Found 9972 publications. Showing page 218 of 399:
Ensuring a healthy and comfortable indoor environment in schools is essential for student well-being and academic performance. The purpose of this study is to investigate the factors influencing students’ satisfaction with indoor air quality (IAQ) and thermal comfort in classrooms. To address this, one year-long measurements were conducted across multiple classrooms in a Norwegian secondary school, collecting data on indoor climate (CO₂, VOC levels, temperature, relative humidity, and air pressure) along with outdoor climate variables (temperature, humidity, and solar radiation). Additional room-specific data, including orientation, floor level, and ventilation system specifications, were also considered. An online feedback system was used to gather 1,473 real-time student responses on satisfaction levels. Supervised machine learning (ML) models were developed to assess the importance of these parameters in predicting perceived indoor comfort: IAQ perceptions and thermal environmental perceptions. Results showed ML models effectively predicted student dissatisfaction, achieving accuracy greater than 80% when environmental and building parameters were considered simultaneously. The findings emphasized that dissatisfaction with indoor conditions is driven by multiple interacting factors of measured variables and building parameters single independent variables. SHAP analysis provided valuable interpretability, revealing how variations in environmental conditions collectively impact students' perceived comfort. This comprehensive approach demonstrates the practical potential of ML-based IEQ monitoring systems, suggesting that schools can proactively improve indoor conditions through targeted interventions informed by real-time predictions.
2025
Machine Learning-Based Digital Twin for Predictive Modeling in Wind Turbines
Wind turbines are one of the primary sources of renewable energy, which leads to a sustainable and efficient energy solution. It does not release any carbon emissions to pollute our planet. The wind farms monitoring and power generation prediction is a complex problem due to the unpredictability of wind speed. Consequently, it limits the decision power of the management team to plan the energy consumption in an effective way. Our proposed model solves this challenge by utilizing a 5G-Next Generation-Radio Access Network (5G-NG-RAN) assisted cloud-based digital twins’ framework to virtually monitor wind turbines and form a predictive model to forecast wind speed and predict the generated power. The developed model is based on Microsoft Azure digital twins infrastructure as a 5-dimensional digital twins platform. The predictive modeling is based on a deep learning approach, temporal convolution network (TCN) followed by a non-parametric k-nearest neighbor (kNN) regression. Predictive modeling has two components. First, it processes the univariate time series data of wind to predict its speed. Secondly, it estimates the power generation for each quarter of the year ranges from one week to a whole month (i.e., medium-term prediction) To evaluate the framework the experiments are performed on onshore wind turbines publicly available datasets. The obtained results confirm the applicability of the proposed framework. Furthermore, the comparative analysis with the existing classical prediction models shows that our designed approach obtained better results. The model can assist the management team to monitor the wind farms remotely as well as estimate the power generation in advance.
2022
A machine learning algorithm combined with measurements obtained by a NILU-UV irradiance meter enables the determination of total ozone column (TOC) amount and cloud optical depth (COD). In the New York City area, a NILU-UV instrument on the rooftop of a Stevens Institute of Technology building (40.74° N, −74.03° E) has been used to collect data for several years. Inspired by a previous study [Opt. Express 22, 19595 (2014)], this research presents an updated neural-network-based method for TOC and COD retrievals. This method provides reliable results under heavy cloud conditions, and a convenient algorithm for the simultaneous retrieval of TOC and COD values. The TOC values are presented for 2014–2023, and both were compared with results obtained using the look-up table (LUT) method and measurements by the Ozone Monitoring Instrument (OMI), deployed on NASA’s AURA satellite. COD results are also provided.
2024
Machine learning-based stocks and flows modeling of road infrastructure
This paper introduces a new method to account for the stocks and flows of road infrastructure at the national level based on material flow accounting (MFA). The proposed method closes some of the current shortcomings in road infrastructures that were identified through MFA: (1) the insufficient implementation of prospective analysis, (2) heavy use of archetypes as a way to represent road infrastructure, (3) inadequate attention to the inclusion of dissipative flows, and (4) limited coverage of the uncertainties. The proposed dynamic bottom-up MFA method was tested on the Norwegian road network to estimate and predict the material stocks and flows between 1980 and 2050. Here, a supervised machine learning model was introduced to estimate the road infrastructure instead of archetypical mapping of different roads. The dissipation of materials from the road infrastructure based on tire–pavement interaction was incorporated. Moreover, this study utilizes iterative classified and regression trees, lifetime distributions, randomized material intensities, and sensitivity analyses to quantify the uncertainties.
2022
We synthesized N2O emissions over North America using 17 bottom-up (BU) estimates from 1980–2016 and five top-down (TD) estimates from 1998 to 2016. The BU-based total emission shows a slight increase owing to U.S. agriculture, while no consistent trend is shown in TD estimates. During 2007–2016, North American N2O emissions are estimated at 1.7 (1.0–3.0) Tg N yr−1 (BU) and 1.3 (0.9–1.5) Tg N yr−1 (TD). Anthropogenic emissions were twice as large as natural fluxes from soil and water. Direct agricultural and industrial activities accounted for 68% of total anthropogenic emissions, 71% of which was contributed by the U.S. Our estimates of U.S. agricultural emissions are comparable to the EPA greenhouse gas (GHG) inventory, which includes estimates from IPCC tier 1 (emission factor) and tier 3 (process-based modeling) approaches. Conversely, our estimated agricultural emissions for Canada and Mexico are twice as large as the respective national GHG inventories.
2021
Main lecturer at libRadtran workshop, Finnish Meteorological Institute, Helsinki, 25-26 October 2016
2016
2020
Main sources controlling atmospheric burdens of persistent organic pollutants on a national scale
National long-term monitoring programs on persistent organic pollutants (POPs) in background air have traditionally relied on active air sampling techniques. Due to limited spatial coverage of active air samplers, questions remain (i) whether active air sampler monitoring sites are representative for atmospheric burdens within the larger geographical area targeted by the monitoring programs, and thus (ii) if the main sources affecting POPs in background air across a nation are understood. The main objective of this study was to explore the utility of spatial and temporal trends in concert with multiple modelling approaches to understand the main sources affecting polychlorinated biphenyls (PCBs) and organochlorine pesticides (OCPs) in background air across a nation. For this purpose, a comprehensive campaign was carried out in summer 2016, measuring POPs in background air across Norway using passive air sampling. Results were compared to a similar campaign in 2006 to assess possible changes over one decade. We furthermore used the Global EMEP Multi-media Modeling System (GLEMOS) and the Flexible Particle dispersion model (FLEXPART) to predict and evaluate the relative importance of primary emissions, secondary emissions, long-range atmospheric transport (LRAT) and national emissions in controlling atmospheric burdens of PCB-153 on a national scale. The concentrations in air of both PCBs and most of the targeted OCPs were generally low, with the exception of hexachlorobenzene (HCB). A limited spatial variability for all POPs in this study, together with predictions by both models, suggest that LRAT dominates atmospheric burdens across Norway. Model predictions by the GLEMOS model, as well as measured isomeric ratios, further suggest that LRAT of some POPs are dictated by secondary emissions. Our results illustrate the utility of combining observations and mechanistic modelling approaches to help identify the main factors affecting atmospheric burdens of POPs across a nation, which, in turn, may be used to inform both national monitoring and control strategies.
2021
2018
2017
2018
2015
2016
2015
2009
2013
2010
2012
2016