| dc.creator |
Kuzugudenli, E. |
|
| dc.date |
2018-01-01T00:00:00Z |
|
| dc.date.accessioned |
2021-12-03T11:47:06Z |
|
| dc.date.available |
2021-12-03T11:47:06Z |
|
| dc.identifier |
af2374db-d2bf-474f-8349-01bc661fe955 |
|
| dc.identifier |
10.15666/aeer/1604_52275235 |
|
| dc.identifier |
https://avesis.sdu.edu.tr/publication/details/af2374db-d2bf-474f-8349-01bc661fe955/oai |
|
| dc.identifier.uri |
http://acikerisim.sdu.edu.tr/xmlui/handle/123456789/94282 |
|
| dc.description |
Air humidity has great importance for living beings, especially plants. Air humidity controls vaporisation on earth's surface and transpiration of plant leaves. Additionally, it prevents most of the radiation from the sun and reflected sun rays from reaching the ground and prevents excessive heating or cooling. The purpose of this study is to predict relative humidity as an important climate parameter, based on annual total precipitation, average ambient temperature, and altitude. Regression and artificial intelligence network models were developed by using monthly average temperature, total precipitation, and altitude parameters obtained from 177 meteorological stations in Turkey to predict relative humidity. When analysed, the model developed with the artificial neural network method had greater predictive power (R-2 = 0.84) than the model developed with multiple linear regression (R-2 = 0.76). In this study may be applicable in climate conditions that are similar to those in Turkey. |
|
| dc.language |
eng |
|
| dc.rights |
info:eu-repo/semantics/closedAccess |
|
| dc.title |
RELATIVE HUMIDITY MODELING WITH ARTIFICIAL NEURAL NETWORKS |
|
| dc.type |
info:eu-repo/semantics/article |
|