Articles | Volume 30, issue 2
https://doi.org/10.5194/hess-30-289-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-30-289-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| Highlight paper
| 
22 Jan 2026
Research article | Highlight paper |
| 22 Jan 2026
| 22 Jan 2026
High resolution monthly precipitation isotope estimates across Australia from machine learning
Georgina Falster
CORRESPONDING AUTHOR
School of Physics, Chemistry and Earth Sciences, Adelaide University, Adelaide 5005, SA, Australia
The ARC Centre of Excellence for Climate Extremes, The Australian National University, Canberra 2601, ACT, Australia
Gab Abramowitz
Climate Change Research Centre, UNSW Sydney, Kensington 2052, NSW, Australia
Sanaa Hobeichi
Climate Change Research Centre, UNSW Sydney, Kensington 2052, NSW, Australia
The ARC Centre of Excellence for the Weather of the 21st Century, UNSW Sydney, Kensington 2052, NSW, Australia
Catherine Hughes
ANSTO, Lucas Heights 2234, NSW, Australia
School of Biological, Earth, and Environmental Sciences, UNSW Sydney, Kensington 2052, NSW, Australia
Pauline Treble
ANSTO, Lucas Heights 2234, NSW, Australia
School of Biological, Earth, and Environmental Sciences, UNSW Sydney, Kensington 2052, NSW, Australia
Nerilie J. Abram
Research School of Earth Sciences, The Australian National University, Canberra 2601, ACT, Australia
The ARC Centre of Excellence for the Weather of the 21st Century, The Australian National University, Canberra 2601, ACT, Australia
The Australian Centre for Excellence in Antarctic Science, The Australian National University, Canberra 2601, ACT, Australia
Michael I. Bird
College of Science and Engineering, James Cook University, Cairns 4878, Queensland, Australia
ARC Centre of Excellence for Indigenous and Environmental Histories and Futures, James Cook University, Cairns 4878, Queensland, Australia
Alexandre Cauquoin
Institute of Industrial Science, The University of Tokyo, Kashiwa 277-8574, Chiba, Japan
Bronwyn Dixon
School of Geography, Earth and Atmospheric Sciences, The University of Melbourne, Melbourne 3053, Victoria, Australia
Russell Drysdale
School of Geography, Earth and Atmospheric Sciences, The University of Melbourne, Melbourne 3053, Victoria, Australia
Chenhui Jin
ARC Centre of Excellence for the Weather of the 21st Century, Monash University, Melbourne 3800, Victoria, Australia
School of Earth Atmosphere and Environment, Monash University, Melbourne 3800, Victoria, Australia
Niels Munksgaard
College of Science and Engineering, James Cook University, Cairns 4878, Queensland, Australia
Bernadette Proemse
School of Natural Sciences, University of Tasmania, Hobart 7001, Tasmania, Australia
Jonathan J. Tyler
School of Physics, Chemistry and Earth Sciences, Adelaide University, Adelaide 5005, SA, Australia
Martin Werner
Alfred Wegener Institute Helmholtz Centre for Polar and Marine Research (AWI), 27570 Bremerhaven, Germany
Carol V. Tadros
ANSTO, Lucas Heights 2234, NSW, Australia
School of Biological, Earth, and Environmental Sciences, UNSW Sydney, Kensington 2052, NSW, Australia
Data sets
Spatially continuous monthly precipitation stable isotope estimates across the Australian continent at 0.25° resolution from 1962–2023 Georgina Falster https://doi.org/10.5281/zenodo.15486277
Video abstract
Video abstract for the publication: High resolution monthly precipitation isotope estimates across Australia from machine learning Georgina Falster https://doi.org/10.5446/72248
Executive editor
This manuscript is an interesting addition to the world of "isoscapes". The authors additionally provide a web-app for downloading the data and obtaining maps.
This manuscript is an interesting addition to the world of "isoscapes". The authors additionally...
Short summary
We used a random forest approach to produce estimates of monthly precipitation stable isotope variability from 1962–2023, at high resolution across the entire Australian continent. Comprehensive skill and sensitivity testing shows that our random forest models skilfully predict precipitation isotope values in places and times that observations are not available. We make all outputs freely available, facilitating use in fields from ecology and hydrology to archaeology and forensic science.
We used a random forest approach to produce estimates of monthly precipitation stable isotope...
