Human and natural processes such as navigation and natural calamities are intrinsically linked to the geographic space and described using place names. Extraction and subsequent geocoding of place names from text are critical for understanding the onset, progression, and end of these processes. Geocoding place names extracted from text requires using an external knowledge base such as a gazetteer. However, a standard gazetteer is typically incomplete. Additionally, widely used place name geocoding—also known as toponym resolution—approaches generally focus on geocoding ambiguous but known gazetteer place names. Hence there is a need for an approach to automatically geocode non -gazetteer place names. In this research, we demonstrate that patterns in place names are not spatially random. Places are often named based on people, geography, and history of the area and thus exhibit a degree of similarity. Similarly, places that co-occur in text are likely to be spatially proximate as they provide geographic reference to common events. We propose a novel data-driven spatially-aware algorithm, Bhugol , that leverages the spatial patterns and the spatial context of place names to automatically geocode the non-gazetteer place names. The efficacy of Bhugol is demonstrated using two diverse geographic areas – USA and India. The results show that Bhugol outperforms well-known state-of-the-art geocoders.
{"title":"A Spatially-Aware Data-Driven Approach to Automatically Geocoding Non-Gazetteer Place Names","authors":"Praval Sharma, Ashok Samal, Leen-Kiat Soh, Deepti Joshi","doi":"10.1145/3627987","DOIUrl":"https://doi.org/10.1145/3627987","url":null,"abstract":"Human and natural processes such as navigation and natural calamities are intrinsically linked to the geographic space and described using place names. Extraction and subsequent geocoding of place names from text are critical for understanding the onset, progression, and end of these processes. Geocoding place names extracted from text requires using an external knowledge base such as a gazetteer. However, a standard gazetteer is typically incomplete. Additionally, widely used place name geocoding—also known as toponym resolution—approaches generally focus on geocoding ambiguous but known gazetteer place names. Hence there is a need for an approach to automatically geocode non -gazetteer place names. In this research, we demonstrate that patterns in place names are not spatially random. Places are often named based on people, geography, and history of the area and thus exhibit a degree of similarity. Similarly, places that co-occur in text are likely to be spatially proximate as they provide geographic reference to common events. We propose a novel data-driven spatially-aware algorithm, Bhugol , that leverages the spatial patterns and the spatial context of place names to automatically geocode the non-gazetteer place names. The efficacy of Bhugol is demonstrated using two diverse geographic areas – USA and India. The results show that Bhugol outperforms well-known state-of-the-art geocoders.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136079075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid advancements in sensing techniques, networking and AI algorithms in the recent years have brought the autonomous driving vehicles closer to common use in vehicular transportation. One of the fundamental components to enable the autonomous driving functionalities are the High Definition (HD) maps – a type of maps that carry highly accurate and much richer information than conventional maps. The creation and use of HD maps rely on advances in multiple disciplines such as computer vision/object perception, geographic information system, sensing, simultaneous localization and mapping, machine learning, etc. To date, several survey papers have been published, describing the literature related to HD maps and their use in specialized contexts. In this survey, we aim to provide: (1) a comprehensive overview of the issues and solutions related to HD maps and their use, without attachment to a particular context; (2) a detailed coverage of the important domain knowledge of HD map furniture, from acquisition techniques and extraction approaches, through HD maps related datasets, to furniture quality assessment metrics, for the purpose of providing a comprehensive understanding of the entire workflow of HD map furniture generation, as well as its use.
{"title":"Data Issues in High Definition Maps Furniture – A Survey","authors":"Andi Zang, Runsheng Xu, Goce Trajcevski, Fan Zhou","doi":"10.1145/3627160","DOIUrl":"https://doi.org/10.1145/3627160","url":null,"abstract":"The rapid advancements in sensing techniques, networking and AI algorithms in the recent years have brought the autonomous driving vehicles closer to common use in vehicular transportation. One of the fundamental components to enable the autonomous driving functionalities are the High Definition (HD) maps – a type of maps that carry highly accurate and much richer information than conventional maps. The creation and use of HD maps rely on advances in multiple disciplines such as computer vision/object perception, geographic information system, sensing, simultaneous localization and mapping, machine learning, etc. To date, several survey papers have been published, describing the literature related to HD maps and their use in specialized contexts. In this survey, we aim to provide: (1) a comprehensive overview of the issues and solutions related to HD maps and their use, without attachment to a particular context; (2) a detailed coverage of the important domain knowledge of HD map furniture, from acquisition techniques and extraction approaches, through HD maps related datasets, to furniture quality assessment metrics, for the purpose of providing a comprehensive understanding of the entire workflow of HD map furniture generation, as well as its use.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":"249 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136013615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yifang Yin, Wenmiao Hu, An Tran, Ying Zhang, Guanfeng Wang, H. Kruppa, Roger Zimmermann, See-Kiong Ng
Automatic inference of missing road attributes (e.g., road type and speed limit) for enriching digital maps has attracted significant research attention in recent years. A number of machine learning based approaches have been proposed to detect road attributes from GPS traces, dash-cam videos, or satellite images. However, existing solutions mostly focus on a single modality without modeling the correlations among multiple data sources. To bridge this gap, we present a multimodal road attribute detection method, which improves the robustness by performing pixel-level fusion of crowdsourced GPS traces and satellite images. A GPS trace is usually given by a sequence of location, bearing, and speed. To align it with satellite imagery in the spatial domain, we render GPS traces into a sequence of multi-channel images that simultaneously capture the global distribution of the GPS points, the local distribution of vehicles’ moving directions and speeds, and their temporal changes over time, at each pixel. Unlike previous GPS based road feature extraction methods, our proposed GPS rendering does not require map matching in the data preprocessing step. Moreover, our multimodal solution addresses single-modal challenges such as occlusions in satellite images and data sparsity in GPS traces by learning the pixel-wise correspondences among different data sources. On top of this, we observe that geographic objects and their attributes in the map are not isolated but correlated with each other. Thus, if a road is partially labeled, the existing information can be of great help on inferring the missing attributes. To fully use the existing information, we extend our model and discuss the possibilities for further performance improvement when partially labeled map data is available. Extensive experiments have been conducted on two real-world datasets in Singapore and Jakarta. Compared with previous work, our method is able to improve the detection accuracy on road attributes by a large margin.
{"title":"Multimodal Deep Learning for Robust Road Attribute Detection","authors":"Yifang Yin, Wenmiao Hu, An Tran, Ying Zhang, Guanfeng Wang, H. Kruppa, Roger Zimmermann, See-Kiong Ng","doi":"10.1145/3618108","DOIUrl":"https://doi.org/10.1145/3618108","url":null,"abstract":"Automatic inference of missing road attributes (e.g., road type and speed limit) for enriching digital maps has attracted significant research attention in recent years. A number of machine learning based approaches have been proposed to detect road attributes from GPS traces, dash-cam videos, or satellite images. However, existing solutions mostly focus on a single modality without modeling the correlations among multiple data sources. To bridge this gap, we present a multimodal road attribute detection method, which improves the robustness by performing pixel-level fusion of crowdsourced GPS traces and satellite images. A GPS trace is usually given by a sequence of location, bearing, and speed. To align it with satellite imagery in the spatial domain, we render GPS traces into a sequence of multi-channel images that simultaneously capture the global distribution of the GPS points, the local distribution of vehicles’ moving directions and speeds, and their temporal changes over time, at each pixel. Unlike previous GPS based road feature extraction methods, our proposed GPS rendering does not require map matching in the data preprocessing step. Moreover, our multimodal solution addresses single-modal challenges such as occlusions in satellite images and data sparsity in GPS traces by learning the pixel-wise correspondences among different data sources. On top of this, we observe that geographic objects and their attributes in the map are not isolated but correlated with each other. Thus, if a road is partially labeled, the existing information can be of great help on inferring the missing attributes. To fully use the existing information, we extend our model and discuss the possibilities for further performance improvement when partially labeled map data is available. Extensive experiments have been conducted on two real-world datasets in Singapore and Jakarta. Compared with previous work, our method is able to improve the detection accuracy on road attributes by a large margin.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47898176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Simon Aagaard Pedersen, B. Yang, Christian S. Jensen, J. Møller
Arriving at a destination within a specific time window is important in many transportation settings. For example, trucks may be penalized for early or late arrivals at compact terminals, and early and late arrivals at general practitioners, dentists, and so on, are also discouraged, in part due to COVID. We propose foundations for routing with arrival-window constraints. In a setting where the travel time of a road segment is modeled by a probability distribution, we define two problems where the aim is to find a route from a source to a destination that optimizes or yields a high probability of arriving within a time window while departing as late as possible. In this setting, a core challenge is to enable comparison between paths that may potentially be part of a result path with the goal of determining whether a path is uninteresting and can be disregarded given the existence of another path. We show that existing solutions cannot be applied in this problem setting and instead propose novel comparison methods. Additionally, we introduce the notion of Stochastic Arrival-Window Contraction Hierarchies that enable accelerated query processing in the article’s setting. Next, we present routing algorithms that exploit the above comparison methods in combination with so-called pivot paths and contraction hierarchies to enable efficient processing of the two types of queries. Finally, a detailed experimental study provides empirical insights that justify the need for the two types of routing and also offers insight into key characteristics of the problem solutions.
{"title":"Stochastic Routing with Arrival Windows","authors":"Simon Aagaard Pedersen, B. Yang, Christian S. Jensen, J. Møller","doi":"10.1145/3617500","DOIUrl":"https://doi.org/10.1145/3617500","url":null,"abstract":"Arriving at a destination within a specific time window is important in many transportation settings. For example, trucks may be penalized for early or late arrivals at compact terminals, and early and late arrivals at general practitioners, dentists, and so on, are also discouraged, in part due to COVID. We propose foundations for routing with arrival-window constraints. In a setting where the travel time of a road segment is modeled by a probability distribution, we define two problems where the aim is to find a route from a source to a destination that optimizes or yields a high probability of arriving within a time window while departing as late as possible. In this setting, a core challenge is to enable comparison between paths that may potentially be part of a result path with the goal of determining whether a path is uninteresting and can be disregarded given the existence of another path. We show that existing solutions cannot be applied in this problem setting and instead propose novel comparison methods. Additionally, we introduce the notion of Stochastic Arrival-Window Contraction Hierarchies that enable accelerated query processing in the article’s setting. Next, we present routing algorithms that exploit the above comparison methods in combination with so-called pivot paths and contraction hierarchies to enable efficient processing of the two types of queries. Finally, a detailed experimental study provides empirical insights that justify the need for the two types of routing and also offers insight into key characteristics of the problem solutions.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45403359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A moving body is a geometry that may translate and rotate over time. Computing the time-varying distance between moving bodies and surrounding static and moving objects is crucial to many application domains including safety at sea, logistics robots, and autonomous vehicles. Not only is it a relevant analytical operation in itself, but it also forms the basis of other operations, such as finding the nearest approach distance between two moving objects. Most moving objects databases represent moving objects using a point representation, and the computed temporal distance is thus inaccurate when working with large moving objects. This paper presents an efficient algorithm to compute the temporal distance between a moving body and other static or moving geometries. We extend the idea of the V-Clip and Lin-Canney closest features algorithms of computational geometry to track the temporal evolution of the closest pair of features between two objects during their movement. We also present a working implementation of this algorithm in an open-source moving objects database and show, using a real-world example on AIS data, that this distance operator for moving bodies is only about 1.5 times as slow as the one for moving points while providing significant improvements in correctness and accuracy of the results.
{"title":"On Computing the Time-Varying Distance Between Moving Bodies","authors":"Maxime Schoemans, M. Sakr, E. Zimányi","doi":"10.1145/3611010","DOIUrl":"https://doi.org/10.1145/3611010","url":null,"abstract":"A moving body is a geometry that may translate and rotate over time. Computing the time-varying distance between moving bodies and surrounding static and moving objects is crucial to many application domains including safety at sea, logistics robots, and autonomous vehicles. Not only is it a relevant analytical operation in itself, but it also forms the basis of other operations, such as finding the nearest approach distance between two moving objects. Most moving objects databases represent moving objects using a point representation, and the computed temporal distance is thus inaccurate when working with large moving objects. This paper presents an efficient algorithm to compute the temporal distance between a moving body and other static or moving geometries. We extend the idea of the V-Clip and Lin-Canney closest features algorithms of computational geometry to track the temporal evolution of the closest pair of features between two objects during their movement. We also present a working implementation of this algorithm in an open-source moving objects database and show, using a real-world example on AIS data, that this distance operator for moving bodies is only about 1.5 times as slow as the one for moving points while providing significant improvements in correctness and accuracy of the results.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":"1 1","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44161705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sujoy Bhore, Robert Ganian, Guangping Li, Martin Nöllenburg, Jules Wulms
Point feature labeling is a classical problem in cartography and GIS that has been extensively studied for geospatial point data. At the same time, word clouds are a popular visualization tool to show the most important words in text data which has also been extended to visualize geospatial data (Buchin et al. PacificVis 2016). In this article, we study a hybrid visualization, which combines aspects of word clouds and point labeling. In the considered setting, the input data consist of a set of points grouped into categories and our aim is to place multiple disjoint and axis-aligned rectangles, each representing a category, such that they cover points of (mostly) the same category under some natural quality constraints. In our visualization, we then place category names inside the computed rectangles to produce a labeling of the covered points which summarizes the predominant categories globally (in a word-cloud-like fashion) while locally avoiding excessive misrepresentation of points (i.e., retaining the precision of point labeling). We show that computing a minimum set of such rectangles is NP -hard. Hence, we turn our attention to developing a heuristic with (optional) exact components using SAT models to compute our visualizations. We evaluate our algorithms quantitatively, measuring running time and quality of the produced solutions, on several synthetic and real-world data sets. Our experiments show that the fully heuristic approach produces solutions of comparable quality to heuristics combined with exact SAT models, while running much faster.
{"title":"Worbel: Aggregating Point Labels into Word Clouds","authors":"Sujoy Bhore, Robert Ganian, Guangping Li, Martin Nöllenburg, Jules Wulms","doi":"10.1145/3603376","DOIUrl":"https://doi.org/10.1145/3603376","url":null,"abstract":"Point feature labeling is a classical problem in cartography and GIS that has been extensively studied for geospatial point data. At the same time, word clouds are a popular visualization tool to show the most important words in text data which has also been extended to visualize geospatial data (Buchin et al. PacificVis 2016). In this article, we study a hybrid visualization, which combines aspects of word clouds and point labeling. In the considered setting, the input data consist of a set of points grouped into categories and our aim is to place multiple disjoint and axis-aligned rectangles, each representing a category, such that they cover points of (mostly) the same category under some natural quality constraints. In our visualization, we then place category names inside the computed rectangles to produce a labeling of the covered points which summarizes the predominant categories globally (in a word-cloud-like fashion) while locally avoiding excessive misrepresentation of points (i.e., retaining the precision of point labeling). We show that computing a minimum set of such rectangles is NP -hard. Hence, we turn our attention to developing a heuristic with (optional) exact components using SAT models to compute our visualizations. We evaluate our algorithms quantitatively, measuring running time and quality of the produced solutions, on several synthetic and real-world data sets. Our experiments show that the fully heuristic approach produces solutions of comparable quality to heuristics combined with exact SAT models, while running much faster.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136337531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Regionalization techniques group spatial areas into a set of homogeneous regions to analyze and draw conclusions about spatial phenomena. A recent regionalization problem, called MP-regions, groups spatial areas to produce a maximum number of regions by enforcing a user-defined constraint at the regional level. The MP-regions problem is NP-hard. Existing approximate algorithms for MP-regions do not scale for large datasets due to their high computational cost and inherently centralized approaches to process data. This article introduces a parallel scalable regionalization framework (PAGE) to support MP-regions on large datasets. The proposed framework works in two stages. The first stage finds an initial solution through randomized search, and the second stage improves this solution through efficient heuristic search. To build an initial solution efficiently, we extend traditional spatial partitioning techniques to enable parallelized region building without violating the spatial constraints. Furthermore, we optimize the region building efficiency and quality by tuning the randomized area selection to trade off runtime with region homogeneity. The experimental evaluation shows the superiority of our framework to support an order of magnitude larger datasets efficiently compared to the state-of-the-art techniques while producing high-quality solutions.
{"title":"PAGE: Parallel Scalable Regionalization Framework","authors":"Hussah Alrashid, Yongyi Liu, A. Magdy","doi":"10.1145/3611011","DOIUrl":"https://doi.org/10.1145/3611011","url":null,"abstract":"Regionalization techniques group spatial areas into a set of homogeneous regions to analyze and draw conclusions about spatial phenomena. A recent regionalization problem, called MP-regions, groups spatial areas to produce a maximum number of regions by enforcing a user-defined constraint at the regional level. The MP-regions problem is NP-hard. Existing approximate algorithms for MP-regions do not scale for large datasets due to their high computational cost and inherently centralized approaches to process data. This article introduces a parallel scalable regionalization framework (PAGE) to support MP-regions on large datasets. The proposed framework works in two stages. The first stage finds an initial solution through randomized search, and the second stage improves this solution through efficient heuristic search. To build an initial solution efficiently, we extend traditional spatial partitioning techniques to enable parallelized region building without violating the spatial constraints. Furthermore, we optimize the region building efficiency and quality by tuning the randomized area selection to trade off runtime with region homogeneity. The experimental evaluation shows the superiority of our framework to support an order of magnitude larger datasets efficiently compared to the state-of-the-art techniques while producing high-quality solutions.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":"9 1","pages":"1 - 26"},"PeriodicalIF":1.9,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44904411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The proliferation of mobile phones and location-based services has given rise to an explosive growth in spatial data. In order 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 paper, 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 data sets demonstrate the superior performance of STAR over existing systems.
{"title":"STAR: A Cache-based Stream Warehouse System for Spatial Data","authors":"Zhida Chen, Gao Cong, Walid G. Aref","doi":"10.1145/3605944","DOIUrl":"https://doi.org/10.1145/3605944","url":null,"abstract":"The proliferation of mobile phones and location-based services has given rise to an explosive growth in spatial data. In order 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 paper, 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 data sets demonstrate the superior performance of STAR over existing systems.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45016530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated our model’s superiority in performance over state-of-the-art models.
{"title":"Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision","authors":"Minxing Zhang, Dazhou Yu, Yun-Qing Li, Liang Zhao","doi":"10.1145/3605358","DOIUrl":"https://doi.org/10.1145/3605358","url":null,"abstract":"Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated our model’s superiority in performance over state-of-the-art models.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":" ","pages":"1 - 26"},"PeriodicalIF":1.9,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49271670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recommending a Point of Interest (PoI) or a sequence of PoIs to visit based on user’s preferences and geo-locations has been one of the most popular applications of Location-Based Services (LBS). Variants have also been considered which take other factors into consideration, such as broader (implicit or explicit) semantic constraints as well as the limitations on the length of the trip. In this work, we present an efficient algorithmic solution to a novel query – PaDOC (Paths with Distance, Origin, and Category constraints) – which combines the generation of a path that (a) can be traversed within a user-specified budget (e.g., limit on distance), (b) starts at one of the user-specified origin locations (e.g., a hotel), and (c) contains PoIs from a user-specified list of PoI categories. We show that the problem of deciding whether such a path exists is an NP-hard problem. Based on a novel indexing structure, we propose two efficient algorithms for approximate PaDOC query processing based on both conservative and progressive distance estimations. We conducted extensive experiments over real, publicly available datasets, demonstrating the benefits of the proposed methodologies over straightforward solutions.
{"title":"Distance, Origin and Category Constrained Paths","authors":"Xu Teng, Goce Trajcevski, Andreas Züfle","doi":"10.1145/3596601","DOIUrl":"https://doi.org/10.1145/3596601","url":null,"abstract":"Recommending a Point of Interest (PoI) or a sequence of PoIs to visit based on user’s preferences and geo-locations has been one of the most popular applications of Location-Based Services (LBS). Variants have also been considered which take other factors into consideration, such as broader (implicit or explicit) semantic constraints as well as the limitations on the length of the trip. In this work, we present an efficient algorithmic solution to a novel query – PaDOC (Paths with Distance, Origin, and Category constraints) – which combines the generation of a path that (a) can be traversed within a user-specified budget (e.g., limit on distance), (b) starts at one of the user-specified origin locations (e.g., a hotel), and (c) contains PoIs from a user-specified list of PoI categories. We show that the problem of deciding whether such a path exists is an NP-hard problem. Based on a novel indexing structure, we propose two efficient algorithms for approximate PaDOC query processing based on both conservative and progressive distance estimations. We conducted extensive experiments over real, publicly available datasets, demonstrating the benefits of the proposed methodologies over straightforward solutions.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":"9 1","pages":"1 - 27"},"PeriodicalIF":1.9,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44010639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：