IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

Urban bus route network design involves determining a route configuration with a set of transit routes and associated frequencies that achieves the desired objective. This can be formulated as an optimization problem of minimizing the overall cost (both the user's and the operator's) incurred. In this paper, the use of genetic algorithms (GAs), a search and optimization method based on natural genetics and selection, in solving the route network design problem is reported. The design is done in two phases. First, a set of candidate routes competing for the optimum solution is generated. Second, the optimum set is selected using a GA. The GA is solved by adopting the usual fixed string length coding scheme along with a new variable string length coding proposed in this study. The former assumes a solution route set size, and tries to find that many best routes from the candidate route set, using a GA. The route set size is varied iteratively to find the optimum solution. In the newly proposed variable string length coding method, the solution route set size and the set of solution routes are found simultaneously. The model is applied to a case study network, and results are presented.Urban bus route network design involves determining a route configuration with a set of transit routes and associated frequencies that achieves the desired objective. This can be formulated as an optimization problem of minimizing the overall cost (both the user's and the operator's) incurred. In this paper, the use of genetic algorithms (GAs), a search and optimization method based on natural genetics and selection, in solving the route network design problem is reported. The design is done in two phases. First, a set of candidate routes competing for the optimum solution is generated. Second, the optimum set is selected using a GA. The GA is solved by adopting the usual fixed string length coding scheme along with a new variable string length coding proposed in this study. The former assumes a solution route set size, and tries to find that many best routes from the candidate route set, using a GA. The route set size is varied iteratively to find the optimum solution. In the newly proposed variable string length coding method, the solution route set size and the set of solution routes are found simultaneously. The model is applied to a case study network, and results are presented.

Department Of Civil Engineering

Journal of Transportation Engineering

Urban bus transit route network design using genetic algorithm

Due to the complexity of irrigation management problems, reliance on experience and experts is necessary for effective decision-making in this domain. Expert systems (ES) are efficient means for providing decision support to tasks that primarily require experience-based knowledge. This paper reviews the adoptability and suitability of ES applications in the domain of irrigation management. Core concepts of ES are briefly discussed. A detailed review of the existing applications of ES is presented under three classes of ES applications: (a) expert systems proper, (b) intelligent front-ends, and (c) hybrid systems. This review of literature shows that the ES approach is applied more recently to broader domain areas in contrast to the earlier systems that were focused on narrower domain problems. Additional research on ES application to domains such as real-time irrigation scheduling, reservoir operation involving stochastic nature of inflows and evapotranspiration demand, and integrated operation of irrigation system components is needed to evolve guidelines for optimal water use. The problem of handling multiple experts to evolve decisions that are less biased than an individual expert needs to be addressed. A methodology that takes into account the uncertainty of the ES decisions is also warranted. Further, there is a need for practical evaluation of the quality of recommendations made by the ES which would result in the successful implementation of the ES.

World University root node

Computers and Electronics in Agriculture

Expert system applications in irrigation management: an overview

Tank irrigation systems contribute nearly one third of the total irrigated area in south India and hence their management is an important practical need. This article examines some major considerations related to tank irrigation systems in south India. A comprehensive view of the problems affecting the sustainability of these systems is presented. The major deficiencies that influence the sustainability are inadequate maintenance. reduction in storage capacity, heavy seepage losses in the delivery system, and poor water management techniques. There is a pressing need to evolve and implement appropriate strategies that must be sound on technical, social, economical, institutional, and economical dimensions for sustainable development and management of tank systems. Important practical solutions are discussed for urgent action in the context of sustainable development and management of these irrigation systems. © 1997, Taylor & Francis Group, LLC.

Water International

Sustainable development and management of tank irrigation systems in south india

An integrated decision support system (DSS) that aids the operation of a tank (small-scale reservoir) irrigation system in south India is described. The DSS includes data subsystem, a model subsystem, a knowledge base, and a user interface. The knowledge base of the DSS was developed from the knowledge derived from field experts as well as from the results of an optimization model. The DSS was evaluated to assess its decision-making capability using five years of data. Shortages in irrigation water supply simulated from the DSS were less than those occurring in the actual operation practiced by water authorities. The forecasts of system variables, namely, inflow and evapotranspiration were found to be adequate for real-time operation of the tank system. ©ASCE,.

Journal of Water Resources Planning and Management

Integrated decision support system for tank irrigation system operation

The application of the Muskingum model to river and channel flood routing may have some limitations because of its inherent assumption of a linear relationship between channel storage and weighted flow. Although nonlinear forms of the Muskingum model have been proposed, an efficient method for parameter estimation in the calibration process is still lacking. In this paper, the objective approach of genetic algorithm is proposed for the purpose of estimating the parameters of two nonlinear Muskingum routing models. The performance of this algorithm is compared with other reported parameter estimation techniques. Results of the application of this approach to an example with high nonlinearity between storage and weighted-flow, show that the genetic algorithm approach is efficient in estimating parameters of the nonlinear routing models. A supplementary analysis of the sensitivity of the parameters during the performance of genetic algorithm shows that a unique set of parameters exists that would result in the best performance for a given problem. In addition, genetic algorithm does not demand any initial estimate of values of any of the parameters, and thus avoids the subjectivity and computation time associated with the traditional estimation methods.

Journal of Hydraulic Engineering

Parameter estimation of nonlinear Muskingum models using genetic algorithm

Journal of Irrigation and Drainage Engineering

Comparison of methods for estimating ref-et

An expert system for flood management is developed for the flood control operation of a reservoir. The procedure uses both expert system tools and traditional computer programming techniques considering the complexity of the reservoir operation problem. The present work has been carried out in four phases, namely, flood estimation, flood simulation, reservoir operation, and expert system development. In the flood simulation phase, rainfall-runoff computation model, and model for computing water surface profiles have been utilized. The use of the developed system is demonstrated with a case study of the Adyar river in the Madras metropolitan city to evolve the safe releases that can be followed during flood considering the reservoir inflows and the overland flow from the urban drainage area. The developed expert system could be a valuable tool in reservoir operation decision-making and thereby help in minimizing the flood damages in the Adyar river flood plains.

GENERAL

Journal of the Institution of Engineers (India): Civil Engineering Division

Development of an Expert System for Flood Management

Evapotranspiration is the most important variable next to rainfall in the context of irrigation to crops and it is a multivariate phenomenon as it is influenced by many hydrological variables. In this paper, the relative importance of different variables involved in evapotranspiration has been investigated through a multivariate tehnique, namely factor analysis. Monthly data pertaining to eight meteorological stations located in two tropical states of India are used in this analysis. Factor analysis was applied to determine the relative effect of rainfall, temperature (maximum and minimum), wind speed, relative humidity, and sunshine duration on evapotranspiration. The analysis was performed in two stages: in the first stage, the principal components were obtained and in the second stage, a set of factors was derived using Varimax factor rotation. Three factors were extracted which explained more than 85% of the total variation in the original data set. The identified factors were related to physical processes influencing the evapotranspiration. The results of the study reveal that the variables, relative humidity, temperature, and wind speed, are those with the most influence in the evapotranspiration process, in that order. The variables rainfall and sunshine duration have been found to have less influence on the ET process. © 1996 Kluwer Academic Publishers.

Water Resources Management

Relative importance of meteorological variables in evapotranspiration: Factor analysis approach

Lag-1 correlation for inflow between consecutive periods is considered into reservoir model in many publications. This consideration greatly improves the reservoir models to incorporate the uncertainty of inflow. However, no publication was found to incorporate a correlation relationship for releases between consecutive periods to improve the operating policy for reservoir operations. This paper presents a methodology of autoregressive decision rule for an aggregated reservoir operation as a surrogate of a multireservoir system of the Upper Colorado River Basin. The method incorporates a lag-1 correlation for the releases between consecutive periods with the optimal operating policy solved by stochastic dynamic program. The decision rules with and without incorporation of the autoregressive correlation for the releases were then used in simulated operation of the reservoir with historical inflow records to evaluate their relative effectiveness. The results showed that the autoregressive decision rule yields more stable and higher reliability of annual water supply for the aggregated reservoir operations. ©ASCE.

Autoregressive decision rule in aggregated reservoir operation

Dastane (1974) recommended four different methods, namely evapotranspiration- rainfall ratio method, Indian-1 and Indian-2 methods and Vietnam method for estimating effective rainfall for rice crop. These methods together with the USDA-SCS method were compared against the physically-based water balance method. The analysis was carried out using daily data of evapotranspiration (ET) and rainfall pertaining to thirteen seasons with special reference to lowland paddy rice in South India. Among the different methods, the ET-rainfall ratio and Indian-2 methods estimate the effective rainfall values nearly closer to those by the water balance method. The USDA-SCS method underpredicts values of effective rainfall compared to other methods. The ET-rainfall ratio and Indian-2 methods can be used as alternatives to the water balance method for determining effective rainfall which in turn be used in estimating irrigation requirements for lowland rice. © 1996 Kluwer Academic Publishers.

Comparative study of effective rainfall estimation methods for lowland rice

Evapotranspiration (ET) is an important parameter needed by water managers for the design, operation and management of irrigation systems. Since there are many methods to compute ET, based on climatic data, an inexperienced engineer or hydrologist is perplexed with the selection of an appropriate method. In this context, an expert system (ES) would be of great use to aid in selection of a suitable ET estimation method, given the location, data availability and climatic conditions. In this paper an intelligent front-end expert system (ETES), that has been developed to select suitable ET estimation methods under South Indian climatic conditions, is presented. Ten meteorological stations located in different climatic regions and thirteen ET estimation methods have been considered in this ES. Like a human consultant, the system asks the user for detailed information regarding the details of the project site such as location, season, climatic zone, and data availability. It then makes a recommendation based on this information and the system's own knowledge of such a situation. Along with the recommended method, ETES will also suggest suitable correction factors for converting the resulting ET values to those of methods that result in accurate estimation. The developed ES would be of much potential use in irrigation management in developing countries like India. © 1995.

An intelligent front-end for selecting evapotranspiration estimation methods

Irrigation land management model

Irrigation systems must be operated efficiently and optimally to manage them under practical situations. Much complexity is involved in respect to system operation and management which puts water managers and operators in a predicament. An expert system (ES) would be an appropriate tool to address these complex problems. In this paper, a hybrid expert system that has been developed for operation of a tank irrigation system in South India, is presented. The heuristics and optimal knowledge are integrated with algorithmic techniques to operate the system under real-time conditions.

Modelling and management of sustainable basin-scale water resource systems Proc. international symposium, Colorado, 1995

Hybrid expert system for operation of a small surface storage system

This paper deals with stochastic modelling of monthly inflows into a reservoir system in the monsoon climatic coditions using a multiplicative seasonal ARIMA model based on 25 years of data with logarithmic transformation. The developed model was applied to forecast the monthly inflows for 27 years. The comparison of these forecasted flows with the actual flows reveals that the ARIMA family models are adequate for longterm forecasting of inflows. The parameter uncertainity was also evaluated and found to be minimal thus avoiding the frequent updating of the model for forecasting. The use of the model in evolving optimal cropping patterns and optimal operational policies is also highlighted. © 1995 Kluwer Academic Publishers.

Multiplicative seasonal Arima model for longterm forecasting of inflows

Models are proposed to extend the monthly streamflow data at a site where the available historic rainfall and streamflow data are too short for adequate systems study, subject to the condition that there are no gauging sites in the basin or adjacent basins with a longer period of streamflow data. Hence rainfall data of a nearby raingauge station are used. Five regression models, namely, runoff coefficient model, single linear regression, monthly linear regression, monthly linear regression with stochastic description for residuals, and a double regressed model are used. The results show that the monthly linear regression model with stochastic description for the residuals is best suited for the purpose when applied to a case study. © 1995 Taylor and Francis Group, LLC.

Hydrological Sciences Journal

Models for extending streamflow data: A case study

Evapotranspiration (ET) is an important process in the hydrological cycle and needs to be accurately quantified for proper irrigation scheduling and optimal water resources systems operation. The time variant characteristics of ET necessitate the need for forecasting ET. In this paper, two techniques, namely a seasonal ARIMA model and Winter’s exponential smoothing model, have been investigated for their applicability for forecasting weekly reference crop ET. A seasonal ARIMA model with one autoregressive and one moving average process and with a seasonality of 52 weeks was found to be an appropriate stochastic model. The ARIMA and Winter’s models were compared with a simple ET model to assess their performance in forecasting. The forecast errors produced by these models were very small and the models would be promisingly of great use in real-time irrigation management. © 1995 Taylor & Francis Group, LLC.

Forecasting weekly reference crop evapotranspiration series

Crop selection is a crucial and decisive task, given the dynamic environment of agricultural systems created by differences in climate, soils, topography, cultivation practices, and available resources. For farmers and farm managers, a decision regarding crop selection is a difficult task since a number of factors have to be considered. A solution of this predicament is an expert system that uses all available information to select the best suitable crops. In this article, the development of a PC-based expert system (CROPES) for selecting crops in a region in Tamilnadu, India, is presented. The system, acting as an intelligent consultant, asks a set of questions and then suggests appropriate crops. It recommends crops to a farmer at an early stage of crop planning based on location, climate, and farm level information pertaining to soils and available resources. The CROPES system was evaluated by specialists using farm data from a selection of farmers to assess its performance. It was found to be a valuable farm tool for crop selection. -Authors

Transactions - American Society of Agricultural Engineers

CROPES: a rule-based expert system for crop selection in India

Meteorological and lysimetric data for a period of nine years were used to develop crop coefficients for rice grown under lowland conditions in a sub-humid tropical climate in India. The estimated crop coefficients were found to be higher than those values recommended by FAO. A crop coefficient model with basal coefficient, moisture availability coefficient and surface wetness coefficient terms has been proposed and found suitable. On most counts, the moisture availability coefficient was found to be near unity and the wetness coefficient was found to be significant. The basal crop coefficients for lowland rice have also been presented for practical use with the proposed models. © 1994 Kluwer Academic Publishers.

Irrigation and Drainage Systems

Irrigation crop coefficients for lowland rice

This paper outlines the development of a Knowledge Based Decision Support System for Water Supply Management (WSMDSS) to emulate and enhance the ability of water planning experts in the decision making process. The case of a medium-size city water supply distribution network in South India is presented as a demonstration of the approach.

Applications of Artificial Intelligence in Engineering

Knowledge based decision support system for water distribution management

Crop coefficients (Kc) were estimated for cotton, sorghum and millet for tropical South India based on lysimeter measured actual evapotranspiration (ET) and reference crop ET computed by the modified Penman method. The estimated crop coefficients were 0.46, 0.70, 1.01, and 0.39 in the four crop stages for cotton. Kc value of the last stage was significantly lower than the FAO Kc value. The estimated Kc values were considerably lower than FAO crop coefficients in the third and fourth stages for sorghum, for which the estimated stagewise Kc values were 0.42, 0.71, 0.62 and 0.23. For millet, the estimated Kc values for four stages were 0.51, 0.78, 0.87 and 0.50 and found to differ markedly from FAO Kc values. Crop coefficient relationships with respect to time were developed using mean crop coefficients derived from multi-year data. The developed crop coefficients and relationships would be of great use for the estimation of crop water requirements under tropical climatic conditions. © 1994.