Forecasting intermittent streamflows is an important issue for water quality management, water supplies, hydropower and irrigation systems. This paper compares the accuracy of several data driven techniques, that is, adaptive neuro fuzzy inference system (ANFIS), artificial neural networks (ANNs) and support vector machine (SVM) for forecasting daily intermittent streamflows. The results are also compared with those of the local linear regression (LLR) and the dynamic local linear regression (DLLR). Intermittent streamflow data from two stations, Uzunkopru and Babaeski, in Thrace region located in north-western Turkey are used in the study. The root mean square error and correlation coefficient were used as comparison criteria. The comparison results indicated that the ANFIS, ANN and SVM models performed better than the LLR and DLLR models in forecasting daily intermittent streamflows. The ANN and ANFIS gave the best forecasts for the Uzunkopru and Babaeski stations, respectively.
A crucial part in designing a robust water quality monitoring network is the selection of appropriate water quality sampling locations. Due to cost and time constraints, it is essential to identify and select these locations in an accurate and efficient manner. The main contribution of the present article is the development of a practical methodology for allocating critical sampling points in present and future conditions of the non-point sources under a case study of the Khoy watershed in northwest Iran, where financial resources and water quality data are limited. To achieve this purpose, the river mixing length method (RML) was applied to propose potential sampling points. A new non-point source potential pollution score (NPPS) was then proposed by the analytic network process (ANP) to classify the importance of each sampling point prior to selecting the most appropriate locations for a river system. In addition, an integrated cellular automata-Markov chain model (CA-Markov) was applied to simulate future change in non-point sources during the period 2026-2036. Finally, by considering anthropogenic activities through land-use mapping, the hierarchy value, the non-point source potential pollution score values and budget deficiency in the study area, the seven sampling points were identified for the present and the future. It is not expected, however, that the present location of the proposed sampling points will change in the future due to the forthcoming changes in non-point sources. The current study provides important insights into the design of a reliable water quality monitoring network with a high level of assurance under certain changes in non-point sources. Furthermore, the results of this study should be valuable for water quality monitoring agencies looking for a cost-effective approach for selecting sampling locations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.