Fant 9801 publikasjoner. Viser side 378 av 393:
Two-Stage Feature Engineering to Predict Air Pollutants in Urban Areas
Air pollution is a global challenge to human health and the ecological environment. Identifying the relationship among pollutants, their fundamental sources and detrimental effects on health and mental well-being is critical in order to implement appropriate countermeasures. The way forward to address this issue and assess air quality is through accurate air pollution prediction. Such prediction can subsequently assist governing bodies in making prompt, evidence-based decisions and prevent further harm to our urban environment, public health, and climate, all of which co-benefit our economy. In this study, the main objective is to explore the strength of features and proposed a two stage feature engineering approach, which fuses the advantage of influential factors along with the decomposition approach and generates an optimum feature combination for five major pollutants including Nitrogen Dioxide (NO 2 ), Ozone (O 3 ), Sulphur Dioxide (SO 2 ), and Particulate Matter (PM2.5, and PM10). The experiments are conducted using a dataset from 2015 to 2020 which is publicly available and is collected from Belfast-based air quality monitoring stations in Northern Ireland, UK. In stage-1, using the dataset new features such as trigonometric and statistical features are created to capture their dependency on the target pollutant and generated correlation-inspired best feature combinations to improve forecasting model performance. This is further enhanced in stage-2 by an optimum feature combination which is an integration of stage-1 and Variational Mode Decomposition (VMD) based features. This study employed a simplified Long Short Term Memory (LSTM) neural network and proposed a single-step forecasting model to predict multivariate time series data. Three performance indicators are used to evaluate the effectiveness of forecasting model: (a) root mean square error (RMSE), (b) mean absolute error (MAE), and (c) R-squared (R 2 ). The results demonstrate the effectiveness of proposed approach with 13% improvement in performance (in terms of R 2 ) and the lowest error scores for both RMSE and MAE.
IEEE (Institute of Electrical and Electronics Engineers)
2024
2024
2024
2024
Måling av gasser i Statsarkivets lokaler i Trondheim. Fase 2 - 2024
Denne rapporten viser resultater fra fase 2 i måleprosjektet NILU har utført ved Statsarkivet i Trondheim. Det er gjort prøvetaking og analyse i en periode på sju dager fra 23. til 30. mai ved to lokaliteter, én innendørs og én utendørs. Totalkonsentrasjonen av VOC’er (TVOC) ble målt til 135 µg/m3 gitt som toluen-ekvivalenter ved lokaliteten inne (MAG A, Reol 097) og 33 µg/m3 ved lokaliteten ute. Resultatene synliggjør effekten av innendørs ventilasjonssystemer og begge studiene vil brukes av Statsarkivet i sitt videre arbeid med innendørs luftkvalitet.
NILU
2024
2024
2024
2024
2024
2024
2024
2024
The participation of a diverse –in terms of geography, discipline and gender– group of Early Career Researchers (ECRs) in the peer review process can help alleviate the workload of senior researchers and counteract the perceptual biases that the latter tend to show. Moreover, ECRs can benefit from developing skills that are often not included in educational programs. From 2018 to 2021, the Association of Polar Early Career Scientists, in collaboration with other associations, organized six group reviews of the Intergovernmental Panel on Climate Change (IPCC) reports by a total of more than 600 ECRs from over 70 different countries. This study aims to evaluate this group review in terms of its contribution to the production of scientific knowledge, and as a career development opportunity for ECRs. The data analyzed consists of application forms, review comments, and feedback surveys that were collected during each review process. The results of this study show that, overall, the group reviews were a success in terms of the experience of ECRs and their contribution to the peer review of the IPCC reports. Most survey respondents considered the general organization of the group reviews satisfactory and expressed interest in participating in future group reviews. However, most participants did not engage in discussions with their peers, which constitutes a missed opportunity to engage in active learning and the shared production of knowledge. ECRs made a significant contribution to the review of the IPCC reports by producing an average of 2,422 ± 532 comments per group review, 36% of which were substantive. PhD students were shown to be as proficient reviewers as postdoctoral researchers and faculty reviewers. More importantly, the diversity of reviewers in terms of geography and discipline, together with the fact that they are ECRs, can help produce more balanced scientific reports since they bring new perspectives, thus counteracting the biases that senior researchers have. These group reviews could be improved by providing more comprehensive training and facilitating communication among reviewers so that they can engage in meaningful exchanges. We conclude that the IPCC should formalize the inclusion of ECRs in future reviews of the IPCC reports.
Frontiers Media S.A.
2024
We determine the global emission distribution of the potent greenhouse gas sulfur hexafluoride (SF6) for the period 2005–2021 using inverse modelling. The inversion is based on 50 d backward simulations with the Lagrangian particle dispersion model (LPDM) FLEXPART and on a comprehensive observation data set of SF6 mole fractions in which we combine continuous with flask measurements sampled at fixed surface locations and observations from aircraft and ship campaigns. We use a global-distribution-based (GDB) approach to determine baseline mole fractions directly from global SF6 mole fraction fields at the termination points of the backward trajectories. We compute these fields by performing an atmospheric SF6 re-analysis, assimilating global SF6 observations into modelled global three-dimensional mole fraction fields. Our inversion results are in excellent agreement with several regional inversion studies in the USA, Europe, and China. We find that (1) annual US SF6 emissions strongly decreased from 1.25 Gg in 2005 to 0.48 Gg in 2021; however, they were on average twice as high as the reported emissions to the United Nations. (2) SF6 emissions from EU countries show an average decreasing trend of −0.006 Gg yr−1 during the period 2005 to 2021, including a substantial drop in 2018. This drop is likely a direct result of the EU's F-gas regulation 517/2014, which bans the use of SF6 for recycling magnesium die-casting alloys as of 2018 and requires leak detection systems for electrical switch gear. (3) Chinese annual emissions grew from 1.28 Gg in 2005 to 5.16 Gg in 2021, with a trend of 0.21 Gg yr−1, which is even higher than the average global total emission trend of 0.20 Gg yr−1. (4) National reports for the USA, Europe, and China all underestimated their SF6 emissions. (5) Our results indicate increasing emissions in poorly monitored areas (e.g. India, Africa, and South America); however, these results are uncertain due to weak observational constraints, highlighting the need for enhanced monitoring in these areas. (6) Global total SF6 emissions are comparable to estimates in previous studies but are sensitive to a priori estimates due to the low network sensitivity in poorly monitored regions. (7) Monthly inversions indicate that SF6 emissions in the Northern Hemisphere were on average higher in summer than in winter throughout the study period.
2024
2024
2024
2024
2024
2024
2024