Search for: All records

Meeting the United Nation’ Sustainable Development Goals (SDGs) calls for an integrative scientific approach, combining expertise, data, models and tools across many disciplines towards addressing sustainability challenges at various spatial and temporal scales. This holistic approach, while necessary, exacerbates the big data and computational challenges already faced by researchers. Many challenges in sustainability research can be tackled by harnessing the power of advanced cyberinfrastructure (CI). The objective of this paper is to highlight the key components and technologies of CI necessary for meeting the data and computational needs of the SDG research community. An overview of the CI ecosystem in the United States is provided with a specific focus on the investments made by academic institutions, government agencies and industry at national, regional, and local levels. Despite these investments, this paper identifies barriers to the adoption of CI in sustainability research that include, but are not limited to access to support structures; recruitment, retention and nurturing of an agile workforce; and lack of local infrastructure. Relevant CI components such as data, software, computational resources, and human-centered advances are discussed to explore how to resolve the barriers. The paper highlights multiple challenges in pursuing SDGs based on the outcomes of several expert meetings. These include multi-scale integration of data and domain-specific models, availability and usability of data, uncertainty quantification, mismatch between spatiotemporal scales at which decisions are made and the information generated from scientific analysis, and scientific reproducibility. We discuss ongoing and future research for bridging CI and SDGs to address these challenges.

 

Due to climate change and rapid urbanization, Urban Heat Island (UHI), featuring significantly higher temperature in metropolitan areas than surrounding areas, has caused negative impacts on urban communities. Temporal granularity is often limited in UHI studies based on satellite remote sensing data that typically has multi-day frequency coverage of a particular urban area. This low temporal frequency has restricted the development of models for predicting UHI. To resolve this limitation, this study has developed a cyber-based geographic information science and systems (cyberGIS) framework encompassing multiple machine learning models for predicting UHI with high-frequency urban sensor network data combined with remote sensing data focused on Chicago, Illinois, from 2018 to 2020. Enabled by rapid advances in urban sensor network technologies and high-performance computing, this framework is designed to predict UHI in Chicago with fine spatiotemporal granularity based on environmental data collected with the Array of Things (AoT) urban sensor network and Landsat-8 remote sensing imagery. Our computational experiments revealed that a random forest regression (RFR) model outperforms other models with the prediction accuracy of 0.45 degree Celsius in 2020 and 0.8 degree Celsius in 2018 and 2019 with mean absolute error as the evaluation metric. Humidity, distance to geographic center, and PM_2.5concentration are identified as important factors contributing to the model performance. Furthermore, we estimate UHI in Chicago with 10-min temporal frequency and 1-km spatial resolution on the hottest day in 2018. It is demonstrated that the RFR model can accurately predict UHI at fine spatiotemporal scales with high-frequency urban sensor network data integrated with satellite remote sensing data.

 

Accomplishing the goals outlined in “Ending the HIV (Human Immunodeficiency Virus) Epidemic: A Plan for America Initiative” will require properly estimating and increasing access to HIV testing, treatment, and prevention services. In this research, a computational spatial method for estimating access was applied to measure distance to services from all points of a city or state while considering the size of the population in need for services as well as both driving and public transportation. Specifically, this study employed the enhanced two-step floating catchment area (E2SFCA) method to measure spatial accessibility to HIV testing, treatment (i.e., Ryan White HIV/AIDS program), and prevention (i.e., Pre-Exposure Prophylaxis [PrEP]) services. The method considered the spatial location of MSM (Men Who have Sex with Men), PLWH (People Living with HIV), and the general adult population 15–64 depending on what HIV services the U.S. Centers for Disease Control (CDC) recommends for each group. The study delineated service- and population-specific accessibility maps, demonstrating the method’s utility by analyzing data corresponding to the city of Chicago and the state of Illinois. Findings indicated health disparities in the south and the northwest of Chicago and particular areas in Illinois, as well as unique health disparities for public transportation compared to driving. The methodology details and computer code are shared for use in research and public policy. 

In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy.