Multivariate time series modeling of short-term system scale irrigation demand
Perera, Kushan C.
MetadataShow full item record
Travel time limits the ability of irrigation system operators to react to short-term irrigation demand ﬂuctuations that result from variations in weather, including very hot periods and rainfall events, as well as the various other pressures and opportunities that farmers face. Short-term system-wide irrigation demand forecasts can assist in system operation. Here we developed a multivariate time series (ARMAX) model to forecast irrigation demands with respect to aggregated service points ﬂows (IDCGi, ASP) and off take regulator ﬂows (ID) based across 5 command areas, which included area covered under four irrigation channels and the study area. These command area speciﬁc ARMAX models forecast 1–5 days ahead daily ID CGi, ASP CGi, OTR and ID using the real time ﬂow data recorded at the service points and the uppermost regulators and observed meteorological data collected from automatic weather stations. The model efﬁciency and the predictive performance were quantiﬁed using the root mean squared error (RMSE), Nash–Sutcliffe model efﬁciency coefﬁcient (NSE), anomaly correlation coefﬁcient (ACC) and mean square skill score (MSSS). During the evaluation period, NSE for ID CGi, OTR across 5 command areas were ranged 0.98–0.78. These models were capable of generating skillful forecasts (MSSS P 0.5 and ACC P 0.6) of ID CGi, ASP and ID CGi, OTR CGi, ASP for all 5 lead days and ID and ID forecasts were better than using the long term monthly mean irrigation demand. Overall these predictive performance from the ARMAX time series models were higher than almost all the previous studies we are aware. Further, ID CGi, OTR CGi, ASP and ID forecasts have improved the operators’ ability to react for near future irrigation demand ﬂuctuations as the developed ARMAX time series models were self-adaptive to reﬂect the short-term changes in the irrigation demand with respect to various pressures and opportunities that farmers’ face, such as changing water policy, continued development of water markets, drought and changing technology. CGi, OTR and ID CGi, ASP CGi, OTR