Estimating particulate matter (PM) from space is not straightforward and is mainly achieved using the aerosol optical depth (AOD) retrieved from satellite sensors. However, AOD is a columnar measure, whereas PM is a ground observation. Linking AOD and PM remains a challenge for air pollution monitoring. In this study, a back-propagation artificial neural network (BP ANN) algorithm trained with bayesian regularization that benefited from the synergy of satellite- and ground-based observations was developed to estimate PM in eastern China. Correlations between observed and estimated PM (denoted by R) during the period 2007-2008 over seven individual sites were investigated comprehensively in terms of site scale, seasonal scale, particle size, and spatio-temporal scale. With respect to site differences, the Nanning site had the best results with 80.3% of cases having a moderate or strong correlation value. Lushan and Zhengzhou followed with results of 75% and 73.8%, respectively. Furthermore, R exhibited a significant seasonal variation characterized by a maximum (80.2%) during the autumn period, whereas no obvious differences in R for various spatial scales (spatial averaging schemes of MODIS AOD) were observed. Likewise, the ratio value for daily averaging (64.7%) was found to be better than those for the two hourly temporal averaging schemes (i.e., 61.1% for HA1 and 58.3% for HA2). In addition, PM(1) estimated from the ANN algorithm developed in this study had slightly higher R values than did PM(10) and PM(2.5). The planetary boundary layer (PBL) effect on PM estimation was decreasing R with increasing height of the PBL, which is consistent with previous studies. Comparisons of observed versus estimated PM(10) mass time series implied that the ANN algorithm basically reproduced the observed PM concentration. However, PM mass at certain sites may be underestimated under the condition of high observed PM concentrations.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.scitotenv.2012.06.033 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A comprehensive review of computational diagnostic techniques for lymphedema.
Prog Biomed Eng (Bristol)
January 2025
Amrita Vishwa Vidyapeetham, Center for Wireless Networks & Applications (WNA), Amrita Vishwa Vidyapeetham Amritapuri, Kollam, India, Kollam, 690525, INDIA.
Lymphedema is localized swelling due to lymphatic system dysfunction, often affecting arms and legs due to fluid accumulation. It occurs in 20% to 94% of patients within 2 to 5 years after breast cancer treatment, with around 20% of women developing breast cancer-related lymphedema (BCRL). This condition involves the accumulation of protein-rich fluid in interstitial spaces, leading to symptoms like swelling, pain, and reduced mobility that significantly impact quality of life.
View Article and Find Full Text PDFSwin UNETR Segmentation with Automated Geometry Filtering for Biomechanical Modeling of Knee Joint Cartilage.
Ann Biomed Eng
January 2025
Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, CCIT216, 2500 University Drive NW, Calgary, AB, T2N 1N4, Canada.
Purpose: Simulation studies, such as finite element (FE) modeling, offer insights into knee joint biomechanics, which may not be achieved through experimental methods without direct involvement of patients. While generic FE models have been used to predict tissue biomechanics, they overlook variations in population-specific geometry, loading, and material properties. In contrast, subject-specific models account for these factors, delivering enhanced predictive precision but requiring significant effort and time for development.
View Article and Find Full Text PDFAssessment of groundwater chemistry to predict arsenic contamination from a canal commanded area: applications of different machine learning models.
Environ Geochem Health
January 2025
School of Environmental Science and Engineering, Shandong University, Qingdao, 266237, China.
Groundwater arsenic (As), contamination is a significant issue worldwide including China and Pakistan, particularly in canal command areas. In this study, 131 groundwater samples were collected, and three machine learning models [Random Forest (RF), Logistic Regression (LR), and Artificial Neural Network (ANN)] were employed to predict As concentration. Descriptive statistics helped to conclude that all of the samples were inside the permitted limit of WHO for pH, Ca, Mg, Turbidity, Cl, K, Na, SO, NO, F and beyond limit of WHO for EC, HCO, TDS, and As.
View Article and Find Full Text PDFAutomated Detection of Isolated REM Sleep Behavior Disorder Using Computer Vision.
Ann Neurol
January 2025
Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY.
Objective: Isolated rapid eye movement (REM) sleep behavior disorder (iRBD) is, in most cases, an early stage of Parkinson's disease or related disorders. Diagnosis requires an overnight video-polysomnogram (vPSG), however, even for sleep experts, interpreting vPSG data is challenging. Using a 3D camera, automated analysis of movements has yielded high accuracy.
View Article and Find Full Text PDFBiomarkers.
Alzheimers Dement
December 2024
Memory and Aging Center, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, USA.
Background: The timing of tau-PET accumulation and cognitive decline in sporadic early-onset Alzheimer's disease (eoAD, age-at-onset<65) has not been established and is needed to optimize tau-PET as an outcome measure in clinical trials. Here we leverage large-sample, longitudinal data from the Longitudinal Early-onset Alzheimer's Disease Study (LEADS) to model tau-PET accumulation in three regions relative to cognitive decline.
Method: Longitudinal [F]Flortaucipir-PET (FTP) and CDR-SB scores were acquired in 195 amyloid-PET-positive, sporadic eoAD patients with MCI or mild dementia due to AD at baseline (Table 1).
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!