Early warning and forecasting of geohazards

Developing robust, community-centric early warning systems for geohazards, with a focus on landslides.

Mission

Our unit is committed to developing robust, community-centric early warning systems for geohazards, with a focus on landslides. By collaborating internationally with scientists, government agencies, NGOs, and industry leaders in Earth observations, we integrate advanced scientific modelling, real-time monitoring, and indigenous knowledge to enhance landslide disaster preparedness and resilience.

Objectives

We specialise in the development of data-driven methods for forecasting and estimation of risks associated with hazards where geology and weather interact. A key area of expertise that informs our research on risk assessment is that of early prediction of failure in complex granular materials and structures -- in particular, soil and rock bodies.  We achieve this by extracting hidden patterns on “dynamics” (the time evolution) of trigger events and motions in the nascent, precursory stages of failure – from data. Our approach comprises an amalgam of complex flow network analytics and AI techniques which can detect emerging order, relationships and subtle regime changes from an optimal subset of failure features.

Capabilities

Our capability to decode big spatiotemporal data, by mapping them to complex networks or a relevant feature state space, is what allows us to extract reliable indicators of where and when failure will likely occur.  A deep knowledge of the fundamental origins of failure at the microstructure level – combined with our analytics tools designed specifically for complex systems – makes our platform for early prediction of failure unique. From this, we can extract actionable intelligence on the future course of failure – irrespective of system size and material microstructure. We have demonstrated success in predicting failure from laboratory samples, in millimetres, to the field scale of kilometres in some of the most complex materials and terrains on Earth.

Impacts

  • Leading National Dialogue on Landslide Early Warning in Nepal.  Prof. Tordesillas will lead a high-level national dialogue on landslide early warning systems in the Australian Embassy in Nepal on April 17, 2025.  Bringing together government officials, UN representatives, NGOs, and local community leaders, this DFAT initiative fosters inclusive and actionable discussions. With sign language interpretation ensuring accessibility, the dialogue will culminate in a report published in both English and Nepali, enhancing policy and decision-making at all levels.
  • International recognition in global disaster risk reduction strategies and Earth Observation.  The study "Pinpointing Early Signs of Impending Slope Failure from Space" (Zhou, Tordesillas et al., 2022) has been featured in the 2024 UN Report on Space Technologies for Early Warning Systems.
  • Advancing Landslide Early Warning Systems in the Himalayas through a 2024-2027 Australian Aid grant.  Leading a team of scientists from the Universities of Melbourne (Australia), Tribhuvan (Nepal), Florence (Italy) and Cambridge (UK), Prof. Tordesillas spearheads the application of SAFE-RISCCS, a cutting-edge landslide early warning system technology that was developed by the unit at the Uni Melbourne.
  • Influencing International Policy and UN Sustainable Development Goals.  Prof. Tordesillas, serving as Deputy Secretary General of the International Panel of Mesoscience (IPM), participated in the drafting of a UNESCO policy brief on “How science can better support the implementation of the 17 SDGs” at the 2024 Board Meeting of IPM held at the Royal Academy of Engineering in London. IPM forged a strategic partnership with UNESCO in 2024, aligning efforts with the UN Sustainable Development Goals and advancing global health and disaster resilience through IPM’s Gates Foundation-supported initiative.
  • Commercialising cutting-edge augmented intelligence forecasting and what-if scenario analytics for high-risk sloped structures, this breakthrough research (Tordesillas et al., 2024, 2021a, 2021b) fuses AI with the physics and dynamics of precursory granular media failure to develop next-generation techniques for real-time spatiotemporal slope stability analytics with quantified uncertainty.  Alongside the patented method for surface event prediction (Tordesillas & Batterham), these innovations are being evaluated for commercial deployment by GroundProbe, Orica—positioning them to revolutionise global geohazard risk mitigation in mining and enhance safety, efficiency, and resilience in high-risk environments.
  • Shaping Global Disaster Resilience Through International Collaboration.  As Co-Director of the 2023 Advanced Research Workshop on Emerging and Disruptive Technologies for Disaster Resilience, Dr. Tordesillas collaborated with Dr. T. Baser (University of Illinois Urbana-Champaign) under a NATO-funded initiative in response to the 2023 Türkiye-Syria Earthquake. This workshop, supported by the NATO Partnership and Cooperative Security Committee, strengthens scientific cooperation in disaster risk management through the Science for Peace and Security Programme.

Unit lead

Antoinette Tordesillas

Professor Antoinette Tordesillas
Professor of Mathematics and Statistics
atordesi@unimelb.edu.au