| ESTIMATING WATER LEVEL IN THE URMIA LAKE USING SATELLITE DATA: A MACHINE LEARNING APPROACH |
| Paper ID : 1143-SMPR |
| Authors: |
|
Mahboubeh Boueshagh *, Mahdi Hasanlou School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran |
| Abstract: |
| Lakes play an essential role in the development of cities and also have a significant impact on the environment and ecosystem balance of their area. Using remote sensing methods and advanced modeling techniques, it is possible to monitor natural phenomena, such as lakes' water level. Urmia Lake is one of the most momentous ecosystems in Iran, whose issue of drying has become a global environmental issue in recent years. There are many parameters involved in this crisis; one of them is snow, which plays an important role in the fluctuations of Urmia Lake's water level and water resources management in the northwest of Iran. In this regard, the purpose of this paper is estimating the water level of the Urmia lake during 2000-2006 using observed water-level, monthly snow cover in the whole catchment area of the Urmia lake, and monthly direct precipitation and evaporation. For this purpose, Support Vector Regression (SVR), the most outstanding kernel method, with various kernel types has been used. Furthermore, four scenarios are considered with different variables as inputs, and the output of all scenarios is the water level of the lake. The results of training and testing data indicate the substantial impact of snow on retrieving the water level of the Urmia Lake at the desired period, and due to the complexity of the data relationships, the Gaussian kernel generally had better results. On the other hand, Quadratic and Cubic kernels did not work well. |
| Keywords: |
| Water Level, Urmia Lake, MODIS Snow Cover, Evaporation, Precipitation, Support Vector Regression (SVR), Water Budget Procedure |
| Status : Conditional Accept (Poster) |
