Close up of a women's face.

Dr Iadine Chades develops and applies new methods to optimally manage invasive and endangered species.

Dr Iadine Chadès: making good conservation decisions under uncertainty

With a background in artificial intelligence and optimisation, Dr Chadès research provides informed guidance to decision makers on how to protect biodiversity in the most efficient way.

  • 16 March 2011 | Updated 3 April 2013
  1. Overview
  2. Publishing History

Overview

Page 1 of 2

Current activities

Dr Chadès' research is at the forefront of linking conservation science and quantitative tools from the field of artificial intelligence (AI). She develops artificial intelligence methods to provide guidance on how to make smart conservation decisions under imperfect knowledge and resource constraints.

In simple terms, she works out how to make the biggest bang for our conservation buck[1].

Combining her expertise in AI with ecological and economic models, Dr Chadès solves complex applied conservation problems in the face of uncertainty. The solutions she provides are optimal decisions that save money and allocate resources more efficiently.

Her work is in demand in applied pest management, health and conservation. For example she has provided solutions to efficiently eradicate invasive weeds, control mosquito-borne diseases and protect threatened species from extinction[3,4].

Dr Chadès' research pioneered the use of Partially observable Markov decision process (POMDP) in conservation and has been recognised in both ecology and AI, with two publications in Proceedings of the National Academy of Sciences[3,4] and the 2012 best paper award for computational sustainability at the high-profile 26th Association for the Advancement of Artificial Intelligence conference [5].

Dr Chadès provides informed guidance to decision makers on how to protect biodiversity in a cost-effective way

The following videos illustrate the use of the optimisation toolbox developed on two applications:
  • Management of a hypothetical invasive weed on a network [external link] – we assume the infected nodes are detected perfectly using Factored Markov Decision Processes. In this case we seek to eradicate the invasive species. The video shows how the prioritisation order varies when a link becomes unidirectional.

Background

During Dr Chadès' PhD studies, she developed new methods to tackle complex optimisation problems for mobile robots using Markov decision processes (MDP). She discovered that MDP models can be an effective tool for improving decision-making in modern conservation science.

It turned out that teaching a robot to navigate utilises the same mathematics as choosing the best conservation actions to save threatened species under uncertainty[2]. Eager to contribute to conservation science, she changed career and turned towards decisions in ecology (2006).

Dr Chadès holds a doctorate in Artificial Intelligence (AI) and has held a permanent research scientist position with the French National Institute of Agronomy (INRA) since 2003.

Seeking inspirational applications, Dr Chadès visited Professor Hugh Possingham in 2005 and became passionate about ecology.

She discovered that her skills in optimisation could be useful to solve problems in conservation and natural resource management science.

In 2008, Dr Chadès successfully submitted a grant proposal to work on the spatial management of invasive species with the Australian Centre of Excellence for Risk Analysis (ACERA).

This resulted in a one-year Postdoctoral Research Fellowship at the University of Queensland, Brisbane.

In 2009, Dr Chadès successfully applied for an Office of the Chief Executive (OCE) Postdoctoral Research Fellowship at CSIRO Sustainable Ecosystems (now Ecosystem Sciences) with Dr Yvonne Buckley.

A desire to continue applying her skills in AI to solve complex ecological problems underpinned her decision to develop a career in Australia with CSIRO. 

Academic qualifications

Dr Chadès was awarded a Doctor of Philosophy from Université Nancy 1/INRIA, France in 2003 and a Masters of Science in Computer Science from 'Informatique de Lyon', Ecole Normale Supérieure (ENS) de Lyon, France in 1998.

Other activities

Dr Chadès was an invited speaker to:

  • Ecological Society of Australia, December 2010
  • International conference on computational sustainability, Cornell University and National Science Foundation, New York, USA, June 2009
  • Centre for Applied Conservation Research, Canada
  • Fisheries and Oceans Canada
  • Applied Environmental Decision Analysis centre, AEDA, Australia.

She has also supervised:

  • S Nicol, Postdoctoral Fellow from CSIRO Ecosystem Sciences, since 2013
  • JB Pichancourt, Postdoctoral Fellow from CSIRO Ecosystem Sciences, since 2010
  • A Moore, Postdoctoral Fellow from French National Institute for Agricultural Research (INRA)/ACERA/AEDA, 2010
  • E McDonald-Madden, CSIRO OCE Postdoctoral Fellow, 2009–10
  • I Grechi, Postdoctoral Fellow from INRA/CSIRO, 2008–09
  • S Nicol, PhD student from the University of Queensland, since 2008.

Read more about CSIRO research on Biodiversity and Ecology.

References

  1. MacKenzie DI. 2009. Getting the biggest bang for our conservation buck. Trends in Ecology & Evolution. 24, 175-177.
  2. Chadès I. 2009. Walking with robots: What’s the connection between mobile robots, endangered cryptic animals and invasive species? Decision Point 29, 5 (2009) [PDF 1.2MB, External link].
  3. Chadès I. et al. 2008. When to stop managing or surveying cryptic threatened species. Proceedings of the National Academy of Sciences USA. 105, 13936.
  4. Chadès I. et al. 2011. General rules for managing and surveying networks of pests, diseases, and endangered species. Proceedings of the National Academy of Sciences USA. 108, 8323-8328.
  5. Chadès I. et al. in The Twenty-Sixth AAAI Conference on Artificial Intelligence (AAAI-12).  267-273.