Akademik Veri Yönetim Sistemi
Mustafa Kemal Üniversitesi tarım bilimleri dergisi (online), cilt.24, sa.1, ss.149-154, 2019 (Hakemli Dergi)
Aims: The aim of this study is to estimate monthly precipitation by supportvector regression and the nearest neighbourhood methods usingmeteorological variables data of Chabahar station.Methods and Results: Monthly precipitation was modelled by using twosupport vector regression and the nearest neighbourhood methods basedon the two proposed input combinations.Conclusions: The results showed that the support vector regressionmethod using normalized polynomial kernel function has higher accuracyand it has lower estimation error than the nearest neighbour method.Significance and Impact of the Study: Precipitation is one of the mostimportant parts of the water cycle and plays an important role in assessingthe climatic characteristics of each region. Modelling of monthlyprecipitation values for a variety of purposes, such as flood and sedimentcontrol, runoff, sediment, irrigation planning, and river basinmanagement, is very important. The modelling of precipitation in eachregion requires the existence of accurately measured historical data suchas humidity, temperature, wind speed, etc. Limitations such as insufficientknowledge of precipitation on spatial and temporal scales as well as thecomplexity of the relationship between precipitation-related climaticparameters make it impossible to estimate precipitation usingconventional inaccurate and unreliable methods.