One of the important factors in fertilizer application efficiency in surface fertigation is the shape of inflow hydrographs. In this research, a fertigation model is developed to analyse the effect of surge flow on furrow fertigation. Saint-Venant equations and the advection-dispersion equation were used to estimate water flow and solute transport characteristics, respectively. The field experiments, including different fertigation treatments with surge flow, were conducted to calibrate and evaluate the developed model. Most of the water and nitrate losses occurred through runoff; water losses through runoff ranged from 13.8 to 33.4%, while fertilizer losses varied between 5.1 and 47%. Water and nitrate losses in the second fertigation experiments were higher than those in the first due to the reduction of the surge effect. A comparison between simulated and observed data shows appropriate accuracy of the developed model; the root mean squared error (RMSE) index for nitrate and water runoff losses was 8.4 and 12.1%, respectively. Fertigation during all advance surges was recognized as the desirable option in furrow irrigation with a surge flow.
In order to optimize the management of groundwater resources, accurate estimates of groundwater level (GWL) fluctuations are required. In recent years, the use of artificial intelligence methods based on data mining theory has increasingly attracted attention. The goal of this research is to evaluate and compare the performance of adaptive network-based fuzzy inference system (ANFIS) and Wavelet-ANFIS models based on FCM for simulation/prediction of monthly GWL in the Maragheh plain in northwestern Iran. A 22-year dataset (1996–2018) including hydrological parameters such as monthly precipitation (P) and GWL from 25 observation wells was used as models input data. To improve the prediction accuracy of hybrid Wavelet-ANFIS model, different mother wavelets and different numbers of clusters and decomposition levels were investigated. The new hybrid model with Sym4-mother wavelet, two clusters and a decomposition level equal to 3 showed the best performance. The maximum values of R2 in the training and testing phases were 0.997 and 0.994, respectively, and the best RMSE values were 0.05 and 0.08 m, respectively. By comparing the results of the ANFIS and hybrid Wavelet-ANFIS models, it can be deduced that a hybrid model is an acceptable method in modeling of GWL because it employs both the wavelet transform and FCM clustering technique.
Drainage is an effective way to control water table in the farm fields with high groundwater level in the north of Iran. This study is carried out in the Ran Behshahr field under subsurface drainage system. Artificial Neural Network and DRAINMOD model were evaluated for predicting water table depth in midpoint between two laterals designated as S3PD14 and S3PD15 and drain discharge. Depth of water table and drain discharge were measured for rainfall seasons of 2004 and 2006 years. In this study the feed-forward back propagation model of ANN was used in MATLAB Software. For evaluation of these two models, the value of absolute error (AE), standard error (SE) and R2 were calculated. For the best ANN model, these values were obtained 4.4cm, 5.8cm, and 0.57 for prediction of water table depth and 0.08 mm/day, 0.1 mm/day and 0.59 for drain discharge, respectively. For DRAINMOD model, these values were obtained 15.6 cm, 18.1 cm and 0.42 and 0.27 mm/day, 0.32mm/day and 0.71, respectively. Results indicated that the accuracy of ANN model is better than DRAINMOD model in prediction of water table depth and drain discharge in this case study.
The use of deficit irrigation technique has become inevitable due to the lack of water resources in many parts of the world. The goal of this study is to improve the performance of border irrigation under deficit strategy by determining the optimal cutoff time (Tco). For this purpose, field experiments and simulation modeling were carried out. The experimental borders were different in terms of inflow discharge, soil texture and length. 1024 combinations included different physical and management factors were analyzed by the WinSRFR software. By determining the optimal Tco for each combination, fifteen regression equations were extracted for three irrigation levels and five advance times (Ta) (times when water advanced to 30 to 70% of the border lengths). Two indexes including Y (combination of efficiency and uniformity indices) and Y′ (combination of efficiency, uniformity, and requirement efficiency) were used to evaluate border irrigation performance. Based on the validation results, the relationship between Tco and Ta at the 70% of the border length was introduced as a suitable option. The performance of the selected equation was evaluated using the field data. The results illustrated that the calculated values of Y and Y′ from the proposed method was in high agreement with theses from the common optimization method. Tco obtained from the proposed relationship improved the Y and Y′ indices by 9.4 and 6.6%, respectively, compared to the field conditions. The proposed relationship will guarantee application efficiency above 60%, uniformity and requirement efficiency above 80%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.