Comparison of artificial intelligence techniques for prediction of soil temperatures in Turkey

Soil temperature is a meteorological data directly affecting the formation and development of plants of all kinds. Soil temperatures are usually estimated with various models including the artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), and multiple linear regression (MLR) models. Soil temperatures along with other climate data are recorded by the Turkish State Meteorological Service (MGM) at specific locations all over Turkey. Soil temperatures are commonly measured at 5-, 10-, 20-, 50-, and 100-cm depths below the soil surface. In this study, the soil temperature data in monthly units measured at 261 stations in Turkey having records of at least 20 years were used to develop relevant models. Different input combinations were tested in the ANN and ANFIS models to estimate soil temperatures, and the best combination of significant explanatory variables turns out to be monthly minimum and maximum air temperatures, calendar month number, depth of soil, and monthly precipitation. Next, three standard error terms (mean absolute error (MAE, °C), root mean squared error (RMSE, °C), and determination coefficient (R ²)) were employed to check the reliability of the test data results obtained through the ANN, ANFIS, and MLR models. ANFIS (RMSE 1.99; MAE 1.09; R ² 0.98) is found to outperform both ANN and MLR (RMSE 5.80, 8.89; MAE 1.89, 2.36; R ² 0.93, 0.91) in estimating soil temperature in Turkey.

     

Regional frequency analyses of successive-duration annual maximum rainfalls by L-moments method

ABSTRACT

The index flood method of the regional L-moments approach is adapted to annual maximum rainfall (AMR) series of successively increasing durations from 5 minutes to 24 hours. In Turkey, there are 14 such AMRs having standard durations of 5, 10, 15, 30, 60, 120, 180, 240, 300, 360, 480, 720, 1080 and 1440 min. The parameters of the probability distributions found suitable for these AMR series in a homogeneous region need to be adjusted so that their quantile functions will not cross each other over the entire range of probabilities. This adjustment is done so as to make (1) the derivative of the quantile function with respect to the Gumbel reduced variate of a longer-duration AMR be greater than or equal to that of the shorter-duration AMR, and (2) the quantile of a longer-duration AMR be greater than that of the shorter-duration AMR, both to be satisfied for any specific probability. Accordingly, the parameters of a probability distribution fitted to some AMR series must either increase or decrease or be constant with respect to increasing rainstorm duration; and the parameters of different distributions fitted to two sequential AMR series must be interrelated. The index flood method by the L-moments approach modified in such manner for successive-duration AMR series is applied to the Inland Anatolia region of Turkey using data recorded at 31 rain-gauging stations with recording lengths from 31 to 66 years.

EDITOR Z.W. Kundzewicz; ASSOCIATE EDITOR A. Viglione     

Fifteen-stage operation of gated spillways for flood routing management through artificial reservoirs

Abstract

A procedure to identify sets of operational rules for gated spillways for optimal flood routing management of artificial reservoirs is proposed. The flood retention storage of a dam having a gated flood spillway is divided into 15 sub-storages whose surface elevations are identified as critical levels. The most suitable operation set for the downstream conditions and for the dam can be chosen from many derived operation sets. The spillway gates are operated in an optimum way for any floods from very small magnitudes to the probable maximum flood (PMF), without having to forecast the actual magnitude of the incoming flood hydrograph. Decision floods are formed by dividing the PMF into 15 sub-hydrographs by 5 and 10% increments in the ranges 5–50% and 50–100% of the PMF, respectively. Many potential spillway gate openings from closed to fully open are chosen initially. As a result of a series of routing simulations of 15 decision floods, a set of 15 gate openings is determined such that all floods from very small magnitudes to the PMF may be routed without overtopping the dam crest. Next, a few more 15-stage operation rules are determined such that the gate openings of the initial stages are decreased as their critical levels are increased stepwise, with the objective of attenuating smaller floods more effectively and releasing higher outflows for larger floods close to and including the PMF. The developed model is applied to the Catalan and Aslantas dams in Turkey, both of which serve for flood mitigation as well as hydropower generation.

Citation Haktanir, T., Citakoglu, H., and Acanal, N., 2013. Fifteen-stage operation of gated spillways for flood routing management through artificial reservoirs. Hydrological Sciences Journal, 58 (5), 1013–1031.

Editor Z.W. Kundzewicz; Associate editor A. Montanari