Irrigation Scheduling Problem Research Articles

An LSTM‐based mixed‐integer model predictive control for irrigation scheduling

AbstractThe development of well‐devised irrigation scheduling methods is desirable from the perspectives of plant quality and water conservation. Accordingly, in this article, a mixed‐integer model predictive control system is proposed to address the daily irrigation scheduling problem. In this framework, a long short‐term memory (LSTM) model of the soil–crop–atmosphere system is employed to evaluate the objective of ensuring optimal water uptake in crops while minimizing total water consumption and irrigation costs. To enhance the computational efficiency of the proposed method, a heuristic method involving the logistic sigmoid function is used to approximate the binary variable that arises in the mixed‐integer formulation. Through computer simulations, the proposed scheduler is applied to homogeneous and spatially variable fields. The results of these simulation experiments reveal that the proposed method can prescribe optimal/near‐optimal irrigation schedules that are typical of irrigation practice within practical computational budgets.

Optimal Irrigation with Perfect Weekly Forecasts versus Imperfect Seasonal Forecasts

AbstractThis study examines the impact of weekly and seasonal weather forecasts on the optimal irrigation scheduling problem. We compare stochastic and deterministic simulation-optimization framewo...

Sequential Irrigation Scheduling Avoiding Night Irrigation

AbstractThe sequential irrigation scheduling problem is one where a set of irrigation jobs have to be scheduled sequentially. In this paper, an integer program is presented to solve this problem. T...

Simultaneous-Irrigation Scheduling GA Model with Identical Discharges and Travel Time

AbstractMultimachine scheduling problems with earliness/tardiness costs and sequence-dependent setup times are analogous to the simultaneous irrigation scheduling problem with water travel times be...

Arranged-Demand Irrigation Scheduling with Nonidentical Discharges

Several irrigation water delivery methods are in practice in irrigated agriculture throughout the world, and a variety of classifications have been suggested by different researchers. Demand, arranged-demand, and rotation are the three main types of irrigation schedules/delivery methods. Irrigation systems may also be classified as either sequential or simultaneous. Supplying water sequentially to farmers according to their requested times constitutes an irrigation scheduling problem analogous to the classical earliness/tardiness single machine scheduling problems in Operational Research (OR). In this paper, the authors describe an irrigation scheduling problem analogous to the complex multimachine scheduling problem. The authors develop a genetic algorithm (GA) and test this algorithm against solutions obtained from an integer program to draw conclusions about the solution quality of the GA. The researchers demonstrate the potential of this GA through an engineering application of the Maira Branch Canal. The authors show that if this canal is operated at a constant discharge, the arranged-demand schedule requires the canal to be operated at 75% of the discharge required if this canal were operated on an on-demand schedule.

Incorporating Reanalysis-Based Short-Term Forecasts from a Regional Climate Model in an Irrigation Scheduling Optimization Problem

AbstractA coupled simulation-optimization with reanalysis-based short-term weather forecasts from a regional climate model (RCM) is proposed to optimize an irrigation scheduling problem. Using different physical configurations of the climate extension of a weather research and forecasting model (CWRF) that is driven by national atmospheric model project reanalysis data, five ensemble outlooks of 15 consecutive daily forecasts have been generated during five different crop-growing seasons. Six daily climatic variables are forecasted, namely, rainfall, minimum temperature, maximum temperature, humidity, wind speed, and solar radiation. To correct the forecasts for any inherent bias, the quantile mapping method is applied to all six daily climatic variables. After bias correction, a skill assessment of the reanalysis-based RCM forecasts indicate that only the first three climatic variables are predicted with reliable accuracy; thus, average climatic means are used to replace the remaining three variables (hu...

Genetic algorithms for the sequential irrigation scheduling problem

A sequential irrigation scheduling problem is the problem of preparing a schedule to sequentially service a set of water users. This problem has an analogy with the classical single machine earliness/tardiness scheduling problem in operations research. In previously published work, integer program and heuristics were used to solve sequential irrigation scheduling problems; however, such scheduling problems belong to a class of combinatorial optimization problems known to be computationally demanding (NP-hard). This is widely reported in operations research. Hence, integer program can only be used to solve relatively small problems usually in a research environment where considerable computational resources and time can be allocated to solve a single schedule. For practical applications, metaheuristics such as genetic algorithms (GA), simulated annealing, or tabu search methods need to be used. These need to be formulated carefully and tested thoroughly. The current research is to explore the potential of GA to solve the sequential irrigation scheduling problems. Four GA models are presented that model four different sequential irrigation scenarios. The GA models are tested extensively for a range of problem sizes, and the solution quality is compared against solutions from integer programs and heuristics. The GA is applied to the practical engineering problem of scheduling water scheduling to 94 water users.

Irrigation Scheduling with Genetic Algorithms

A typical irrigation scheduling problem is one of preparing a schedule to service a group of outlets that may be serviced simultaneously. This problem has an analogy with the classical multimachine earliness/tardiness scheduling problem in operations research (OR). In previously published work, integer programming was used to solve irrigation scheduling problems; however, such scheduling problems belong to a class of combinatorial optimization problems known to be computationally demanding. This is widely reported in OR literature. Hence integer programs (IPs) can be used only to solve relatively small problems typically in a research environment where considerable computational resources and time can be allocated to solve a single schedule. For practical applications, metaheuristics such as genetic algorithms, simulated annealing, or tabu search methods need to be used. However, these need to be formulated carefully and tested thoroughly. The current research explores the potential of genetic algorithms to solve the simultaneous irrigation scheduling problem. For this purpose, two models are presented: the stream tube model and the time block model. These are formulated as genetic algorithms, which are then tested extensively, and the solution quality is compared with solutions from an IP. The suitability of these models for the simultaneous irrigation scheduling problem is reported.

Evaluation of a Genetic Algorithm for the Irrigation Scheduling Problem

A typical irrigation scheduling problem is one of preparing a schedule to service a group of outlets which may be serviced simultaneously. This problem has an analogy with the classical earliness/tardiness problem in operations research. In previously published work an integer program was used to solve this problem, however such scheduling problems belong to a class of combinatorial problems known to be computationally demanding (N-P hard). This is widely reported in operations research. Hence integer programs can only be used to solve relatively small problems usually in a research environment where considerable computational resources and time can be allocated to solve a single schedule. For practical applications metaheuristics such as genetic algorithms, simulated annealing, or tabu search methods need to be used. However as reported in the literature, these need to be formulated carefully and tested thoroughly. This paper demonstrates the importance of robust testing of one such genetic algorithm formulated to solve the irrigation scheduling problem with simultaneous outlets serviced against an integer program formulated to solve the same problem.

Irrigation Scheduling with Travel Times

In preparing water allocation schedules for fields in a lateral unit, the time required for water to travel from one point on a lateral to another can be significant and is dependent on the sequence in which users abstract water. This paper illustrates the problem of ignoring travel time and/or considering travel time to be sequence independent. For two users, each requesting water for a duration of 4 h, by assuming travel time to be sequence independent, one user receives water for 5 h, a 25% increase, and the other receives water for only 3 h, a 25% decrease. This paper presents a formulation of the irrigation scheduling problem for sequential users with sequent dependent travel time. The formulation is implemented as an integer program and applied to part of a lateral unit on the Juan Distributary, Haryana, India. Two models are presented, the first of which allows for noncontiguous jobs, i.e., idle time is permitted between jobs. The second model does not permit noncontiguous jobs.

Configuration irrigation schedule based on expert systems and operations research

This paper presents configuration design knowledge to solve irrigation scheduling problem in agriculture domain and a general approach for configuration management knowledge. It also introduces a Configuration Agriculture Irrigation Schedule (CAIS) tool that produces the configuration irrigation schedule design according to the CommonKADS methodology. A configuration that satisfy the user requirements, and that additionally satisfy some optimality criteria is required. By integrating Dynamic programming and inference knowledge, with demand including different objective, that it is used in generating the inference steps (PPSM) to select the suitable components of the inference steps minimizing the number of components and/or maximizing the accuracy of the result of each inference step. Operations Research techniques greatly improved the understanding of the interactions of a large number of components and enhanced the decision selection under uncertain outcomes.

Irrigation Scheduling. I: Integer Programming Approach

This paper shows how a sequential irrigation schedule for a tertiary unit can be interpreted as a single machine scheduling problem with earliness, tardiness, and a common deadline. An integer program solution is presented for this irrigation scheduling problem. Two different models are presented to reflect different management options at the tertiary level. The first model allows jobs to be scheduled noncontiguously. In the second model only contiguous jobs are allowed. The second model has three submodels reflecting the various ways in which contiguous jobs can be scheduled over a fixed interval. Earlier work in determining unit costs of earliness/tardiness is reviewed and an alternative improved method is suggested. The models presented in this paper are applied to a tertiary unit with 16 users, both as a single interval and multi-interval irrigation scheduling problem. An alternative integer program is also presented which although computationally more efficient can only be used for single period scheduling problems. The models developed in this paper can be used to solve small scheduling problems and also to calibrate the heuristics as presented in the companion paper.

A heuristic dynamic optimization algorithm for irrigation scheduling

An irrigation scheduling problem is formulated based on a dynamic crop response model for corn and an evapotranspiration model, which considers the various water losses such as evapotranspiration, evaporation from soil surface, transpiration under different climatic conditions, in detail. A heuristic dynamic optimization method, which reduces the problem to a one variable problem, is developed with a pseudo profit function to resolve the ties that occur due to the missing state variables. The procedure obtained a fairly accurate approximate solution, the accuracy of which depends on the number of iterations and the step size used. Compared with the dynamic programming or other dynamic approaches, this heuristic algorithm is much more efficient.

Dynamic irrigation scheduling with stochastic rainfall

The dynamic irrigation scheduling problem with stochastic weather data was investigated by using the Markov process and dynamic programming. Several stochastic optimization models of different complexity were formulated. A simple one-stage or one-day decision model was also formulated, based on certain simplifying assumptions. This simple model not only considers the daily fluctuations of the price of the crop and the cost of irrigation, it also requires much less memory and thus can be implemented in a small personal computer. Numerical examples based on actual data were solved to illustrate the approach.

Improved Approach to Irrigation Scheduling Programs

Several available irrigation scheduling computer programs use the water balance method. The acceptance of these irrigation scheduling programs among farmers has been slow. A possible reason for the slow acceptance of these programs is that they are research oriented and do not look at the scheduling problem from the farmer's point of view. An improved approach to writing irrigation scheduling programs using the water balance method is suggested. It is based on defining the irrigation scheduling problem from the farmer's viewpont and adapts the model interface to his concepts and needs. The program adds to the traditional approach of “management depletion,” scheduling by interval, scheduling by irrigation amount (irrigation depth, duration and volume), and scheduling by crop indicators.

Irrigation control in the presence of salinity: Extended linear quadratic approach

An intraseasonal irrigation scheduling problem is dealt with via extended linear quadratic (ELQ) control. The ELQ control is well‐suited for constrained multidimensional problems and provides openloop feedback control rules over the control horizon. A conceptual model is developed to describe the dynamics of water allocation and salt movement in the root zone of a crop. Moisture stress and osmotic stress are combined to obtain the integrated inhibitory effect of salinity on transpiration. For the intraseasonal model to be effective against perennial salt accumulation in the root zone, it should be able to yield control laws which will lead to favorable root zone conditions at the end of an irrigation season, thus avoiding any significant leaching prior to the next growing season. This long‐term aspect of salinity control is handled via probabilistic state constraints which impose desired salinity and moisture levels with desired confidence level. The ELQ control is employed in a case study of expected net benefit maximization over an irrigation season of corn in Fort Morgan, Colorado. The results, in general, correspond well with expected irrigation schedules under different conditions and provide valuable information on both short‐ and long‐term aspects of irrigation control under saline conditions. The ELQ control, being an analytic iterative solution scheme with theoretically guaranteed fast convergence, has a distinct computational advantage over state‐of‐the‐art procedures.

Conditional Distributions of Neyman‐Scott Models for Storm Arrivals and Their Use in Irrigation Scheduling

This paper solves the deficit irrigation scheduling problem assuming that rainfall arrivals obey a Neyman‐Scott cluster model. The implied dependence between storms is represented by derived conditional distributions of the occurrence of rainfall based on the history of past storm arrivals. This new result is used on a physicostochastic model of the soil moisture history which in turn leads to an optimal control algorithm for making irrigation decisions. The decision of when and how much to irrigate now depends on measured soil moisture, available irrigation water, and time since the last rainfall occurrence.

The irrigation scheduling problem and evapotranspiration uncertainty

Scheduling and determining of irrigation water applications are important considerations given limited water resources and increasing concern about agricultural productivity. Past literature has repeatedly been concerned with the influence of the variability of actual evapotranspiration on crop irrigation needs. This work investigates the above issue. A model, based on stochastic dynamic programing, is formulated to maximize net benefits from a crop facing uncertain, correlated evapotranspiration demands. Weekly irrigation decisions are made after observing current soil moisture and available irrigation water, as well as potential evapotranspiration in the past week. The model is similar to the traditional reservoir control algorithms popular in the surface water literature. A case study example indicates that although the model formulation is useful and feasible, the effect of uncertain evapotranspiration on irrigation performance measures is apparently minimal. This work should be of interest to researchers of agricultural management and to those studying the applications and use of operation research techniques in water resources. Computer programs utilized in this paper are available from the authors.