scholarly journals Correlation networks of air particulate matter ($$\hbox {PM}_{2.5}$$): a comparative study

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Dimitrios M. Vlachogiannis ◽  
Yanyan Xu ◽  
Ling Jin ◽  
Marta C. González
Keyword(s):  
Air Quality ◽  
Time Series Data ◽  
Series Data ◽  
Pollution Transport ◽  
Concentration Data ◽  
Significant Drop ◽  
Pm 2.5 ◽  
Correlation Networks ◽  
Spatial Coverage ◽  
Haze Pollution

AbstractOver the last decades, severe haze pollution constitutes a major source of far-reaching environmental and human health problems. The formation, accumulation and diffusion of pollution particles occurs under complex temporal scales and expands throughout a wide spatial coverage. Seeking to understand the transport patterns of haze pollutants in China, we review a proposed framework of time-evolving directed and weighted air quality correlation networks. In this work, we evaluate monitoring stations’ time-series data from China and California, to test the sensitivity of the framework to region size, climate and pollution magnitude across multiple years (2014–2020). We learn that the use of hourly $$\hbox {PM}_{2.5}$$ PM 2.5 concentration data is needed to detect periodicities in the positive and negative correlations of the concentrations. In addition, we show that the standardization of the correlation function method is required to obtain networks with more meaningful links when evaluating the dispersion of a severe haze event at the North China Plain or a wildfire event in California during December 2017. Post COVID-19 outbreak in China, we observe a significant drop in the magnitude of the assigned weights, indicating the improved air quality and the slowed transport of $$\hbox {PM}_{2.5}$$ PM 2.5 due to the lockdown. To identify regions where pollution transport is persistent, we extend the framework, partitioning the dynamic networks and reducing the networks’ complexity through node subsampling. The end result separates the temporal series of $$\hbox {PM}_{2.5}$$ PM 2.5 in set of regions that are similarly affected through the year.

scholarly journals PREDICTION OF OZONE (O3) VALUES USING SUPPORT VECTOR REGRESSION METHOD

2021 ◽  
Vol 7 (4) ◽  
pp. 81-88
Author(s):  
Chasandra Puspitasari ◽  
Nur Rokhman ◽  
Wahyono
Keyword(s):  
Air Quality ◽  
Support Vector Regression ◽  
Time Series Data ◽  
Motor Vehicles ◽  
Primary Data ◽  
Series Data ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Linear Kernel ◽  
Air Quality Prediction

A large number of motor vehicles that cause congestion is a major factor in the poor air quality in big cities. Ozone (O3) is one of the main indicators in measuring the level of air pollution in the city of Surabaya to find out how air quality. Prediction of Ozone (O3) value is important as a support for the community and government in efforts to improve the air quality. This study aims to predict the value of Ozone (O3) in the form of time series data using the Support Vector Regression (SVR) method with the Linear, Polynomial, RBF, and ANOVA kernels. The data used in this study are 549 primary data from the daily average of ozone (O3) value of Surabaya in the period 1 July 2017 - 31 December 2018. The data will be used in the training and testing process until prediction results are obtained. The results obtained from this study are the Linear kernel produces the best prediction model with a MAPE value of 21.78% with a parameter value 𝜆 = 0.3; 𝜀 = 0.00001; cLR = 0.005; and C = 0.5. The results of the Polynomial kernel are not much different from the Linear kernel which has a MAPE value of 21.83%. While the RBF and ANOVA kernels each produce a model with MAPE value of 24.49% and 22.0%. These results indicate that the SVR method with the kernels used can predict Ozone values quite well.

scholarly journals Finding the signal in the noise: objective data-selection criteria improve the assessment of western Baltic spring-spawning herring

2009 ◽  
Vol 66 (8) ◽  
pp. 1673-1680 ◽  
Author(s):  
Mark R. Payne ◽  
Lotte Worsøe Clausen ◽  
Henrik Mosegaard
Keyword(s):  
Selection Criteria ◽  
Time Series Data ◽  
Stock Assessment ◽  
Clupea Harengus ◽  
Data Selection ◽  
Series Data ◽  
Distribution Area ◽  
Fish Stock ◽  
Objective Data ◽  
Spatial Coverage

Abstract Payne, M. R., Clausen, L. W., and Mosegaard, H. 2009. Finding the signal in the noise: objective data-selection criteria improve the assessment of western Baltic spring-spawning herring. – ICES Journal of Marine Science, 66: 1673–1680. In the art of fish-stock assessment, it is common practice to include all available data without properly testing their validity in terms of their signal-to-noise ratio. The western Baltic spring-spawning herring (Clupea harengus) stock has been historically difficult to assess in a reliable manner. The population is spread between the Skagerrak, Kattegat, the Danish islands, and the western Baltic, but the distribution depends on age and season. Although the distribution area is covered by five separate surveys, none covers the entire stock. Using all time-series data may cause high noise levels and could lead to a poor-quality assessment. We examine the temporal and spatial coverage of each survey in terms of current biological understanding of stock distribution and, employing the observed internal consistency between age classes within cohorts as additional criteria, select the most appropriate data subsets. Assessments based on the revised dataset show greatly improved quality in terms of both accuracy and precision. The results highlight the often-ignored principle that a judicious choice of input data, based on rational and justifiable selection criteria, can enhance the ultimate quality of a stock assessment.

scholarly journals Effect of COVID-19 pandemic induced lockdown (general holiday) on air quality of Dhaka City

2020 ◽  
Author(s):  
Md. Saiful Islam ◽  
Tahmid Anam Chowdhury
Keyword(s):  
Time Series ◽  
Air Quality ◽  
Environmental Protection Agency ◽  
Time Series Data ◽  
Urban Air Pollution ◽  
Motor Vehicles ◽  
Series Data ◽  
Dhaka City ◽  
Criteria Pollutants ◽  
Us Epa

Abstract A worldwide pandemic of COVID-19 has forced to implement a lockdown during April-May 2020 by restricting people's movement, the shutdown of industries and motor vehicles in Dhaka, Bangladesh, to contain the virus. This type of strict measures returned an outcome of the reduction of urban air pollution around the world. The present study aims to investigate the reduction of the concentration of pollutants in the air of Dhaka City and the reduction of the Air Quality Index (AQI). Necessary time-series data of the concentration of PM2.5, NO2, SO2, and CO have been collected from the archive of the U.S. Environmental Protection Agency (US EPA) and Sentinel-5P. The time-series data have been analyzed by descriptive statistics, and AQI is calculated following an appropriate formula suggested by US EPA based on the criteria pollutants. The study found that the concentrations of PM2.5, NO2, SO2, and CO have been reduced by 23, 30, 07, and 07% during April-May 2020, respectively, compared with the preceding year's concentration. Moreover, the AQI has also been reduced by up to 35% than the previous year in April-May 2020. However, the magnitude of pollution reduction in Dhaka is lower than other cities and countries globally, including Delhi, Sao Paulo, Wuhan, Spain, Italy, USA, etc. The main reason includes the poor implementation of lockdown, especially in the first week of April and the second fortnight of May. The findings will be useful for policymakers to find a way to control the pollution sources to enhance Dhaka's air quality.

scholarly journals Biogeochemical variations at the Porcupine Abyssal Plain Sustained Observatory (PAP-SO) in the northeast Atlantic Ocean, from weekly to inter-annual time scales

2014 ◽  
Vol 11 (8) ◽  
pp. 12415-12439
Author(s):  
S. E. Hartman ◽  
Z.-P. Jiang ◽  
D. Turk ◽  
R. S. Lampitt ◽  
H. Frigstad ◽  
...  
Keyword(s):  
Wind Speed ◽  
Time Series Data ◽  
Mixed Layer Depth ◽  
Co2 Flux ◽  
Abyssal Plain ◽  
Carbon Dioxide Partial Pressure ◽  
Series Data ◽  
Concentration Data ◽  
Northeast Atlantic

Abstract. We present high-resolution autonomous measurements of carbon dioxide partial pressure p(CO2) taken in situ at the Porcupine Abyssal Plain sustained observatory (PAP-SO) in the Northeast Atlantic (49° N, 16.5° W; water depth of 4850 m) for the period 2010 to 2012. Measurements of p(CO2) made at 30 m depth on a sensor frame are compared with other autonomous biogeochemical measurements at that depth (including chlorophyll a-fluorescence and nitrate concentration data) to analyse weekly to seasonal controls on p(CO2) flux in the inter-gyre region of the North Atlantic. Comparisons are also made with in situ regional time-series data from a ship of opportunity and mixed layer depth (MLD) measurements from profiling Argo floats. There is a persistent under saturation of CO2 in surface waters throughout the year which gives rise to a perennial CO2 sink. Comparison with an earlier dataset collected at the site (2003 to 2005) confirms seasonal and inter-annual changes in surface seawater chemistry. There is year-to-year variability in the timing of stratification and deep winter mixing. The 2010 to 2012 period shows an overall increase in p(CO2) values when compared to the 2003–2005 period. This is despite similar surface temperature, wind speed and MLD measurements between the two periods of time. Future work should incorporate daily CO2 flux measurements made using CO2 sensors at 1 m depth and the in situ wind speed data now available from the UK Met Office Buoy.

scholarly journals Personalized Network Modeling in Psychopathology: The Importance of Contemporaneous and Temporal Connections

2017 ◽  
Author(s):  
Sacha Epskamp ◽  
Claudia van Borkulo ◽  
Date C. van der Veen ◽  
Michelle Servaas ◽  
Adela-Maria Isvoranu ◽  
...  
Keyword(s):  
Time Series ◽  
Partial Correlation ◽  
Time Series Data ◽  
Recent Literature ◽  
Series Data ◽  
Network Structures ◽  
Cross Sectional ◽  
Correlation Networks ◽  
Relevant Variables ◽  
Analysis Of Time Series

Recent literature has introduced (1) the network perspective to psychology, and (2) collection of time-series data in order to capture symptom fluctuations and other time varying factors in daily life. Combining these trends allows for the estimation of intra-individual network structures. We argue that these networks can be directly applied in clinical research and practice as hypothesis generating structures. Two networks can be computed: a temporal network, in which one investigates if symptoms (or other relevant variables) predict one another over time, and a contemporaneous network, in which one investigates if symptoms predict one another in the same window of measurement. The contemporaneous network is a partial correlation network, which is emerging in the analysis of cross-sectional data but is not yet utilized in the analysis of time-series data. We explain the importance of partial correlation networks and exemplify the network structures on time-series data of a psychiatric patient.

scholarly journals Vayu: An Open-Source Toolbox for Visualization and Analysis of Crowd-Sourced Sensor Data

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7726
Author(s):  
Sachit Mahajan
Keyword(s):  
Air Quality ◽  
Open Source ◽  
Time Series Data ◽  
Sensor Data ◽  
Quality Data ◽  
Sensor Technology ◽  
Data Conversion ◽  
Series Data ◽  
Monitoring Networks ◽  
Systematic Analysis

Recent advances in sensor technology and the availability of low-cost and low-power sensors have changed the air quality monitoring paradigm. These sensors are being widely used by scientists and citizens for monitoring air quality at finer spatial-temporal resolution. Such practices are opening up opportunities to enhance the traditional monitoring networks, but at the same time, these sensors are producing large data sets that can become overwhelming and challenging when it comes to the scientific tools and skills required to analyze the data. To address this challenge, an open-source, robust, and cross-platform sensor data analysis toolbox called Vayu is developed that allows researchers and citizens to do detailed and reproducible analyses of air quality data. Vayu combines the power of visualization and statistical analysis using a simple and intuitive graphical user interface. Additionally, it offers a comprehensive set of tools for systematic analysis such as data conversion, interpolation, aggregation, and prediction. Even though Vayu was developed with air quality research in mind, it can be used to analyze different kinds of time-series data.

scholarly journals Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks

2021 ◽  
Vol 18 (22) ◽  
pp. 12213
Author(s):  
Taesung Kim ◽  
Jinhee Kim ◽  
Wonho Yang ◽  
Hunjoo Lee ◽  
Jaegul Choo
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Air Quality ◽  
Time Series Data ◽  
Quality Data ◽  
Series Data ◽  
Missing Value ◽  
Missing Value Imputation ◽  
Spatio Temporal ◽  
Air Quality Data

To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based missing value imputation models have been proposed. However, often they are barely interpretable, which makes it difficult to analyze the imputed data. Thus, we propose a novel deep learning-based imputation model that achieves high interpretability as well as shows great performance in missing value imputation for spatio-temporal data. We verify the effectiveness of our method through quantitative and qualitative results on a publicly available air-quality dataset.

scholarly journals Changes in Nutrient Concentrations in Shenzhen Bay Detected Using Landsat Imagery between 1988 and 2020

2021 ◽  
Vol 13 (17) ◽  
pp. 3469
Author(s):  
Jingjing Huang ◽  
Difeng Wang ◽  
Fang Gong ◽  
Yan Bai ◽  
Xianqiang He
Keyword(s):  
Remote Sensing ◽  
Water Quality ◽  
Hong Kong ◽  
Time Series Data ◽  
Inorganic Nitrogen ◽  
Landsat Imagery ◽  
Machine Learning Algorithms ◽  
Series Data ◽  
Nutrient Concentrations ◽  
Spatial Coverage

Shenzhen Bay (SZB), situated between Shenzhen and Hong Kong, is a typical bay system. The water quality of the bay is notably affected by domestic and industrial discharge. Rivers and various types of drainage outlets carry terrestrial pollutants into SZB, resulting in elevated concentrations of nitrogen and phosphorous as well as relatively poor water quality. For over 200 years, Hong Kong has practiced oyster farming within brackish estuarine waters. Oyster farming is a type of mariculture which includes oyster breeding in oyster rafts. Remote sensing is a monitoring technique characterized by large spatial coverage, high traceability, and low cost, making it advantageous over conventional point-based and ship-borne monitoring methods. In this study, remote-sensing models were established using machine-learning algorithms to retrieve key water-quality factors (dissolved inorganic nitrogen (DIN) and orthophosphate-phosphorous (PO4_P) concentrations, CDIN and CPO4_P, respectively) from long-term time-series data acquired by the Landsat satellites. (1) Spatially, the water quality in Inner SZB was worse than that in Outer SZB. (2) The water quality temporarily deteriorated between the end of the 20th century and the beginning of the 21st century; then it gradually improved in the late 2000s. (3) Monitoring the water quality in an oyster-farming area revealed that oyster farming did not adversely affect the water quality. (4) The result of monitoring the water quality in river estuaries in SZB shows that water quality was mainly affected by river input.

Sign in / Sign up

Export Citation Format

Share Document