Aims
The emphasis of the meeting is on environmental applications where methodology is drawn from spatial (and possibly temporal) statistics. We are planning to have a mixture of new and experienced researchers in this field. The meeting is partially sponsored by the Environmental Statistics Section of the Royal Statistical Society and the Southampton Statistical Sciences Research Institute (S3RI).
Please note you must book a place for this meeting (see below).
Programme and Abstracts
To display the abstract for each talk, click on the title of the talk.
- 09:30 - 10:00: Coffee and Registration
- 10:00 - 11:20: Session 1 : Biodiversity (Species Abundance)
- 10:00 - 10:40: Alan Gelfand, Latent Spatial Modeling for Species Abundance ---
Download Slides Alan Gelfand, Department of Statistical Science, Duke University
Predicting biodiversity, i.e., the abundance of species, in response to environment is a primary goal of much ecological research. This talk attempts to explain observed abundance using spatial modeling incorporating local environmental features. In particular, it assumes that abundance is available as an ordinal categorical variable which is subject to measurement error. In addition, it recognizes the effect of transformation of the landscape which alters the chance of species presence. Through latent variable specifications in the form of a bivariate spatial process, we are able to infer about potential abundance in the absence of transformation (useful for planning and conservation decisionmaking) as well as to explain observed abundance in the presence of transformation (useful for understanding the spatial variation in abundance). We work with a large data set covering 37,000 minute by minute pixels in the Cape Floristic Region in South Africa. Sampling over these pixels is very irregular but still we have roughly 60,000 sampled sites. We consider spatial analysis of abundance for six species of proteaceae. This is joint work with Avishek Chakraborty.
- 10:40 - 11:20: Mark Brewer, Accounting for observer effort in the spatial modelling of African bird data --- Download Slides
Mark Brewer, Biomathematics and Statistics Scotland (BioSS)
Forecasts of rapid climatic change highlight the importance of gaining an understanding of the relationship between animal populations and climate. Given spatially-referenced data on observer effort and recorded presence of 154 species of bird living in Tanzania's semi-arid habitats between 1960 and 2007, we explore the spatial pattern of distribution change via a Bayesian hierarchical model while modelling observer effort directly. We discuss the estimation of probability of detection and consider methods for relating changes in population locations over time to environmental covariates. The implementation of the model in WinBUGS is discussed.
This is joint work with Colin Beale of the Macaulay Institute.- 11:20 - 11:40: Coffee
- 11:40 - 13:00: Session 2 : Data Assimilation (Downscaling)
- 11:40 - 12:20: Li Chen, Spatial prediction, data assimilation and ensemble adjustment Kalman filter --- Download Slides
Li Chen, Department of Statistics, University of Bristol
This talk gives a brief overview of spatial prediction, data assimilation and Kalman filter type techniques. Particularly, a new approach is presented for data assimilation using the ensemble adjustment Kalman filter for surface measurements of carbon monoxide in a single tracer version of the community air quality model. Three different sets of numerical experiments were performed to test the effectiveness of the procedure and the range of key parameters used in implementing the procedure. In each case the proposed method provided better results than the method without data assimilation.
- 12:20 - 13:00: Serge Guillas, Statistical correction and downscaling of chemical transport model ozone forecasts --- Download Slides
Serge Guillas, Department of Statistics, University College, London
The Regional Air Quality forecAST (RAQAST) model is a regional chemical transport modeling system for ozone and its precursors over the United States. Since the grid size is 70 by 70km, forecasts cannot be made for a specific surface site. We use EPA monitoring stations from the South-East US to downscale and improve local forecasts using RAQAST outputs. We first use a time series regression approach to correct deficiencies. Evaluation using measurements for a different period confirms that the statistically adjusted outputs reduce forecast errors by up to 25%. Then, we implement a spatio-temporal approach with a non-separable covariance structure having autoregressive marginals in time. The result enable us to spatially describe the deficiencies of RAQAST. (Joint work with C. Ma and F. Al-Kuwari)
- 13:00 - 14:00: Lunch
- 14:00 - 15:20: Session 3 : Spatial Modelling of Air Pollution
- 14:00 - 14:40: Adrian Bowman, Additive models for environmental applications --- Download Slides
Adrian Bowman, Department of Statistics, University of Glasgow
Additive models extend standard regression methods by allowing very flexible, but smooth, relationships between variables of interest. The role of these models in environmental applications, where there is a need to model complex forms of spatial and temporal trends, as well as spatial and temporal correlation, will be discussed. The technical aspects of the talk will focus on computational strategies for spatiotemporal smoothing and on the construction of appropriate models of spatial variation over river networks. Applications will include the modelling of SO2 pollution over Europe and water quality in the River Tweed.
- 14:40 - 15:20: Gavin Shaddick, Issues of bias in spatial studies of environmental factors --- Download Slides
Gavin Shaddick, University of Bath
In this talk, I will discuss some of the problems encountered when analysing the long-term effects of air pollution on health. In particular, I will concentrate on problems that can occur when examining associations using aggregate level studies, including the problems of ecological bias, i.e. examining the associations between aggregate disease counts and environmental exposures measured, for example via air pollution monitors, at point locations. There may also be problems when using spatial models where the monitoring network might be sparse relative to the study area, in which case the use of predicted concentrations can produce serious bias in effect parameters because the number of monitors is not sufficient to characterize the concentration surface. These aspects are investigated through simulations and a study of the association between sulphur dioxide and respiratory mortality.
- 15:20 - 16:00: Panel Discussion
- 16:00: Close of Meeting
Location and Time
Start and finish time: Friday 19th June 2009, 10AM - 4PM.
Location: Main Lecture Theatre, Building 58 (Murray), Highfield Campus, University of Southampton, Southampton, UK
The map below shows the location of Building 58 on the Highfield Campus. The main lecture theatre is best accessed from the south side of the building. If you have never been to Southampton you can find information about how to arrive at the University at Southampton's website.
Cost
Cost: £25 to include full buffet lunch and teas and coffees.
Short Course
The meeting will be preceded by a three-day short course given by Alan Gelfand (Duke University) and Sujit Sahu (S3RI) on Hierarchical modelling of spatial and temporal data. For further information and to register for the course please visit the Short Course Homepage.
To Book Your Place...
We cannot accept participants on the day. You must book a place for this meeting.
Please download and complete the following registration form (which can also provide registration for the short course) and send to the S3RI coordinator whose address is provided below.
Registration Form (Word Document)
Registration Form (Adobe PDF)
Fax: +44 (0)23 8059 5763
Tel: +44 (0)23 8059 3216
E-mail: C.C.Thompson@soton.ac.uk
Contact
If you would like further information please contact Sujit Sahu (S.K.Sahu@soton.ac.uk).