Sema Arıman

This study developed an innovative hybrid modelling approach to predict one-month-ahead water levels (LWL (T + 1)) for two major lakes in Türkiye (Eber and Eğirdir), aiming to model complex dynamics of hydrological systems and optimize sustainable water resources management. In the proposed methodological framework, Singular Spectrum Analysis (SSA) was employed to decompose hydrometeorological time series into sub-components, while Mutual Information (MI) and Partial Autocorrelation Function (PACF) techniques were utilized to determine optimal input variables. The hybrid model architecture, incorporating Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and CatBoost algorithms, was optimized using 70% of the data for training and 30% for testing, and its performance was evaluated through deterministic and probabilistic metrics. The analyses revealed that SSA-based data preprocessing significantly improved the performance of prediction models, and depending on lake characteristics, CNN-based models demonstrated superior performance for Lake Eber, while DNN architecture excelled for Lake Eğirdir. The developed hybrid approach presents an original methodology that can be integrated into decision support systems for water resources management, contributing to the development of sustainable water management strategies and adaptability to similar hydrological systems.

In the field of environmental sustainability, the preservation of water resources and the maintenance of water quality are of utmost importance. The aim of this study is to develop a predictive model for assessing the water quality of the Kızılırmak river by integrating Principal Component Analysis (PCA) and Multivariate Adaptive Regression Splines (MARS) methodologies. To assess water quality, surface water samples obtained from six distinct locations during the 2022–2023 period were analyzed with respect to seventeen physicochemical parameters. The first stage of the present study was the determination of the most informative variables in the water quality data set using the dimensionality reduction method PCA. In the second phase, a predictive model was developed using the MARS algorithm based on the principal components derived from the PCA-reduced dataset. The MARS algorithm was proposed to predict Water Quality Index (WQI) values using this reduced dataset. A coefficient of determination (R²) value of 0.997 was achieved for predicting the WQI in the study area. According to the results of this study, the MARS model developed using PCA demonstrated high precision and performance in estimating the WQI. This methodological framework clarified the interactions between parameters in water quality assessment studies, allowing for a comprehensive analysis of their overall effects on WQI.

Drought, earthquake, flood, and fire are disasters whose effects occur after a more extended period than other disasters. Meteorological drought is called the beginning of drought types. In this study, trend analyses and temporal changes in temperature, precipitation, and drought index values were carried out between 1981 and 2022 at three meteorological observation stations in the Southeastern Anatolia region of Türkiye. Standardized Precipitation Index, Standardized Precipitation Evapotranspiration Index, China-Z Index, and Effective Drought Index methods were used for drought analysis, while Sen's slope, Mann–Kendall, and innovative trend analysis methods were used to detect the trend in precipitation. It was determined that precipitation generally had tended to decrease, and drought increased since 1996. Although every type of dry and wet periods has occurred, normal dry periods were observed more. In the spatial distribution of drought, the inverse distance weighted method gives larger areas with more extreme drought and wet values than the Kriging method. The increase in extreme values in the region indicates that the severity of drought will increase. It has been determined that the region's water resources and agricultural activities are under pressure due to climate change and drought.

Meteorolojik değişkenlerin trend analizi iklim değişikliğinin belirlenmesinde önemlidir. Özellikle yağış, hidrolojik çevrimin önemli bir bileşenidir. Sıcaklık ve yağıştaki değişimler tarımı, canlı ekosistemleri ve su kaynakları yönetimini etkiler. Bu çalışmada, Siirt ilinin 1980-2023 yılları arasında sıcaklık ve yağış değişkenlerinin eğilimlerini belirlemek için İnovatif Trend analizi (ITA), Mann-Kendall, Sen eğimi ve İnovatif Poligon Trend Analiz (IPTA) analizleri yapılarak iklim değişikliği göstergeleri belirlenmiştir. Meteorolojik değişkenler aylık, mevsimsel ve yıllık olarak ayrı ayrı değerlendirilmiştir. Yağış ve sıcaklık değişkenlerinin, Mann-Kendall, ITA, IPTA ve Sen trend analizlerinden elde edilen sonuçları birbirleriyle karşılaştırılmıştır. Yağış bütün trend analizlerinin sonuçlarına göre azalan bir eğim gösterirken, sıcaklık değerlerinde ise artan bir trend tespit edilmiştir. Aylık ve mevsimsel ölçekte daha büyük trend değerleri elde edilmiştir. Mevcut çalışmada elde edilen trend sonuçlarına göre Siirt ilinde kuraklık risk yönetimi ve su kaynakları yönetimine daha fazla dikkat edilmesini göstermektedir.

Groundwater represents one of the largest resources of freshwater in the world. Thus, investigations of groundwater level variations due to climate change and increasing human activities are of great importance, especially in resource scarce regions. Our research aimed to understand the long‐term effects of climate events and water use on groundwater levels over the study area via Mann‐Kendall, Sen's Slope, Innovative Polygon Trend Analysis (IPTA), and Innovative Trend Analysis (ITA) analyses. Although several studies are available in relation to GWL trend analysis via ITA, Mann‐Kendall and Sen slope in the literature, there are few IPTA studies conducted. The focus of the study was seven wells across Türkiye over the period 1987–2022. Results demonstrate that there was a downward trend in GWL in all stations annually, regardless of the method. At monthly scale, a decrease was noted, especially in June, August, and September, while seasonally, decreases were seen in autumn and winter. Moreover, it was evident the results of the Sen slope and ITA were compatible, while the IPTA was a useful tool in detecting GWL trends. Identifying and understanding GWL trends is highly valuable in informing groundwater resource managers of critical areas of overuse and other factors affecting groundwater, resulting in preventive interventions to overcome such problems and protect this critical resource.

This study aimed to characterize the chemical composition and spatial distribution of groundwater in the Kızılırmak Delta of Turkey and to evaluate the suitability of groundwater in the Kızılırmak Delta for drinking water use through a Water Quality Index (WQI) assessment. Eleven water parameters, including nitrate (NO₃⁻), calcium (Ca²⁺), magnesium (Mg²⁺), sodium (Na⁺), chloride (Cl⁻), potassium (K⁺), bicarbonate (HCO₃⁻), sulfate (SO₄²⁻), hardness (measured as CaCO₃), electrical conductivity (EC), and pH were analyzed to determine the water quality of each groundwater sample. The WQI was determined using the weighted arithmetic index method and the method specified by the Canadian Council of Ministers of the Environment (CCME). The spatial distribution of the result for all observation wells was plotted. Principal Component Analysis (PCA) was generated utilizing the analytical data from eleven selected samples. As a result of the study, according to the calculated WQI values, the water in most of the wells was not suitable for drinking purposes. The minimum Ca²⁺ concentration in the study area was 108,817 mg/L, and the maximum was 692,382 mg/L, which showed that the samples in all wells exceeded the WHO limit. The same situation is valid for Mg²⁺, and the values vary between 100.383 and 5183.026 mg/L. From the spatial distribution of the water quality parameters it has been understood that the eastern part of the region is more suitable than the western part for drinking purposes. The results from correlation analysis showed the strongest positive correlation between Mg²⁺ and Na⁺ and Na⁺ and EC as 0.989. The present study shows that the groundwater of the delta, which has deteriorating water quality, should be treated before it is used for drinking water and protected from contamination hazards.

Akarsuların su potansiyelinin belirlenmesi için sezgisel tahmin modelleri sıklıkla kullanılmaktadır. Bu modellerden birisi olan Uyarlamalı Ağ Tabanlı Bulanık Mantık Çıkarım Sistemi (ing. kıs. ANFIS); yapay sinir ağlarının (YSA) öğrenme yeteneğini ve bulanık mantık (BM) yaklaşımının karar verme mekanizmasını kullanarak tahmin modeli geliştirmektedir. Bu çalışmada; Kızılırmak Nehri’nde yer alan iki adet Akım Gözlem İstasyonu’nda (AGİ) günlük ortalama debi, iki farklı ANFIS modeli ile tahmin edilmeye çalışılmıştır. AGİ’lere ait 2014-2021 yılları arasında gözlemlenmiş günlük ortalama debi verileri ile AGİ’lerin kurulu olduğu akarsu havzalarını temsil eden iki Meteoroloji Gözlem İstasyonu (MGİ)’ye ait günlük toplam yağış verileri mekansallaştırılarak modellerde kullanılmıştır. Membadaki Kızılırmak–Ahmethacı AGİ-1 için, 2 giriş 1 çıkış yaklaşımı, bu AGİ’nin mansabında kalan Kızılırmak–Bulakbaşı AGİ-2 için ise 3 giriş 1 çıkış yaklaşımı ile ANFIS modelleri kurgulanmıştır. Giriş verilerinden günlük toplam yağış, zaman ölçeğinde (t-2). gün, günlük ortalama debi, (t-1). gün alınmış ve çıkış olarak (t). güne ait ortalama debi tahmin edilmiştir. Modellerde verilerin %75’i eğitim, %25’i test verisi olarak kullanılmıştır. Kurallar oluşturulurken 3 farklı kümeleme yapılmış ve hedef değerin üyelik fonksiyonu belirlenmiştir. Her iki AGİ için eğitim ve test verilerinde 3 ayrı kümelemeye ait sonuçlar elde edilmiş ve modellerin başarımları için determinasyon katsayısı (R2) ve karekök ortalama hatası (RMSE) metrikleri kullanılmıştır. AGİ-1 için en iyi sonucu R2 = 0.9578, RMSE = 1.49 ile 3 kümelemeli model verirken AGİ-2 için en iyi sonucu; R2 = 0.976 ve RMSE = 2.20 ile yine 3 kümelemeli model vermiştir. Sonuç olarak ANFIS modeli, yüksek başarım ile günlük ortalama debiyi tahmin etmiştir.