Forecasting the average monthly rainfall in the northwest of Iran using teleconnections and machine learning

Articles in Press

Document Type : Research Article

Authors

1 Climate research Institute - Assistant Professor

2 Associate Professor,

3 Faculty Member

Abstract

Forecasting monthly and seasonal rainfall is very important from both hydrology to supply water resources and climatology and atmospheric hazards points of views. Monthly and seasonal forecasts are widely used in sectors such as energy and agriculture. On the other hand, it has been proven that large-scale atmospheric teleconnections and indices have an effect on the atmospheric conditions of different parts of the earth. Machine learning methods are widely used to predict different atmospheric variables. The reason for using these methods is the high modeling ability of these algorithms when faced with a large amount of data. At the same time, these algorithms have many other capabilities such as the ability to model uncertainty. In this article, three machine learning methods including artificial neural network, gradient boosting and random forest are used for prediction. The performance of these algorithms will be compared with each other in monthly and seasonal forecasting scales. The studied area includes a part of northwestern Iran, including the area of Lake Urmia basin, which is of great importance. Three evaluation criteria including Nash-Sutcliffe, correlation coefficient and root mean square error were used to evaluate the result.

In this paper, by using the Nino 3.4, WP, and NAO indices, the regional average monthly rainfall in northwestern Iran, including the Lake Urmia, is predicted with the help of several machine learning methods. The reason for choosing these three indicators is their effectiveness on the rainfall of the study area in the northwest of Iran, which has been discussed in the literature review of the research. In this paper, two monthly and seasonal modeling methods are compared. Since teleconnections may be effective on precipitation with a delay, different delays of zero to three months were considered for all three studied teleconnections and the best results were obtained. In this research, three methods of machine learning, random forest, neural network and gradient boosting were used. In the monthly mode, the performance of the gradient boosting method (with a three-month delay for the WP index and the other two indices without delay) was better than the random forest method, and the neural network ranked last in terms of performance. In terms of estimating the extreme precipitation, the gradient boosting method has an acceptable performance. In seasonal modeling, for the three seasons of Spring (March-April-May (MAM)), Autumn (September-October-November (SON)) and Winter (December-January-February (DJF)), the performance of random forest and for the Summer season ( June-July-August (JJA)), the performance of the gradient boosting method was superior to other methods.

Keywords

Iranian Journal of Geophysics

Articles in Press, Accepted Manuscript
Available Online from 16 December 2023

Files

Share

How to cite

Statistics