ABSTRACT
Nitrogen dioxide (NO2) is an important target for monitoring atmospheric quality. Deriving ground-level NO2 concentrations with much finer resolution, it requires high-resolution satellite tropospheric NO2 column as input and a reliable estimation algorithm. This paper aims to estimate the daily ground-level NO2 concentrations over China based on machine learning models and the TROPOMI NO2 data with high spatial resolution. In this study, four tree-based algorithm machine learning models, decision trees (DT), gradient boost decision tree (GBDT), random forest (RF) and extra-trees (ET), were used to estimate ground-level NO2 concentrations. In addition to considering many influencing factors of the ground-level NO2 concentrations, we especially introduced simplified temporal and spatial information into the estimation models. The results show that the extra-trees with spatial and temporal information (ST-ET) model has great performance in estimating ground-level NO2 concentrations with a cross-validation R-2 of 0.81 and RMSE of 3.45 mu g/m(3) in test datasets. The estimated results for 2019 based on the ST-ET model achieves a satisfactory accuracy with a cross-validation R-2 of 0.86 compared with the other models. Through time-space analysis and comparison, it was found that the estimated high-resolution results were consistent with the ground observed NO2 concentrations. Using data from January 2020 to test the prediction power of the models, the results indicate that the ST-ET model has a good performance in predicting ground-level NO2 concentrations. Taking four ground-level NO2 concentrations hotspots as examples, the estimated ground-level NO2 concentrations and ground-based observation data during the coronavirus disease (COVID-19) pandemic were lower compared with the same period in 2019. The findings offer a solid solution for accurately and efficiently estimating ground-level NO2 concentrations by using satellite observations, and provide useful information for improving our understanding of the regional atmospheric environment.
ABSTRACT
INTRODUCTION: The coronavirus disease 2019 (COVID-19) pandemic has put tremendous pressure on healthcare systems. Most transcatheter aortic valve implantation (TAVI) centres have adopted different triage systems and procedural strategies to serve highest-risk patients first and to minimise the burden on hospital logistics and personnel. We therefore assessed the impact of the COVID-19 pandemic on patient selection, type of anaesthesia and outcomes after TAVI. METHODS: We used data from the Netherlands Heart Registration to examine all patients who underwent TAVI between March 2020 and July 2020 (COVID cohort), and between March 2019 and July 2019 (pre-COVID cohort). We compared patient characteristics, procedural characteristics and clinical outcomes. RESULTS: We examined 2131 patients who underwent TAVI (1020 patients in COVID cohort, 1111 patients in pre-COVID cohort). EuroSCORE II was comparable between cohorts (COVID 4.5⯱ 4.0 vs pre-COVID 4.6⯱ 4.2, pâ¯= 0.356). The number of TAVI procedures under general anaesthesia was lower in the COVID cohort (35.2% vs 46.5%, pâ¯< 0.001). Incidences of stroke (COVID 2.7% vs pre-COVID 1.7%, pâ¯= 0.134), major vascular complications (2.3% vs 3.4%, pâ¯= 0.170) and permanent pacemaker implantation (10.0% vs 9.4%, pâ¯= 0.634) did not differ between cohorts. Thirty-day and 150-day mortality were comparable (2.8% vs 2.2%, pâ¯= 0.359 and 5.2% vs 5.2%, pâ¯= 0.993, respectively). CONCLUSIONS: During the COVID-19 pandemic, patient characteristics and outcomes after TAVI were not different than before the pandemic. This highlights the fact that TAVI procedures can be safely performed during the COVID-19 pandemic, without an increased risk of complications or mortality.