Yao-Yi Chiang

• PhD
• Professor (Associate) at University of Southern California

Geospatial question answering (QA) is a fundamental task in navigation and point of interest (POI) searches. While existing geospatial QA datasets exist, they are limited in both scale and diversity, often relying solely on textual descriptions of geo-entities without considering their geometries. A major challenge in scaling geospatial QA datasets...

Trajectory anomaly detection is crucial for effective decision-making in urban and human mobility management. Existing methods of trajectory anomaly detection generally focus on training a trajectory generative model and evaluating the likelihood of reconstructing a given trajectory. However, previous work often lacks important contextual informati...

Historical maps are invaluable sources of information about the past, and scanned historical maps are increasingly accessible in online libraries. To retrieve maps from these large libraries that contain specific places of interest, previous work has applied computer vision techniques to recognize words on historical maps, enabling searches for map...

Multimodal learning plays a crucial role in enabling machine learning models to fuse and utilize diverse data sources, such as text, images, and audio, to support a variety of downstream tasks. A unified representation across various modalities is particularly important for improving efficiency and performance. Recent binding methods, such as Image...

Diagnosing epilepsy requires accurate seizure detection and classification, but traditional manual EEG signal analysis is resource-intensive. Meanwhile, automated algorithms often overlook EEG's geometric and semantic properties critical for interpreting brain activity. This paper introduces NeuroGNN, a dynamic Graph Neural Network (GNN) framework...

Documents hold spatial focus and valuable locality characteristics. For example, descriptions of listings in real estate or travel blogs contain information about specific local neighborhoods. This information is valuable to characterize how humans perceive their environment. However, the first step to making use of this information is to identify...

Forecasting the number of visits to Points-of-Interest (POI) in an urban area is critical for planning and decision-making for various application domains, from urban planning and transportation management to public health and social studies. Although this forecasting problem can be formulated as a multivariate time-series forecasting task, the cur...

Background Access to water and sanitation is a basic human right; however, in many parts of the world, communities experience water, sanitation, and hygiene (WaSH) insecurity. While WaSH insecurity is prevalent in many low and middle-income countries, it is also a problem in high-income countries, like the United States, as is evident in vulnerable...

As the availability, size and complexity of data have increased in recent years, machine learning (ML) techniques have become popular for modeling. Predictions resulting from applying ML models are often used for inference, decision-making, and downstream applications. A crucial yet often overlooked aspect of ML is uncertainty quantification, which...

Named geographic entities (geo-entities for short) are the building blocks of many geographic datasets. Characterizing geo-entities is integral to various application domains, such as geo-intelligence and map comprehension, while a key challenge is to capture the spatial-varying context of an entity. We hypothesize that we shall know the characteri...

Historical maps provide rich information for researchers in many areas, including the social and natural sciences. These maps contain detailed documentation of a wide variety of natural and human-made features and their changes over time, such as changes in transportation networks or the decline of wetlands or forest areas. Analyzing changes over t...

Transportation infrastructure, such as road or railroad networks, represent a fundamental component of our civilization. For sustainable planning and informed decision making, a thorough understanding of the long-term evolution of transportation infrastructure such as road networks is crucial. However, spatially explicit, multi-temporal road networ...

Background: Access to water and sanitation is a basic human right; however, in many parts of the world, communities experience water, sanitation, and hygiene (WaSH) insecurity. While WaSH insecurity is prevalent in many low and middle-income countries, it is also a problem in high-income countries, like the United States, as is evident in vulnerabl...

Transportation infrastructure, such as road or railroad networks, represent a fundamental component of our civilization. For sustainable planning and informed decision making, a thorough understanding of the long-term evolution of transportation infrastructure such as road networks is crucial. However, spatially explicit, multi-temporal road networ...

Electric vehicle route planning (EVRP) is generated from the collaborative operation of smart grids and intelligent transportation systems. It has become an essential issue for the widespread use of battery electric vehicles. However, the existed EVRP solutions are of either high computational complexity or low efficiency for large-scale problems....

Advances in measurement technology are producing increasingly time-resolved environmental exposure data. We aim to gain new insights into exposures and their potential health impacts by moving beyond simple summary statistics (e.g., means, maxima) to characterize more detailed features of high-frequency time series data. This study proposes a novel...

Many historical map sheets are publicly available for studies that require long-term historical geographic data. The cartographic design of these maps includes a combination of map symbols and text labels. Automatically reading text labels from map images could greatly speed up the map interpretation and helps generate rich metadata describing the...

Thousands of scanned historical topographic maps contain valuable information covering long periods of time, such as how the hydrography of a region has changed over time. Efficiently unlocking the information in these maps requires training a geospatial objects recognition system, which needs a large amount of annotated data. Overlapping geo-refer...

The increasing availability and accessibility of numerous overhead images allows us to estimate and assess the spatial arrangement of groups of geospatial target objects, which can benefit many applications, such as traffic monitoring and agricultural monitoring. Spatial arrangement estimation is the process of identifying the areas which contain t...

Many scientific prediction problems have spatiotemporal data- and modeling-related challenges in handling complex variations in space and time using only sparse and unevenly distributed observations. This paper presents a novel deep learning architecture, Deep learning predictions for LocATion-dependent Time-sEries data (DeepLATTE), that explicitly...

Historical maps contain detailed geographic information difficult to find elsewhere covering long-periods of time (e.g., 125 years for the historical topographic maps in the US). However, these maps typically exist as scanned images without searchable metadata. Existing approaches making historical maps searchable rely on tedious manual work (inclu...

Large network logs, recording multivariate time series generated from heterogeneous devices and sensors in a network, can often reveal important information about abnormal activities, such as network intrusions and device malfunctions. Existing machine learning methods for anomaly detection on multivariate time series typically assume that 1) norma...

Spatially explicit, fine-grained datasets describing historical urban extents are rarely available prior to the era of operational remote sensing. However, such data are necessary to better understand long-term urbanization and land development processes and for the assessment of coupled nature–human systems (e.g., the dynamics of the wildland–urba...

Many domains including policymaking, urban design, and geospatial intelligence benefit from understanding people’s mobility behaviors (e.g., work commute, shopping), which can be achieved by clustering massive trajectories using the geo-context around the visiting locations (e.g., sequence of vectors, each describing the geographic environment near...

Electric Vehicles (EVs) have grown in recent years as they have become a promising alternative to traditional fossil fuel-driven vehicles. As a result, new routing algorithms that consider both the locations of charging stations and the charging preferences of users are necessary to maintain urban traffic efficiency. This paper proposes a Constrain...

Many approaches to time series classification rely on machine learning methods. However, there is growing interest in going beyond black box prediction models to understand discriminatory features of the time series and their associations with outcomes. One promising method is time-series shapelets (TSS), which identifies maximally discriminative s...

Major societal and environmental challenges involve complex systems that have diverse multi-scale interacting processes. Consider, for example, how droughts and water reserves affect crop production and how agriculture and industrial needs affect water quality and availability. Preventive measures, such as delaying planting dates and adopting new a...

The Multiple Ground/Aerial Parcel Delivery Problem (MGAPDP), an extension of the Ground/Aerial Parcel Delivery Problem (GAPDP), aims to find an optimal partition that minimizes the overall delivery time of all trucks by serving all destinations once and returning to the distribution center. This paper presents two heuristic solutions to the MGAPDP...

Spatially explicit, fine-grained datasets describing historical urban extents are rarely available prior to the era of operational remote sensing. However, such data are necessary to better understand long-term urbanization and land development processes and for the assessment of coupled nature-human systems, e.g., the dynamics of the wildland-urba...

We introduce the modular and scalable design of Kartta Labs, an open source, open data, and scalable system for virtually reconstructing cities from historical maps and photos. Kartta Labs relies on crowdsourcing and artificial intelligence consisting of two major modules: Maps and 3D models. Each module, in turn, consists of sub-modules that enabl...

Background Advances in measurement technology are producing increasingly time-resolved environmental exposure data. We aim to gain new insights into exposures and their potential health impacts by moving beyond simple summary statistics (e.g., means, maximums) to characterize more detailed features of high-frequency time-series data. Methods This s...

Historical maps provide a rich source of information for researchers in the social and natural sciences. These maps contain detailed documentation of a wide variety of natural and human-made features and their changes over time, such as the changes in the transportation networks and the decline of wetlands. It can be labor-intensive for a scientist...

Charging infrastructure deployment is to seek the proper plan of settling charging stations and charging piles under multiple constraints, such as recharging demand, cruising range, etc., and it has been asserted as an NP-Complete problem. In this paper, we propose a multicriteria-oriented approach of efficiently deploying charging infrastructure t...

Air quality models (AQMs) are useful for studying various types of air pollutions and provide the possibility to reveal the contributors of air pollutants. Existing AQMs have been used in many scenarios having a variety of goals, e.g., focusing on some study areas and specific spatial units. Previous AQM reviews typically cover one of the forming e...

Historical maps provide a rich source of information for researchers in the social and natural sciences. These maps contain detailed documentation of a wide variety of natural and human-made features and their changes over time, such as the changes in the transportation networks and the decline of wetlands. It can be labor-intensive for a scientist...

Identifying mobility behaviors in rich trajectory data is of great economic and social interest to various applications including urban planning, marketing and intelligence. Existing work on trajectory clustering often relies on similarity measurements that utilize raw spatial and/or temporal information of trajectories. These measures are incapabl...

Digital map processing has been an interest in the computer science and geographic information science communities since the early 1980s. With the increase of available map scans, a variety of researchers in the natural and social sciences developed a growing interest in using historical maps in their studies. The lack of an understanding of how hi...

Historical map scans contain valuable information (e.g., historical locations of roads, buildings) enabling the analyses that require long-term historical data of the natural and built environment. Many online archives now provide public access to a large number of historical map scans, such as the historical USGS (United States Geological Survey)...

Historical geographic data are essential for a variety of studies of cancer and environmental epidemiology, urbanization, and landscape ecology. However, existing data sources typically contain only contemporary information. Historical maps hold a great deal of detailed geographic information at various times in the past. Yet, finding relevant maps...

This chapter summarizes the book and provides a brief outlook.

This book illustrates the first connection between the map user community and the developers of digital map processing technologies by providing several applications, challenges, and best practices in working with historical maps. After the introduction chapter, in this book, Chapter 2 presents a variety of existing applications of historical maps...

Information extraction from historical maps represents a persistent challenge due to inferior graphical quality and the large data volume of digital map archives, which can hold thousands of digitized map sheets. Traditional map processing techniques typically rely on manually collected templates of the symbol of interest, and thus are not suitable...

Understanding the impacts of climate change on natural and human systems poses major challenges as it requires the integration of models and data across various disciplines, including hydrology, agriculture, ecosystem modeling, and econometrics. While tactical situations arising from an extreme weather event require rapid responses, integrating the...

With large amounts of digital map archives becoming available, automatically extracting information from scanned historical maps is needed for many domains that require long-term historical geographic data. Convolutional Neural Networks (CNN) are powerful techniques that can be used for extracting locations of geographic features from scanned maps...

This paper introduces the Kartta Labs project, an ongoing open-source and open-data project aiming at organizing the world's historical maps and making them universally accessible and useful. Kartta Labs' framework is designed as a composition of multiple modules. Each module has a crowdsourcing implementation and an artificial intelligence based i...

This paper presents ADMSv2, an end-to-end data-driven system that enables real-time and historical data analytics and machine learning tasks over big, streaming, spatiotemporal data. ADMSv2 employs a unified multi-layered architecture that integrates several open-source frameworks to collect, store, manage, and analyze a variety of data sources, in...

With the widespread installation of location-enabled devices on public transportation, public vehicles are generating massive amounts of trajectory data in real time. However, using these trajectory data for meaningful analysis requires careful considerations in storing, managing, processing, and visualizing the data. Using the location data of the...

Scientific models often depend on complex, interrelated datasets, and finding, preparing, and cleaning these datasets often dominates the time devoted to scientific inquiry. We are addressing these problems by creating a Data Catalog that provides a central clearinghouse for metadata about scientific datasets, supports fuzzy searching for data vari...

Homelessness is a problem increasingly visible in many urban and rural communities that have rendered these marginalized people invisible. In Los Angeles County, approximately 53,000 people experience homelessness in a single-night, 4,294 of which reside in downtown’s “Skid Row” (LASHA, 2018). In the past months, cases of hepatitis A and murine typ...

Understanding the interactions between natural processes and human activities poses major challenges as it requires the integration of models and data across disparate disciplines. It typically takes many months and even years to create valid end-to-end simulations as different models need to be configured in consistent ways and generate data that...

In this paper, we propose a Geographic Information Mining framework to contribute some exploratory results concerning harvesting the featured place information entities from the Web. In the framework, we suggest an iterative geographic information mining model reflecting the data evolution along the mining process. Associating the iterations, we pr...

In StarCraft, buildings arrangement near the intersections is one of most the critical strategic decisions in the early stage. The high time complexity of the buildings arrangement makes it difficult for AI bot to make the real-time decision. This paper presents an approach to analyze the intersection in StarCraft II maps. We propose a radar-like a...

Extracting residential areas from historical raster topographic maps benefits to analyze land type change. The existing algorithms have the shortcomings including easily misidentifying objects and low positional accuracy of the identified boundary, so we have presented a new automatic recognition method based on Gabor filter for extracting resident...

Geospatial artificial intelligence (geoAI) is an emerging scientific discipline that combines innovations in spatial science, artificial intelligence methods in machine learning (e.g., deep learning), data mining, and high-performance computing to extract knowledge from spatial big data. In environmental epidemiology, exposure modeling is a commonl...

Forecasting spatially correlated time series data is challenging because of the linear and non-linear dependencies in the temporal and spatial dimensions. Air quality forecasting is one canonical example of such tasks. Existing work, e.g., auto-regressive integrated moving average (ARIMA) and artificial neural network (ANN), either fails to model t...

With the widespread installation of location-enabled devices on public transportation, public vehicles are generating massive amounts of trajectory data in real time. However, using these trajectory data for meaningful analysis requires careful considerations in storing, managing, processing, and visualizing the data. Using the location data of the...

In StarCraft, buildings arrangement near the intersections is one of most the critical strategic decisions in the early stage. The high time complexity of the buildings arrangement makes it difficult for AI bot to make the real-time decision. This paper presents an approach to analyze the intersection in StarCraft II maps. We propose a radarlike al...

With a significant amount of spatial data archives online, data conflation is becoming more and more critical in the domain of Geographical Information Science (GIScience) because of its broad applications such as detecting the development of road networks and the change of river course. Existing conflation approaches usually rely on the vector dat...

Convolutional neural networks (CNNs) such as encoder–decoder CNNs have increasingly been employed for semantic image segmentation at the pixel-level requiring pixel-level training labels, which are rarely available in real-world scenarios. In practice, weakly annotated training data at the image patch level are often used for pixel-level segmentati...

BACKGROUND Time-resolved quantification of physical activity can contribute to both personalized medicine and epidemiological research studies, for example, managing and identifying triggers of asthma exacerbations. A growing number of reportedly accurate machine learning algorithms for human activity recognition (HAR) have been developed using dat...

Background Time-resolved quantification of physical activity can contribute to both personalized medicine and epidemiological research studies, for example, managing and identifying triggers of asthma exacerbations. A growing number of reportedly accurate machine learning algorithms for human activity recognition (HAR) have been developed using dat...

Historical maps are unique sources of retrospective geographical information. Recently, several map archives containing map series covering large spatial and temporal extents have been systematically scanned and made available to the public. The geographical information contained in such data archives makes it possible to extend geospatial analysis...

Historical maps constitute unique sources of retrospective geographic information. Recently, several map archives containing map series covering large spatial and temporal extents have been systematically scanned and made available to the public. The geographic information contained in such data archives allows extending geospatial analysis retrosp...

Historical maps constitute unique sources of retrospective geographic information. Recently, several map archives containing map series covering large spatial and temporal extents have been systematically scanned and made available to the public. The geographic information contained in such data archives allows extending geospatial analysis retrosp...

Matching spatial entities (e.g., polygonal residential areas) from sources of significantly different map scales is challenging. The reason is that the same entities in two map scales have significant variations in their positions, structure shapes (and numbers), and topological relationships. Traditional matching methods based on minimum boundary...

Historical maps store abundant and valuable information about the evolution of natural features and human activities, such as changes in hydrography, the development of the railroad networks, and the expansion of human settlements. Such knowledge represents a unique resource that can be extremely useful for researchers in the social and natural sci...