Abstract Biochemical oxygen demand (BOD) has been shown to be an important variable in water quality management and planning. However, BOD is difficult measure needs longer time periods (5 days) get results. Artificial neural networks (ANNs) are being used increasingly predict forecast resource variables. The objective of this research was develop ANNs model estimate daily the inlet wastewater biochemical treatment plants. plantscale data set (364 records year 2005) obtained from a local...

Abstract. The results of the application an unsupervised learning (neural network) approach comprising a Self Organizing Map (SOM), to distinguish micro-earthquakes from quarry blasts in vicinity Istanbul, Turkey, are presented and discussed. SOM is constructed as neural classifier complementary reliability estimator seismic events, was employed for varying map sizes. Input parameters consisting frequency time domain data (complexity, spectral ratio, S/P wave amplitude peak ratio origin...

Abstract The transport of sediment load in rivers is important with respect to pollution, channel navigability, reservoir filling, longevity hydroelectric equipment, fish habitat, river aesthetics and scientific interest. However, conventional rating curves cannot estimate accurately. An adaptive neuro-fuzzy technique investigated for its ability improve the accuracy streamflow—suspended curve daily suspended estimation. streamflow data four stations Black Sea region Turkey are used as case...

Abstract. Two unsupervised pattern recognition algorithms, k-means, and Gaussian mixture model (GMM) analyses have been applied to classify seismic events in the vicinity of Istanbul. Earthquakes, which are occurring at different seismicity rates extensions Thrace-Eskisehir Fault Zone North Anatolian (NAF), Turkey, being contaminated by quarries operated around We used two time variant parameters, complexity, ratio integrated powers velocity seismogram, S/P amplitude as classifiers using...

One of the key factors for flood modeling and control is hydrograph, which not always available due to lack discharge observations. In reverse flow routing, hydraulic or hydrological calculations are performed from downstream end upstream end. present study, a routing approach developed based on Muskingum model. The storage function conceptualized as linear five different nonlinear forms. Euler fourth-order Runge–Kutta numerical methods used solving models. shuffled complex evolution (SCE)...

Floods pose significant risks worldwide, impacting lives, infrastructure, and economies. The Susurluk basin, covering 24,319 km2 in Türkiye, is highly vulnerable to flooding. This study updates the flood management plan for integrating hydrological modeling, GIS-based mapping, early warning system evaluations alignment with EU Flood Directive. A total of 503 hydrodynamic models (226 one-dimensional 277 two-dimensional) were developed, analyzing 2116 km stream length. As a result evaluation,...

Purpose Many construction companies use the diversification strategy to take advantage of its various advantages. However, previous studies on this have neither analysed management perspective nor considered pre-diversification stage companies. The purpose study is provide a detailed discussion about motivations and evaluate decision-making criteria at corporate level in industry from senior managers. Design/methodology/approach related literature was reviewed determine reasons for...

While 1D, 2D, and coupled 1D/2D models are widely used in flood extent mapping, a significant research gap remains comparative analyses of 2D approaches. Study the Dinsiz Stream Basin is critical importance due to its proximity industrial zones residential areas, as well susceptibility risk. Due lack insufficiency flow data basin, only long-term rainfall were analysis. Rainfall return periods 50, 100, 200, 500 years estimated using statistical methods, these values utilized generate...

Doubt regarding the applicability of laboratory results to alluvial streams has led some develop sediment transport predictors based solely on field data, and most current formulae have typically been calibrated at least partially data. This paper examines transferability flume by exploring extent which a unified approach prediction (1) flow regime, (2) depth, (3) total can be developed entirely with Relevance vector machine (RVM)‐based probabilistic models were constructed only their...

Appropriate and acceptable prediction of bed load being carried by streams is vitally important for water resources quantity quality studies. Although measuring the rate in situ most consistent method, it very expensive cannot be conducted as many measurement suspended sediment load. Therefore, this study role on bedload was examined using sensitivity analysis. On other hand, conventional rating curves equations can not predict accurately so recently usage machine learning algorithms...

Abstract Evapotranspiration, an important component in terrestrial water balance and net primary productivity models, is difficult to measure estimate. In this study, the potential of adaptive neuro‐fuzzy inference system (ANFIS) investigated modelling daily grass crop reference evapotranspiration (ET o ) obtained using Penman–Monteith equation. Various combinations climatic data, namely solar radiation, air temperature, relative humidity wind speed, are used as inputs ANFIS so evaluate...

Abstract The Eastern Mediterranean region of the Middle East and North Africa (MENA) is experiencing patterns major drought due to effects rising temperatures falling precipitation levels. multiscale evaluation Standardized Precipitation Evapotranspiration Index (SPEI) reveals evolving severe from Sinai desert toward East. While there has been a period without between 1970 1990, severity frequency increased considerably after 1990. Current conditions in MENA are moderate with 60–100%...

Abstract This paper presents the use of artificial neural network (ANN) to develop a model for predicting rejection rate (R o) single salt (NaCl) by nanofiltration based on experimental data-sets. The rates NaCl were obtained when operating conditions, such as feed pressure (ΔP) and cross flow velocity (V), varied along with different physicochemical properties water like dye concentrations, pH. In modeling work, sensitivity analyses performed identify relative impact each parameter find...