@article{yang_ruiz-suarez_reich_guan_rappold_2023, title={A Data-Fusion Approach to Assessing the Contribution of Wildland Fire Smoke to Fine Particulate Matter in California}, volume={15}, ISSN={["2072-4292"]}, url={https://www.mdpi.com/2072-4292/15/17/4246}, DOI={10.3390/rs15174246}, abstractNote={The escalating frequency and severity of global wildfires necessitate an in-depth understanding and monitoring of wildfire smoke impacts, specifically its contribution to fine particulate matter (PM2.5). We propose a data-fusion method to study wildfire contribution to PM2.5 using satellite-derived smoke plume indicators and PM2.5 monitoring data. Our study incorporates two types of monitoring data, the high-quality but sparse Air Quality System (AQS) stations and the abundant but less accurate PurpleAir (PA) sensors that are gaining popularity among citizen scientists. We propose a multi-resolution spatiotemporal model specified in the spectral domain to calibrate the PA sensors against accurate AQS measurements, and leverage the two networks to estimate wildfire contribution to PM2.5 in California in 2020 and 2021. A Bayesian approach is taken to incorporate all uncertainties and our prior intuition that the dependence between networks, as well as the accuracy of PA network, vary by frequency. We find that 1% to 3% increase in PM2.5 concentration due to wildfire smoke, and that leveraging PA sensors improves accuracy.}, number={17}, journal={REMOTE SENSING}, author={Yang, Hongjian and Ruiz-Suarez, Sofia and Reich, Brian J. and Guan, Yawen and Rappold, Ana G.}, year={2023}, month={Sep} }
 @article{ao_dinakaran_yang_wright_chirkova_2021, title={Trustworthy Knowledge Graph Population From Texts for Domain Query Answering}, ISSN={["2639-1589"]}, DOI={10.1109/BigData52589.2021.9671514}, abstractNote={Obtaining answers to domain-specific questions over large-scale unstructured (text) data is an important component of data analytics in many application domains. As manual question answering does not scale to large text corpora, it is common to use information extraction (IE) to preprocess the texts of interest prior to posing the questions. This is often done by transforming text corpora into the knowledge-graph (KG) triple format that is suitable for efficient processing of the user questions in graph-oriented data-intensive systems.In a number of real-life scenarios, trustworthiness of the answers obtained from domain-specific texts is vital for downstream decision making. In this paper we focus on one critical aspect of trustworthiness, which concerns aligning with the given domain vocabularies (ontologies) those KG triples that are obtained from the source texts via IE solutions. To address this problem, we introduce a scalable domain-independent text-to-KG approach that adapts to specific domains by using domain ontologies, without having to consult external triple repositories. Our IE solution builds on the power of neural-based learning models and leverages feature engineering to distinguish ontology-aligned data from generic data in the source texts. Our experimental results indicate that the proposed approach could be more dependable than a state-of-the-art IE baseline in constructing KGs that are suitable for trustworthy domain question answering on text data.}, journal={2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)}, author={Ao, Jing and Dinakaran, Swathi and Yang, Hungjian and Wright, David and Chirkova, Rada}, year={2021}, pages={4590–4599} }