Member's Area - Login/Register

Optimal temporal distribution curves for the classification of heavy precipitation using hierarchical clustering on principal components

Paper Topic: 
Protection and restoration of the environment
 
Volume: 
 
Issue: 
 

Pages :
530 - 538

Corresponing Author: 
Konstantinos Vantas
 
Authors: 
Vantas K., Sidiropoulos E., Vafeiadis M.
Paper ID: 
gnest_02997
Paper Status: 
Published
Date Paper Accepted: 
30/07/2019
Paper online: 
09/09/2019
Abstract: 

A novel method that utilizes a combination of statistical and clustering techniques is presented in order to classify statistically independent heavy rainstorm events and create a limited number of temporal distribution curves. These curves represent the centers of many unitless cumulative rainstorm events and express the temporal distribution patterns in a probabilistic way. The whole process includes the necessary steps from importing raw precipitation time series data to producing the initially unknown optimal number of representative curves. These hyetographs can be used for stochastic simulation, water resources planning, water quality assessment and global change studying. The present type of analysis is fully unsupervised, as no empirical knowledge of local rainfalls is implicated or any arbitrary introduction of quartiles for grouping as is the case in the pertinent literature. An example using data from a Greek Water Division illustrates that the proposed method produces clusters with superior internal structure and temporal distribution curves that are not coming from the same distribution, in contrast to the results using Huff’s curves classification.

Keywords: 
rainfall temporal distribution, design hyetographs, optimal number of clusters, unsupervised learning, hierarchical clustering, principal components analysis, cluster validity