Browsing by Author "Dengiz, Orhan"

Now showing 1 - 3 of 3

An Assessment of Pasture Soils Quality Based on Multi-Indicator Weighting Approaches in Semi-Arid Ecosystem
(Elsevier, 2021) Karaca, Siyami; Dengiz, Orhan; Turan, Inci Demirag; Ozkan, Baris; Dedeoglu, Mert; Gulser, Fusun; Ay, Abdurahman
The development of soil quality index in the vicinity of the Van Lake pasture lands located in the Northern East Part of Turkey under semi-arid terrestrial ecosystem is very important since there are certain degradation signs indicating how their sustainability is being threatened. A total of 150 soils in the pastures throughout the region were sampled and several soil physical, chemical and biological indicators were quantified. A minimum data set of the most sensitive indicators was chosen using principal component analyses. Linear scoring functions for these indicators were used to develop soil quality index integrated with remote sensing (RS) and geographical information system (GIS). In this current study, classes between SQIs calculated using the minimum data set (MDS) and total data set (TDS) approaches showed a parallel trend in each other and match analysis for agreement showed also a significant statistically relationship between TDSSQI/MDSSQI and REOSAVI in May and June months for pasture area. Furthermore, this study also showed that advance techniques (PCA, geostatistic, AHP-Fuzzy) and the technologies of RS and GIS, which are essential to the analysis and processing of original and generated information were used effectively by integrating each other for SQI in large area.
Pythagorean Fuzzy Swara Weighting Technique for Soil Quality Modeling of Cultivated Land in Semi-Arid Terrestrial Ecosystems
(Elsevier Sci Ltd, 2024) Sargin, Bulut; Alaboz, Pelin; Karaca, Siyami; Dengiz, Orhan
Currently, the assessment of soil quality and creating digital soil maps are crucial for sustainable land management. In the present study, the main objective is to evaluate soil quality around Lake Van's agricultural areas using Pythagorean Fuzzy SWARA (PF-SWARA) weighting for soil indicator assessment. Additionally, the predictability of soil quality is demonstrated through spatial distribution maps using random forest (RF) and artificial neural network (ANN) algorithms. PF-SWARA weighting assigns higher weights to indicators of physical quality. Soil quality index (SQI) values for the study area range between 0.36 and 0.74, classified as "from very low to high." RF and ANN models provide Lin's concordance correlation coefficient (LCCC) values of 0.93 and 0.87, respectively, for soil quality prediction. The RF model exhibits the lowest error rate (root mean square error (RMSE): 0.03; mean absolute percentage error (MAPE): 4.51%). The RF algorithm identified pH, available phosphorus, organic matter, CaCO3 and electrical conductivity as the most effective soil properties for estimating SQI. Ordinary Kriging geostatistical interpolation is identified as the interpolation method with the lowest RMSE value based on observed and predicted values' spatial distribution maps using Gaussian semivariogram from the geostatistical model. The study concludes that machine learning algorithms can be utilized alongside PF-SWARA approaches for digital soil quality mapping.
Van Edremit İlçesi Elma Bahçelerinde Çok Kriterli Karar Verme Analizi-cbs ile Toprak Kalite Özelliklerinin Belirlenmesi
(2023) Dengiz, Orhan; Sarğın, Bulut; Turan, İnci Demirağ; Karaca, Sıyamı
Bu çalışma yarı kurak karasal ekosisteme sahip olan Van ili Erdemit ilçesinde elma bahçelerinde dağılım gösteren toprakların toprak kalite indekslerinin değerlendirilmesi amacıyla gerçekleştirilmiştir. Çalışma alanından alınan 52 adet toprak örneğinde toprak kalitesi, çok kriterli karar analizlerinden birisi olan analitik hiyerarşik süreç (AHS) yöntemi ve standart skorlama fonksiyon ile beraber kullanılarak değerlendirilmiştir. Ayrıca, belirlenen 29 adet toprak kalite indikatörlerin minimum veri seti oluşturulması amacıyla temel bileşenler analizi uygulanmış ve 10 indikatöre indirilmiştir. Gerek toplam veri seti gerekse de minimum veri setine ait kalite indekslerinin alan içerisinde konumsal dağılım haritalarının üretilmesi amacıyla 15 enterpolasyon modeli uygulanmış olup, bu modeller içerisinde en düşük RMSE değerleri olarak, Kriking’in simple semivariogramına ait Sperical modeli belirlenmiştir. Çalışma alanı içerisinde toprakların kalite indeksi 0.334 ile 0.634 arasında değişkenlik sergilemiş, kalite çok düşük ve orta olarak sınıflandırılmıştır. Ayrıca, gerek istatistiksel gerekse de jeoistatistiksel olarak önemli farklılık bulunmayan her iki veri setinde de toprak kalite indeksi birbirine yakın seviyelerde belirlenmiş ve konumsal dağılım haritalarının birbirine benzerlik gösterdiği tespit edilmiştir.