Prediction of caspian sea level fluctuations using artificial intelligence

Moslem Imani, Rey Jer You, Chung Yen Kuo

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

An analysis and accurate prediction of the sea level uctuations in Caspian Sea is always important because it potentially aects the natural processes occurring in the basin and inuences the infrastructure built along the coastlines. In this article, dierent approaches in analysis and forecasting of Caspian Sea level anomalies derived satellite altimetry are presented. Compared with the conventional linear regression methods, such as the routine Autoregressive Moving Average (ARMA) models, neural network methodologies and arti�cial intelligence approaches are the more powerful tools inproviding reliable results of the short-term Caspian Sea level anomaly prediction according to our study. Based on the analysis of the minimum Root Mean Square Error and the maximum coeƒcient of determination, the Support Vector Machine (SVM) shows the best performance in predicting the Caspian Sea level anomalies. …e excellent methods and models for the Caspian Sea level analysis included in this article can be employed to monitor water level changes in other water bodies whose time series of water levels have the stochastic behavior in the future.

Original languageEnglish
Title of host publicationGeospatial Technology for Water Resource Applications
PublisherCRC Press
Pages243-257
Number of pages15
ISBN (Electronic)9781498719698
ISBN (Print)9781498719681
DOIs
Publication statusPublished - 2016 Jan 1

All Science Journal Classification (ASJC) codes

  • Agricultural and Biological Sciences(all)
  • Environmental Science(all)
  • Engineering(all)
  • Earth and Planetary Sciences(all)

Fingerprint Dive into the research topics of 'Prediction of caspian sea level fluctuations using artificial intelligence'. Together they form a unique fingerprint.

  • Cite this

    Imani, M., You, R. J., & Kuo, C. Y. (2016). Prediction of caspian sea level fluctuations using artificial intelligence. In Geospatial Technology for Water Resource Applications (pp. 243-257). CRC Press. https://doi.org/10.1201/9781315370989-25