Dam blocks movement prediction using artifical neural networks
Journal Title: Geodetski glasnik - Year 2017, Vol 51, Issue 48
Abstract
The dams are very important objects for production of electric energy, irrigation, flood management and tourism. However, besides all benefits the dams provide, they also represent great danger for areas downstream because there is always risk of dam failure. To prevent dam failure it is important to perform regular dam monitoring and for that purpose geodetic and physical methods are used. Geodetic methods use special network of points for object monitoring where reference points are used for monitoring of object points which are strategically distributed on the object. By quality prediction of object behavior it would be possible to prevent further damage on the object and additionally to save human lives in cases of great danger. In this paper artificial neural networks (ANNs) are used for dam movement prediction. ANNs are very popular tool for prediction since they are known for their quick learning ability and good generalization ability which gives them advantage compared to traditional statistical methods.
Authors and Affiliations
Hamzić Adis, Zikrija Avdagić
Keywords
Related Articles
- EP ID EP309219
- DOI -
- Views 213
- Downloads 0
Dam blocks movement prediction using artifical neural networks
The dams are very important objects for production of electric energy, irrigation, flood management and tourism. However, besides all benefits the dams provide, they also represent great danger for areas downstream becau...
Vela and Mala Palagruža - Diomediae Insulae
Sailing route leading from central Dalmatia to the Gargano region was one of the most heavily travelled seaways in antiquity. On the one hand it is marked by the toponyms associated with Diomedes and his cult in historic...
Evaluating training data for crop type classifıcation using support vector machine and random forests
This study evaluated the effectiveness of three different training datasets for crop type classification using both support vector machines (SVMs) and random forests (RFs). In supervised classification, one of the main f...
Different methods for remote sensing data integration
Nowadays remote sensing is an indispensable source of information about Earth's surface, primarily satellite-based remote sensing systems. Traditionally, the analysis of data collected from a particular area was based on...
Changes in the level of magnetic declination in the Adriatic from 1806 to 1995 – a contribution to the history of Adriatic seafaring
The paper analyzes changes in magnetic declination in the Adriatic Sea from the first measurements in 1806 to the latest isogonic charts from 1995. The basis of analysis are data provided by the Adriatic pilot books as l...