Time-Variability of Flow Recession Dynamics: Application of Machine Learning and Learning From the Machine

Minseok Kim, Hannes H. Bauser, Keith Beven, Peter A. Troch

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Flow recession analysis, relating discharge Q and its time rate of change −dQ/dt, has been widely used to understand catchment scale flow dynamics. However, data points in the recession plot, the plot of −dQ/dt versus Q, typically form a wide point cloud due to noise and hysteresis in the storage-discharge relationship, and it is still unclear what information we can extract from the plot and how to understand the information. There seem to be two contrasting approaches to interpret the plot. One emphasizes the importance of the ensemble characteristics of many recessions (i.e., the lower envelope or a measure of central tendency), and the other highlights the importance of the event scale analysis and questions the meaning of the ensemble characteristics. We examine if those approaches can be reconciled. We utilize a machine learning tool to capture the point cloud using the past trajectory of daily discharge. Our model results for a catchment show that most of the data points can be captured using 5 days of past discharge. We show that we can learn the catchment scale flow recession dynamics from what the machine learned. We analyze patterns learned by the machine and explain and hypothesize why the machine learned those characteristics. The hysteresis in the plot mainly occurs during the early time dynamics, and the flow recession dynamics eventually converge to an attractor in the plot, which represents the master recession curve. We also illustrate that a hysteretic storage-discharge relationship can be estimated based on the attractor.

Original languageEnglish (US)
Article numbere2022WR032690
JournalWater Resources Research
Issue number5
StatePublished - May 2023


  • catchment flow attractor
  • catchment sensitivity function
  • flow recession dynamics
  • machine learning
  • master recession curve
  • storage-discharge relationship

ASJC Scopus subject areas

  • Water Science and Technology


Dive into the research topics of 'Time-Variability of Flow Recession Dynamics: Application of Machine Learning and Learning From the Machine'. Together they form a unique fingerprint.

Cite this