Author Archives: Eleni Matechou

PhD projects

Fully-funded ARIES PhD project on New statistical models for smartphone app data on recreational fishing

This is a collaborative project between the University of Kent and the Centre for Environment, Fisheries & Aquaculture Science (Cefas)

Click here to submit your application by the 8th of January.

The project is at the intersection of big data, citizen-science, and sustainable fisheries. The student will provide new analytical tools for fisheries scientists to understand fish distributions, catches, effort, and angling behaviour through development of new statistical methods for the analysis of data collected by the smartphone-app Fishbrain, alongside information from current surveys.

The student will lead the development of state-of-the-art statistical methods on the timely topic of inference from large citizen-science data collected using new technologies. They will develop high-level, highly transferable statistical, programming and data skills, working with large app-derived data-sets and designed surveys using tools such as R, Python and Stan. The work will be presented and communicated to statisticians, fisheries-experts, and policy-makers at national and international conferences and meetings.

As a member of the Statistical Ecology @ Kent group and the National Centre for Statistical Ecology the student will be exposed to the latest developments in the fields of statistics and ecology. As part of the cohort of 80 Cefas PhD students they will interact with scientists and advisors from a diverse range of marine and freshwater sciences.

Through supervision and time visiting Cefas, the student will experience working in a multi-disciplinary science organisation and learn how their research fits into the wider policy context. Their work will be part of an MRF research programme at Cefas, Ball State and Danish Technical Universities, and broader fisheries advice through ICES.

The acquired knowledge and expertise in the topic of citizen-science data collected using new technologies will be of great benefit to the student in their future in academia, government, or industry. Although the models will be motivated by angling, the methods will be much more generally applicable to app-collected data on individual behaviour. The available data-sets are large and require efficient, sophisticated algorithms that fit models in reasonable time. Hence the project will equip the student with valuable skills in the growing areas of big data and data-mining.

Additional information on the project can be found here

ARIES is committed to equality & diversity, and inclusion of students of any and all backgrounds. All ARIES Universities have Athena Swan Bronze status as a minimum.

Students with high level numerical skills will be eligible for 3 months of additional stipend after the end of the 3.5 years to take advanced-level courses in branches of environmental sciences related to the project in the first 3-6 months of study.

Applicants should have a good degree in statistics, mathematics, computer science, or related subjects with a strong numerical component. They should be comfortable working with data and learning new methods, determined, and interested in engaging with the practical applications of their research.

Shortlisted applicants will be interviewed by ARIES on the 26th/27th February 2019, with shortlisting taking place at the University of Kent on the 31st of January.

Successful candidates who meet UKRI’s eligibility criteria will be awarded a NERC studentship – in 2018/19 the stipend is £14,777. In most cases, UK and EU nationals who have been resident in the UK for 3 years are eligible for a full award.

Supervisors
Dr Eleni Matechou and Dr Maria Kalli, University of Kent
David Maxwell and Dr Kieran Hyder, Centre for Environment, Fisheries & Aquaculture Science
Dr Christian Skov, National Institute of Aquatic Resources
Dr Paul Venturelli, Ball State University

The supervisory team brings together multidisciplinary expertise covering statistics, data science, recreational fisheries, app development, monitoring, and policy.

Funding Notes
The project has been shortlisted for up to 4 years, with 3.5 years minimum, of funding by the ARIES NERC Doctoral Training Partnership with a stipend of £14,777 per annum and a generous training and travel budget for attending UK-based and international conferences.

 

Standard
News, Papers, Publications

New paper by Eleni and colleagues published in JABES

The paper, titled  “Caste-Specific Demography and Phenology in Bumblebees: Modelling BeeWalk Data”, by Eleni Matechou, Stephen N. Freeman, and Richard Comont is available open-access. 

The work presents novel dynamic mixture models for the monitoring of bumblebee populations on an unprecedented geographical scale, motivated by the UK citizen science BeeWalk.

The models allow us for the first time to estimate bumblebee phenology and within-season productivity, defined as the number of individuals in each caste per colony in the population in that year, from citizen science data.

All of these parameters are estimated separately for each caste, giving a means of considerable ecological detail in examining temporal changes in the complex life cycle of a social insect in the wild. Due to the dynamic nature of the models, we are able to produce population trends for a number of UK bumblebee species using the available time-series. Via an additional simulation exercise, we show the extent to which useful information will increase if the survey continues, and expands in scale, as expected.

Bumblebees are extraordinarily important components of the ecosystem, providing pollination services of vast economic impact and functioning as indicator species for changes in climate or land use. Our results demonstrate the changes in both phenology and productivity between years and provide an invaluable tool for monitoring bumblebee populations, many of which are in decline, in the UK and around the world.

Standard
Papers

Model averaging in ecology: a review of Bayesian, information-theoretic and tactical approaches for predictive inference

The review paper, by Dormann, C.F., Calabrese, J.M., Gurutzeta, G., Matechou, E., Bahn, V., Bartoń, K., et al. to appear in Ecological Monographs, explores different model averaging techniques in terms of ways to calculate the model weights and to combine predictions from different models. The advantages and disadvantages of model averaging are discussed and code for methods falling under three categories (Bayesian, information theoretical and tactical) is provided.

Read a blog post written by the main contributors of the paper here.

 

Standard
Uncategorized

NERC Advanced Training Course

Statistical models for wildlife population assessment and conservation

19-23 March 2018

University of Kent

Further details of the workshop and details of how to apply for a place can be found here:

https://www.kent.ac.uk/graduateschool/skills/advancedtraining.html

Please note that the deadline for applications is 1st October 2017.  Successful applicants will be informed in early September.

We have 30 fully-funded places (inc. travel and accommodation) and priority is given to NERC-funded PhD students but if spaces remain we are able to offer the funded places to other PhD students and early-career researchers.

Within the environmental sector there is currently a shortage of practitioners equipped with the statistical modelling skills to carry out reliable population assessments. Consequently, environmental impact assessments (EIAs) and development mitigation projects often use population assessment protocols that are not fit-for-purpose1. The skills shortage arises because (1) recent advances in statistical models for population assessment are largely confined to the academic sector with little penetration to the end-users; and (2) although many postgraduate programmes have a statistical modelling training component, this often fails to expose PhD students to new models in the area and the potential applications these have for conservation practice2. This training programme will provide a cohort of PhD students and early career researchers/practitioners with the relevant modelling skills required for a career that involves wildlife population assessment for conservation.

  1. Griffiths, Foster, Wilkinson and Sewell (2015). Science, statistics and surveys: a herpetological perspective. Journal of Applied Ecology. doi: 10.1111/1365-2664.12463
  2. McCrea and Morgan (2015). Analysis of capture-recapture data. Chapman & Hall/CRC Press, Florida.

 

Proposed programme of the course

The workshop will focus on ecological questions that arise in conservation practice and use real case study data. Training will include individual-based models, such as capture-recapture, but will also embrace scenarios more frequently used in EIA, such as batch-marked, presence/absence, site occupancy and counts. Applications will include newts, butterflies, birds, bees, beetles, ibex and bats. Each module will be accompanied by a practical computer session using R and each module builds on the last so that delegates build a portfolio of statistical skills.

Training outcomes:  By the end of the course, attendees will be able to:

  • construct, interpret and fit relevant stochastic models, use different methods of inference, understand the pros and cons of Bayesian and classical methods and the use of prior information;
  • personalise R code to undertake modelling of their own research data;
  • understand data needs for animal population assessments for EIAs and conservation;
  • analyse animal population data to meet both conservation and commercial needs.

Draft timetable:

Module 1: Background in statistics and R (Monday PM)
  • Likelihood and probability theory
  •  Bayesian inference
  • Basic model assessment (AIC/absolute GOF)
  • Practical session: Introduction
Plenary session and Round table discussions (Tuesday AM)
Module 2: Understanding statistical uncertainty (Tuesday PM)
  • Imperfect detection
  • Data types, relationships and summaries.
  • Introduction to data sets/case studies (bees, butterflies, newts, mallards etc)
  • Practical session: converting format of data and summarising complex data.
Module 3: Model fitting and assessment (Wednesday AM+PM)
  • Estimating abundance
  • M0,Mtbh, removal
  • CR/RR
  • Occupancy
  • Practical session: model fitting, optimisation, use of packages.
Module 4: Modern challenges (Thursday AM)
  • Citizen science data
  • Small/sparse data and big data issues
  •  Cost-effectiveness in study design and statistical power.
  • Informative prior information.
  • Practical session: power analyses and adapting models
Module 5: Advanced stochastic modelling (Thursday PM)
  • modelling movement
  •  state uncertainty
  • species interaction
  • spatial models
  • integrated modelling
  • Practical session: use of Rjags, Bayesian graphical models using MCMC.
One-to-one consultation sessions (Friday AM)
Module 6: Advanced aspects of R (Friday AM)
  • Practical session: self-lead worksheets
  • Multistate examples
  • PR diagnosis
  • Diagnostic GOF testing
Standard
Uncategorized

Eleni gave a seminar at Sheffield

Eleni gave a seminar on the 15th of March 2017 as part of the Ecology, Evolution and Environment seminar series at the Department of Animal and Plant Sciences, University of Sheffield.

Title: Modelling phenology for marked and unmarked populations

Abstract: In this seminar I will discuss fairly recent models for capture-recapture and for count data that enable us to estimate, among other things, phenology of wildlife populations. The methods explored will include classical as well as Bayesian parametric and non-parametric approaches. They will be demonstrated using data on breeding great crested newts, migrating reed warblers, bivoltine butterfly species , bumblebees from the citizen science scheme BeeWalk as well as data on anglers in Norway.

Standard
Conferences/Meetings/Workshops

Ming participated in postgraduate research festival

Ming presented a poster titled “Optimal Design for Removal Sampling” at the postgraduate research festival that took place at the University of Kent.

She presented her work in which she investigates removal models accounting for temporary emigration analytically and examines how to optimally allocate a fixed level of total sampling effort in terms of maximising the Fisher information.

Standard
News

SE@K student Alex Diana doing field work!

First year student Alex Diana and his supervisor, Dr Eleni Matechou, took part in field work sampling for newts.

The long-running project, coordinated by the Durrell Institute for Conservation and Ecology (DICE) at the University of Kent, collects data on newt populations breeding in ponds located near the Canterbury campus.

They saw and identified male and female great crested, palmate and smooth newts. They also learned where newts place their eggs and what male newts do to attract the females (thanks to a very vivid description by Professor Richard Griffiths from DICE!)

Standard
Conferences/Meetings/Workshops

SE@K students run masterclasses for SMSAS

Three SE@K students (Ming, Marina and Alex) took part in masterclasses organised by the SMSAS outreach officer, Joe Watkins. For details about master classes and other outreach events at SMSAS see here https://www.kent.ac.uk/smsas/outreach/on-campus.html.

The classes took place on two days and involved four sessions: i) Introduction to probability and statistics ii) Removal modelling, iii) Occupancy modelling and iv) Capture-recapture modelling. They were attended by some of the most enthusiastic and engaged year 9 students in the local area.

All sessions were interactive and the participating year 9 students had the opportunity to replicate real-life sampling techniques for monitoring populations of lizards, penguins and birds. These involved digging for lizards in the sand, looking for hidden penguins and marking birds. No animals were hurt in the process as they were all made out of plastic!

Standard