Manish Kumar Goyal

Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS

Abstract This paper investigates the abilities of Artificial Neural Networks (ANN), Least Squares – Support Vector Regression (LS-SVR), Fuzzy Logic, and Adaptive Neuro-Fuzzy Inference System (ANFIS) techniques to improve the accuracy of daily pan evaporation estimation in sub-tropical climates. Meteorological data from the Karso watershed in India (consisting of 3801 daily records from the year 2000 to 2010) were used to develop and test the models for daily pan evaporation estimation. The measured meteorological variables include daily observations of rainfall, minimum and maximum air temperatures, minimum and maximum humidity, and sunshine hours. Prior to model development, the Gamma Test (GT) was used to derive estimates of the noise variance for each input–output set in order to identify the most useful predictors for use in the machine learning approaches used in this study. The ANN models consisted of feed forward backpropagation (FFBP) models with Bayesian Regularization (BR), along with the Levenberg–Marquardt (LM) algorithm. A comparison was made between the estimates provided by the ANN, LS-SVR, Fuzzy Logic, and ANFIS models. The empirical Hargreaves and Samani method (HGS), as well as the Stephens–Stewart (SS) method, were also considered for comparison with the newer machine learning methods. The Root Mean Square Error (RMSE) and Correlation Coefficient (CORR) were the statistical performance indices that were used to evaluate the accuracy of the various models. Based on the comparison, it was found that the Fuzzy Logic and LS-SVR approaches can be employed successfully in modeling the daily evaporation process from the available climatic data. In addition, results showed that the machine learning models outperform the traditional HGS and SS empirical methods.

Modeling of Suspended Sediment Concentration at Kasol in India Using ANN, Fuzzy Logic, and Decision Tree Algorithms

The prediction of the sediment loading generated within a watershed is an important input in the design and management of water resources projects. High variability of hydro-climatic factors with sediment generation makes the modelling of the sediment process cum- bersome and tedious. The methods for the estimation of sediment concentration based on the properties of flow and sediment have limitations attributed to the simplification of important parameters and boundary conditions. Under such circumstances, soft computing approaches have proven to be an efficient tool in modelling the sediment concentration. The focus of this paper is to present the development of models using Artificial Neural Network (ANN) with back propagation and Levenberg-Maquardt algorithms, radial basis function (RBF), Fuzzy Logic, and decision tree algorithms such as M5 and REPTree for predicting the suspended sediment concentration at Kasol, upstream of the Bhakra reservoir, located in the Sutlej basin in northern India. The input vector to the various models using different algorithms was derived con- sidering the statistical properties such as auto-correlation function, partial auto-correlation, and cross-correlation function of the time series. It was found that the M5 model performed well compared to other soft computing techniques such as ANN, fuzzy logic, radial basis function, and REPTree investigated in this study, and results of the M5 model indicate that all ranges of sediment concentration values were simulated fairly well. This study also suggests that M5 model trees, which are analogous to piecewise linear functions, have certain advantages over other soft computing techniques because they offer more insight into the generated model, are acceptable to decision makers, and always converge. Further, the M5 model tree offers explicit expressions for use by field engineers. DOI: 10.1061/(ASCE)HE.1943-5584.0000445.

Application of ANN, Fuzzy Logic and Decision Tree Algorithms for the Development of Reservoir Operating Rules

Optimal use of scarce water resources is the prime objective for water resources development projects in the developing country like India. Optimal releases have been generally expressed as a function of reservoir state variables and hydrologic inputs by a relationship which ultimately allows the policy/water managers to determine the water to be released as a function of available information. Optimal releases were obtained by using optimal control theory with inflow series and revised reservoir characteristics such as elevation area capacity table, zero elevation level as input in this study. Operating rules for reservoir were developed as a function of demand, water level and inflow. Artificial Neural Network (ANN) with back propagation algorithm, Fuzzy Logic and decision tree algorithms such as M5 and REPTree were used for deriving the operating rules using the optimal releases for an irrigation and power supply reservoir, located in northern India. It was found that fuzzy logic model performed well compared to other soft computing techniques such as ANN, M5P and REPTree investigated in this study.

Modeling of Sediment Yield Prediction Using M5 Model Tree Algorithm and Wavelet Regression

The forecast of the sediment yield generated within a watershed is an important input in the water resources planning and management. The methods for the estimation of sediment yield based on the properties of flow and sediment have limitations attributed to the simplification of important parameters and boundary conditions. Under such circumstances, soft computing approaches have proven to be an efficient tool in modelling the sediment yield. The focus of present study is to deal with the development of decision tree based M5 Model Tree and wavelet regression models for modeling sediment yield in Nagwa watershed in India. A comparison is also performed with the artificial neural network (ANN) model for streamflow forecasting. The root mean square errors (RMSE), Nash-Sutcliff efficiency index (N-S Index), and correlation coefficient (R) statistics are used for the statistical criteria. A comparative evaluation of the performance of M5 Model Tree and wavelet regression versus ANN clearly shows that M5 Model Tree and wavelet regression can prove more useful than ANN models in estimation of sediment yield. Further, M5 model tree offers explicit expressions for use by design engineers.

Fate of pharmaceutical compounds in hydroponic mesocosms planted with Scirpus validus

A systematic approach to assess the fate of selected pharmaceuticals (carbamazepine, naproxen, diclofenac, clofibric acid and caffeine) in hydroponic mesocosms is described. The overall objective was to determine the kinetics of depletion (from solution) and plant uptake for these compounds in mesocosms planted with S. validus growing hydroponically. The potential for translocation of these pharmaceuticals from the roots to the shoots was also assessed. After 21 days of incubation, nearly all of the caffeine, naproxen and diclofenac were eliminated from solution, whereas carbamazepine and clofibric acid were recalcitrant to both photodegradation and biodegradation. The fact that the BAFs for roots for carbamazepine and clofibric acid were greater than 5, while the BAFs for naproxen, diclofenac and caffeine were less than 5, implied that the latter two compounds although recalcitrant to biodegradation, still had relatively high potential for plant uptake. Naproxen was sensitive to both photodegradation (30-42%) and biodegradation (>50%), while diclofenac was particularly sensitive (>70%) to photodegradation alone. No significant correlations (p > 0.05) were found between the rate constants of depletion or plant tissue levels of the pharmaceuticals and either log Kow or log Dow.

Development of stage-discharge rating curve using model tree and neural networks: An application to Peachtree Creek in Atlanta

The applicability and the performance of the M5P model tree machine learning technique is investigated in modeling of the stage-discharge problem for Peachtree Creek in Atlanta, Georgia. The stage-discharge relationship has an important bearing on the correct assessment of discharge. This technique is compared to three different algorithms of artificial neural network and conventional rating curve. It is shown that the model trees, being analogous to piecewise linear functions, have certain advantages over neural networks; they are more transparent and hence acceptable by decision makers, they are very fast in training, and they always converge. The accuracy of M5P trees is superior to neural network models and conventional model. It was found that M5P outperformed when fewer data events were available for model development. In other words, M5P has potential to be a useful and practical tool for cases where less measured data is available for modeling stage-discharge problem. This study has also showed high consistency between the training and testing phases of modeling when using M5P compared to neural network models and conventional method. Furthermore, a partition analysis has been performed. This analysis reveals that the results obtained using M5P model performed better than ANN for both the high flows and the low flows.

Identification of Homogeneous Rainfall Regimes in Northeast Region of India using Fuzzy Cluster Analysis

Regionalization methods are often used in hydrology for frequency analysis of floods. The hydrologically homogeneous regions should be determined using cluster analysis instead of the geographically close stations. In view of the ongoing environmental and climate changes in the Northeastern of India, regionalization of homogeneous rainfall region is essential to lay out an effective flood frequency analysis of this region. The choice of appropriate cluster approach used according to the data of the basin is also significant. In the context of this study, total precipitation data of stations operated by Indian Meteorological Department (IMD) in Northeastern of India basins for cluster analysis are used. Further, five cluster validity indices, namely Partition Coefficient, Partition Entropy, Extended Xie-Beni index, Fukuyama-Sugeno index and Kwon index have been tested to determine the effectiveness in identifying optimal partition provided by the fuzzy c mean clustering algorithm (FCM). A comparison is also performed using K- Mean clustering algorithm. Additionally, regional homogeneity tests based on l-moments approach are used to check homogeneity of regions identified by both cluster analysis approaches. It was concluded that regional homogeneity test results show that regions defined by FCM method are sufficiently homogeneous for regional frequency analysis.

Evaluation of machine learning tools as a statistical downscaling tool : temperatures projections for multi-stations for Thames River Basin, Canada

Many impact studies require climate change information at a finer resolution than that provided by global climate models (GCMs). This paper investigates the performances of existing state-of-the-art rule induction and tree algorithms, namely single conjunctive rule learner, decision table, M5 model tree, and REPTree, and explores the impact of climate change on maximum and minimum temperatures (i.e., predictands) of 14 meteorological stations in the Upper Thames River Basin, Ontario, Canada. The data used for evaluation were large-scale predictor variables, extracted from National Centers for Environmental Prediction/National Center for Atmospheric Research reanalysis dataset and the simulations from third generation Canadian coupled global climate model. Data for four grid points covering the study region were used for developing the downscaling model. M5 model tree algorithm was found to yield better performance among all other learning techniques explored in the present study. Hence, this technique was applied to project predictands generated from GCM using three scenarios (A1B, A2, and B1) for the periods (2046–2065 and 2081–2100). A simple multiplicative shift was used for correcting predictand values. The potential of the downscaling models in simulating predictands was evaluated, and downscaling results reveal that the proposed downscaling model can reproduce local daily predictands from large-scale weather variables. Trend of projected maximum and minimum temperatures was studied for historical as well as downscaled values using GCM and scenario uncertainty. There is likely an increasing trend for Tmax and Tmin for A1B, A2, and B1 scenarios while decreasing trend has been observed for B1 scenarios during 2081–2100.

Nonparametric Statistical Downscaling of Temperature, Precipitation, and Evaporation in a Semiarid Region in India

AbstractThe climate impact studies in hydrology often rely on climate change information at fine spatial resolution. Because general circulation models (GCMs) operate on a coarse scale, the output from a GCM has to be downscaled to obtain the information relevant to hydrologic studies. In this paper, downscaling models are developed using the state-of-the-art nonparametric method K-Nearest Neighbor (K-NN) approach, with an emphasis on optimal choice in selection of nearest neighbors for obtaining simultaneous projections of mean monthly maximum and minimum temperatures (Tmax⁡ and Tmin⁡) as well as monthly precipitation and pan evaporation to lake-basin scale in a semiarid region that is considered to be a climatically sensitive region in India. The performance of the K-NN approach was evaluated based on several statistical performance indicators. A comparison of K-NN has been made with a linear multiple regression (LMR)-based downscaling model. Also, the prevailing view in the literature regarding optimal...

Robust weighted regression as a downscaling tool in temperature projections

Downscaling models are developed using robust version of locally weighted regression smoothing scatter plots technique (LOWESS) regression approach for obtaining projections of mean monthly maximum and minimum temperatures (Tmax and Tmin) to Pichola watershed in an arid region in India. Variable Importance in the Projection (VIP) score from Partial Least Squares (PLSs) regression is used to select the variables. A comparison is also done with LOWESS regression approach. The results show that an increasing trend is observed for Tmax and Tmin for A1B, A2 and Bl scenarios whereas no trend is discerned with the COMMIT.