Dataset Information

Predicting monthly high-resolution PM2.5 concentrations with random forest model in the North China Plain.

ABSTRACT: Exposure to fine particulate matter (PM2.5) remains a worldwide public health issue. However, epidemiological studies on the chronic health impacts of PM2.5 in the developing countries are hindered by the lack of monitoring data. Despite the recent development of using satellite remote sensing to predict ground-level PM2.5 concentrations in China, methods for generating reliable historical PM2.5 exposure, especially prior to the construction of PM2.5 monitoring network in 2013, are still very rare. In this study, a high-performance machine-learning model was developed directly at monthly level to estimate PM2.5 levels in North China Plain. We developed a random forest model using the latest Multi-angle implementation of atmospheric correction (MAIAC) aerosol optical depth (AOD), meteorological parameters, land cover and ground PM2.5 measurements from 2013 to 2015. A multiple imputation method was applied to fill the missing values of AOD. We used 10-fold cross-validation (CV) to evaluate model performance and a separate time period, January 2016 to December 2016, was used to validate our model's capability of predicting historical PM2.5 concentrations. The overall model CV R2 and relative prediction error (RPE) were 0.88 and 18.7%, respectively. Validation results beyond the modeling period (2013-2015) shown that this model can accurately predict historical PM2.5 concentrations at the monthly (R2?=?0.74, RPE?=?27.6%), seasonal (R2?=?0.78, RPE?=?21.2%) and annual (R2?=?0.76, RPE?=?16.9%) level. The annual mean predicted PM2.5 concentration from 2013 to 2016 in our study domain was 67.7 ?g/m3 and Southern Hebei, Western Shandong and Northern Henan were the most polluted areas. Using this computationally efficient, monthly and high-resolution model, we can provide reliable historical PM2.5 concentrations for epidemiological studies on PM2.5 health effects in China.

SUBMITTER: Huang K

PROVIDER: S-EPMC6690389 | biostudies-literature | 2018 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting monthly high-resolution PM2.5 concentrations with random forest model in the North China Plain.

Huang Keyong K Xiao Qingyang Q Meng Xia X Geng Guannan G Wang Yujie Y Lyapustin Alexei A Gu Dongfeng D Liu Yang Y

Environmental pollution (Barking, Essex : 1987) 20180711 Pt A

Exposure to fine particulate matter (PM2.5) remains a worldwide public health issue. However, epidemiological studies on the chronic health impacts of PM2.5 in the developing countries are hindered by the lack of monitoring data. Despite the recent development of using satellite remote sensing to predict ground-level PM2.5 concentrations in China, methods for generating reliable historical PM2.5 exposure, especially prior to the construction of PM ...[more]

PMID: 30025341

Similar Datasets

Project description:Background: Responses to hypoxia have been investigated in many species; however, comparative study between conspecific geographical populations in different altitude regions is rare, especially for invertebrates . The migratory locust, Locusta migratoria, is widely distributed both on high-altitude Tibetan Plateau (TP) and on low-altitude North China Plain (NP). TP locusts have inhabited Tibetan Plateau since Quaternary glaciations events and thus probably have evolved superior capacity to deal with hypoxia. Results: Here we compared the hypoxic responses of TP and NP locusts from morphological, behavioral and physiological perspectives. We found that TP locusts were more tolerant of extreme hypoxia than NP locusts, with a lower proportion exhibiting stupor, a faster recovery time, and higher respiration rates. We compared the transcriptional profiles of field TP and NP locusts and found that their differences were possibly attributed to a combination of multiple factors, e.g. oxygen, UV radiation, temperature and nutrition. To evaluate why TP locusts respond to extreme hypoxia differently from NP locusts, we subjected them to extreme hypoxia and compared their transcriptional responses. We found that the aerobic metabolism was more active in TP locusts than in NP locusts. RNAi disruption of PDHE1b, an entry gene from glycolysis to TCA cycle, increased the ratio of stupor in Tibetan locusts and decreased the ATP content of Tibetan locusts in hypoxia, confirming the significant importance of this metabolic branch for TP locusts to conquer hypoxia. Conclusions: Here we show that TP locusts are better tolerant of hypoxia than NP locusts and the better capacity to modulate primary metabolism in TP locusts contributes to their superior tolerance of hypoxia compared to NP locusts. FIELD POPULATION: TP locusts vs. NP locusts;direct comparison on 6 separate microarrays; each microarray compares one biological replicate; each biological replicate contains 10 individuals. LAB POPULATION: hypoxia-treated TP locusts vs TP locusts in normoxia; hypoxia-treated NP locusts vs NP locusts in normoxia; direct comparison on 6 separate microarrays; each microarray compares one biological replicate; each biological replicate contains 10 individuals.

Dataset Information

Predicting monthly high-resolution PM2.5 concentrations with random forest model in the North China Plain.

Publications

Predicting monthly high-resolution PM<sub>2.5</sub> concentrations with random forest model in the North China Plain.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets