previous research on real-time deterministic sea wave prediction has generally focused on evaluating the accuracy and efficiency of short-term wave fields within a specific prediction zone. However, for a real-time wave prediction system, it is necessary to provide a continuous description of the ocean wave surface based on short-term prediction segments. In this regard, we have developed algorithms for continuous wave prediction in directional wave fields based on the “practical” prediction zone. The practical prediction zone refers to the time interval available for generating a continuous wave forecast by excluding the reconstructed waves from the prediction zone proposed by Kim et al. (2023). We also introduce and discuss several important time factors, such as the update interval of the spatio-temporal wave dataset, the total computation time, and the length of the practical prediction zone. By gaining a deeper understanding of numerical modeling setups, we have established strategies to reduce computational costs, which are directly related to the accuracy of continuous wave prediction. In particular, the development of these strategies suggests guidance in specifying direction and frequency bandwidths for continuous wave prediction.

The potential for spatiotemporal population data sets for aviation noise studies

Aviation noise analysis has traditionally focused on modeling the noise from an average day of operations. We investigate the potential of moving from this static approach to a dynamic method of assessing aircraft noise experienced by people where they are as they move about the day and night. In this research conducted on behalf of the National Academy of Sciences Airport Cooperative Research Program, we evaluated population data sets that account for the movement of people between their daytime versus nighttime location and assessed their applicability for aviation noise studies. We provided guidance on using these spatiotemporal data sets for aviation noise studies using the Aviation Environmental Design Tool, including sample maps and analyses. We also discussed the limitations of spatiotemporal population data, namely they only account for a person's location by time of day and not whether they are engaged in noise-sensitive activities. A fuller picture of noise impact by location and time of day may be achieved by developing an activity-based model, which combines data on location and level of noise sensitivity. We outline the basic elements of such a model.

Forecasting global climate drivers using Gaussian processes and convolutional autoencoders

Machine learning (ML) methods have become an important tool for modelling and forecasting complex high-dimensional spatiotemporal datasets such as those found in environmental and climate modelling applications. ML approaches can offer a fast, low-cost alternative to short-term forecasting than expensive numerical simulation while addressing a significant outstanding limitation of numerical modelling by being able to robustly and dynamically quantify predictive uncertainty. Low-cost and near-instantaneous forecasting of high-level climate variables has clear applications in early warning systems, nowcasting, and parameterising small-scale locally relevant simulations. This paper presents a novel approach for multi-task spatiotemporal regression by combining data-driven autoencoders with Gaussian Processes (GP) to produce a probabilistic tensor-based regression model. The proposed method is demonstrated for forecasting one-step-ahead temperature and pressure on a global scale simultaneously. By conducting probabilistic regression in the learned latent space, samples can be propagated back to the original feature space to produce uncertainty estimates at a vastly reduced computational cost. The composite GP-autoencoder model was able to simultaneously forecast global temperature and pressure values with average errors of 3.82 °C and 638 hPa, respectively. Further, on average the true values were within the proposed posterior distribution 95.6% of the time illustrating that the model produces a well-calibrated predictive posterior distribution.

How to manage massive spatiotemporal dataset from stationary and non-stationary sensors in commercial DBMS?

AbstractThe growing diffusion of the latest information and communication technologies in different contexts allowed the constitution of enormous sensing networks that form the underlying texture of smart environments. The amount and the speed at which these environments produce and consume data are starting to challenge current spatial data management technologies. In this work, we report on our experience handling real-world spatiotemporal datasets: a stationary dataset referring to the parking monitoring system and a non-stationary dataset referring to a train-mounted railway monitoring system. In particular, we present the results of an empirical comparison of the retrieval performances achieved by three different off-the-shelf settings to manage spatiotemporal data, namely the well-established combination of PostgreSQL + PostGIS with standard indexing, a clustered version of the same setup, and then a combination of the basic setup with Timescale, a storage extension specialized in handling temporal data. Since the non-stationary dataset has put much pressure on the configurations above, we furtherly investigated the advantages achievable by combining the TSMS setup with state-of-the-art indexing techniques. Results showed that the standard indexing is by far outperformed by the other solutions, which have different trade-offs. This experience may help researchers and practitioners facing similar problems managing these types of data.

Cellular and molecular mechanisms of fibrosis and resolution in bleomycin-induced pulmonary fibrosis mouse model revealed by spatial transcriptome analysis

The bleomycin-induced pulmonary fibrosis mouse model is commonly used in idiopathic pulmonary fibrosis research, but its cellular and molecular changes and efficiency as a model at the molecular level are not fully understood. In this study, we used spatial transcriptome technology to investigate the cellular and molecular changes in the lungs of bleomycin-induced pulmonary fibrosis mouse models. Our analyses revealed cell dynamics during fibrosis in epithelial cells, mesenchymal cells, immunocytes, and erythrocytes with their spatial distribution available. We confirmed the differentiation of the alveolar type II (AT2) cell type expressing Krt8, and we inferred their trajectories from both the AT2 cells and club cells. In addition to the fibrosis process, we also noticed evidence of self-resolving, especially to identify possible self-resolving related genes, including Prkca. Our findings provide insights into the cellular and molecular mechanisms underlying fibrosis resolution and represent the first spatiotemporal transcriptome dataset of the bleomycin-induced fibrosis mouse model.

A Novel and Efficient Spatio-Temporal Clustering Algorithm to Discover Patterns in Indian Earthquake Data

The seismic activity in India, including the Himalayas, the North-East region, and the Andaman-Nicobar Islands, is prominently displayed on the seismic map. It is important to analyze the specific characteristics of seismic events on the Indian sub-continent. This research paper introduces a new algorithm for data analysis using a partitioning technique that mines clustering patterns. The algorithm generates clusters of spatial and spatio-temporal data by distributing the data into spatial bins or buckets, identifying neighboring bins, and minimizing distance calculations. Furthermore, the selection of centroids is based on the density of data in the spatial region, utilizing a random selection method. It requires minimal parameter settings, enhancing its efficiency and practicality for analyzing large-scale spatio-temporal datasets. We validate the algorithm's efficacy through experiments conducted on the Indian earthquake spatio-temporal dataset, demonstrating its ability to detect spatio-temporal patterns and identify earthquake-prone regions.The conducted experiments reveal a correlation between the frequency of earthquake events and the number of clusters formed, indicating that regions with a higher occurrence of earthquakes exhibit a greater clustering tendency, signifying their susceptibility to seismic activity. The results imply promising clustering quality, with Silhouette index in the range of 0.88 to 0.93.

Adding attention to the neural ordinary differential equation for spatio-temporal prediction

Explainable spatio-temporal prediction gains attraction in the development of geospatial artificial intelligence. The neural ordinal differential equation (NODE) emerges as a new solution for explainable spatio-temporal prediction. However, challenges still need to be solved in most existing NODE-based prediction models, such as difficulty modeling spatial data and mining long-term temporal dependencies in data. In this study, we propose a spatio-temporal attentional NODE (STA-ODE) to address the two challenges above. First, we define a spatio-temporal ordinary differential equation to predict a value at each time iteratively by a novel spatio-temporal derivative network. Second, we develop an attention mechanism to fuse multiple prediction values for capturing long-term temporal dependencies in data. To train the STA-ODE model, we design a loss function that aligns the prediction results in spatial dimension with prediction results in temporal dimension to calibrate the parameters of the model. The proposed model was validated with three real-world spatio-temporal datasets (traffic flow dataset, PM2.5 monitoring dataset, and temperature monitoring dataset). Experimental results showed that STA-ODE outperformed seven existing baselines regarding prediction accuracy. In addition, we used visualization to demonstrate the sound interpretability and prediction accuracy of the STA-ODE model.