Matej Radinja (Author), Mateja Škerjanec (Author), Sašo Džeroski (Author), Ljupčo Todorovski (Author), Nataša Atanasova (Author)

Abstract

Stormwater control measures (SCMs) are decentralized technical elements, which can prevent the negative effects of uncontrolled stormwater flow while providing co-benefits. Optimal SCMs have to be selected and designed to achieve the desired hydrological response of an urban catchment. In this study, automated modeling and domain-specific knowledge in the fields of modeling rainfall-runoff (RR) and SCMs are applied to automate the process of optimal SCM design. A new knowledge library for modeling RR and SCMs, compliant with the equation discovery tool ProBMoT (Process-Based Modeling Tool), was developed. The proposed approach was used to (a) find the optimal RR model that best fits the available pipe flow measurements, and (b) to find the optimal SCMs design that best fits the target catchment outflow. The approach was applied to an urban catchment in the city of Ljubljana, Slovenia. First, nine RR models were created that generally had "very good" performance according to the Nash%Sutcliffe efficiency criteria. Second, six SCM scenarios (i.e., detention pond, storage tank, bio-retention cell, infiltration trench, rain garden, and green roof) were automatically designed and simulated, enabling the assessment of their ability to achieve the target outflow. The proposed approach enables the effective automation of two complex calibration tasks in the field of urban drainage.

Keywords

ukrepi za obvladovanje padavinskih voda;model površinskega odtoka;avtomatizirano modeliranje;domensko znanje;odkrivanje enačb;procesno bazirani modeli;stormwater control measures;rainfall-runoff model;automated modeling;domain knowledge;equation discovery;process-based modeling;

Data

Language: English
Year of publishing:
Typology: 1.01 - Original Scientific Article
Organization: UL FGG - Faculty of Civil and Geodetic Engineering
UDC: 004:626/627
COBISS: 73739779 Link will open in a new window
ISSN: 2073-4441
Views: 209
Downloads: 31
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: Slovenian
Secondary keywords: ukrepi za obvladovanje padavinskih voda;model površinskega odtoka;avtomatizirano modeliranje;domensko znanje;odkrivanje enačb;procesno bazirani modeli;
Type (COBISS): Article
Pages: [26] str.
Volume: ǂVol. ǂ13
Issue: ǂno. ǂ16
Chronology: 2021
DOI: 10.3390/w13162268
ID: 13641420