I develop AI for environmental and social good. I aim to discover the mechanistic insights that explain decisions in ecology, health and biosecurity. Recently, I have been investigating how to integrate AI sciences and social sciences – a small task really :-).

My research is at the forefront of linking domain sciences such as ecology, epidemiology, social sciences with quantitative tools from the field of artificial intelligence (AI). I develop AI methods to provide guidance on how to make smart decisions under imperfect knowledge and resource constraints (1). During my PhD, I developed new methods to tackle complex optimisation problems for mobile robots using Markov decision processes (MDP). I discovered that MDP models can be an effective tool for improving decision-making in modern conservation science – teaching a robot to navigate utilizes the same mathematics as choosing the best conservation actions to save threatened species under uncertainty (2). Eager to contribute to conservation science, I changed career and turned towards decisions in ecology (2006). Combining my expertise in AI with ecological and economic models, I solve complex applied conservation problems in the face of uncertainty. The solutions I provide are optimal decisions that save money and allocate resources more efficiently. My work is in demand in applied pest management, health and conservation. For example, I have provided solutions to efficiently eradicate invasive weeds, control mosquito-borne diseases and protect threatened species from extinction (3-5). Recently I have focused on developing optimal adaptive management and adaptive experimental design approaches (6-8).

At CSIRO, I lead several externally funded projects and some strategic initiatives. I currently lead the team “Socio-technical Innovations” with experts in AI/ML and social sciences. I have broaden my area of interest to AI for environmental and social good.

I am a Chief Investigator with NHMRC Centre for Research Excellence SPECTRUM (Supporting Participatory Evidence generation to Control Transmissible diseases in our Region Using Modelling).

From 2019 to 2013, I was the activity leader with the CSIRO MLAI Future Science Platform (2019-2023) where I focus on developing ML/AI for decision-making for all of CSIRO’s application domain (health, ecology, synthetic biology, manufacturing etc). Before that I was an international collaborator of the NSF expedition CompSustNet research network. Finally, from 2012 to 2021, I was the team leader of the Conservation Decisions team (CSIRO, Land and Water) a multi-disciplinary group with expertise in ecology, systematic conservation planning, priority threat management, artificial intelligence, and decision theory. While the team doesn’t officially exist anymore, we continue to perform this research with the same motivation of solving pressing global conservation problems by connecting ecological data with decision science to determine what actions to take, when and where to get the best outcomes for biodiversity conservation, while taking into account the many other competing needs of society.

  1.  MacKenzie, D. I. Getting the biggest bang for our conservation buck. Trends Ecol. Evol. 24, 175-177 (2009).
  2.  Chadès, I. What’s the connection between mobile robots, endangered cryptic animals and invasive species? Decision Point 29, 5 (2009).
  3. Chadès, I. et al. When to stop managing or surveying cryptic threatened species. Proc. Natl. Acad. Sci. U. S. A. 105, 13936 (2008).
  4. Chadès, I. et al. General rules for managing and surveying networks of pests, diseases, and endangered species. Proc. Natl. Acad. Sci. U. S. A. 108, 8323-8328 (2011).
  5. Chadès, I. al., Benefits of integrating complementarity into priority threat management. Cons. Biol., 2015
  6. Luz V Pascal, Marianne Akian, Sam Nicol, Iadine Chades. A Universal 2-State n-Action Adaptive Management Solver. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021.
  7. Jonathan Ferrer Mestres, Thomas Dietterich, Olivier Buffet, Iadine Chades. K-N-MOMDPs: Towards Interpretable Solutions for Adaptive Management. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021.
  8. Blau, T., Bonilla, E. V., Chades, I., & Dezfouli, A. (2022, June). Optimizing sequential experimental design with deep reinforcement learning. In International Conference on Machine Learning (pp. 2107-2128). PMLR.

One thought on “About”

Leave a Reply

Your email address will not be published. Required fields are marked *