Search

In this study, two manufacturing systems, a kanban-controlled system and a multi-stage, multi-server production line in a diamond tool production system, are optimized utilizing neural network metamodels (ts•NNM) trained via tabu search (TS) which was developed previously by the authors. The most widely used training algorithm for neural networks has been back propagation which is based on a gradient technique that requires significant computational effort. To deal with the major shortcomings of back propagation (BP) such as the tendency to converge to a local optimal and a slow convergence rate, the TS metaheuristic method is used for the training of artificial neural networks to improve the performance of the metamodelling approach. The metamodels are analysed based on their ability to predict simulation results versus traditional neural network metamodels that have been trained by BP algorithm (bp•NNM). Computational results show that ts•NNM is superior to bp•NNM for both of the manufacturing systems. [ABSTRACT FROM AUTHOR]

Today, data mining has become a relevant topic in digital soil mapping. In this current study, prediction of some soil properties and their spatial distribution were examined by machine learning algorithms (Support Vector Machine, Artificial Neural Network) using reflectance values of Triplesat satellite image bands in Vezirköprü district of Samsun province. The band data obtained from different wavelengths revealed positive correlations between the electrical conductivity and calcium carbonate equivalent contents of the soils. The support vector machine algorithm was the most successful to estimate the textural fractions, organic matter, electrical conductivity, and calcium carbonate equivalent contents of the soils using the bands obtained from satellite images. The mean absolute error for estimating sand, silt, and clay contents by support vector machine was 4.05%, 3.05%, and 3.66%, respectively. Texture classes were determined with an accuracy of 82% with support vector machine and 60% with artificial neural network. In all estimations, the highest percentage of error was for calcium carbonate equivalent content with very low estimation reliability. The mean absolute percentage of error values for this property are 101.13% and 51.61% for artificial neural network and support vector machine, respectively. Also, in both algorithms, the most successfully estimated soil property was clay fraction of soils. It was also investigated the spatial distribution of actual and estimated values using various interpolation methods (Kriging, inverse distance weighting-, radial basis function). Considering the spatial distributions, it was determined that the most successful method was kriging for sand, silt, and clay contents and inverse distance weighting for electrical conductivity, calcium carbonate equivalent, and organic matter contents. According to our findings, it is concluded that successful estimations and spatial distributions can be made by the support vector machine algorithm using band data from different wavelengths., (© 2023. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)

The main purpose of this study is to identify suitable potential areas for agricultural activities in the semi-arid terrestrial ecosystem in the Central Anatolia Region. MCDA was performed in fuzzy environment integrated with GIS techniques and different geostatistical interpolation models, which was chosen as the basis for the present study. A total of nine criteria were used, as four terrain properties and five soil features to identify potential sites suitable for agriculture lands in Central Anatolia which covers approximately 195,012.7 km 2 . In order to assign weighting value for each criterion, FAHP approach was used to make sufficiently sensitive levels of importance of the criteria. DEM with 10 m pixel resolution used to determine the height and slope characteristics, digital geology and soil maps, CORINE land use/land cover, long-term meteorological data, and 4517 soil samples taken from the study area were used. It was identified that approximately 30.7% of the total area (59,921.8 ha) is very suitable and suitable for potential agriculture activities on S1 and S2 levels, 42.7% of the area is not suitable for agricultural uses, and only 27% of the area is marginally suitable for agricultural activities. Besides, it was identified that 34.8% of the area is slightly suitable.

The aim of this study was to produce a land productivity dynamic map of a degraded catchment located in dryland ecosystem via a land degradation assessment using three indicators, namely land use, land productivity, and soil organic carbon density. The study was conducted in the Mogan Catchment, Turkey, between 2000 and 2010. The study embraced the current trend for assessing ecosystem services over wide areas. For this purpose, satellite images were used to determine changes in land use and vegetation density. In addition, a total of 834 soil samples were collected from the surface soil in 2000 and 2010 to assess the soil organic carbon density. In more than 37% of the catchment area of approx. 37,100 ha, land productivity had declined, while about 43% of the catchment showed early signs of decline. Analysis of long-term changes and the conversion of levels of vegetative or standing biomass into land productivity dynamics (LPD) is only the first step. Current land management practices are contributing to serious, widespread land degradation, with only a very small area of the catchment showing a stable or increasing LPD for the period from 2000 to 2010. The implementation of land management policies and practices in order to achieve sustainable land management are urgently required.

The aim of this study is to analyze the similarity of soils formed on limestone/marl alluvial parent material and different topography using some physical and chemical properties via cluster analysis (CA) and multidimensional scaling analysis (MDSA). Physical and chemical soil properties included in this study are texture, CaCO3, organic matter, pH, electrical conductivity, cation exchange capacity, and available water content. The study was carried out in Çetinkaya region located on Bafra Deltaic Plain. The study area has two main physiographic units. The first one is the flat or gently slope alluvial lands (0-2 %), and the other one involves hills with slopes ranging from middle to steep (3-20 %). The soil in the study area is mainly classified as entisol, inceptisol and vertisol. According to the CA results, while C horizons of the soils formed on alluvial deposits (typic ustifluvent and typic ustipsamment) bear similarity, Ap horizons of the soils formed on lime/marl parent material (vertic ustorhent, vertic calciustept, and calci haplustert) appear in the same group. Additionally, in order to support CA, MDSA was performed. Significant correlations were observed between the results of both analyses.

This study, conducted in 2011, researches the effects of different tillage practices on the physical soil quality of clayey soil. This soil quality index (SQI) assessment was made by studying the changes in physical soil functions such as suitability for root development, facilitation for water entry, movement and storage, and resistance against surface degradation based on tillage management. When compared with the control parcel, statistically significant decreases were seen in the SQI with different tillage practices (p < 0.05). Among the tillage practices, the highest SQI was seen with the plow + rotary tiller + direct seeding machine, while the lowest SQI was seen with the direct drilling practice. On the other hand, the statistically insignificant effects of tillage practices on the soil quality of the study area were considered to be a result of either the study period or the joint effect of soil texture and climatic features. Thus, long-term tillage practices were recommended in order to get healthier information about soil quality by considering soil and climatic conditions. In addition, for heavy clayey soils, reduced tillage practices, which included plowing, were thought to develop physical soil qualities of root development and water movement.

The Salt Lake Specially Protected Area is a unique ecosystem for both agricultural activities and natural life in Turkey. In the present study, an attempt was made to develop a conceptual land use strategy and methodology, taking into account ecological factors for regional development in the Salt Lake Specially Protected Area. A detailed Geographic Information System (GIS) analysis was done to create a comprehensive database including land use, land suitability, and environmental factors (soil, climate, water quality, fertilizing status, and heavy metal and pesticide pollution). The results of the land suitability survey for agricultural use showed that, while 62.6% of the study area soils were classified as best and relatively good, about 15% were classified as problematic and restricted lands, only 22.2% of the study area soils were not suitable for agricultural uses. However, this is not enough to derive maximum benefit with minimum degradation. Therefore, environmental factors and ecological conditions were combined to support this aim and to protect the ecosystem. Excessive irrigation practices, fertilizer and pesticide application, and incorrect management practices all accelerate salinization and degradation. In addition to this, it was found that a multi-layer GIS analysis made it easy to develop a framework for optimum land use and could increase the production yield preserving the environmental conditions. Finally, alternative management and crop patterns were undertaken to sustain this unique ecosystem, considering water, soil, climate, land use characteristics, and to provide guidance for planners or decision makers.

The main objective of the study was to find out the effects of various organic matter sources such as bio-solid (BS) and tea waste (TW) on macro nutrient content of eroded soils. In order to determine different soil erodibility levels (slightly, moderately and severely), erosion ratio (ER) and soil erodibility factor (K) parameters were used. Soil samples used in this research were taken from bulk surface (0-20 cm depth) located on agricultural lands of Asagi Aksu village that is 20 km far from Samsun province in the north part of Turkey. These lands have been used as agricultural activity. Some properties of the soil classified as Vertic calciudoll were determined as follows; fine in texture, organic matter content varies between 0.83% and 0.90%. In addition, pH and EC values of these soils are 8.0-8.1 and 0.64-0.79 dSm( - 1) respectively. This study was conducted by applying four different doses of BS and TW (0%, 2%, 4% and 6%) in eroded soils under greenhouse condition. Each treatment was replicated three times in a split block design. After 18 weeks incubation period associated parameters were determined in all pots. According to analysis results, it was found that while BS treatments increased total N, available P and exchangeable K content of all eroded soils comparing to control treatment, effectiveness of TW on P is very low in slightly and moderately erosion levels. BS and TW applications increased K content in soils. However, it was determined not significant statistically between effectiveness of these various organic residues whereas, N and P values significantly correlated with BS and TW (P < 0.05). In addition, change of N, P and K values depending on the application doses and soil erosion levels were found statistically significant (P < 0.001).

Land quality assessment is of great important for decisions on sustainable land uses and the conservation of ecosystems of high biodiversity value. The main objective of this study was to determine properties of land quality of specially protected area of the Salt Lake using CORINE land quality assessment methodology and to propose a revision for this model. In addition to field study and laboratory analysis, digital soil map, digital elevation model, satellite image and climatic data were used and analyzed with remote sensing and geographic information systems techniques to generate actual land quality map and to form database for study area. Results show that 42.1% of the study area has high quality, 28.7% was classified as moderate quality and 4.0% was determined as low quality. On the other hand, some places classified as moderate quality, were not accurately classified. These places should be low land quality due to content of high salt concentration. Therefore, to resolve this insufficient situation, some soil parameters such as chemical properties should be collaborated with this model. In this case, moderate land quality level of the study area decreased from 28.7 to 12.3%, whereas 4.0% of low quality land of the study area increased to 20.8%. In addition, this research was also carried out to provide guidance for planner or decision makers about specially protected area of the Salt Lake.