Drip irrigation is considered as one of the most efficient irrigation systems. Knowledge of the soil wetted perimeter arising from infiltration of water from drippers is important in the design and management of efficient irrigation systems. To this aim, numerical models can represent a powerful tool to analyze the evolution of the wetting pattern during irrigation, in order to explore drip irrigation management strategies, to set up the duration of irrigation, and finally to optimize water use efficiency. This paper examines the potential of genetic programming (GP) in simulating wetting patterns of drip irrigation. First by considering 12 different soil textures of USDA-SCS soil texture triangle, different emitter discharge and duration of irrigation, soil wetting patterns have been simulated by using HYDRUS 2D software. Then using the calculated values of depth and radius of wetting pattern as target outputs, two different GP models have been considered. Finally, the capability of GP for simulating wetting patterns was analyzed using some values of data set that were not used in training. Results showed that the GP method had good agreement with results of HYDRUS 2D software in the case of considering full set of operators with R2 of 0.99 and 0.99 and root mean squared error of 2.88 and 4.94 in estimation of radius and depth of wetting patterns, respectively. Also, field experimental results in a sandy loam soil with emitter discharge of 4 L h–1 showed reasonable agreement with GP results. As a conclusion, the results of the study demonstrate the usefulness of the GP method for estimating wetting patterns of drip irrigation.

Samadianfard, S., Sadraddini, A., Nazemi, A.H., Provenzano, G., & Kisi, Ö. (2012). Estimating soil wetting patterns for drip irrigation using genetic programming. SPANISH JOURNAL OF AGRICULTURAL RESEARCH, 10(4)(4), 1155-1166 [http://dx.doi.org/10.5424/sjar/2012104-502-11].

Estimating soil wetting patterns for drip irrigation using genetic programming

PROVENZANO, Giuseppe;
2012

Abstract

Drip irrigation is considered as one of the most efficient irrigation systems. Knowledge of the soil wetted perimeter arising from infiltration of water from drippers is important in the design and management of efficient irrigation systems. To this aim, numerical models can represent a powerful tool to analyze the evolution of the wetting pattern during irrigation, in order to explore drip irrigation management strategies, to set up the duration of irrigation, and finally to optimize water use efficiency. This paper examines the potential of genetic programming (GP) in simulating wetting patterns of drip irrigation. First by considering 12 different soil textures of USDA-SCS soil texture triangle, different emitter discharge and duration of irrigation, soil wetting patterns have been simulated by using HYDRUS 2D software. Then using the calculated values of depth and radius of wetting pattern as target outputs, two different GP models have been considered. Finally, the capability of GP for simulating wetting patterns was analyzed using some values of data set that were not used in training. Results showed that the GP method had good agreement with results of HYDRUS 2D software in the case of considering full set of operators with R2 of 0.99 and 0.99 and root mean squared error of 2.88 and 4.94 in estimation of radius and depth of wetting patterns, respectively. Also, field experimental results in a sandy loam soil with emitter discharge of 4 L h–1 showed reasonable agreement with GP results. As a conclusion, the results of the study demonstrate the usefulness of the GP method for estimating wetting patterns of drip irrigation.
Settore AGR/08 - Idraulica Agraria E Sistemazioni Idraulico-Forestali
Samadianfard, S., Sadraddini, A., Nazemi, A.H., Provenzano, G., & Kisi, Ö. (2012). Estimating soil wetting patterns for drip irrigation using genetic programming. SPANISH JOURNAL OF AGRICULTURAL RESEARCH, 10(4)(4), 1155-1166 [http://dx.doi.org/10.5424/sjar/2012104-502-11].
File in questo prodotto:
File Dimensione Formato  
74 Genetic programming.pdf

Solo gestori archvio

Dimensione 2.88 MB
Formato Adobe PDF
2.88 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10447/73251
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 22
  • ???jsp.display-item.citation.isi??? 17
social impact