Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   IRANIAN JOURNAL OF SOIL AND WATER RESEARCH   2008 , Volume 39 , Number 1; Page(s) 47 To 56.
 
Paper: 

ESTIMATING BARLEY YIELD IN EASTERN AZERBAIJAN USING DROUGHT INDICES AND CLIMATIC PARAMETERS BY ARTIFICIAL NEURAL NETWORK (ANN)

 
 
Author(s):  RAHMANI E., LIAGHAT A.M.*, KHALILI A.
 
* UNIVERSITY COLLEGE OF AGRICULTURE AND NATURAL RESOURCES, UNIVERSITY OF TEHRAN
 
Abstract: 

Finding the meteorological parameters' and drought indices' relationship with barley yield through an employment of Artificial Neural Network was the main objective of the present research work. To achieve the objective, such meteorological parameters as: precipitation; averages of maximum and minimum temperatures; mean average temperature; sumation of temperature recordings exceeding 10oc; evaporation; water vapor pressure; average wind speed, as well as sunshine were taken into account. Such drought indices as: Percent Normal Index, Standard Index of Annual Precipitation, Hydrothermal Index, Nguyen Index, Transeau Index, Standardized Precipitation Index, Shashko Moisture Drought Index and Rainfall Anormaly Index obtained from Tabriz and Miane meteorological stations were evaluated in terms of normality as well as their mutual influences. Optimum ANN models between barely yield and the above mentioned climatic parameters and drought indexes were obtained. Among the proposed models, the one with five input parameters (Rainfall Anomaly Index, Transeau Index, SP124, Sunshine, and the average of minimum temperatures) for Tabriz station with 30 years of data was found out to be the most suitable model. The results of the study indicated that drought indexes, Nguyen Index, Transeau Index, Rainfall Anomaly Index, and Standardized Precipitation Index (SPI24) bear the highest correlation with barely yield. Due to a high determination coefficient of. the optimum model concluded in this research, ANN model is recommended for monitoring and predicting agricultural drought.

 
Keyword(s): SOIL QUALITY, PEDO-TRANSFER FUNCTIONS, SOIL MOISTURE RETENTION CURVE, INFLECTION POINT, CONVENIENTLY MEASURABLE SOIL PROPERTIES, SALINE SOIL, CALCAREOUS SOIL
 
 
References: 
  • Not Registered.
  •  
  •  
 
Citations: 
  • Not Registered.
 
+ Click to Cite.
APA: Copy

RAHMANI, E., & LIAGHAT, A., & KHALILI, A. (2008). ESTIMATING BARLEY YIELD IN EASTERN AZERBAIJAN USING DROUGHT INDICES AND CLIMATIC PARAMETERS BY ARTIFICIAL NEURAL NETWORK (ANN). IRANIAN JOURNAL OF SOIL AND WATER RESEARCH, 39(1), 47-56. https://www.sid.ir/en/journal/ViewPaper.aspx?id=276343



Vancouver: Copy

RAHMANI E., LIAGHAT A.M., KHALILI A.. ESTIMATING BARLEY YIELD IN EASTERN AZERBAIJAN USING DROUGHT INDICES AND CLIMATIC PARAMETERS BY ARTIFICIAL NEURAL NETWORK (ANN). IRANIAN JOURNAL OF SOIL AND WATER RESEARCH. 2008 [cited 2021July31];39(1):47-56. Available from: https://www.sid.ir/en/journal/ViewPaper.aspx?id=276343



IEEE: Copy

RAHMANI, E., LIAGHAT, A., KHALILI, A., 2008. ESTIMATING BARLEY YIELD IN EASTERN AZERBAIJAN USING DROUGHT INDICES AND CLIMATIC PARAMETERS BY ARTIFICIAL NEURAL NETWORK (ANN). IRANIAN JOURNAL OF SOIL AND WATER RESEARCH, [online] 39(1), pp.47-56. Available: https://www.sid.ir/en/journal/ViewPaper.aspx?id=276343.



 
 
Persian Abstract Yearly Visit 35
 
 
Latest on Blog
Enter SID Blog