ESTIMATION RAINFALL VARIATION USING ARTIFICIAL NEURAL NETWORKS AND GEOSTATISTICS TECHNIQUES OVER NORTHWEST OF IRAN

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

MATKAN A.A.; ARABI B.; LASHKARI H.; MIRBAGHERI B.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Iranian Journal of Remote Sensing & GIS Year:2013 | Volume:4 | Issue:4 Page(s): 37-54

Download Full-Text

Persian Verion

View:

1,090

Download:

Cites:

Information Journal Paper

Title

ESTIMATION RAINFALL VARIATION USING ARTIFICIAL NEURAL NETWORKS AND GEOSTATISTICS TECHNIQUES OVER NORTHWEST OF IRAN

Author(s)

MATKAN A.A. | ARABI B. | LASHKARI H. | MIRBAGHERI B. | Issue Writer Certificate

Keywords

SPATIOTEMPORAL RECONSTRUCTIONQ2

ARTIFICIAL NEURAL NETWORKSQ2

BACK PROPAGATION ERROR ALGORITHMQ2

INTERPOLATIONQ2

GEOSTATICTICSQ2

Abstract

Accessing the long-term rainfall statistics in most of regions is restrained due to the lack of rainfall stations and drawbacks in recording data. Developing the ARTIFICIAL NEURAL NETWORKS leads to reconstruct the missing information in dispersed meteorological stations even within the years in which the recording stations were absent. In this research the average monthly rainfall data including 36600 collected records for 305 meteorological stations were employed to reconstruct the missing monthly average rainfall values. The selected study area is a vast part in north west of Iran; including the provinces Ardebil and West East Azerbaijan and the models have been run for a decade between 1995 and 2004. The network structure has been based on two hidden layers and trained using the BACK PROPAGATION ERROR ALGORITHM. The longitude, latitude, elevation, slope, month number (1-12) and the average monthly rainfall values for 1 to 26 nearest neighbors for each station have been used as the model input variables. The results showed that using 5 nearest neighboring stations gives the highest precision and the obtained correlation coefficient during 1995-2004 is 0.86 for the training data. The corresponding value of reconstructed data for West and East Azerbaijan and Ardebil provinces were 0.82, 0.78 and 0.70 during 1985-1994 respectively. The reason of such differences in the mentioned provinces arises from the fact that the number of stations taking part in training process decreases from West Azerbaijan to Ardebil. The interpolated maps have then been created using different geostatistics methods based on the output predicted estimates resulted from neural networks. Consequently, this method allows investigating the spatiotemporal distribution of rainfall along with creating the monthly interpolated maps for years 1985 to 2004 in the study area. For validating the INTERPOLATION methods, the cross validation has been employed and the Mean Biased Error and Mean Absolute Error and Root Mean Square Error have been compared.

Cites

No record.

References

No record.

Cite

APA: Copy

MATKAN, A.A., ARABI, B., LASHKARI, H., & MIRBAGHERI, B.. (2013). ESTIMATION RAINFALL VARIATION USING ARTIFICIAL NEURAL NETWORKS AND GEOSTATISTICS TECHNIQUES OVER NORTHWEST OF IRAN. REMOTE SENSING & GIS, 4(4), 37-54. SID. https://sid.ir/paper/184187/en

Vancouver: Copy

MATKAN A.A., ARABI B., LASHKARI H., MIRBAGHERI B.. ESTIMATION RAINFALL VARIATION USING ARTIFICIAL NEURAL NETWORKS AND GEOSTATISTICS TECHNIQUES OVER NORTHWEST OF IRAN. REMOTE SENSING & GIS[Internet]. 2013;4(4):37-54. Available from: https://sid.ir/paper/184187/en

IEEE: Copy

A.A. MATKAN, B. ARABI, H. LASHKARI, and B. MIRBAGHERI, “ESTIMATION RAINFALL VARIATION USING ARTIFICIAL NEURAL NETWORKS AND GEOSTATISTICS TECHNIQUES OVER NORTHWEST OF IRAN,” REMOTE SENSING & GIS, vol. 4, no. 4, pp. 37–54, 2013, [Online]. Available: https://sid.ir/paper/184187/en

Related Journal Papers