Evapotranspiration modelling from climatic data using a neural computing technique

Evapotranspiration is one of the basic components of the hydrologic cycle and essential for estimating irrigation water requirements. This paper investigates the modelling of evapotranspiration using the feed‐forward artificial neural network (ANN) technique with the Levenberg–Marquardt (LM) training algorithm. The LM algorithm has never been used in evapotranspiration estimation before. The LM is used for the optimization of network weights, since this algorithm is more powerful and faster than the conventional gradient descent. Various combinations of daily climatic data, i.e. wind speed, air temperature, relative humidity and solar radiation, from three stations in Los Angeles, USA, are used as inputs to the ANN so as to evaluate the degree of effect of each of these variables on evapotranspiration. A comparison is made between the estimates provided by the ANN and those of the following empirical models: Penman, Hargreaves, Turc. Mean square error, mean absolute error and determination coefficient statistics are used as comparing criteria for the evaluation of the models' performances. Based on the comparisons, it was found that the neural computing technique could be employed successfully in modelling evapotranspiration process from the available climatic data. The results also indicate that the Hargreaves method provides better performance than the Penman and Turc methods in estimation of the evapotranspiration. The accuracy of the ANN technique in evapotranspiration estimation using nearby station data was also investigated. Copyright © 2007 John Wiley & Sons, Ltd.     

River suspended sediment load prediction based on river discharge information: application of newly developed data mining models

ABSTRACT

Suspended sediment load (SSL) is one of the essential hydrological processes that affects river engineering sustainability. Sediment has a major influence on the operation of dams and reservoir capacity. This investigation is aimed at exploring a new version of machine learning models (i.e. data mining), including M5P, attribute selected classifier (AS M5P), M5Rule (M5R), and K Star (KS) models for SSL prediction at the Trenton meteorological station on the Delaware River, USA. Different input scenarios were examined based on the river flow discharge and sediment load database. The performance of the applied data mining models was evaluated using various statistical metrics and graphical presentation. Among the applied data mining models, the M5P model gave a superior prediction result. The current and one-day lead time river flow and sediment load were the influential predictors for one-day-ahead SSL prediction. Overall, the applied data mining models achieved excellent predictions of the SSL process.     

Predicting daily pan evaporation by soft computing models with limited climatic data

Abstract

Accurate prediction of daily pan evaporation (PE) is important for monitoring, surveying, and management of water resources as well as reservoir management and evaluation of drinking water supply systems. This study develops and applies soft computing models to predict daily PE in a dry climate region of south-western Iran. Three soft computing models, namely the multilayer perceptron-neural networks model (MLP-NNM), Kohonen self-organizing feature maps-neural networks model (KSOFM-NNM), and gene expression programming (GEP), were considered. Daily PE was predicted at two stations using temperature-based, radiation-based, and sunshine duration-based input combinations. The results obtained by the temperature-based 3 (TEM3) model produced the best results for both stations. The Mann-Whitney U test was employed to compute the rank of different input combination for hypothesis testing. Comparison between the soft computing models and multiple linear regression model (MLRM) demonstrated the superiority of MLP-NNM, KSOFM-NNM, and GEP over MLRM. It was concluded that the soft computing models can be successfully employed for predicting daily PE in south western Iran.

Editor D. Koutsoyiannis     

Trend analysis of rainfall pattern over the Central India during 1901–2010

In the present study, trends of rainfall of the Central India were evaluated in monthly, seasonal, and annual time scales using the Revised Mann-Kendall (RMK) test, Sen’s slope estimator, and innovative trend method (ITM). For this purpose, the monthly rainfall data for 20 stations in Madhya Pradesh (MP) and Chhattisgarh (CG) states in Central India during 1901–2010 was used. The Sen’s slope estimator was utilized for calculating the slope of rainfall trend line. Based on the obtained results of RMK test, there is no significant trend in the stations for the January and October months. The results also showed that for MP, two out of 15 considered stations indicate significant annual trend, while the CG has four out of five stations with significant trend. The results of applying ITM test indicated that most of the stations have decreasing trends in annual (16 stations), summer (16 stations), and monsoon (11 stations) seasons, while the winter (12 stations) and post monsoon (11 stations) seasons generally show increasing trend. Unlike the RMK, the ITM shows significant increasing trend in rainfall of November and December months. The finding of current study can be used for irrigation and water resource management purpose over the Central India.     

Change in response of bridges isolated with LRBs due to lead core heating

This study focuses on the response of seismic isolated bridges subjected to near-field ground motions with distinct pulse type behavior in terms of maximum isolator displacements (MIDs) and maximum isolator forces (MIFs) transferred to the substructure. The employed isolation systems are composed of lead rubber bearings (LRBs) with bi-linear force-deformation relations that consider cycle-to-cycle deterioration in the yield strength of the LRBs due to heating of the lead core. MIDs and MIFs with due consideration of cycle-to-cycle deterioration are compared with that of non-deteriorating ones. Bounding analyses are also performed for comparison purposes. Nonlinear response history analyses are conducted with two bins of ground motions recorded at different soil conditions to investigate the effect of ground motion characteristics. Results indicate that MIDs are overestimated by lower bound analyses when seismic isolated bridges are subjected to near-field motions with high velocity pulses especially for the bearings with higher Q/W ratios.     

The combined RUSLE/SDR approach integrated with GIS and geostatistics to estimate annual sediment flux rates in the semi-arid catchment,Turkey

Quantitative evaluation of the spatial distribution of the erosion risk in any watershed or ecosystem is one of the most important tools for environmentalists, conservationists and engineers to plan natural resource management for the sustainable environment in a long term. This study was performed in the semi-arid catchment of the Saraykoy II Irrigation Dam, Cankiri, located in the transition zone between the Central Anatolia Steppe and the Black Sea Forests of Turkey. The total area of the catchment is 262.31 ha. The principal objectives were to quantify both potential and actual soil erosion risks by the Revised Universal Soil Loss Equation (RUSLE) and to estimate the amount of sediments to be delivered from the hillslope of the catchment to the reservoir of the dam using the sediment delivery ratio (SDR) in combination with the RUSLE model. All factor and sub-factor calculations required for solving the RUSLE model and SDR in the catchment were made spatially using DEM, GIS and Geostatistics. As the main catchment was divided into twenty-five sub-catchments, the predicted actual soil loss (by the model) was 146,657.52 m³ year^?1 and the weighted average of SDR estimated by areal distribution (%) of the sub-watersheds was 0.344 for whole catchment, resulted in 50,450.19 m³ year^?1 sediment arriving to the reservoir. Since the Dam has a total storage capacity of 509 × 10³ m³, the life expectancy of the Dam is estimated as 10.09 year. This estimation indicated that the dam has a relatively short economic life and there is a need for water-catchment management and soil conservation measures to reduce erosion.