Ali Aytek

Discussion of “Generalized regression neural networks for evapotranspiration modelling”

Hydrological Sciences Journal-journal Des Sciences Hydrologiques, Aug 1, 2007

There is no doubt that so-called "artificial neural networks" (ANN) are powerful computational to... more There is no doubt that so-called "artificial neural networks" (ANN) are powerful computational tools to model complex nonlinear systems. In my view, an ANN establishes a data-driven nonlinear relationship between inputs and outputs of a system. The fact that such a nonlinear model is generally very complicated (usually one does not even write down the equations) renders it a black-box model. The fact that the model contains numerous parameters makes imperative the use of an advanced optimization method to calibrate its parameters. Once an ANN is fitted, it can be used to predict outputs from known inputs. Thus, there have been numerous successful applications of ANN in forecasting the future evolution of complex systems (e.g. Casdagli & Eubank, 1992; Weigend & Gershenfeld, 1994). However, I am afraid that there has also been an abuse in other cases, indirectly assisted by the numerous technical details, inapproachable for the majority of scientists (in our case hydrologists), and even by the exotic ANN vocabulary. The paper by Kişi (2006) stimulated my "reflex" questions about "neural networks", their use and abuse, and helped me to organize them so that they can be addressed to the "central nervous system". I start with the vocabulary itself. How "neural" are ANN? This question may be philosophical and related to the nature of the so called "artificial intelligence". I am not prepared to discuss in depth this type of question, for which profound analyses can be found in Dreyfus & Dreyfus (1986), Penrose (1989, 1994, 1996) and Hodges (2000-2002). However, I thought of a simplified version of this question: Is it necessary to call these mathematical models "neural" networks? Structures such as graphs and networks are very common in science (including hydrology, hydraulics and water resources), and consist of nodes (or vertices) and arcs (edges, or arrows in directed graphs and networks). Why in this case should we speak of "neurons" instead of nodes or arcs? After all, while in other cases (e.g. a river network, a water distribution network) the network has a physical hypostasis, in ANN the network is just a convenient pictorial representation of a complicated mathematical nonlinear relationship, which could be handled even without the notion of a network. A lot of similar questions can arise: Why use such terms as "one-pass learning algorithm with a highly parallel structure" or "training vector"? Isn't it more understandable to speak about "model calibration", "model fitting" and "parameter optimization" instead of "learning" or "training"? If yes, why have these anthropomorphized terms been so prevalent? Furthermore, is an ANN approach appropriate for any type of problem? Kişi (2006) seems to reply positively to this question. His motivation for the paper is simply this: "However, the application of ANN to evapotranspiration modelling is limited in the literature. ... To the knowledge of the author, no work has been reported

Download

SPI ve SPEI ile Samsun İli Kuraklık Analizi

Kahramanmaraş Sütçü İmam universitesi mühendislik bilimleri dergisi, Sep 3, 2022

Kuraklığın tanımlanması, izlenmesi ve karakterizasyonu; su kaynakları planlaması ve yönetiminde b... more Kuraklığın tanımlanması, izlenmesi ve karakterizasyonu; su kaynakları planlaması ve yönetiminde büyük önem taşımaktadır. Bu çalışmada, Samsun kent merkezinde bulunan 17030 no'lu meteoroloji istasyonundan 1938-2020 yılları arasında kaydedilen aylık yağış verileri ve Standart Yağış İndeksi (SPI) ile Standartlaştırılmış Yağış Evapotranspirasyon İndeksi (SPEI) kullanılarak kuraklık analizi yapılmıştır. Çalışmanın ilk kısmında, iklim değişikliğinin yağış, sıcaklık, nispi nem ve buharlaşma verileri üzerindeki etkileri %95 güven aralığına göre incelenmiştir. Sıcaklık verisinde artan bir eğilim söz konusu iken, yağış, nispi nem ve buharlaşma verilerinde herhangi bir eğilim gözlemlenmemiştir. SPI ve SPEI arasında 1 aylık zaman serilerinde güçlü bir ilişki elde edilirken, 3-, 6-, 9-, 12 ve 24-aylık zaman serilerinde bu ilişki güçlü olsa da belirleme katsayısı olan R 2 değerlerinde azalma olduğu gözlemlenmiştir. Samsun ili için kuraklık kategorileri arasında en fazla normal kuraklık görülmesine rağmen, çok şiddetli kuraklık kategorisi ise en az paya sahiptir. İki indeks arasında çok az farklılık gözlemlenmiştir. Ancak, çok şiddetli kuraklık kategorisinde yapılan indeks karşılaştırmaya dayalı analizler SPI indeksinin, SPEI indeksine göre daha hassas sonuçlar verdiğini ortaya koymuştur. İki indeks ile elde edilen bulgulara göre, 1950 yılında hem kuraklık süresi bakımından hem de kuraklık şiddeti bakımından uzun süren bir kuraklık gözlemlenmiştir.

Download

Mathematical modeling for river delta formation

Akarsular üzerine yapılan çeşitli düzenleme yapıları, bu akarsuların taşıdığı ka... more Akarsular üzerine yapılan çeşitli düzenleme yapıları, bu akarsuların taşıdığı katı madde miktarını değiştirmektedir. Bu değişikliklerin olumsuz etkilerinin en belirgin olarak görüldüğü yer, akarsuların çıkış ağızlarında oluşan deltalardır. Denge halinde bulunan bir akarsu kesiminde bir barajın yapılması sonucunda, baraj gölünün yukarısında, su kabarması görülen nehir kısmında, su hızı düştüğü için akarsuyun taşıdığı katı maddelerin önce iri malzemeleri çökelir.  Daha sonra biraz daha ince olan kum ve çakıl gibi malzemeler baraj gölünün menba kesiminde çökelir ve bu çökelmeler delta oluşturur. Kil ve silt iriliğindeki malzemeler ise baraj gölünde akmaya devam eder ve baraj gövdesine yakın bölgede çökelirler.  Böylece barajlarda üç türlü yığılma söz konusu olur...

Download

Sea water level forecasting using genetic programming and comparing the performance with Artificial Neural Networks

Computers & Geosciences, 2010

Water level forecasting at various time intervals using records of past time series is of importa... more Water level forecasting at various time intervals using records of past time series is of importance in water resources engineering and management. In the last 20 years, emerging approaches over the conventional harmonic analysis techniques are based on using Genetic Programming (GP) and Artificial Neural Networks (ANNs). In the present study, the GP is used to forecast sea level variations, three time steps ahead, for a set of time intervals comprising 12 h, 24 h, 5 day and 10 day time intervals using observed sea levels. The measurements from a single tide gauge at Hillarys Boat Harbor, Western Australia, were used to train and validate the employed GP for the period from December 1991 to December 2002. Statistical parameters, namely, the root mean square error, correlation coefficient and scatter index, are used to measure their performances. These were compared with a corresponding set of published results using an Artificial Neural Network model. The results show that both these artificial intelligence methodologies perform satisfactorily and may be considered as alternatives to the harmonic analysis.

Download

Genetic Programming-Based Empirical Model for Daily Reference Evapotranspiration Estimation

CLEAN - Soil, Air, Water, 2008

Genetic programming (GP) is presented as a new tool for the estimation of reference evapotranspir... more Genetic programming (GP) is presented as a new tool for the estimation of reference evapotranspiration by using daily atmospheric variables obtained from the California Irrigation Management Information System (CIMIS) database. The variables employed in the model are daily solar radiation, daily mean temperature, average daily relative humidity and wind speed. The results obtained are compared to seven conventional reference evapotranspiration models including: (1) the Penman-Monteith equation modified by CIMIS, (2) the Penman-Monteith equation modified by the Food and Agricultural Organization (FAO 56), (3) the Hargreaves-Samani equation, (4) the solar radiation-based ET 0 equation, (5) the Jensen-Haise equation, (6) the Jones-Ritchie equation, and (7) the Turc method. Statistical measures such as average, standard deviation, minimum and maximum values, as well as criteria such as mean square error and determination coefficient are used to measure the performance of the model developed by employing GP. Statistics and scatter plots indicate that the new equation produces quite satisfactorily results and can be used as an alternative to the conventional models.

Download

Akarsu deltaları oluşumunun matematik modellenmesi

Akarsular uzerine yapilan cesitli duzenleme yapilari, bu akarsularin tasidigi kati madde miktarin... more Akarsular uzerine yapilan cesitli duzenleme yapilari, bu akarsularin tasidigi kati madde miktarini degistirmektedir. Bu degisikliklerin olumsuz etkilerinin en belirgin olarak goruldugu yer, akarsularin cikis agizlarinda olusan deltalardir. Denge halinde bulunan bir akarsu kesiminde bir barajin yapilmasi sonucunda, baraj golunun yukarisinda, su kabarmasi gorulen nehir kisminda, su hizi dustugu icin akarsuyun tasidigi kati maddelerin once iri malzemeleri cokelir. Daha sonra biraz daha ince olan kum ve cakil gibi malzemeler baraj golunun menba kesiminde cokelir ve bu cokelmeler delta olusturur. Kil ve silt iriligindeki malzemeler ise baraj golunde akmaya devam eder ve baraj govdesine yakin bolgede cokelirler. Boylece barajlarda uc turlu yigilma soz konusu olur. a)- suyun kabardigi akarsu kesimindeki yigilmalar, b)- kum ve cakilin olusturdugu deltalar ve c-) kil ve siltin olusturdugu taban yigilmalari. Yigilma sekilleri, kil malzemesinin mineral karakteristigine ve suyun hareket sekline...

Download

Rheological and strength performances of cold-bonded geopolymer made from limestone dust and bottom ash for grouting and deep mixing

Bulletin of Engineering Geology and the Environment

This paper aims to research the potential use of cold-bonded geopolymer stabilizer made from lime... more This paper aims to research the potential use of cold-bonded geopolymer stabilizer made from limestone dust and bottom ash for grouting and deep soil (clay) mixing. For this purpose, the rheology and strength performances of the cement (PC)-based grouts with the stabilizers of limestone dust (LD), bottom ash (BA), geopolymerized cold-bonded limestone dust (GLD), and geopolymerized cold-bonded bottom ash (GBA) were investigated. The rheometer tests were conducted for the rheological performances at a wide range of stabilizer replacement (0–100%) and water/binder (w/b) ratio (0.75–1.5). Using proper replacements from the grout rheology, the unconfined compressive strength (UCS) tests (7 days, 28 days) were performed for the grouting (w/b = 1) and deep mixing (w/b = 1–1.25). The effect of stabilizer on the failure patterns was also examined from specimens of UCS tests. From the experimental work, the rheology of grout mixtures indicated (i) the adequacy of low amount of stabilizer replacements (< 50%); (ii) the dilatant behavior similar to PC; (iii) a decreasing trend of the shear stress, apparent viscosity, yield stress, and plastic viscosity with the increased w/b; (iv) slight to moderate responses of PC mostly; and (v) a potentially favorable rheology of cold-bonded stabilizers (GLD, GBA) for grout flow and workability regarding the yield stress and plastic viscosity. From the strength tests of grout mixtures (0–40%), the GBA additions yielded higher UCS performances for the grouting. For the deep mixing, both the additions of GLD and GBA were found more successful for the strength. The failure planes of UCS specimens were observed independent from the stabilizer types and dosage rates that dominantly failed in axially or near-axial splitting. From the study, the contributions of GLD and GBA from the potential of cold bonding are relatively promising for grouting and deep mixing.

Co-active neurofuzzy inference system for evapotranspiration modeling

Soft Computing, 2009

This study proposes co-active neuro-fuzzy inference system (CANFIS) for daily reference evapotran... more This study proposes co-active neuro-fuzzy inference system (CANFIS) for daily reference evapotranspiration (ET 0) modeling by using daily atmospheric parameters obtained from California Irrigation Management Information System (CIMIS) database. The CANFIS model is trained and tested using three stations from different geographical locations in California. The model is compared with the well-known conventional ET 0 models such as the CIMIS Penman equation, the Penman-Monteith equation standardized by the Food and Agriculture Organization (FAO-56 PM), the Hargreaves equation and the Turc equation. Meteorological variables; solar radiation, air temperature, relative humidity and wind speed taken from CIMIS database for 4 years (January 2002-December 2005) are used to evaluate the performance analysis of the models. Statistics such as average, standard deviation, minimum and maximum values, as well as criteria such as root mean square error (RMSE), the efficiency coefficient (E) and determination coefficient (R 2) are used to measure the performance of the CANFIS. Considerably well performance is achieved in modeling ET 0 by using CANFIS. It is concluded from the results that CANFIS can be proposed as an alternative ET 0 model to the existing conventional models.

Download

Akarsu deltaları oluşumunun matematik modellenmesi

Itudergisi D, Apr 28, 2011

... Böylece barajlarda üç türlü yığılma söz konusu olur. a)- suyun kabardığı akarsu kesimindeki y... more

Comment on `Kisi O. 2007. Evapotranspiration modelling from climatic data using a neural computing technique.Hydrological Processes21: 1925 1934

Hydrol Process, 2008

... Turkey. Email: Hafzullah Aksoy (haksoy@itu.edu.tr). *Correspondence: Hafzullah Aksoy, Istanbu... more

A genetic programming technique for lake level modeling

Hydrology Research, 2014

The potential of gene expression programming (GEP) approach for modeling monthly lake levels is i... more The potential of gene expression programming (GEP) approach for modeling monthly lake levels is investigated. The application of the methodology is presented for the monthly water level data of Van Lake, which is the biggest lake in Turkey. The root mean square errors, mean absolute relative errors, determination coefficient, and modified coefficient of efficiency (EM) are used for evaluating the accuracy of the genetic programming-based models. The results of the proposed models are compared with those of the neuro-fuzzy models. The comparison results indicate that the suggested GEP-based models perform better than the neuro-fuzzy models in forecasting monthly lake levels.

Explicit neural network in suspended sediment load estimation

Neural Network World, 2013

Correct estimation of sediment volume carried by a river is very important for many water resourc... more Correct estimation of sediment volume carried by a river is very important for many water resources projects. Traditionally, artificial neural networks (ANNs) are used as black-box models without understanding what happens inside the box. The question is that, how anyone who may be unfamiliar with ANNs can apply this kind of models in any other study, while the model has not been formulated. This paper proposes an explicit neural network (ENN) formulation which is simple and can be used, by anyone who is even not familiar with ANNs, for modeling daily suspended sediment-discharge relationship. The daily streamflow and suspended sediment data from two stations on Tongue River in Montana are used as case studies. Two different sediment rating curves (SRC), multi-linear regression (MLR) and nonlinear regression (NLR) are also applied to the same data. The ENN estimates are compared with those of the SRC, MLR and NLR models. The root mean square errors (RMSE), mean absolute errors (MAE), correlation coefficient (R) and model efficiency (E) statistics are used to evaluate the performance of the models. The comparison results reveal that the suggested model performs better than the conventional SRC, MLR and NLR.

Download

Co-active neurofuzzy inference system for evapotranspiration modeling

Soft Computing, 2009

This study proposes co-active neuro-fuzzy inference system (CANFIS) for daily reference evapotran... more This study proposes co-active neuro-fuzzy inference system (CANFIS) for daily reference evapotranspiration (ET 0) modeling by using daily atmospheric parameters obtained from California Irrigation Management Information System (CIMIS) database. The CANFIS model is trained and tested using three stations from different geographical locations in California. The model is compared with the well-known conventional ET 0 models such as the CIMIS Penman equation, the Penman-Monteith equation standardized by the Food and Agriculture Organization (FAO-56 PM), the Hargreaves equation and the Turc equation. Meteorological variables; solar radiation, air temperature, relative humidity and wind speed taken from CIMIS database for 4 years (January 2002-December 2005) are used to evaluate the performance analysis of the models. Statistics such as average, standard deviation, minimum and maximum values, as well as criteria such as root mean square error (RMSE), the efficiency coefficient (E) and determination coefficient (R 2) are used to measure the performance of the CANFIS. Considerably well performance is achieved in modeling ET 0 by using CANFIS. It is concluded from the results that CANFIS can be proposed as an alternative ET 0 model to the existing conventional models.

Download

Stochastic generation of hourly mean wind speed data

Renewable Energy, 2004

Use of wind speed data is of great importance in civil engineering, especially in structural and ... more Use of wind speed data is of great importance in civil engineering, especially in structural and coastal engineering applications. Synthetic data generation techniques are used in practice for cases where long wind speed data are required. In this study, a new wind speed data generation scheme based upon wavelet transformation is introduced and compared to the existing wind speed generation methods namely normal and Weibull distributed independent random numbers, the first-and second-order autoregressive models, and the first-order Markov chain. Results propose the wavelet-based approach as a wind speed data generation scheme to alternate the existing methods.

Download

A practical approach to formulate stage–discharge relationship in natural rivers

Neural Computing and Applications, 2013

ABSTRACT This study proposes a new formulation technique for modeling stage–discharge relationshi... more ABSTRACT This study proposes a new formulation technique for modeling stage–discharge relationship, as an alternative approach to standard regression techniques. An explicit neural network formulation (ENNF) is derived by using data obtained from United States Geological Survey data base. The neural network model is trained and tested using time series of daily stage and discharge data from two stations in Pennsylvania, USA. The model is compared with the standard rating curve (SRC) technique. Statistical parameters such as average, standard deviation, minimum, and maximum values, as well as criteria such as root mean square error, the efficiency coefficient (E), and determination coefficient (R 2) are used to measure the performance of the ENNF. Considerably, well performance is achieved in modeling streamflow by using ENNF. The comparison results reveal that the suggested formulations perform better than the conventional SRC.

A genetic programming approach to suspended sediment modelling

Journal of Hydrology, 2008

... Examples of such models are presented by [Wicks and Bathurst, 1996] , [Kothyari et al., 1997]... more

New Approach for Stage–Discharge Relationship: Gene-Expression Programming

Journal of Hydrologic Engineering, 2009

An application of artificial intelligence for rainfall-runoff modeling

Journal of Earth System Science, 2008

This study proposes an application of two techniques of artificial intelligence (AI) for rainfall... more This study proposes an application of two techniques of artificial intelligence (AI) for rainfall-runoff modeling: the artificial neural networks (ANN) and the evolutionary computation (EC). Two different ANN techniques, the feed forward back propagation (FFBP) and generalized regression neural network (GRNN) methods are compared with one EC method, Gene Expression Programming (GEP) which is a new evolutionary algorithm that evolves computer programs. The daily hydrometeorological data of three rainfall stations and one streamflow station for Juniata River Basin in Pennsylvania state of USA are taken into consideration in the model development. Statistical parameters such as average, standard deviation, coefficient of variation, skewness, minimum and maximum values, as well as criteria such as mean square error (MSE) and determination coefficient (R 2) are used to measure the performance of the models. The results indicate that the proposed genetic programming (GP) formulation performs quite well compared to results obtained by ANNs and is quite practical for use. It is concluded from the results that GEP can be proposed as an alternative to ANN models.

Download

Discussion of “Generalized regression neural networks for evapotranspiration modelling”

Hydrological Sciences Journal, 2007

There is no doubt that so-called "artificial neural networks" (ANN) are powerful computational to... more There is no doubt that so-called "artificial neural networks" (ANN) are powerful computational tools to model complex nonlinear systems. In my view, an ANN establishes a data-driven nonlinear relationship between inputs and outputs of a system. The fact that such a nonlinear model is generally very complicated (usually one does not even write down the equations) renders it a black-box model. The fact that the model contains numerous parameters makes imperative the use of an advanced optimization method to calibrate its parameters. Once an ANN is fitted, it can be used to predict outputs from known inputs. Thus, there have been numerous successful applications of ANN in forecasting the future evolution of complex systems (e.g. Casdagli & Eubank, 1992; Weigend & Gershenfeld, 1994). However, I am afraid that there has also been an abuse in other cases, indirectly assisted by the numerous technical details, inapproachable for the majority of scientists (in our case hydrologists), and even by the exotic ANN vocabulary. The paper by Kişi (2006) stimulated my "reflex" questions about "neural networks", their use and abuse, and helped me to organize them so that they can be addressed to the "central nervous system". I start with the vocabulary itself. How "neural" are ANN? This question may be philosophical and related to the nature of the so called "artificial intelligence". I am not prepared to discuss in depth this type of question, for which profound analyses can be found in Dreyfus & Dreyfus (1986), Penrose (1989, 1994, 1996) and Hodges (2000-2002). However, I thought of a simplified version of this question: Is it necessary to call these mathematical models "neural" networks? Structures such as graphs and networks are very common in science (including hydrology, hydraulics and water resources), and consist of nodes (or vertices) and arcs (edges, or arrows in directed graphs and networks). Why in this case should we speak of "neurons" instead of nodes or arcs? After all, while in other cases (e.g. a river network, a water distribution network) the network has a physical hypostasis, in ANN the network is just a convenient pictorial representation of a complicated mathematical nonlinear relationship, which could be handled even without the notion of a network. A lot of similar questions can arise: Why use such terms as "one-pass learning algorithm with a highly parallel structure" or "training vector"? Isn't it more understandable to speak about "model calibration", "model fitting" and "parameter optimization" instead of "learning" or "training"? If yes, why have these anthropomorphized terms been so prevalent? Furthermore, is an ANN approach appropriate for any type of problem? Kişi (2006) seems to reply positively to this question. His motivation for the paper is simply this: "However, the application of ANN to evapotranspiration modelling is limited in the literature. ... To the knowledge of the author, no work has been reported

Download

An explicit neural network formulation for evapotranspiration

Hydrological Sciences Journal, 2008

Uploads

Papers by Ali Aytek

Log In