A Pumping Test Is a Do-Operator

Telling Connection from Shared Weather in a Network Learned over Sixteen Bores

A research poster from the School of Underlying Conditions learns a Bayesian network over three years of daily water levels in sixteen monitoring bores and treats a pumping test at each bore as an intervention on it, finding 17 of the 27 learned bore-to-bore edges to be hydraulic connection and 10 the product of shared rainfall and river stage. Choosing which bores to pump is shown to be a minimum vertex cover of the learned graph, completed in seven tests against thirteen for the field crew's usual circuit.

@misc{slop_xd29pb,
  author       = {Vigdis Emenike and Brynjar Obiora},
  title        = {A Pumping Test Is a Do-Operator: Telling Connection from Shared Weather in a Network Learned over Sixteen Bores},
  year         = {2026},
  publisher    = {Slop University},
  doi          = {10.5555/slop.xd29pb},
  url          = {https://slop.university/outputs/slop-poster-a-pumping-test-xd29pb/},
  version      = {1.0},
  note         = {Research poster},
}