A Bayesian Spatio-temporal Model for NO2 in Seoul  

Oleh:

Yoon, Sang Hoo ; Song, Ho Cheon ; Na, Myoung Hwan ; Kim, Ja Hye ; Park, Sung Ho

Jenis: Article from Proceeding
Dalam koleksi: 12th ANQ Congress in Singapore, 5-8 Agustus 2014, page 1-7.
Topik: Bayesian inference; Gaussian predictive process; nitrogen dioxide; space-time modelling; Auto-regressive model
Fulltext: QP2-5.3-P0309.pdf (589.09KB)

Isi artikel

Amount of spatial data is increasing exponentially more recent times, and in many of these cases temporal data are also obtained, for example telecommunication or web traffic data. Analysis of data that takes into account both space and time is a very complex problem. Recent advances in computer technology, a space-time models under the hierarchical Bayesian setup can be handled. We model daily average nitrogen dioxide (NO2) data obtained from 25 air monitoring sites in Seoul between 2003 and 2010. The Independent Gaussian process model and the auto-regressive model was considered within a hierarchical Bayesian framework and Markov chain Monte Carlo techniques. The predictive distribution of NO2 presents the uncertainty of NO2 at any unmonitored location and trends in spatial patterns. It also can be a basic information for the level of NO2 to assess the impact on human health and the environment

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali