Special Issue "Advancements in Data-Driven Modeling and Data-Mining Techniques in Hydrology"

A special issue of Hydrology (ISSN 2306-5338).

Deadline for manuscript submissions: closed (31 December 2015).

Special Issue Editors

Prof. Dr. Luigi Berardi
Website
Guest Editor
Department of Engineering and Geology, University “G. D’Annunzio” of Chieti Pescara, viale Pindaro 42, 65127 Pescara, Italy
Interests: data-driven modeling of environmental phenomena; evolutionary computing and hybrid evolutionary computing; multi-objective decision support tools; water distribution and sewer system analysis; optimization applied to management of water systems
Special Issues and Collections in MDPI journals
Dr. Daniele Laucelli
Website
Guest Editor
Civil Engineering and Architecture Department Technical University of Bari v. E. Orabona 4, 70125 Bari, Italy
Interests: Data modeling and soft-computing for environmental systems; management and planning of water distribution systems; analysis of leakage in water systems; hydroinformatics and decision support in the management of water systems
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

In the last two decades, developments in computational intelligence and machine learning greatly expanded the capabilities of empirical modeling in hydrological applications via data-driven modeling. Examples include artificial neural networks, fuzzy rule-based models, and population-based techniques. Data-driven modeling techniques are generally based on analyzing field data, using a training data set that is representative of the system behavior, and determining the relationship between the system state variables (input, internal and output variables), without including prior explicit knowledge of the physical behavior of the system. Additionally, computational intelligence and machine learning techniques have also been applied to perform data-mining in terms of knowledge discovery on hydrological phenomena, starting from the available measured data aimed at unveiling possible new relationships among observable variables.

More recently, enhancements in computational capabilities (e.g. parallel computing), innovations in observation and measurement devices (e.g., ICT devices), and, consequently, increased availability of hydrological data (e.g., real time data) of different time and spatial scales, open up new and fascinating scenarios for the application of data-driven modeling techniques and data-mining approaches for new knowledge discovery. The exploitation of such a great bulk of new information can contribute greatly to enhance the robustness of hydrological models for prediction of extreme phenomena (e.g. flood forecasting, rain development, etc.) mitigating the uncertainty related to ongoing climate change. Methodological innovations in this area are expected to be of direct relevance to support engineers in taking effective decisions and setting up appropriate boundary conditions for designing and managing water infrastructures.

This Special Issue aims to collate advancements in the application of data-driven modeling techniques and data-mining approaches in the different possible applications in hydrology, with the purpose of sharing opinions, encouraging the exchange of information and knowledge acquired, promoting the integration of technological progress and scientific knowledge, and helping to increase the acceptance of such applications in the international scientific community.

Due to the interdisciplinary nature of the data-driven modeling techniques and data-mining approaches, there are no preferential topics in the field of hydrology, also because it is in the spirit of this special issue to promote the exchange of experiences and knowledge even from apparently antipodal applications.

Dr. Luigi Berardi
Dr. Daniele Laucelli
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Hydrology is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.


Keywords

  • data-driven modeling
  • data mining
  • computational intelligence
  • machine learning
  • hydrological cycle
  • rainfall-runoff
  • groundwater
  • hydrological modeling
  • climate change
  • in-situ monitoring
  • real-time monitoring

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
Optimizing Groundwater Monitoring Networks Using Integrated Statistical and Geostatistical Approaches
Hydrology 2015, 2(3), 148-175; https://doi.org/10.3390/hydrology2030148 - 24 Aug 2015
Cited by 3
Abstract
The aim of this work is to investigate new approaches using methods based on statistics and geo-statistics for spatio-temporal optimization of groundwater monitoring networks. The formulated and integrated methods were tested with the groundwater quality data set of Bitterfeld/Wolfen, Germany. Spatially, the monitoring [...] Read more.
The aim of this work is to investigate new approaches using methods based on statistics and geo-statistics for spatio-temporal optimization of groundwater monitoring networks. The formulated and integrated methods were tested with the groundwater quality data set of Bitterfeld/Wolfen, Germany. Spatially, the monitoring network was optimized using geo-statistical methods. Temporal optimization of the monitoring network was carried out using Sen’s method (1968). For geostatistical network optimization, a geostatistical spatio-temporal algorithm was used to identify redundant wells in 2- and 2.5-D Quaternary and Tertiary aquifers. Influences of interpolation block width, dimension, contaminant association, groundwater flow direction and aquifer homogeneity on statistical and geostatistical methods for monitoring network optimization were analysed. The integrated approach shows 37% and 28% redundancies in the monitoring network in Quaternary aquifer and Tertiary aquifer respectively. The geostatistical method also recommends 41 and 22 new monitoring wells in the Quaternary and Tertiary aquifers respectively. In temporal optimization, an overall optimized sampling interval was recommended in terms of lower quartile (238 days), median quartile (317 days) and upper quartile (401 days) in the research area of Bitterfeld/Wolfen. Demonstrated methods for improving groundwater monitoring network can be used in real monitoring network optimization with due consideration given to influencing factors. Full article
Show Figures

Figure 1

Back to TopTop