A Random Forest Approach to Estimate Daily Particulate Matter, Nitrogen Dioxide, and Ozone at Fine Spatial Resolution in Sweden

Stafoggia, Massimo; Johansson, Christer; Glantz, Paul; Renzi, Matteo; Shtein, Alexandra; Hoogh, Kees de; Kloog, Itai; Davoli, Marina; Michelozzi, Paola; Bellander, Tom

doi:10.3390/atmos11030239

Cited by 60 publications

(31 citation statements)

References 47 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jain et al [ 25 ] purpose dynamic weighing scheme for RF using the correlation between decision tree and data samples. In the global problem field, Stafoggia et al [ 26 ] estimate daily particulate matter for weather forecasting by RF. Modeling the global forest area by RF is the main target of [ 27 ].…”

Section: Related Workmentioning

confidence: 99%

“…At each instant n, the action probability vector pi(n) is updated by the linear learning algorithm given in equation ( 13) if the chosen action ai(k) is rewarded by the environment, and it is updated according to equation ( 14) if the chosen action is penalized [104]. [11], [12], [13] Global problem [26], [27], [28] Healthcare [32], [33], [34], [35], [36], [41], [98], [37], [39], [40], [42], [43], [45], [46], [47], [48], [49], [50], [51], Industrial [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62] Network [63], [67], [68], [69], [99], [100] Physics [71], [72] Text processing …”

Section: Learning Automatamentioning

confidence: 99%

See 1 more Smart Citation

A New Random Forest Algorithm Based on Learning Automata

Savargiv

Masoumi

Keyvanpour

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The goal of aggregating the base classifiers is to achieve an aggregated classifier that has a higher resolution than individual classifiers. Random forest is one of the types of ensemble learning methods that have been considered more than other ensemble learning methods due to its simple structure, ease of understanding, as well as higher efficiency than similar methods. The ability and efficiency of classical methods are always influenced by the data. The capabilities of independence from the data domain, and the ability to adapt to problem space conditions, are the most challenging issues about the different types of classifiers. In this paper, a method based on learning automata is presented, through which the adaptive capabilities of the problem space, as well as the independence of the data domain, are added to the random forest to increase its efficiency. Using the idea of reinforcement learning in the random forest has made it possible to address issues with data that have a dynamic behaviour. Dynamic behaviour refers to the variability in the behaviour of a data sample in different domains. Therefore, to evaluate the proposed method, and to create an environment with dynamic behaviour, different domains of data have been considered. In the proposed method, the idea is added to the random forest using learning automata. The reason for this choice is the simple structure of the learning automata and the compatibility of the learning automata with the problem space. The evaluation results confirm the improvement of random forest efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Learning Automatamentioning

confidence: 99%

A New Random Forest Algorithm Based on Learning Automata

Savargiv

Masoumi

Keyvanpour

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Random forest (RF)—a machine learning method can be classified as a multivariable method that aggregates the predictions of several regression trees to improve the performance of single regression models. Several studies have been published using RF and other multivariable models to predict missing air pollutants in areas with no or sparse monitoring networks [ 16 , 17 , 19 , 20 , 21 ]. However, this study aims to leverage on the spatial and temporal dependence characteristics of air pollutants [ 22 , 23 ], by combining observed PM 10 data with spatial and temporal predictors as well as chemical transport estimates of PM 10 , ozone (O 3 ) and nitrogen dioxide (NO 2 ) in a RF model to predict missing daily PM 10 observation in some monitoring stations across four provinces of South Africa for years 2010–2017.…”

Section: Introductionmentioning

confidence: 99%

Comparing Methods to Impute Missing Daily Ground-Level PM10 Concentrations between 2010–2017 in South Africa

Arowosegbe

Röösli

Künzli

et al. 2021

IJERPH

Self Cite

View full text Add to dashboard Cite

Good quality and completeness of ambient air quality monitoring data is central in supporting actions towards mitigating the impact of ambient air pollution. In South Africa, however, availability of continuous ground-level air pollution monitoring data is scarce and incomplete. To address this issue, we developed and compared different modeling approaches to impute missing daily average particulate matter (PM10) data between 2010 and 2017 using spatiotemporal predictor variables. The random forest (RF) machine learning method was used to explore the relationship between average daily PM10 concentrations and spatiotemporal predictors like meteorological, land use and source-related variables. National (8 models), provincial (32) and site-specific (44) RF models were developed to impute missing daily PM10 data. The annual national, provincial and site-specific RF cross-validation (CV) models explained on average 78%, 70% and 55% of ground-level PM10 concentrations, respectively. The spatial components of the national and provincial CV RF models explained on average 22% and 48%, while the temporal components of the national, provincial and site-specific CV RF models explained on average 78%, 68% and 57% of ground-level PM10 concentrations, respectively. This study demonstrates a feasible approach based on RF to impute missing measurement data in areas where data collection is sparse and incomplete.

show abstract

“…Air pollution is strongly associated with morbidity and mortality cases across the word, and accurate assessment of its spatial and temporal variation is important for epidemiological studies to estimate the health effects [1]. Air pollution is a major problem faced by the modern civilization having harmful toxicological bearings on the environment and human health [2].…”

Section: Introductionmentioning

confidence: 99%

“…Air pollutant such as nitrogen dioxide (NO 2 ) is tra c generated air pollutant and harmful to human health [7]. There is a paucity in research related to the health effects of NO 2 exposures in smaller urban areas and there is reason to believe that effect of NO 2 vary from urban to non-urban areas [1]. Respiratory diseases are commonly encountered in medicine and pose a very high burden on healthcare infrastructure [8].…”

Section: Introductionmentioning

confidence: 99%

Source Profiling of Air Pollution and its Association with Acute Respiratory Infections in the Himalayan Bound Region of India

Wani

Mishra

Sharma

et al. 2020

Preprint

View full text Add to dashboard Cite

The studies related to air pollution and its association with human health over the mountainous region are of utmost importance, and are sparse especially over the Himalayan region of India. This study gives an understanding of increase in the occurrence of respiratory diseases due to the accumulation of pollutants during winter season in the Himalayan region (Kashmir valley). The linkages between various atmospheric variables and clinically validated data have been done using various datasets procured from the satellite, model reanalysis and surface observations. Monthly managed data from 2013-2017 for upper and lower respiratory tract infections is obtained from the Ministry of health, Government of India. Aerosol optical depth, air temperature, and wind speed are significantly related (p <0.001) to the incidence of acute respiratory infections with its peak during winter. Model derived particulate matters having aerodynamic diameters less than 2.5 µm (PM2.5) shows high contribution of black carbon, organic carbon and sulphate during winter. This is mainly due to the burning of biomass and biofuels (both indoor and outdoor) with low planetary boundary layer height, accumulating high air pollution and deteriorating air quality during winter months that affects the respiratory health of the habitants. The wind roses generated shows the passage of winds from western side of the region surrounded by Pir panjal Himalayan sub division. Concentrated weighted trajectory analysis has shown that most of the winds coming from the western side are taking southward direction before reaching the study area and may be bringing pollutants from Indo-Gangetic Plain. Our study shows that the accumulation of pollutants in the Himalayan valley is owing to the meteorological stability with significant emissions from burning of biomass and biofuels during winter season, that significantly correlated with the incidence of acute respiratory infections in the region.

show abstract

A Random Forest Approach to Estimate Daily Particulate Matter, Nitrogen Dioxide, and Ozone at Fine Spatial Resolution in Sweden

Cited by 60 publications

References 47 publications

A New Random Forest Algorithm Based on Learning Automata

A New Random Forest Algorithm Based on Learning Automata

Comparing Methods to Impute Missing Daily Ground-Level PM10 Concentrations between 2010–2017 in South Africa

Source Profiling of Air Pollution and its Association with Acute Respiratory Infections in the Himalayan Bound Region of India

Contact Info

Product

Resources

About