Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
The leaf area measurement is an important parameter in understanding the growth and physiology of a plant. Therefore, this study aimed to develop the best leaf area estimation model for tomato plants grown in plastic greenhouse conditions. | Turkish Journal of Agriculture and Forestry Turk J Agric For (2016) 40: 203-212 © TÜBİTAK doi:10.3906/tar-1408-28 http://journals.tubitak.gov.tr/agriculture/ Research Article A modeling study with an artificial neural network: developing estimation models for the tomato plant leaf area 1 1 2, 3 Hande KÜÇÜKÖNDER , Sedat BOYACI *, Adil AKYÜZ Department of Business Administration, Faculty of Economics and Administrative Sciences, Bartın University, Bartın, Turkey 2 Department of Biosystems Engineering, Ahi Evran University, Kırşehir, Turkey 3 Department of Biosystems Engineering, Kahramanmaraş Sütçü İmam University, Kahramanmaraş, Turkey Received: 08.08.2014 Accepted/Published Online: 21.08.2015 Final Version: 05.02.2016 Abstract: The leaf area measurement is an important parameter in understanding the growth and physiology of a plant. Therefore, this study aimed to develop the best leaf area estimation model for tomato plants grown in plastic greenhouse conditions. The artificial neural network (ANN) and regression analysis techniques were used in the formation of a leaf area estimation model by using the leaf width and leaf length measurements determined by the linear measurement method. The plant material for the study consisted of 420 leaf samples of the Typhoon F1 tomato type grown in plastic greenhouse conditions. In the comparison of the created models according to both methods, the criteria of selecting low values for the root mean square error (RMSE), the mean absolute error (MAE), and the mean absolute percentage error (MAPE), and high value for the determination coefficient (R2) were taken into account, and the best estimation models were determined. In the comparison made according to these criteria, it was concluded that the error values of the ANN model [R2 = 0.96, RMSE = 3.30, MAE = 1.94, and MAPE = 0.05] were lower than those of the regression model [R2 = 0.92, RMSE = 4.71, MAE = 3.31, and MAPE = 0.08], and that the ANN method provided a .
