Publication Abstracts

Marvel and Cook 2022

Marvel, K., and B.I. Cook, 2022: Using machine learning to identify novel hydroclimate states. Phil. Trans. Roy. Soc. A, 380, no. 2238, 20210287, doi:10.1098/rsta.2021.0287.

Anthropogenic climate change is expected to alter drought risk in the future. However, droughts are not uncommon or unprecedented, as documented in tree-ring-based reconstructions of the summer average Palmer drought severity index (PDSI). Using an unsupervised machine-learning method trained on these reconstructions of pre-industrial climate, we identify outliers: years in which the spatial pattern of PDSI is unusual relative to 'normal' variability. We show that in many regions, outliers are more frequently identified in the twentieth and twenty-first centuries. This trend is more pronounced when the regional drought atlases are combined into a single global dataset. By definition, outlier patterns at the 10% level are expected to occur once per decade, but from 1950 to 2000 more than 6 years per decade are identified as outliers in the global drought atlas (GDA). Extending the GDA through 2020 using an observational dataset suggests that anomalous global drought conditions are present in 80% of years in the twenty-first century. Our results indicate, without recourse to climate models, that the world is more frequently experiencing drought conditions that are highly unusual in the context of past natural climate variability.

Export citation: [ BibTeX ] [ RIS ]

BibTeX Citation

@article{ma01610f,
  author={Marvel, K. and Cook, B. I.},
  title={Using machine learning to identify novel hydroclimate states},
  year={2022},
  journal={Phil. Trans. Roy. Soc. A},
  volume={380},
  number={2238},
  pages={20210287},
  doi={10.1098/rsta.2021.0287},
}

[ Close ]

RIS Citation

TY  - JOUR
ID  - ma01610f
AU  - Marvel, K.
AU  - Cook, B. I.
PY  - 2022
TI  - Using machine learning to identify novel hydroclimate states
JA  - Phil. Trans. Roy. Soc. A
VL  - 380
IS  - 2238
SP  - 20210287
DO  - 10.1098/rsta.2021.0287
ER  -

[ Close ]

• Return to 2022 Publications

• Return to Publications Homepage