doktorska disertacija
Mateja Škerjanec (Author), Boris Kompare (Mentor), Matjaž Mikoš (Thesis defence commission member), Jože Panjan (Thesis defence commission member), Marina Pintar (Thesis defence commission member), Mitja Brilly (Thesis defence commission member), Sašo Džeroski (Thesis defence commission member), Nataša Atanasova (Co-mentor)

Abstract

V doktorski disertaciji predstavljamo nov pristop k modeliranju hidroloških pojavov in kakovosti voda na ravni porečij, ki omogoča avtomatsko izgradnjo modelov na podlagi domenskega znanja in merjenih podatkov. Osnovo za tovrstno modeliranje predstavlja domenska knjižnica, ki smo jo razvili v sklopu naloge. V knjižnici je zbrano znanje s področja hidrološkega modeliranja in modeliranja procesov spiranja hranil na ravni porečij, pri čemer je vsak proces predstavljen z alternativnimi enačbami. Formalizem, ki smo ga uporabili za zapis knjižnice, je kompatibilen z orodjem ProBMoT. Na podlagi domenske knjižnice in opisa izbranega porečja, ki ga poda uporabnik, ProBMoT generira vse alternativne strukture modela opazovanega sistema. Slednje so avtomatsko umerjene na meritve. Model, ki kaže najmanjše odstopanje med rezultati simulacije modela in meritvami, je izbran kot najboljši model za opis opazovanega sistema. Metodologijo smo testirali na porečju reke Quarteire (Algarve, Portugalska). Rezultati analize povprečne letne vodne bilance ter povprečnih letnih obremenitev reke Quarteire s sedimentom in hranili potrjujejo ugotovitve predhodnih raziskav, kar kaže na primernost uporabe predlaganega pristopa za potrebe hidrološkega modeliranja in modeliranja kakovosti voda na ravni porečij. Dobljeni rezultati so z vidika natančnosti primerljivi oz. boljši od rezultatov, dobljenih z orodjem SWAT. Posledično predstavlja predlagan avtomatiziran pristop pomembno alternativo obstoječim konceptualnim pristopom. S testiranjem dveh modelnih scenarijev (scenarija podnebnih sprememb in scenarija povečanja števila priključkov na čistilne naprave) smo potrdili logično odzivanje zgrajenih modelov na spremenjene vrednosti parametrov in vhodnih podatkov, kar potrjuje uporabnost tovrstnih modelov v sistemih za podporo odločanju na področju celostnega upravljanja z vodnimi viri.

Keywords

gradbeništvo;disertacije;model porečja;hidrologija;obremenitev s hranili;knjižnica znanja;avtomatizirano modeliranje;

Data

Language: Slovenian
Year of publishing:
Typology: 2.08 - Doctoral Dissertation
Organization: UL FGG - Faculty of Civil and Geodetic Engineering
Publisher: [M. Škerjanec]
UDC: 004.925:574.5:628.113(043)
COBISS: 6550113 Link will open in a new window
Views: 3202
Downloads: 685
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: English
Secondary title: Automated modelling for integrated water resources management
Secondary abstract: We introduce a new approach to hydrologic and water quality modelling on a watershed scale, which automatically induces suitable models from domain modelling knowledge and measured data. A central component of the proposed methodology is the domain knowledge library, which was developed within this dissertation. The knowledge encoded in the library comprises hydrological and nutrient loading processes on a watershed scale. For each conceptual process, the library contains various alternative formulations. The library is written in a formalism compliant with the equation discovery tool ProBMoT. Given a user specification of the modelling task, ProBMoT searches the space of alternative candidate models encoded in the library. The generated models are optimized against provided measured data. The best fitted model is proposed to the user as the best model of the observed system. The methodology was applied to the Quarteira river catchment (Algarve, Portugal). Analysis of the average annual water balance, sediment yields and nutrient loadings to the Quarteira river supports the findings of the previous research work, justifying the use of the proposed methodology for hydrological and water quality modelling at the watershed scale. In terms of accuracy, ProBMoT results are comparable or better than the results obtained with SWAT. Consequently, the proposed methodology presents a worthy alternative to the existing conceptual modelling approaches. By testing two different scenarios (climate change scenario and scenario of the increased wastewater treatment plant utilization), we confirmed that the generated hydrological and water quality models are logically responding to the modified parameter values and input data. Therefore, such models could be incorporated into decision support systems in the field of integrated water resources management.
Secondary keywords: civil engineering;thesys;watershed model;hydrology;nutrient loading;knowledge library;automated modelling;
URN: URN:NBN:SI
File type: application/pdf
Type (COBISS): Dissertation
Thesis comment: Univ. v Ljubljani, Fak. za gradbeništvo in geodezijo, Podiplomski študij gradbeništva, Doktorski študij
Pages: XXX, 132 str., 7 pril.
ID: 8707923
Recommended works:
, diplomsko delo visokošolskega strokovnega študija Varnost in policijsko delo