Knowledge of infiltration process is very helpful in designing and planning of irrigation networks. In this study, the Artificial Neural Network (ANN) technique was used to estimate the infiltration rate of the soil. The performance of ANN was equated with other types of artificial intelligence techniques such as Gaussian process (GP), gene expression Programming (GEP), and generalized neural network (GRNN). While a GP, GRNN, and GEP model gives a good estimation performance, the ANN model outperforms them. For this study, a data-set containing 155 observations of the field was analyzed. Out of 155, a sum of 105 data was selected for preparing different algorithms, whereas rest 50 data were selected to test the models. The best ANN model was generated with a single hidden layer with 9 neurons, momentum = 0.2, learning rate = 0.1, and iteration = 1500, respectively. The ANN achieved a coefficient of correlation (CC) equal to 0.9816 and 0.9133 for the preparing and testing data, respectively. Sensitivity analysis concludes that the parameter time is the most effective parameter for the estimation of infiltration rate.

The aim of the present investigation is to evaluate the performance of infiltration models used to calculate the infiltration rate of the soils. Ten different locations were chosen to measure the infiltration rate in NIT Kurukshetra. The instrument used for the experimentation was double ring infiltrometer. Some of the popular infiltration models like Horton’s, Philip’s, Modified Philip’s and Green–Ampt were fitted with infiltration test data and performance of the models was determined using Nash–Sutcliffe efficiency (NSE), coefficient of correlation (C.C) and Root mean square error (RMSE) criteria. The result suggests that Modified Philip’s model is the most accurate model where values of C.C, NSE and RMSE vary from 0.9947–0.9999, 0.9877–0.9998 to 0.1402–0.6913 (mm/h), respectively. Thus, this model can be used to synthetically produce infiltration data in the absence of infiltration data under the same conditions.

Knowledge of the infiltration process is beneficial in designing and planning of irrigation networks, soil erosion, hydrologic design, and watershed management. In this study, the infiltration process was analyzed using predictive models of artificial neural network (ANN), multi-linear regression (MLR), Random Forest regression (RF), M5P tree, and their performances were compared with the empirical model: Kostiakov model. Field experimental data was implemented for training and testing the above models, and their outcomes were assessed with the help of suitable performance assessment parameters. These models were assessed using a field dataset containing 340 observations, out of which 70% were used for the training purpose and the remaining for the testing. The RF-based models perform better than other models with Nash-Sutcliffe model efficiency (NSE) equal to 0.9963 and 0.9904 for the training and testing stages, correspondingly. ANN, MLR, and M5P model also give a good prediction performance, but the Kostiakov model’s performance is inferior. Sensitivity investigation suggests that the parameters, cumulative time, and moisture content in the soil are the most influential parameters for assessing the cumulative infiltration of soil.

In this investigation, the performance of the four soft computing techniques, that is M5P model tree, random forest (RF), bagging M5P model tree and group method for data handling (GMDH) were compared to estimate the sodium absorption ratio (SAR). Total data set consists of water quality of three (Alsthar, Biranshahr and Khoramabad in Iran) watershed out of which 70% data used to train the model and 30% data were used to test the model. The models’ accuracy were assessed using three performance evaluation parameters, which were correlation coefficient (C.C.), root mean square error (RMSE) and maximum absolute error (MAE). The obtained results suggest that the bagging M5P model tree regression technique (with C.C. = 0.9993, RMSE = 0.0097 and MAE = 0.006) is more accurate to estimate the SAR as compare to the M5P model tree, RF and GMDH for the given study area. Uncertainty analysis also suggested the same trends with minimum mean prediction error, standard deviation of prediction error and width of uncertainty band. Further, a comparison was also done with the previous study which also shows bagging M5P model tree predicts the SAR accurately.

Estimating soil temperature (ST) profile is identified as essential knowledge for plants, crop growth, and germination in all agriculture regions. In this study, daily soil temperature (DST) was modeled using Multilayer perceptron (MLP) model, Gaussian Process (GP), Random Forest (RF), and the M5P model methods for estimating and comparing DST in arid regions. The data selected to test the proposed models are obtained from two stations in Tabriz and Ahar, located in the Azerbaijan province of Iran. Input dataset includes air temperature, relative humidity, wind speed, and sunshine as dependent parameters, whereas ST at depths of 5 cm was selected for the target in model development. The results show the MLP works better than GP-, RF-, and M5P-based models in estimating the DST, with excellent performance indicators such as the mean absolute error, root mean square error, and coefficient of correlation. Results showed that the MLP model with RMSE = 3.2626°C was more suitable than other models in ST estimation 2 days ahead for Tabriz station. Also, in Ahar, MLP with RMSE = 6.3332°C was more suitable than GP-, RF-, and M5P-based models for estimating DST. As a conclusion, the developed MLP is recommended for estimating the DST profiles.