Soil temperature modeling at different depths using neuro-fuzzy,neural network,and genetic programming techniques     

Ozgur?KisiEmail author  Hadi?Sanikhani  Murat?Cobaner 《Theoretical and Applied Climatology》2017,129(3-4):833-848

The applicability of artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS), and genetic programming (GP) techniques in estimating soil temperatures (ST) at different depths is investigated in this study. Weather data from two stations, Mersin and Adana, Turkey, were used as inputs to the applied models in order to model monthly STs. The first part of the study focused on comparison of ANN, ANFIS, and GP models in modeling ST of two stations at the depths of 10, 50, and 100 cm. GP was found to perform better than the ANN and ANFIS-SC in estimating monthly ST. The effect of periodicity (month of the year) on models’ accuracy was also investigated. Including periodicity component in models’ inputs considerably increased their accuracies. The root mean square error (RMSE) of ANN models was respectively decreased by 34 and 27 % for the depths of 10 and 100 cm adding the periodicity input. In the second part of the study, the accuracies of the ANN, ANFIS, and GP models were compared in estimating ST of Mersin Station using the climatic data of Adana Station. The ANN models generally performed better than the ANFIS-SC and GP in modeling ST of Mersin Station without local climatic inputs.  相似文献   

Estimation of Hardgrove grindability index of Turkish coals by neural networks     

Gülhan Özbayoğlu  A. Murat Özbayoğlu  M. Evren Özbayoğlu 《International Journal of Mineral Processing》2008

In this research, different techniques for the estimation of coal HGI values are studied. Data from 163 sub-bituminous coals from Turkey are used by featuring 11 coal parameters, which include proximate analysis, group maceral analysis and rank. Non-linear regression and neural network techniques are used for predicting the HGI values for the specified coal parameters. Results indicate that a hybrid network which is a combination of 4 separate neural networks gave the most accurate HGI prediction and all of the neural network models outperformed non-linear regression in the estimation process.  相似文献   

Hydrochemical and microbiological quality of groundwater in West Thrace Region of Turkey     

H. Murat Özler  Ali Aydın 《Environmental Geology》2008,54(2):355-363

The aim of this study was to do a preliminary assessment of the hydrochemical and microbial groundwater quality of the West Thrace region. Forty samples of groundwater collected from Edirne (Site 1) to Gelibolu (Site 2) were assessed for their suitability for human consumption. As³⁻ was non-detectable in all the groundwater and Zn²⁺, Pb²⁺, F⁻, Cu²⁺, NH₄⁺, Cn⁻ PO₄³⁻ and Cl⁻ were all below their respective European Union drinking water directive (EU-DWD) and Turkish food codex-drinking water directive (TFC-DWD). Maximum Acceptable Concentrations (MAC) Ni²⁺, Pb²⁺, Cd²⁺, Mg²⁺, Mn²⁺, and Ca²⁺ levels were detected in upper maximum acceptable concentrations 77.5, 42.5, 35.0, 50.0, 50.0, and 32.5% of the groundwater samples, respectively. However, in terms of Cr³⁺, Ni²⁺ and Pb²⁺, the differences between groundwaters of Sites 1 and 2 were significant (p < 0.05). Eight water samples (20%) had HPC exceeding the EU and Turkish water directive limit 20 CFU (Colony Forming Unit)/ml in drinking water and the maximum bacteria count recorded was 44 CFU/ml. Total coliforms, thermotolerant coliforms, E. coli, Enterococcus spp., Salmonella sp., Staphylococcus spp. and P. aeruginosa were detected in 25, 17.5, 15, 47.5, 15, 27.5, and 15% of the groundwater samples, respectively. Furthermore, heavy metals and trace elements were found after chemical analyzes in most samples. The pollution of groundwater come from a variety of sources, Meric and Ergene rivers, including land application of agricultural chemicals and organics wastes, infiltration of irrigation water, septic tanks, and infiltration of effluent from sewage treatment plants, pits, lagoons and ponds used storage.  相似文献   

Determining of the local housing identity in urban transformation areas under disaster risk: Bursa,Turkey     

Nilüfer Taş  Murat Taş 《Natural Hazards》2015,75(1):119-139

  相似文献   

Large scale moisture flux characteristics of the mediterranean basin and their relationships with drier and wetter climate conditions     

Sinan Şahin  Murat Türkeş  Sheng-Hung Wang  David Hannah  Warren Eastwood 《Climate Dynamics》2015,45(11-12):3381-3401

  相似文献   

Tsunami risk and impacts on coastlines     

Ioan Nistor  Murat Saatcioglu 《Natural Hazards》2012,60(1):1

  相似文献   

A new approach to use AHP in landslide susceptibility mapping: a case study at Yenice (Karabuk, NW Turkey)   总被引：9，自引：4，他引：5  

G?k?e Deniz Hasekio?ullar?  Murat Ercanoglu 《Natural Hazards》2012,63(2):1157-1179

This study aimed to investigate the parameter effects in preparing landslide susceptibility maps with a data-driven approach and to adapt this approach to analytical hierarchy process (AHP). For this purpose, at the first stage, landslide inventory of an area located in the Western Black Sea region of Turkey covering approximately 567?km² was prepared, and a total of 101 landslides were mapped. In order to assess the landslide susceptibility, a total of 13 parameters were considered as the input parameters: slope, aspect, plan curvature, topographical elevation, vegetation cover index, land use, distance to drainage, distance to roads, distance to structural elements, distance to ridges, stream power index, sediment transport capacity index, and wetness index. AHP was selected as the major assessment methodology since the adapted approach and AHP work in data pairs. Adapted to AHP, a similarity relation?Cbased approach, namely landslide relation indicator (LRI) for parameter selection method, was also proposed. AHP and parametric effect analyses were performed by the proposed approach, and seven landslide susceptibility maps were produced. Among these maps, the best performance was gathered from the landslide susceptibility map produced by 9 parameter combinations using area under curve (AUC) approach. For this map, the AUC value was calculated as 0.797, while the others ranged between 0.686 and 0.771. According to this map, 38.3?% of the study area was classified as having very low, 8.5?% as low, 15.0?% as moderate, 20.3?% as high, and 17.9?% as very high landslide susceptibility, respectively. Based on the overall assessments, the proposed approach in this study was concluded as objective and applicable and yielded reasonable results.  相似文献   

A Simplified Failure Criterion for Intact Rocks Based on Rock Type and Uniaxial Compressive Strength   总被引：2，自引：1，他引：1  

Jiayi Shen  Rafael Jimenez  Murat Karakus  Chaoshui Xu 《Rock Mechanics and Rock Engineering》2014,47(2):357-369

The uniaxial compressive strength (UCS) of intact rock, which can be estimated using relatively straightforward and cost-effective techniques, is one of the most practical rock properties used in rock engineering. Thus, constitutive laws to represent the strength and behavior of (intact) rock frequently use it, along with additional intrinsic rock properties. Although triaxial tests can be employed to obtain best-fit failure criterion parameters that provide best strength predictions, they are more expensive and require time-consuming procedures; as a consequence, they are often not readily available at early stages of a project. Based on the analysis of an extensive triaxial test database for intact rocks, we propose a simplified empirical failure criterion in which rock strength at failure is expressed in terms of confining stress and UCS, with a new parameter which can be directly estimated from the UCS for a specified rock type in the absence of triaxial test data. Performance of the proposed failure criterion is then tested for validation against experimental data for eight rock types. The results show that strengths of intact rock estimated by the proposed failure criterion are in good agreement with experimental test data, with small discrepancies between estimated and measurements strengths. Therefore, the proposed criterion can be useful for preliminary (triaxial) strength estimation of intact rocks when triaxial tests data are not available.  相似文献   

Mixing processes in hydrothermal spring systems and implications for interpreting geochemical data: a case study in the Cappadocia region of Turkey     

Mustafa Afsin  Diana M. Allen  Dirk Kirste  U. Gokcen Durukan  Ali Gurel  Ozcan Oruc 《Hydrogeology Journal》2014,22(1):7-23

Mixing is a dominant hydrogeological process in the hydrothermal spring system in the Cappadocia region of Turkey. All springs emerge along faults, which have the potential to transmit waters rapidly from great depths. However, mixing with shallow meteoric waters within the flow system results in uncertainty in the interpretation of geochemical results. The chemical compositions of cold and warm springs and geothermal waters are varied, but overall there is a trend from Ca–HCO₃ dominated to Na–Cl dominated. There is little difference in the seasonal ionic compositions of the hot springs, suggesting the waters are sourced from a well-mixed reservoir. Based on δ¹⁸O and δ²H concentrations, all waters are of meteoric origin with evidence of temperature equilibration with carbonate rocks and evaporation. Seasonal isotopic variability indicates that only a small proportion of late spring and summer precipitation forms recharge and that fresh meteoric waters move rapidly into the flow system and mix with thermal waters at depth. ³H and percent modern carbon (pmC) values reflect progressively longer groundwater pathways from cold to geothermal waters; however, mixing processes and the very high dissolved inorganic carbon (DIC) of the water samples preclude the use of either isotope to gain any insight on actual groundwater ages.  相似文献   

Reciprocal influence of Kürtün Dam and wastewaters from the settlements on water quality in the stream Harşit,NE Turkey     

Adem Bayram  Hızır Önsoy  Murat İhsan Kömürcü  Mehmet Tüfekçi 《Environmental Earth Sciences》2014,72(8):2849-2860

This paper aims to reveal the reciprocal influence of Kürtün Dam and wastewaters from the settlements on the water quality in the stream Har?it, NE Turkey. Several key water-quality indicators were measured: water temperature (T), pH, dissolved oxygen (DO), electrical conductivity, water hardness, chemical oxygen demand (COD), ammonium nitrogen (NH₄ ⁺–N), nitrite nitrogen (NO₂ ^?–N), nitrate nitrogen (NO₃ ^?–N), total Kjeldahl nitrogen (TKN), total nitrogen (TN), orthophosphate phosphorus (PO₄ ^3?–P), and methylene blue active substances (MBAS). The monitoring and sampling studies were conducted every 15 days from March 2009 to February 2010 at two stations selected in the upstream and downstream of the Kürtün Dam. It was concluded that the Kürtün Dam Lake had a high-quality water in terms of T, pH, DO, COD, NH₄ ⁺–N, NO₂ ^?–N and NO₃ ^?–N values, but slightly polluted water with respect to TKN, PO₄ ^3?–P, and MBAS according to the Turkish Water Pollution Control Regulation. The dam improved the stream water quality by increasing the DO concentration, and decreasing the NO₂ ^?–N and PO₄ ^3?–P concentrations thanks to its hydraulic residence time despite the wastewater discharge by the nearby settlements. However, the wastewater discharge deteriorated the stream water quality increasing the COD, NH₄ ⁺–N, NO₃ ^––N, and TN concentrations.  相似文献