EGU22-1437
https://doi.org/10.5194/egusphere-egu22-1437
EGU General Assembly 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Identifying conditions that sculpted bedforms - Human insights to build an effective artificial intelligence ‘AI’

John K. Hillier1, Chris Unsworth2, Luke De Clerk3, and Sergey Savel'ev3
John K. Hillier et al.
  • 1Loughborough University, Geography and Environment, Loughborough, Leicestershire, UK. (j.hillier@lboro.ac.uk)
  • 2School of Ocean Sciences, Bangor University, Bangor, LL59 5AB, UK.
  • 3Loughborough University, Physics, Loughborough, Leicestershire, UK.

Insights from a geoscience communication activity, verified using preliminary investigations with an artificial neural network, illustrate that observation of humans’ abilities can help design an effective machine learning algorithm - colloquially known as Artificial Intelligence or ‘AI’. Even given only one set of 'training' examples, survey participants could visually recognise which flow conditions created bedforms (e.g. sand dunes, riverbed ripples) from their shapes, but an interpreter's geoscience expertise does not help.  Together, these observations were interpreted as indicating that a machine learning algorithm might be trained successfully from limited data, particularly if it is 'helped' by pre-processing bedforms into a simple shape familiar from childhood play. [https://gc.copernicus.org/articles/5/11/2022/]

How to cite: Hillier, J. K., Unsworth, C., De Clerk, L., and Savel'ev, S.: Identifying conditions that sculpted bedforms - Human insights to build an effective artificial intelligence ‘AI’, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-1437, https://doi.org/10.5194/egusphere-egu22-1437, 2022.

Comments on the display material

to access the discussion