Analysis of factors affecting evapotranspiration zoning.

Reference evapotranspiration (ETo) has a significant role in water resource planning and management as well as analysis of crop production and other agricultural tasks. Methods for estimating ETo may require diurnal/monthly assessments to perceive the consequences of climatic changes on local regions. The spatial and temporal patterns of ETo were analyzed in the current work using data from 340 weather stations in Iran. The entropy theory was used to assess the uncertainty of the utilized variables and the modified Kendall test was applied for temporal trend analysis. The interpolation (e.g., kriging) and ordinary least squares (OLS) methods were used for spatio-temporal ETo classification/modeling. The spatial analysis demonstrated that the OLS method with a good fit measure (R2 = 0.985) successfully simulated the spatial relationships of ETo with climatic parameters. After examining error indices, the cokriging method with an exponential variogram was introduced as the best method of seasonal and annual ETo classification in Iran. Spatially and temporally calculated ETo patterns using modified Hargreaves (MHGR) and MODIS methods closely resembled the standard FAO Penman-Monteith (FPM-56) method, all indicating a gradual increase in ETo. MHGR and MODIS methods serve as suitable alternatives for estimating ETo in various climatic regions of Iran, provided data availability.

Estimation of CO2 flux components over northern hemisphere forest ecosystems by using random forest method through temporal and spatial data scanning procedures.

Modeling CO2 flux components is an important task in ecosystem analysis and terrestrial studies. Net ecosystem exchange (NEE), ecosystem respiration (R), and gross primary production (GPP) are three CO2 flux components. Despite the ecosystem land cover characteristics, climatic factors can make considerable impact on quantity and mechanism of these components. Nevertheless, such climatic factors are not available in most of the areas, especially in developing regions. Therefore, obtaining the models that can exempt using locally recorded variables would be of great importance. A modeling study was carried out here to simulate CO2 flux components using soft computing-based random forest (RF) model in both local and external (spatial) scales, assessed by k-fold validation procedure. Data from 11 sites located in three forest ecosystems, e.g. deciduous broad leaf (DBF), evergreen needle leaf (ENF), and mixed forest (MF), were used to simulate the flux components. The obtained results showed that the temperature-related parameters (e.g., air and soil temperature, vapor pressure deficit) along with the net radiation play key role in determining the flux components in all studied ecosystems. It was confirmed that a chronologic scan of the available patterns is needed for a thorough assessment of the performance accuracy of the local models. The external models provided promising results when compared with the locally trained models. This is a very great step forward in estimating CO2 flux components under data scarcity conditions.

Development of artificial intelligence models for well groundwater quality simulation: Different modeling scenarios.

Groundwater is one of the most important freshwater resources, especially in arid and semi-arid regions where the annual amounts of precipitation are small with frequent drought durations. Information on qualitative parameters of these valuable resources is very crucial as it might affect its applicability from agricultural, drinking, and industrial aspects. Although geo-statistics methods can provide insight about spatial distribution of quality factors, applications of advanced artificial intelligence (AI) models can contribute to produce more accurate results as robust alternative for such a complex geo-science problem. The present research investigates the capacity of several types of AI models for modeling four key water quality variables namely electrical conductivity (EC), sodium adsorption ratio (SAR), total dissolved solid (TDS) and Sulfate (SO4) using dataset obtained from 90 wells in Tabriz Plain, Iran; assessed by k-fold testing. Two different modeling scenarios were established to make simulations using other quality parameters and the geographical information. The obtained results confirmed the capabilities of the AI models for modeling the well groundwater quality variables. Among all the applied AI models, the developed hybrid support vector machine-firefly algorithm (SVM-FFA) model achieved the best predictability performance for both investigated scenarios. The introduced computer aid methodology provided a reliable technology for groundwater monitoring and assessment.

Assessment of groundwater vulnerability using genetic algorithm and random forest methods (case study: Miandoab plain, NW of Iran).

One of the appropriate ways to prevent groundwater contamination is identifying the vulnerable areas of the aquifers. The DRASTIC framework, for assessing the intrinsic vulnerability of the aquifer, is a common method which uses a specific parameter's weight and a uniform distributed contaminant in overall the aquifer. Therefore, it should be calibrated for specific aquifer and contaminant distribution conditions. In this research, random forest (RF) and genetic algorithm (GA) methods were used for DRASTIC framework optimization in Miandoab plain (NW of Iran). In optimizing the basic DRASTIC framework (BDF) using GA, decision variables are the weight of DRASTIC parameters and weight values for each data layer are the outputs of the optimization. The final optimized map (BDF-GA map) was obtained using overlaying the layers with optimized weights based on the GA method. In optimization of BDF using RF, the model is made up of from 1 to 100 trees and the m parameter or split variables was optimized by changing the number of variables between one and the maximum variables of each subset. Also, the feature selection method is used to reduce the dimensions and increase the accuracy of the model. To induct the nitrate contaminant model, raster layer data of 7 BDF parameters, together with the target variable (VI of BDF map), were used. In the final step, variables' importance was identified by the RF method and then, the vulnerability map was obtained based on variable importance. In validation and comparison of methods with CI and ROC methods, the BDF-RF method with the higher CI and ROC values was ranked as the most accurate approach in groundwater vulnerability evaluation. The optimized map using the RF method (BDF-RF map) showed that 14.5, 13, 18, 26.5, and 28% of the plain are located in areas with very low, low, moderate, high, and very high vulnerability categories, respectively.

Generalized gene expression programming models for estimating reference evapotranspiration through cross-station assessment and exogenous data supply.

Adopting methodologies utilizing exogenous data from ancillary stations for determining crop water requirement is a suitable approach to exempt local shortcomings due to the lack of meteorological data/stations. Meanwhile, soft computing techniques might be suitable tools to be used with such data management scenarios. The present paper aimed at evaluating the generalizability of the gene expression programming (GEP) technique for estimating reference evapotranspiration (ET0) through cross-station assessment and exogenous data supply, using data from Turkey and Iran. The GEP-based models were established and learnt using data from 10 stations in Turkey, and then the developed models were tested (validated) in 18 stations of Iran with considerable latitude differences. Different time periods (beginning and the end of time series) were selected for the training and testing stations so that there was no overlap among the dates of the events in both the groups. A comparison was also performed between the GEP models and the corresponding commonly used empirical equations. The obtained results revealed that the generalized GEP models presented promising outcomes in simulating daily ET0 values when they were trained and tested in quite distant stations with different chronological periods of the applied parameters. The performance accuracy of the empirical equations calibrated using exogenous data was reduced in comparison with their original (non-calibrated) versions. Further, although the generalization ability of the GEP models was reduced when the climatic context of the training-testing stations was different, the overall performance accuracy of those models was higher than those of the commonly used classic empirical equations.

High throughput mathematical modeling and multi-objective evolutionary algorithms for plant tissue culture media formulation: Case study of pear rootstocks.

Simplified prediction of the interactions of plant tissue culture media components is of critical importance to efficient development and optimization of new media. We applied two algorithms, gene expression programming (GEP) and M5' model tree, to predict the effects of media components on in vitro proliferation rate (PR), shoot length (SL), shoot tip necrosis (STN), vitrification (Vitri) and quality index (QI) in pear rootstocks (Pyrodwarf and OHF 69). In order to optimize the selected prediction models, as well as achieving a precise multi-optimization method, multi-objective evolutionary optimization algorithms using genetic algorithm (GA) and particle swarm optimization (PSO) techniques were compared to the mono-objective GA optimization technique. A Gamma test (GT) was used to find the most important determinant input for optimizing each output factor. GEP had a higher prediction accuracy than M5' model tree. GT results showed that BA (Γ = 4.0178), Mesos (Γ = 0.5482), Mesos (Γ = 184.0100), Micros (Γ = 136.6100) and Mesos (Γ = 1.1146), for PR, SL, STN, Vitri and QI respectively, were the most important factors in culturing OHF 69, while for Pyrodwarf culture, BA (Γ = 10.2920), Micros (Γ = 0.7874), NH4NO3 (Γ = 166.410), KNO3 (Γ = 168.4400), and Mesos (Γ = 1.4860) were the most important influences on PR, SL, STN, Vitri and QI respectively. The PSO optimized GEP models produced the best outputs for both rootstocks.

Modeling groundwater quality by using hybrid intelligent and geostatistical methods.

Simulation of groundwater quality is important for managing water resources and mitigating water shortages, especially in arid and semiarid areas. Geostatistical models have been used for spatial prediction and interpolation of groundwater parameters. Recently, hybrid intelligent models have been employed for the simulation of dynamic systems. In this study, hybrid intelligent models, based on a neuro-fuzzy system integrated with fuzzy c-means data clustering (FCM) and grid partition (GP) models as well as artificial neural networks integrated with particle swarm optimization algorithm, were used to predict the spatial distribution of chlorine (Cl), electrical conductivity (EC), and sodium absorption ratio (SAR) parameters of groundwater. Results of the hybrid models were compared with geostatistical methods, including kriging, inverse distance weighting (IDW), and radial basis function (RBF). The latitude and longitude values of observation wells and qualitative parameters in three states of maximum, average, and minimum were introduced as input and output to the models, respectively. To evaluate the models, the root mean squared error (RMSE), the mean absolute error (MAE), and CC statistical criteria were used. Results showed that in the hybrid models, NF-GP with the lowest RMSE and MAE and highest CC was the most suitable model for the prediction of water quality parameters. The RMSE, MAE, and CC values were 107.175 (mg/L), 79.804 (mg/L), and 0.924 in the average state for Cl; were 518.544 (µmho/cm), 444.152 (µmho/cm), and 0.882 for electrical conductivity; and were 1.596, 1.350, and 0.582 for sodium absorption ratio, respectively. Among the geostatistical models, the kriging was found more accurate. Using the coordinates of wells will eventually allow the NF-GP to be used for more sampling and replace the visual techniques that require more time, cost, and facilities.

Combining gene expression programming and genetic algorithm as a powerful hybrid modeling approach for pear rootstocks tissue culture media formulation.

BACKGROUND: Predicting impact of plant tissue culture media components on explant proliferation is important especially in commercial scale for optimizing efficient culture media. Previous studies have focused on predicting the impact of media components on explant growth via conventional multi-layer perceptron neural networks (MLPNN) and Multiple Linear Regression (MLR) methods. So, there is an opportunity to find more efficient algorithms such as Radial Basis Function Neural Network (RBFNN) and Gene Expression Programming (GEP). Here, a novel algorithm, i.e. GEP which has not been previously applied in plant tissue culture researches was compared to RBFNN and MLR for the first time. Pear rootstocks (Pyrodwarf and OHF) were used as case studies on predicting the effect of minerals and some hormones in the culture medium on proliferation indices. RESULTS: Generally, RBFNN and GEP showed extremely higher performance accuracy than the MLR. Moreover, GEP models as the most accurate models were optimized using genetic algorithm (GA). The improvement was mainly due to the RBFNN and GEP strong estimation capability and their superior tolerance to experimental noises or improbability. CONCLUSIONS: GEP as the most robust and accurate prospecting procedure to achieve the highest proliferation quality and quantity has also the benefit of being easy to use.

Evaluating the performance of four different heuristic approaches with Gamma test for daily suspended sediment concentration modeling.

Accurate prediction of suspended sediment concentration (SSC) carried by a river or watershed basin is essential for understanding the hydrology of basin in terms of water quality, river bed sustainability and aquatic habitats. In this study, four heuristic methods, namely, radial basis neural network (RBNN), self-organizing map neural network (SOMNN), least square support vector regression (LSSVR), and multivariate adaptive regression spline (MARS) were employed for daily SSC modeling at Ashti, Bamini, and Tekra stations located in Godavari River basin, Andhra Pradesh, India. The Gamma test (GT) was utilized for identifying the most significant input variables for the applied heuristic approaches. The results obtained by RBNN, SOMNN, LSSVR, and MARS models were compared with those of the traditional sediment rating curve (SRC). The performance of the models was evaluated based on the root mean square error (RMSE), coefficient of efficiency (COE), Pearson correlation coefficient (PCC), Willmott index (WI), and pooled average relative error (PARE) indices, as well as the visual inspection using line diagram, scatter diagram, and Taylor diagram (TD). The results of comparison revealed that the four heuristic methods gave higher accuracy than the SRC model. Among the heuristic models, the RBNN-3 (RMSE = 0.045, 0.062, 0.131 g/l; COE = 0.884, 0.883, 0.914; PCC = 0.955, 0.961, 0.958; and WI = 0.970, 0.963, 0.976) outperformed the other models in simulating daily SSC records in the studied stations.