Spatial Data Analytics Research Articles

WEST is an ensemble method for spatial transcriptomics analysis.

Spatial transcriptomics is a groundbreaking technology, enabling simultaneous profiling of gene expression and spatial orientation within biological tissues. Yet when analyzing spatial transcriptomics data, effective integration of expression and spatial information poses considerable analytical challenges. Although many methods have been developed to address this issue, many are platform specific and lack the general applicability to analyze diverse datasets. In this article, we propose a method called the weighted ensemble method for spatial transcriptomics (WEST) that utilizes ensemble techniques to improve the performance and robustness of spatial transcriptomics data analytics. Wecompare the performance of WEST with six methods on both synthetic and real-world datasets. WEST represents a significant advance in detecting spatial domains, offering improved accuracy andflexibility compared to existing methods, making it a valuable tool for spatial transcriptomics data analytics.

Supporting Fire Response: Advanced Spatial Data Analytics for Hydrant Access Assessment

ABSTRACTCalifornia faces increasing wildfire frequency and severity, necessitating effective firefighting strategies along with well‐located infrastructure. Hydrants are vital for urban safety and must comply with established standards to adequately protect people and property. One such standard involves hydrant spacing, critical for ensuring effective emergency response in the event of a fire. Traditional geographic information systems techniques are not well suited to fully assess hydrant networks, especially in the context of spacing given complex road network geographies. This paper introduces an innovative approach to assess hydrant spacing. The developed technique is applied in the evaluation of infrastructure in Santa Barbara, California. The results reveal significant code violations along streets throughout the region, suggesting clustered pockets of vulnerability and risk. Potential strategies emerge from this analysis to enhance firefighting preparedness, offering guidance to local agencies regarding hydrant system limitations across this fire‐prone region.

High-Performance Spatial Data Analytics: Systematic R&D for Scale-Out and Scale-Up Solutions from the Past to Now

We released open-source software Hadoop-GIS in 2011, and presented and published the work in VLDB 2013. This work initiated the development of a new spatial data analytical ecosystem characterized by its large-scale capacity in both computing and data storage, high scalability, compatibility with low-cost commodity processors in clusters and open-source software. After more than a decade of research and development, this ecosystem has matured and is now serving many applications across various fields. In this paper, we provide the background on why we started this project and give an overview of the original Hadoop-GIS software architecture, along with its unique technical contributions and legacy. We present the evolution of the ecosystem and its current state-of-the-art, which has been influenced by the Hadoop-GIS project. We also describe the ongoing efforts to further enhance this ecosystem with hardware accelerations to meet the increasing demands for low latency and high throughput in various spatial data analysis tasks. Finally, we will summarize the insights gained and lessons learned over more than a decade in pursuing high-performance spatial data analytics.

The Geospatial Crowd: Emerging Trends and Challenges in Crowdsourced Spatial Analytics

Crowdsourced spatial analytics is a rapidly developing field that involves collecting and analyzing geographical data, utilizing the collective power of human observation. This paper explores the field of spatial data analytics and crowdsourcing and how recently developed tools, cloud-based GIS, and artificial intelligence (AI) are being applied in this domain. This paper examines and discusses cutting-edge technologies and case studies in different fields of spatial data analytics and crowdsourcing used in a wide range of industries and government departments such as urban planning, health, transportation, and environmental sustainability. Furthermore, by understanding the concerns associated with data quality and data privacy, this paper explores the potential of crowdsourced data while also examining the related problems. This study analyzes the obstacles and challenges related to “geospatial crowdsourcing”, identifying significant limitations and predicting future trends intended to overcome the related challenges.

Demographic Well-Being of the Ethnonational Regions of the Russian Federation

The article explores the concept of demographic well-being in the context of the study of 27 ethnonational regions of the Russian Federation in the period from 2018 to 2022. The paper proposes a methodology developed by the authors that combines the analysis of qualitative and quantitative indicators with cartographic visualization of intermediate and final results. This approach allows for a comprehensive analysis of demographic processes over a five-year period together with spatial data analytics. As a result, a summary indicator of demographic well-being is presented, which allows us to distinguish demographically prosperous, demographically disadvantaged and demographically intermediate regions. The key trends and features of demographic development in ethnonational regions at the present stage are considered. More than 55 cartographic works have been developed– series of maps for the period under review for 11 demographic indicators. The final typology is visualized on the map of the Russian Federation.

STAR: A Cache-based Stream Warehouse System for Spatial Data

The proliferation of mobile phones and location-based services has given rise to an explosive growth in spatial data. To enable spatial data analytics, spatial data needs to be streamed into a data stream warehouse system that can provide real-time analytical results over the most recent and historical spatial data in the warehouse. Existing data stream warehouse systems are not tailored for spatial data. In this article, we introduce the STAR system. STAR is a distributed in-memory data stream warehouse system that provides low-latency and up-to-date analytical results over a fast-arriving spatial data stream. STAR supports both snapshot and continuous queries that are composed of aggregate functions and ad hoc query constraints over spatial, textual, and temporal data attributes. STAR implements a cache-based mechanism to facilitate the processing of snapshot queries that collectively utilizes the techniques of query-based caching (i.e., view materialization) and object-based caching. Moreover, to speed up processing continuous queries, STAR proposes a novel index structure that achieves high efficiency in both object checking and result updating. Extensive experiments over real datasets demonstrate the superior performance of STAR over existing systems.

Analytical assessment of street-level tree canopy in Austrian cities: Identification of re-naturalisation potentials of the urban fabric

Climate change-related impacts such as heat stress, extreme weather events, and their consequences are particularly felt within densely built-up urban areas. Urban re-naturalisation is recognised as a promising cost-effective strategy for improving urban resilience to these environmental and societal issues. In this respect, the present contribution focuses on a comprehensive city-wide assessment of street-level urban tree canopy to detect the existing vegetation gaps and identify re-naturalisation potentials within the urban fabric for the three largest cities in Austria (Vienna, Graz, and Linz). The study relies on QGIS and R software environments to carry out spatial data analytics on georeferenced tree cadastre data and the global map of Local Climate Zones (LCZ) to compute spatial density maps and urban structure parameters. The results suggest a rather random distribution of tree clusters and highly fragmented instances within the city. This fragmentation is predominantly observed within central densely built urban fabric for all three cities, with the absence of street trees in peripheral urbanised areas being more prominent in Graz and Linz. The computed percentage of potentially disconnected areas in terms of the tree canopy for Vienna, Graz, and Linz amounts to 45%, 54%, and 37%, respectively. The analysis of urban structure revealed a homogeneous densely built-up character over central districts and a dominantly heterogeneous character across non-central and peripheral districts with a more openly built fabric (this heterogeneity is, generally more prominent in the case of Graz and Linz). In general, there are numerous opportunities for urban re-naturalisation, focusing on urban trees within such openly arranged buildings. Due to the evident physical constraints of the urban space within central districts, the consideration of building-level greening (e.g. green roofs, green facades) may be a better approach to urban re-naturalisation in these cases. Given the further constraints imposed by the abundance of historic buildings, such measures may not be feasible in every event. Hence, this calls for consideration of novel, innovative and emerging greening systems with the proposition of movable vertical green screens and vertical gardens.

The geography of social media platform attention for tourist attractions - spatial digital data analytics of scenic hot spots in China

The geography of social media platform attention for tourist attractions - spatial digital data analytics of scenic hot spots in China

Intelligent Pandemic Surveillance via Privacy-Preserving Crowdsensing.

Intelligently responding to a pandemic like Covid-19 requires sophisticated models over accurate real-time data, which is typically lacking at the start, e.g., due to deficient population testing. In such times, crowdsensing of spatially tagged disease-related symptoms provides an alternative way of acquiring real-time insights about the pandemic. Existing crowdsensing systems aggregate and release data for pre-fixed regions, e.g., counties. However, the insights obtained from such aggregates do not provide useful information about smaller regions - e.g., neighborhoods where outbreaks typically occur - and the aggregate-and-release method is vulnerable to privacy attacks. Therefore, we propose a novel differentially private method to obtain accurate insights from crowdsensed data for any number of regions specified by the users (e.g., researchers and a policy makers) without compromising privacy of the data contributors. Our approach, which has been implemented and deployed, informs the development of the future privacy-preserving intelligent systems for longitudinal and spatial data analytics.

Abstract 456: Jointly leveraging spatial transcriptomics and deep learning models for image annotation achieves better-than-pathologist performance in cell type identification in tumors

Abstract For over 100 years, the traditional tools of pathology, such as tissue-marking dyes (e.g. the H&E stain) have been used to study the disorganization and dysfunction of cells within tissues. This has represented a principal diagnostic and prognostic tool in cancer. However, in the last 5 years, new technologies have promised to revolutionize histopathology, with Spatial Transcriptomics technologies allowing us to measure gene expression directly in pathology-stained tissue sections. In parallel with these developments, Artificial Intelligence (AI) applied to histopathology tissue images now approaches pathologist level performance in cell type identification. However, these new technologies still have severe limitations, with Spatial Transcriptomics suffering difficulties distinguishing transcriptionally similar cell types, and AI-based pathology tools often performing poorly on real world out-of-batch test datasets. Thus, century-old techniques still represent standard-of-care in most areas of clinical cancer diagnostics and prognostics. Here, we present a new frontier in digital pathology: describing a conceptually novel computational methodology, based on Bayesian probabilistic modelling, that allows Spatial Transcriptomics data to be leveraged together with the output of deep learning-based AI used to computationally annotate H&E-stained sections of the same tumor. By leveraging cell-type annotations from multiple independent pathologists, we show that this integrated methodology achieves better performance than any given pathologist’s manual tissue annotation in the task of identifying regions of immune cell infiltration in breast cancer, and easily outperforms either technology alone. We also show that on a subset of histopathology slides examined, the methodology can identify regions of clinically relevant immune cell infiltration that were missed entirely by an initial pathologist’s manual annotation. While this use case has clear diagnostic and prognostic value in cancer (e.g. predicting response to immunotherapy), our methodology is generalizable to any type of pathology images and also has broad applications in spatial transcriptomics data analytics, where most applications (such as identifying cell-cell interactions) rely on correct cell type annotations having been established a priori. We anticipate that this work will spur many follow-up studies, including new computational innovations building on the approach. The work sets the stage for better-than-pathologist performance in other cell-type annotation tasks, with relevant applications in diagnostics and prognostics across almost all cancers. Citation Format: Asif Zubair, Rich Chapple, Sivaraman Natarajan, William C. Wright, Min Pan, Hyeong-Min Lee, Heather Tillman, John Easton, Paul Geeleher. Jointly leveraging spatial transcriptomics and deep learning models for image annotation achieves better-than-pathologist performance in cell type identification in tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 456.

Investigating Health Context Using a Spatial Data Analytical Tool: Development of a Geospatial Big Data Ecosystem

BackgroundEnabling the use of spatial context is vital to understanding today’s digital health problems. Any given location is associated with many different contexts. The strategic transformation of population health, epidemiology, and eHealth studies requires vast amounts of integrated digital data. Needed is a novel analytical framework designed to leverage location to create new contextual knowledge. The Geospatial Analytical Research Knowledgebase (GeoARK), a web-based research resource has robust, locationally integrated, social, environmental, and infrastructural information to address today’s complex questions, investigate context, and spatially enable health investigations. GeoARK is different from other Geographic Information System (GIS) resources in that it has taken the layered world of the GIS and flattened it into a big data table that ties all the data and information together using location and developing its context.ObjectiveIt is paramount to build a robust spatial data analytics framework that integrates social, environmental, and infrastructural knowledge to empower health researchers’ use of geospatial context to timely answer population health issues. The goal is twofold in that it embodies an innovative technological approach and serves to ease the educational burden for health researchers to think spatially about their problems.MethodsA unique analytical tool using location as the key was developed. It allows integration across source, geography, and time to create a geospatial big table with over 162 million individual locations (X-Y points that serve as rows) and 5549 attributes (represented as columns). The concept of context (adjacency, proximity, distance, etc) is quantified through geoanalytics and captured as new distance, density, or neighbor attributes within the system. Development of geospatial analytics permits contextual extraction and investigator-initiated eHealth and mobile health (mHealth) analysis across multiple attributes.ResultsWe built a unique geospatial big data ecosystem called GeoARK. Analytics on this big table occur across resolution groups, sources, and geographies for extraction and analysis of information to gain new insights. Case studies, including telehealth assessment in North Carolina, national income inequality and health outcome disparity, and a Missouri COVID-19 risk assessment, demonstrate the capability to support robust and efficient geospatial understanding of a wide spectrum of population health questions.ConclusionsThis research identified, compiled, transformed, standardized, and integrated multifaceted data required to better understand the context of health events within a large location-enabled database. The GeoARK system empowers health professionals to engage more complex research where the synergisms of health and geospatial information will be robustly studied beyond what could be accomplished today. No longer is the need to know how to perform geospatial processing an impediment to the health researcher, but rather the development of how to think spatially becomes the greater challenge.

Variational model with nonstandard growth conditions for restoration of satellite optical images using synthetic aperture radar

In this paper, the problem of restoration of cloud contaminated optical images is studied in the case when we have no information about brightness of such images in the damage region. We propose a new variational approach for exact restoration of optical multi-band images utilising Synthetic Aperture Radar (EOS – Spatial Data Analytics, GIS Software, Satellite Imagery – is a cloud-based platform to derive remote sensing data and analyse satellite imagery for business and science purposes) images of the same regions. We prove existence of solutions, propose an alternating minimisation method for computing them, prove convergence of this method to weak solutions of the original problem and derive optimality conditions.

A Survey on Spatio-temporal Data Analytics Systems

Due to the surge of spatio-temporal data volume, the popularity of location-based services and applications, and the importance of extracted knowledge from spatio-temporal data to solve a wide range of real-world problems, a plethora of research and development work has been done in the area of spatial and spatio-temporal data analytics in the past decade. The main goal of existing works was to develop algorithms and technologies to capture, store, manage, analyze, and visualize spatial or spatio-temporal data. The researchers have contributed either by adding spatio-temporal support with existing systems, by developing a new system from scratch, or by implementing algorithms for processing spatio-temporal data. The existing ecosystem of spatial and spatio-temporal data analytics systems can be categorized into three groups, (1) spatial databases (SQL and NoSQL), (2) big spatial data processing infrastructures, and (3) programming languages and GIS software. Since existing surveys mostly investigated infrastructures for processing big spatial data, this survey has explored the whole ecosystem of spatial and spatio-temporal analytics. This survey also portrays the importance and future of spatial and spatio-temporal data analytics.

Multiscale spatial analysis of fracture arrangement and pattern reconstruction using Ripley's K-function

This work presents novel multiscale spatial data analytics using Ripley's K-function, as a measure of spatial interaction, to study one-dimensional arrangement of fractures. Fracture spatial arrangements are classified into clustered, anticlustered, or indistinguishable from random by testing statistical significance of the calculated Ripley's K-function. Characterizations of fracture arrangements are performed as a function of length scale and position. Analysis of the K-function along the study interval identifies where fracture clustering and anticlustering occur. A simulation technique is also introduced here to statistically reconstruct spatial arrangements and to generate fracture realizations that are spatially similar to the fractures observed in the field. With this simulation technique, one can also fill spatial gaps in fracture measurements where data are absent, unreliable, or unused. Synthetic as well as field-measured 1D fracture datasets are used for testing and demonstration. Methods introduced in this work can be readily applied to fracture datasets observed in outcrops, borehole image logs, and cores.

Evaluation of Land Use/Land Cover Classification based on Different Bands of Sentinel-2 Satellite Imagery using Neural Networks

Spatial data analytics is an emerging technology. Artificial neural network techniques play a major role in analysing any critical dataset. Integrating remote sensing data with deep neural networks has led a way to several research problems. This paper aims at producing land use land cover map of Bangalore region, Karnataka, India with various band combinations of sentinel satellite imagery obtained from google earth engine. LULC map classes include water, urban, forest, vegetation and openland. Band combinations of satellite images represent different characteristics of spatial data. Hence, several band combinations are used to build LULC maps. Also, classified maps are generated using different neural networks with pixel-based classification approach. Appropriate performance metrics were identified to evaluate the classification results such as Accuracy, Precision, Recall, F1-score and Confusion Matrix. Among neural networks, Convolutional Neural Network technique outperformed with 98.1 % of accuracy and less error rates in confusion matrix considering RGBNIR (4328) band combination of satellite imagery.

UAVs for Vegetation Monitoring: Overview and Recent Scientific Contributions

This paper reviewed a set of twenty-one original and innovative papers included in a special issue on UAVs for vegetation monitoring, which proposed new methods and techniques applied to diverse agricultural and forestry scenarios. Three general categories were considered: (1) sensors and vegetation indices used, (2) technological goals pursued, and (3) agroforestry applications. Some investigations focused on issues related to UAV flight operations, spatial resolution requirements, and computation and data analytics, while others studied the ability of UAVs for characterizing relevant vegetation features (mainly canopy cover and crop height) or for detecting different plant/crop stressors, such as nutrient content/deficiencies, water needs, weeds, and diseases. The general goal was proposing UAV-based technological solutions for a better use of agricultural and forestry resources and more efficient production with relevant economic and environmental benefits.

Progress in Remote Sensing of Grass Senescence: A Review on the Challenges and Opportunities

Grass senescence estimation in rangeland is particularly important for monitoring the conditions of forage quality and quantity. During senescence, grasses lose their nutrients from the leaves to the root and thereby affecting forage productivity. Studies on the remote sensing of grasslands have been conducted during the senescent phenological stage. However, despite the efforts made in previous remote sensing studies on grass senescence, its role in estimating grass senescence is rudimentary. More so, the strengths and limitations presented by the newly developed remote sensing instruments in grass senescence estimation are not well documented. This work, therefore, provides a detailed overview on the progress of remote sensing applications in characterizing grass senescence. The review further highlights the challenges and opportunities presented by these techniques. Overall, the review indicates that studies on remotely sensed grass senescence are focused on understanding biophysical and biochemical properties, and these studies identify the leaf area index, biomass, and chlorophyll content, among others, as the key indicators of grass senescence. Nonetheless, recent scientific research highlights a mismatch between studies on the grass senescence and the development in remote sensing technologies. The use of sophisticated and robust time-series analysis techniques together with improved sensing characteristics from the new generation sensors seem to present new opportunities for the optimal quantification of grass senescence at resolutions complementary to the spatial extents of the rangelands. We, therefore, recommend further research in this field through the adoption of new satellite technologies and advanced spatial data analytics to enhance the monitoring of rangeland resources.

Big issues for big data: challenges for critical spatial data analytics

In this paper we consider some of the issues of working with big data and big spatial data and highlight the need for an open and critical framework. We focus on a set of challenges underlying the collection and analysis of big data. In particular, we consider 1) inference when working with usually biased big data, challenging the assumed inferential superiority of data with observations, n, approaching N, the population n -> N. We also emphasise 2) the need for analyses that answer questions of practical significance or with greater emphasis on the size of the effect, rather than the truth or falsehood of a statistical statement; 3) the need to accept messiness in your data and to document all operations undertaken on the data because of this, in support of openness and reproducibility paradigms; and 4) the need to explicitly seek to understand the causes of bias, messiness etc in the data and the inferential consequences of using such data in analyses, by adopting critical approaches to spatial data science. In particular we consider the need to place individual data science studies in a wider social and economic contexts, along with the role of inferential theory in the presence of big data, and issues relating to messiness and complexity in big data.

A Spatial Correlation-Based Anomaly Detection Method for Subsurface Modeling

Spatial data analytics provides new opportunities for automated detection of anomalous data for data quality control and subsurface segmentation to reduce uncertainty in spatial models. Solely data-driven anomaly detection methods do not fully integrate spatial concepts such as spatial continuity and data sparsity. Also, data-driven anomaly detection methods are challenged in integrating critical geoscience and engineering expertise knowledge. The proposed spatial anomaly detection method is based on the semivariogram spatial continuity model derived from sparsely sampled well data and geological interpretations. The method calculates the lag joint cumulative probability for each matched pair of spatial data, given their lag vector and the semivariogram under the assumption of bivariate Gaussian distribution. For each combination of paired spatial data, the associated head and tail Gaussian standardized values of a pair of spatial data are mapped to the joint probability density function informed from the lag vector and semivariogram. The paired data are classified as anomalous if the associated head and tail Gaussian standardized values fall within a low probability zone. The anomaly decision threshold can be decided based on a loss function quantifying the cost of overestimation or underestimation. The proposed spatial correlation anomaly detection method is able to integrate domain expertise knowledge through trend and correlogram models with sparse spatial data to identify anomalous samples, region, segmentation boundaries, or facies transition zones. This is a useful automation tool for identifying samples in big spatial data on which to focus professional attention.

Inference of Distribution Grids Based on Crowdsourced Grid Data and Drone Imagery

Distribution System Operators (DSOs) face several challenges in managing comprehensive and up-to-date models of distribution grids. To address these problems, we propose a crowdsourcing framework for collecting grid devices. We also provide an inference approach for generating topological models of the distribution grids. Since distribution cables are often underground, we use spatial data analytics on the collected data in combination with other open data sources to infer the topology of the distribution grid. Additionally, to increase the quality of crowdsourced data, we propose a cost-effective approach for collecting and detecting grid elements in urban areas using commercial drones with an RGB camera. To evaluate our approach, we organized a crowdsourcing campaign to map and infer a district in Munich, Germany. The results are compared with the ground truth of the distribution system operator. Our results report a precision of up to 82 percent and a recall of up to 65 percent for the correctly crowdsourced grid devices. We also observe that the inferred models achieve a power length accuracy of 88 percent compared to the ground truth. We evaluated the detection of solar panels from aerial imagery by conducting field experiments, showing precision and recall levels of 68 and 69 percent, respectively.