Spatio-temporal air pollution modelling using a compositional approach

Sánchez-Balseca, Joseph; Foguet, Agustí Pérez

doi:10.1016/j.heliyon.2020.e04794

Cited by 16 publications

(6 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the air density from the ideal gas law was used to transform the concentration from volume to weight (Equation ( 7)). The concentration by weight has absolute units, while the volume concentration has relative units that depend on the temperature [49]. The air density is defined by temperature (T), pressure (P), and the ideal gas constant for dry air (R).…”

Section: Methodology: Proposed Approach Application In Stepsmentioning

confidence: 99%

“…The empirically derived correlation range was defined in km. The spatial distribution of PM 2.5 in places with no monitoring stations was featured using a triangular irregular mesh for monitoring stations of PM 2.5 and a grid of 4 km between each intersection of meteorological data, as proposed by Sánchez-Balseca and Pérez-Foguet (2020) [49].…”

Section: Methodology: Proposed Approach Application In Stepsmentioning

confidence: 99%

“…This empirically derived correlation range is the distance at which the correlation is close to 0.1. For more details, see [34,[47][48][49].…”

Section: Meteorological Datamentioning

confidence: 99%

See 2 more Smart Citations

Compositional Spatio-Temporal PM2.5 Modelling in Wildfires

Sánchez-Balseca

Foguet

2021

Atmosphere

Self Cite

View full text Add to dashboard Cite

Wildfires are natural ecological processes that generate high levels of fine particulate matter (PM2.5) that are dispersed into the atmosphere. PM2.5 could be a potential health problem due to its size. Having adequate numerical models to predict the spatial and temporal distribution of PM2.5 helps to mitigate the impact on human health. The compositional data approach is widely used in the environmental sciences and concentration analyses (parts of a whole). This numerical approach in the modelling process avoids one common statistical problem: the spurious correlation. PM2.5 is a part of the atmospheric composition. In this way, this study developed an hourly spatio-temporal PM2.5 model based on the dynamic linear modelling framework (DLM) with a compositional approach. The results of the model are extended using a Gaussian–Mattern field. The modelling of PM2.5 using a compositional approach presented adequate quality model indices (NSE = 0.82, RMSE = 0.23, and a Pearson correlation coefficient of 0.91); however, the correlation range showed a slightly lower value than the conventional/traditional approach. The proposed method could be used in spatial prediction in places without monitoring stations.

show abstract

Section: Methodology: Proposed Approach Application In Stepsmentioning

confidence: 99%

Section: Methodology: Proposed Approach Application In Stepsmentioning

confidence: 99%

See 1 more Smart Citation

Compositional Spatio-Temporal PM2.5 Modelling in Wildfires

Sánchez-Balseca

Foguet

2021

Atmosphere

Self Cite

View full text Add to dashboard Cite

show abstract

“…This network minimizes parameter complexity, in contrast to others. Foguet, 2020). Discovering connections between distant events is very difficult using the BPTT methods due to its susceptibility to vanishing gradients caused by several derivative runs, which yields very little update.…”

Section: Rnn: Recurrent Neural Networkmentioning

confidence: 99%

“…Relationships are discovered using RNN using an activation function that is nonlinear, and the backpropagation process is used to update network values. (Sánchez-Balseca & Pérez-Foguet, 2020). Discovering connections between distant events is very difficult using the BPTT methods due to its susceptibility to vanishing gradients caused by several derivative runs, which yields very little update.…”

mentioning

confidence: 99%

Deep Learning Techniques for Air Quality Prediction: A Focus on PM2.5 and Periodicity

Shankar,

Arasu

2023

Migrat. Lett.

View full text Add to dashboard Cite

The rapid increase in traffic, urbanization, and industrial expansion has all contributed to a decrease in air quality, which has a vital impact on both the long-term feasibility of the environment and the health of humans, particularly in industrialized nations. Numerous studies have explored using machine learning for air quality forecasting to reduce pollution. While shallow machine learning architectures offer less accurate forecasts, deep learning, a recent advancement in computational intelligence, has immense potential in predicting air quality. Deep learning frameworks can identify intricate correlations and patterns in data on air quality, resulting in more accurate and dependable predictions. Several aspects, including climatic conditions, emission sources, and geographical characteristics, may be considered by these models, which can help one better understand and anticipate air pollution levels. This research investigates deep learning applications' periodic changes in air quality. Hybrid deep learning methods utilize optimization, data decomposition, and correlation evaluation between PM2.5 particles and other factors to overcome limitations. This study contrasts various deep learning algorithms for forecasts of air quality and demonstrates that hybrid deep learning is more accurate compared to each model alone at predicting future periods of air quality. It proposes future research directions for the future generation of models. The literature summary provides valuable insights for academics seeking future studies in this field.

show abstract

Advances in Air Quality Monitoring: A Comprehensive Review of Algorithms for Imaging and Sensing Technologies

Elbestar,

Aly,

Ghannam

2024

Advanced Sensor Research

View full text Add to dashboard Cite

Air pollution is a major global concern, leading to serious health problems and environmental damage. This article provides a comprehensive review of historical and current methods used to monitor and predict air quality. It emphasizes the ongoing need for better monitoring techniques. 47 studies are critically analyzed, and computational advancements in air quality monitoring are categorized into sensor‐based and image‐based techniques. This review reveals that sensor‐based algorithmic methods, representing 62% of the reviewed literature, are reliable but often lack flexibility and real‐time monitoring capabilities. On the other hand, image‐based techniques, while innovative, are limited by the size and diversity of datasets, primarily functioning only during daylight hours. To address these limitations, a hybrid approach that integrates both sensor and image‐based methods is proposed. This aims to enhance monitoring by allowing users to visualize pollution levels through an augmented reality layer. The proposed model seeks to provide mobile users with the ability to accurately monitor surrounding air quality by establishing a comprehensive image‐based dataset that includes various features not previously considered in existing datasets.

show abstract

Spatio-temporal air pollution modelling using a compositional approach

Cited by 16 publications

References 65 publications

Compositional Spatio-Temporal PM2.5 Modelling in Wildfires

Compositional Spatio-Temporal PM2.5 Modelling in Wildfires

Deep Learning Techniques for Air Quality Prediction: A Focus on PM2.5 and Periodicity

Advances in Air Quality Monitoring: A Comprehensive Review of Algorithms for Imaging and Sensing Technologies

Contact Info

Product

Resources

About