| 1. |
- Jeihouni, Mehrdad, et al.
(författare)
-
Decision Tree-Based Data Mining and Rule Induction for Identifying High Quality Groundwater Zones to Water Supply Management : a Novel Hybrid Use of Data Mining and GIS
- 2020
-
Ingår i: Water Resources Management. - : Springer Science and Business Media LLC. - 0920-4741 .- 1573-1650. ; 34:1, s. 139-154
-
Tidskriftsartikel (refereegranskat)abstract
- Groundwater is an important source to supply drinking water demands in both arid and semi-arid regions. Nevertheless, locating high quality drinking water is a major challenge in such areas. Against this background, this study proceeds to utilize and compare five decision tree-based data mining algorithms including Ordinary Decision Tree (ODT), Random Forest (RF), Random Tree (RT), Chi-square Automatic Interaction Detector (CHAID), and Iterative Dichotomiser 3 (ID3) for rule induction in order to identify high quality groundwater zones for drinking purposes. The proposed methodology works by initially extracting key relevant variables affecting water quality (electrical conductivity, pH, hardness and chloride) out of a total of eight existing parameters, and using them as inputs for the rule induction process. The algorithms were evaluated with reference to both continuous and discrete datasets. The findings were speculative of the superiority, performance-wise, of rule induction using the continuous dataset as opposed to the discrete dataset. Based on validation results, in continuous dataset, RF and ODT showed higher and RT showed acceptable performance. The groundwater quality maps were generated by combining the effective parameters distribution maps using inducted rules from RF, ODT, and RT, in GIS environment. A quick glance at the generated maps reveals a drop in the quality of groundwater from south to north as well as from east to west in the study area. The RF showed the highest performance (accuracy of 97.10%) among its counterparts; and so the generated map based on rules inducted from RF is more reliable. The RF and ODT methods are more suitable in the case of continuous dataset and can be applied for rule induction to determine water quality with higher accuracy compared to other tested algorithms.
|
|
| 2. |
- Jeihouni, Mehrdad, et al.
(författare)
-
Long term groundwater balance and water quality monitoring in the eastern plains of Urmia Lake, Iran : A novel GIS based low cost approach
- 2018
-
Ingår i: Journal of African Earth Sciences. - : Elsevier BV. - 1464-343X. ; 147, s. 11-19
-
Tidskriftsartikel (refereegranskat)abstract
- Groundwater quality and quantity are two major challenges in arid and semi-arid regions, due to their critical roles in sustainable agricultural development. Irrigated lands are spread all over Urmia Lake's surrounding plains in Iran. Due to the risk of saltwater intrusion as a result of over-exploitation from groundwater resources, it is important to monitor the groundwater quality and quantity through time and space. In this paper, the groundwater quantity was assessed over 11 years applying a novel groundwater balance estimation method based on water table data and 3D modeling; groundwater quality were monitored over 10 years using GIS and geostatistics; and the saltwater intrusion were investigated through generated quality maps and regression analysis. Results indicate that the groundwater balance was negative during the study period. Furthermore, the aquifers quality decreased over the study period, which was severe in west and southwest of the study area. The saltwater intrusion was proved and salty water was spread from west to other zones. The saltwater intrusion into aquifers increased electrical conductivity, chloride and sodium concentrations and will cause many ecological and agricultural problems. The novel and practicable approach utilized for groundwater balance quantitative assessment is suitable for countries lacking hydrological properties databases.
|
|
| 3. |
- Mansourian, Ali, et al.
(författare)
-
Expert System to Enhance the Functionality of Clearinghouse Services
- 2011
-
Ingår i: Computers, Environment and Urban Systems. - : Elsevier BV. - 0198-9715. ; 35:2, s. 159-172
-
Tidskriftsartikel (refereegranskat)abstract
- Abstract in UndeterminedSpatial data clearinghouses are one of the key features of a spatial data infrastructure (SDI). However, recent research indicates that few national clearinghouses function well, as the spatial data resources available cannot be satisfactorily accessed or optimally used. To improve the functionality, we propose that clearinghouses to be complemented with expert systems and semantic matching. The expert system facilitates automatic determination of candidate datasets and the conversion of the available data to the required data. A schema translator is also used to find similar data that might be used in other disciplines or other datasets by semantic matching. In order to accomplish this, we have developed a method of identifying available data and methods for data conversion. The methodology is implemented using standardized map services. Practical tests show that the discovery of available data in the clearinghouse satisfying users' requirements is substantially increased, which is an important step forward in building future SDIs. (C) 2010 Elsevier Ltd. All rights reserved.
|
|
| 4. |
- Omidipoor, Morteza, et al.
(författare)
-
Knowledge discoveryweb service for spatial data infrastructures
- 2021
-
Ingår i: ISPRS International Journal of Geo-Information. - : MDPI AG. - 2220-9964. ; 10:1
-
Tidskriftsartikel (refereegranskat)abstract
- The size, volume, variety, and velocity of geospatial data collected by geo-sensors, people, and organizations are increasing rapidly. Spatial Data Infrastructures (SDIs) are ongoing to facilitate the sharing of stored data in a distributed and homogeneous environment. Extracting high-level information and knowledge from such datasets to support decision making undoubtedly requires a relatively sophisticated methodology to achieve the desired results. A variety of spatial data mining techniques have been developed to extract knowledge from spatial data, which work well on centralized systems. However, applying them to distributed data in SDI to extract knowledge has remained a challenge. This paper proposes a creative solution, based on distributed computing and geospatial web service technologies for knowledge extraction in an SDI environment. The proposed approach is called Knowledge DiscoveryWeb Service (KDWS), which can be used as a layer on top of SDIs to provide spatial data users and decision makers with the possibility of extracting knowledge from massive heterogeneous spatial data in SDIs. By proposing and testing a system architecture for KDWS, this study contributes to perform spatial data mining techniques as a service-oriented framework on top of SDIs for knowledge discovery. We implemented and tested spatial clustering, classification, and association rule mining in an interoperable environment. In addition to interface implementation, a prototype web-based system was designed for extracting knowledge from real geodemographic data in the city of Tehran. The proposed solution allows a dynamic, easier, and much faster procedure to extract knowledge from spatial data.
|
|
| 5. |
- Pilesjo, Petter, et al.
(författare)
-
Features of the international MSC educational programme in environmental management and modelling
- 2018
-
Ingår i: Geodesy and Cartography. - : Vilnius Gediminas Technical University. - 2029-6991 .- 2029-7009. ; 44:4, s. 134-139
-
Tidskriftsartikel (refereegranskat)abstract
- “International Msc Educational Programme in Environmental Management and Modelling” (GeoNetC) is a European Commission funded project under ERASMUS+: Higher Education – International Capacity Building programme (Project No 561967-EPP-1-2015-1-SE-EPPKA2-CBHE-JP). It began in October 2015 and ended in October 2018. Initiated by the Lund University and partners from the Middle East countries, the GeoNetC project is an ambitious project aiming to match labour market needs with geospatial education offer both in Europe and Middle East countries. The aim of this three-year project is to enable European universities to exchange best practices and innovation with each other and with Middle Eastern universities regarding the mismatch between Europe’s geospatial education and training and the geospatial education in Middle East countries. There is a growing need for well-trained students at all levels – vocational, bachelors, masters – in the field of geospatial technologies. Obviously there is a growing number of jobs available in land surveying, mapping data collection, data processing, data delivery and turning data into information in both European and Middle East countries. Through cooperation, all partners will improve the quality of their respective academic programs. The European partners will make their courses more attractive and well adjusted for students from the Middle East. As well, they will increase the general quality and add state-of-the-art learning components to their offerings, and the partners from the region will significantly increase the academic level and quality in the education they provide. There will be spin-offs into other subjects than environment/Geomatics, since both the pedagogic models developed (e.g. e-Learning) and communication and administrative tools can be used throughout the partner universities. Therefore, this partnership cooperation will be of great value to Partner Countries as well as to Programme Countries. A number of distance learning courses/modules are developed jointly by partner institutions in Europe and the Middle East. The main aim of the network is to promote the use of spatial information and earth observation for environmental management and modelling through capacity building and institutional development, via a network in which all partners would contribute from their own positions of strength. All 13 modules are following EU higher education standards regarding e.g. ECTS, and learning outcomes. The outcome of the project, in terms of courses/modules, will be freely used among the partners, with the possibilities of offering individual courses or a whole MSc programme, whether individually or together. All produced material was evaluated/quality controlled by an external evaluation group of independent experts within environmental management and modelling, higher education, as well as pedagogy.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Toomanian, Ara, et al.
(författare)
-
Automatic integration of spatial data in viewing services
- 2013
-
Ingår i: Journal of Spatial Information Science. - 1948-660X. ; 6:2013, s. 43-58
-
Tidskriftsartikel (refereegranskat)abstract
- Geoportals are increasingly used for searching, viewing, and downloading spatial data. This study concerns methods to improve the visual presentation in viewing services. When spatial data in a viewing service are taken from more than one source there are often syntactic, semantic, topological, and geometrical conflicts that prevent maps being fully consistent. In this study we extend a standard view service with methods to solve these conflicts. The methods are based on: (1) semantic labels of data in basic services, (2) a rule-base in the portal layer, and (3) integration methods in the portal layer. To evaluate the methodology, we use a case study for adding historical borders on top of a base-map. The results show that the borders are overlaid on top of the map without conflicts, and that a consistent map is generated automatically as an output. The methodology can be generalized to add other types of data on top of a base-map.
|
|
| 9. |
- Toomanian, Ara, et al.
(författare)
-
Automatic Symbolisation Methods for Geoportals
- 2012
-
Ingår i: Cartographic Journal. - 0008-7041. ; 49:2, s. 153-163
-
Tidskriftsartikel (refereegranskat)abstract
- There is currently a high demand for spatial data usage within web applications. From a technical viewpoint, web services and geoportals aim to fulfil user requirements; however, the current cartographic methods do not satisfy the needs of the end users. The problem is more challenging when the final map contains data from various sources that have various cartographic characteristics; therefore, the vital information might be located under the base map layer. In this paper, we propose the concept of layer priorities as foreground, middle ground or background, and we propose the two following methods to enhance the symbolisation: polygon overlay and colour saturation methods. The results from two case studies show that these methods can satisfy the requirements of the end users.
|
|
| 10. |
- Toomanian, Ara, et al.
(författare)
-
Cartographic enhanced geoportals
- 2011
-
Ingår i: Proceedings of the 25th International Cartographic Conference. - 9781907075056
-
Konferensbidrag (refereegranskat)
|
|
