東華大學圖書館 |

Land-Use Regression and Spatio-Temporal Hierarchical Models for Environmental Processes.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Land-Use Regression and Spatio-Temporal Hierarchical Models for Environmental Processes./
作者:	Zapata-Marin, Sara.
面頁冊數:	1 online resource (208 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-10, Section: A.
Contained By:	Dissertations Abstracts International84-10A.
標題:	Air pollution. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30346955click for full text (PQDT)
ISBN:	9798377672135

Land-Use Regression and Spatio-Temporal Hierarchical Models for Environmental Processes.
Zapata-Marin, Sara.

Land-Use Regression and Spatio-Temporal Hierarchical Models for Environmental Processes. - 1 online resource (208 pages)

Source: Dissertations Abstracts International, Volume: 84-10, Section: A.

Thesis (Ph.D.)--McGill University (Canada), 2022.

Includes bibliographical references

Land-use regression is a popular method used to describe the spatial variability of different environmental processes using local variables. However, there are situations in which there might be some complex spatio-temporal structure left after accounting for land-use variables. In this work, three different Bayesian hierarchical models are proposed to model the spatial and spatio-temporal dispersion of air pollutants and aeroallergens within cities. Bayesian inference can easily accommodate complex interactions while naturally accounting for uncertainties in the estimation of unknowns in the model when performing predictions.In the first study, a spatial hierarchical model is used to analyze the concentration of volatile organic compounds (VOCs) in Montreal, Canada. The data consists of concentration measurements of five VOCs measured over two-week periods for three monitoring campaigns between 2005 and 2006 over 130 locations in the city. The five VOCs of interest are: benzene, decane, ethylbenzene, hexane, and trimethylbenzene. Four different models are fitted to each of the five VOCs. These models extend land-use regression by accounting for any spatial structure left after including the covariates while also capturing the across campaign variation through an indicator variable or campaign-specific coefficients. Predicted surfaces are obtained for each campaign. For all VOCs higher levels are found during the December campaign, and the predicted areas with the highest levels correspond to multiple sections of major highways.For the second and third studies, we have available data on the daily and weekly measurements of pollen concentration in Toronto, Canada collected in 2018. The measurements consist of tree, weed, grass, and total pollen concentration at 18 monitoring sites and were obtained daily for eleven of these sites and weekly for the other seven sites.In the second study, the weekly concentration of each of the four pollen types is modeled. Instead of considering the temporal window that only has positive values, that is, removing the zeros, a hurdle model is proposed to account for the high number of measurements equal to zero. This structure allows for the estimation of the probability of the pollen concentration being equal to zero at any given week, which provides further information on temporal windows with positive concentrations of the different types of pollen. Additionally, a dynamic linear model is used to capture the weekly trend of pollen concentration in the city.In the third study, the daily concentration of total pollen is modeled. Rather than aggregating the data to the weekly scale, a temporal misalignment model is proposed to account for the difference in scale and to take advantage of the daily measurements. Using the properties of dynamic linear models and the multivariate normal distribution, a spatio-temporal model to account for temporal misalignment is proposed. This model allows to estimate the fine-scale measurements at locations where only coarse-scale observations were available. Additionally, the model is fitted to artificial data with different temporal structures, including trend and seasonality.The predicted surfaces obtained in these three studies will help inform future health-related studies. Furthermore, the methods proposed here are flexible, easily adaptable, and can improve our understanding of similar environmental processes.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798377672135Subjects--Topical Terms:

888377
Air pollution.
Index Terms--Genre/Form:

542853
Electronic books.

Land-Use Regression and Spatio-Temporal Hierarchical Models for Environmental Processes.
LDR:08784nmm a2200397K 4500 001 2363511
005 20231127093425.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798377672135
035 $a (MiAaPQ)AAI30346955
035 $a (MiAaPQ)McGill_nz806532r
035 $a AAI30346955
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Zapata-Marin, Sara. $3 3704273
245 1 0 $a Land-Use Regression and Spatio-Temporal Hierarchical Models for Environmental Processes.
264 0 $c 2022
300 $a 1 online resource (208 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-10, Section: A.
500 $a Advisor: Schmidt, Alexandra M.
502 $a Thesis (Ph.D.)--McGill University (Canada), 2022.
504 $a Includes bibliographical references
520 $a Land-use regression is a popular method used to describe the spatial variability of different environmental processes using local variables. However, there are situations in which there might be some complex spatio-temporal structure left after accounting for land-use variables. In this work, three different Bayesian hierarchical models are proposed to model the spatial and spatio-temporal dispersion of air pollutants and aeroallergens within cities. Bayesian inference can easily accommodate complex interactions while naturally accounting for uncertainties in the estimation of unknowns in the model when performing predictions.In the first study, a spatial hierarchical model is used to analyze the concentration of volatile organic compounds (VOCs) in Montreal, Canada. The data consists of concentration measurements of five VOCs measured over two-week periods for three monitoring campaigns between 2005 and 2006 over 130 locations in the city. The five VOCs of interest are: benzene, decane, ethylbenzene, hexane, and trimethylbenzene. Four different models are fitted to each of the five VOCs. These models extend land-use regression by accounting for any spatial structure left after including the covariates while also capturing the across campaign variation through an indicator variable or campaign-specific coefficients. Predicted surfaces are obtained for each campaign. For all VOCs higher levels are found during the December campaign, and the predicted areas with the highest levels correspond to multiple sections of major highways.For the second and third studies, we have available data on the daily and weekly measurements of pollen concentration in Toronto, Canada collected in 2018. The measurements consist of tree, weed, grass, and total pollen concentration at 18 monitoring sites and were obtained daily for eleven of these sites and weekly for the other seven sites.In the second study, the weekly concentration of each of the four pollen types is modeled. Instead of considering the temporal window that only has positive values, that is, removing the zeros, a hurdle model is proposed to account for the high number of measurements equal to zero. This structure allows for the estimation of the probability of the pollen concentration being equal to zero at any given week, which provides further information on temporal windows with positive concentrations of the different types of pollen. Additionally, a dynamic linear model is used to capture the weekly trend of pollen concentration in the city.In the third study, the daily concentration of total pollen is modeled. Rather than aggregating the data to the weekly scale, a temporal misalignment model is proposed to account for the difference in scale and to take advantage of the daily measurements. Using the properties of dynamic linear models and the multivariate normal distribution, a spatio-temporal model to account for temporal misalignment is proposed. This model allows to estimate the fine-scale measurements at locations where only coarse-scale observations were available. Additionally, the model is fitted to artificial data with different temporal structures, including trend and seasonality.The predicted surfaces obtained in these three studies will help inform future health-related studies. Furthermore, the methods proposed here are flexible, easily adaptable, and can improve our understanding of similar environmental processes.
520 $a La modelisation de l'occupation de l'espace par la regression est une methode tres repandue et utilisee pour decrire la variabilite spatiale de differents processus environnementaux a l'aide de variables locales. Cependant, une structure spatio-temporelle complexe subsiste apres l'ajustement aux variables d'occupation de l'espace.Dans cette these, trois modeles hierarchiques bayesiens sont proposes pour modeliser la dispersion spatiale et spatio-temporelle des polluants et allergenes aeriens au sein de villes. L'inference bayesienne peut facilement tenir compte des interactions complexes tout en tenant compte naturellement, lors de predictions, du niveau d'incertitude lie a l'estimation d'inconnues dans un modele.Dans le premier projet, un modele spatial hierarchique est utilise pour analyser la concentration de composes organiques volatils (COVs) a Montreal, au Canada. Les donnees sont constituees de mesures de concentrations de cinq COVs relevees au cours de periodes de deux semaines lors de trois campagnes de surveillance sur 130 sites urbains entre 2005 et 2006. Les cinq COVs d'interets sont le benzene, le decane, l'ethylbenzene, l'hexane et le trimethylbenzene. Quatre modeles differents sont consideres pour les cinq COVs. Ces modeles developpent la modelisation de l'occupation de l'espace par la prise en compte de toute structure spatiale qui subsiste apres l'inclusion de variables explicatives; et par leur consideration de la variation inter-campagne au moyen d'une variable indicatrice ou de coefficients propres a chaque campagne de surveillance. Pour tous les COVs, les niveaux les plus eleves sont releves au cours d'une campagne en decembre et les zones predites avec les plus hauts niveaux correspondent a plusieurs sections de principales autoroutes.Pour les deuxieme et troisieme projets, nous utilisons des donnees quotidiennes et hebdomadaires liees a la concentration de pollen mesuree a Toronto, au Canada en 2018. Les mesures concernent la concentration de pollen d'arbre, d'herbes, de gazon et total sur 18 sites de surveillance, qui ont ete relevees quotidiennement sur onze de ces sites et hebdomadairement sur les sept autres.Dans le deuxieme projet, la concentration hebdomadaire de chacun des quatre types de pollen est modelisee. Au lieu de ne considerer que la periode ou les valeurs sont positives, c'est-a-dire d'enlever les zeros, un modele hurdle est propose afin de considerer les nombreuses mesures egales a zero. Cela permet l'estimation de la probabilite que la concentration de pollen soit nulle, ce qui donne davantage d'information sur les periodes avec des concentrations positives des differents types de pollen. De plus, un modele lineaire dynamique est utilise pour representer la tendance hebdomadaire de la concentration de pollen en ville.Dans le troisieme projet, la concentration quotidienne du pollen total est modelisee. Plutot que d'agreger les donnees a une echelle hebdomadaire, un modele de desalignement temporel est propose afin de considerer les differences d'echelle et afin de profiter des mesures quotidiennes. En utilisant les proprietes des modeles lineaires dynamiques et de la distribution normale multivariee, un modele spatio-temporel qui tient compte du desalignement temporel, est propose. Ce modele estime des mesures a une echelle precise a des localisations ou seules des mesures d'echelle plus grossieres etaient relevees. De plus, ce modele est ajuste a des donnees artificielles presentant differentes structures temporelles telles qu'une tendance generale et une saisonnalite.Les surfaces predites dans ces projets aideront a faconner de futures etudes en sante. D'autre part, les methodes proposees ici sont flexibles, facilement adaptables et peuvent aider a ameliorer notre comprehension de processus environnementaux similaires. Tous les codes sont disponibles publiquement afin que l'implementation de l'approche proposee dans des situations similaires puisse facilement etre implementee.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Air pollution. $3 888377
650 4 $a Outdoor air quality. $3 3560044
650 4 $a Epidemiology. $3 568544
650 4 $a Climate change. $2 bicssc $3 2079509
650 4 $a Atmospheric chemistry. $3 544140
650 4 $a Atmospheric sciences. $3 3168354
650 4 $a Chemistry. $3 516420
650 4 $a Land use planning. $3 2122760
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0404
690 $a 0766
690 $a 0371
690 $a 0725
690 $a 0485
690 $a 0536
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a McGill University (Canada). $3 1018122
773 0 $t Dissertations Abstracts International $g 84-10A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30346955 $z click for full text (PQDT)