Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns.

Accurate estimation of photovoltaic (PV) system performance is crucial for determining its feasibility as a power generation technology and financial asset. PV-based energy solutions offer a viable alternative to traditional energy resources due to their superior Levelized Cost of Energy (LCOE). A significant challenge in assessing the LCOE of PV systems lies in understanding the Performance Loss Rate (PLR) for large fleets of PV systems. Estimating the PLR of PV systems becomes increasingly important in the rapidly growing PV industry. Precise PLR estimation benefits PV users by providing real-time monitoring of PV module performance, while explainable PLR estimation assists PV manufacturers in studying and enhancing the performance of their products. However, traditional PLR estimation methods based on statistical models have notable drawbacks. Firstly, they require user knowledge and decision-making. Secondly, they fail to leverage spatial coherence for fleet-level analysis. Additionally, these methods inherently assume the linearity of degradation, which is not representative of real world degradation. To overcome these challenges, we propose a novel graph deep learning-based decomposition method called the Spatio-Temporal Graph Neural Network for fleet-level PLR estimation (PV-stGNN-PLR). PV-stGNN-PLR decomposes the power timeseries data into aging and fluctuation components, utilizing the aging component to estimate PLR. PV-stGNN-PLR exploits spatial and temporal coherence to derive PLR estimation for all systems in a fleet and imposes flatness and smoothness regularization in loss function to ensure the successful disentanglement between aging and fluctuation. We have evaluated PV-stGNN-PLR on three simulated PV datasets consisting of 100 inverters from 5 sites. Experimental results show that PV-stGNN-PLR obtains a reduction of 33.9% and 35.1% on average in Mean Absolute Percent Error (MAPE) and Euclidean Distance (ED) in PLR degradation pattern estimation compared to the state-of-the-art PLR estimation methods.

American Twitter users revealed social determinant-related oral health disparities amid the COVID-19 pandemic.

OBJECTIVES: To assess self-reported population oral health conditions amid the COVID-19 pandemic using user reports on Twitter. METHOD AND MATERIALS: Oral health-related tweets during the COVID-19 pandemic were collected from 9,104 Twitter users across 26 states (with sufficient samples) in the United States between 12 November 2020 and 14 June 2021. User demographics were inferred by leveraging the visual information from the user profile images. Other characteristics including income, population density, poverty rate, health insurance coverage rate, community water fluoridation rate, and relative change in the number of daily confirmed COVID-19 cases were acquired or inferred based on retrieved information from user profiles. Logistic regression was performed to examine whether discussions vary across user characteristics. RESULTS: Overall, 26.70% of the Twitter users discussed "Wisdom tooth pain/jaw hurt," 23.86% tweeted about "Dental service/cavity," 18.97% discussed "Chipped tooth/tooth break," 16.23% talked about "Dental pain," and the rest tweeted about "Tooth decay/gum bleeding." Women and younger adults (19 to 29 years) were more likely to talk about oral health problems. Health insurance coverage rate was the most significant predictor in logistic regression for topic prediction. CONCLUSION: Tweets inform social disparities in oral health during the pandemic. For instance, people from counties at a higher risk of COVID-19 talked more about "Tooth decay/gum bleeding" and "Chipped tooth/tooth break." Older adults, who are vulnerable to COVID-19, were more likely to discuss "Dental pain." Topics of interest varied across user characteristics. Through the lens of social media, these findings may provide insights for oral health practitioners and policy makers.