RESUMO
BACKGROUND: Real-time air pollution monitoring is a valuable tool for public health and environmental surveillance. In recent years, there has been a dramatic increase in air pollution forecasting and monitoring research using artificial neural networks. Most prior work relied on modeling pollutant concentrations collected from ground-based monitors and meteorological data for long-term forecasting of outdoor ozone (O3), oxides of nitrogen, and fine particulate matter (PM2.5). Given that traditional, highly sophisticated air quality monitors are expensive and not universally available, these models cannot adequately serve those not living near pollutant monitoring sites. Furthermore, because prior models were built based on physical measurement data collected from sensors, they may not be suitable for predicting the public health effects of pollution exposure. OBJECTIVE: This study aimed to develop and validate models to nowcast the observed pollution levels using web search data, which are publicly available in near real time from major search engines. METHODS: We developed novel machine learning-based models using both traditional supervised classification methods and state-of-the-art deep learning methods to detect elevated air pollution levels at the US city level by using generally available meteorological data and aggregate web-based search volume data derived from Google Trends. We validated the performance of these methods by predicting 3 critical air pollutants (O3, nitrogen dioxide, and PM2.5) across 10 major US metropolitan statistical areas in 2017 and 2018. We also explore different variations of the long short-term memory model and propose a novel search term dictionary learner-long short-term memory model to learn sequential patterns across multiple search terms for prediction. RESULTS: The top-performing model was a deep neural sequence model long short-term memory, using meteorological and web search data, and reached an accuracy of 0.82 (F1-score 0.51) for O3, 0.74 (F1-score 0.41) for nitrogen dioxide, and 0.85 (F1-score 0.27) for PM2.5, when used for detecting elevated pollution levels. Compared with using only meteorological data, the proposed method achieved superior accuracy by incorporating web search data. CONCLUSIONS: The results show that incorporating web search data with meteorological data improves the nowcasting performance for all 3 pollutants and suggest promising novel applications for tracking global physical phenomena using web search data.
RESUMO
The bioCADDIE dataset retrieval challenge brought together different approaches to retrieval of biomedical datasets relevant to a user's query, expressed as a text description of a needed dataset. We describe experiments in applying a data-driven, machine learning-based approach to biomedical dataset retrieval as part of this challenge. We report on a series of experiments carried out to evaluate the performance of both probabilistic and machine learning-driven techniques from information retrieval, as applied to this challenge. Our experiments with probabilistic information retrieval methods, such as query term weight optimization, automatic query expansion and simulated user relevance feedback, demonstrate that automatically boosting the weights of important keywords in a verbose query is more effective than other methods. We also show that although there is a rich space of potential representations and features available in this domain, machine learning-based re-ranking models are not able to improve on probabilistic information retrieval techniques with the currently available training data. The models and algorithms presented in this paper can serve as a viable implementation of a search engine to provide access to biomedical datasets. The retrieval performance is expected to be further improved by using additional training data that is created by expert annotation, or gathered through usage logs, clicks and other processes during natural operation of the system. Database URL: https://github.com/emory-irlab/biocaddie
