KKKübra Küllahcı

Kübra Küllahcı

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kübra Küllahcı has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Groundwater Forecasting Under Missing Data Uncertainty: A Multi-Horizon Assessment Using Hyperbolic Deep Learning

    by Kübra Küllahcı, Kürşat Şekerci

    Groundwater resources are increasingly exposed to climatic variability, anthropogenic pressure, and unsustainable abstraction, creating an urgent need for reliable groundwater level (GWL) forecasting frameworks that can support adaptive aquifer management. Despite recent advances in deep learning, accurate multi-horizon groundwater forecasting remains hindered by two persistent limitations: incomplete monitoring records caused by observational gaps and the accumulation of prediction uncertainty at longer forecast horizons. Addressing these challenges requires forecasting frameworks capable of simultaneously handling missing information and preserving complex temporal structures in groundwater dynamics. This study proposes an integrated multi-horizon forecasting framework that combines optimal missing-data reconstruction with hyperbolic deep representation learning for robust groundwater prediction under incomplete observational conditions. Monthly in-situ GWL observations from three monitoring wells in eastern Türkiye covering the period 1978–2015 were used as the experimental dataset. Multiple imputation approaches were systematically evaluated using quantitative reconstruction metrics to identify the most reliable data completion strategy prior to forecasting. The reconstructed time series were subsequently used to generate predictions for five lead times ranging from t+1 to t+5 months. The predictive capability of the proposed hyperbolic framework was benchmarked against hybrid CNN-BiLSTM–GRU and TimesNet architectures under comprehensive statistical evaluation. Results demonstrated that the hyperbolic model consistently improved predictive stability across extended forecast horizons, particularly under long-range forecasting conditions where conventional architectures exhibited stronger error accumulation. The proposed framework produced lower RMSE values at longer lead times (particularly t+5), maintained stronger temporal consistency, and reduced forecast degradation across sequential prediction steps. Statistical validation using the Wilcoxon signed-rank test confirmed the significance and robustness of the forecasting results, while Pearson correlation analysis and residual diagnostics indicated strong agreement between observed and predicted groundwater levels across all prediction horizons. The findings suggest that hyperbolic representation learning provides a structurally efficient mechanism for capturing hierarchical temporal dependencies in groundwater systems and offers a promising pathway for improving multi-step forecasting reliability in datasets affected by missing observations and long-term monitoring uncertainties.

  • Open Access

    A Novel Spectral Decomposition Framework for TimesNet: Integrating DCT and Wavelet Transforms for Hydrological Forecasting

    by Kübra Küllahcı, Elif Kartal, Abdüsselam Altunkaynak

    This study presents methodological enhancements to the TimesNet architecture for deep learning–based streamflow forecasting. To this end, alternative spectral decomposition techniques—namely the Discrete Cosine Transform (DCT) and the Discrete Wavelet Transform (DWT)—were integrated into the TimesNet framework in place of the conventional Fast Fourier Transform (FFT). The primary objective of this modification is to improve feature representation and learning efficiency when modeling complex hydrological time series. In addition, LSTM and Naive Persistence models were included as baseline approaches to position TimesNet relative to commonly used temporal forecasting methods. The proposed models were applied to daily discharge data obtained from three key hydrometric stations—Chilia, Sulina, and Sfântu Gheorghe—located along the main distributary branches of the Danube River prior to its discharge into the Black Sea. Model performance was evaluated not only using station-specific univariate time series but also using aggregated discharge time series constructed by combining flow records from all three stations, representing the total freshwater inflow to the Black Sea. Forecasting accuracy was quantitatively assessed using standard hydrological performance metrics, including Mean Squared Error (MSE), Mean Absolute Error (MAE), and Nash–Sutcliffe Efficiency (NSE). The results demonstrate that the DCT-TimesNet model consistently outperforms both the original TimesNet architecture and the wavelet-enhanced variant across all test scenarios. DCT-TimesNet-based models were also found to more effectively capture both short-term fluctuations and long-term temporal dependencies compared to the LSTM and Naive Persistence benchmarks. Furthermore, station-level modeling yielded slightly higher accuracy than aggregated time series forecasting.


  • Su Farkındalığının Dijital İzi: Google Trends ve Baraj Doluluğu Türkiye Örneği

    by Kübra Küllahcı

    Su kaynakları üzerindeki baskılar, küresel ölçekte etkisini artırırken, yalnızca fiziksel sistemlerin değil, toplumsal davranışların da izlenmesi sürdürülebilir yönetim açısından kritik bir gereklilik hâline gelmiştir. Bu çalışma, Türkiye’deki baraj doluluk oranları ile dijital bilgi arama davranışları arasında zamansal bir ilişki olup olmadığını ortaya koymayı amaçlamaktadır. Çalışmada İstanbul’daki 10 baraja ait günlük doluluk verileri aylık ortalamalar üzerinden birleştirilerek, kenti temsil eden bir baraj doluluk serisi elde edilmiştir. Bu veri seti, “baraj doluluk” anahtar kelimesine yönelik Google Trends verileriyle eşleştirilmiş ve z-normalizasyon yöntemiyle ölçeklendirilmiştir. Elde edilen veriler üzerinden mevsimsel eğilimler, eşik davranışları ve zaman gecikmeli korelasyonlar analiz edilmiştir. Bulgular, dijital arama eğilimlerinin baraj doluluk oranlarıyla özellikle 1–2 aylık gecikmeyle anlamlı ilişkiler taşıdığını ortaya koymuştur. Sonuçlar dijital platformlardaki kullanıcı davranışlarının, çevresel sistemlerdeki değişimlere karşı gelişen toplumsal farkındalığın bir yansıması olabileceğini göstermektedir. Bu bağlamda çalışma, açık dijital veri kaynaklarının sosyo-hidrolik izleme süreçlerine entegre edilebileceğini göstererek literatüre yenilikçi bir katkı sunmaktadır.


  • Open Access

    Maximizing daily rainfall prediction accuracy with maximum overlap discrete wavelet transform‐based machine learning models

    by Kübra Küllahcı, Abdüsselam Altunkaynak

    Rainfall is an important phenomenon for various aspects of human life and the environment. Accurate prediction of rainfall is crucial for a wide range of sectors, including agriculture, water resources management, energy production, disaster management and many more. The ability to predict rainfall in an accurate fashion enables stakeholders to make informed decisions and take necessary actions to mitigate the impacts of natural disasters, water scarcity and other issues related to rainfall. In addition, advances in rainfall prediction technologies have the potential to contribute to sustainable water management and the preservation of water resources by providing the necessary information for decision‐makers to plan and implement effective water management strategies. Hence, it is important to continuously improve the accuracy of rainfall prediction. In this paper, the integration of the maximum overlap discrete wavelet transform (MODWT) and machine learning algorithms for daily rainfall prediction is proposed. The main objective of this study is to investigate the potential of combining MODWT with various machine‐learning algorithms to increase the accuracy of rainfall prediction and extend the forecast time horizon to 3 days. In addition, the performances of the proposed hybrid models are contrasted with the models hybridized with commonly used discrete wavelet transform (DWT) algorithms in the literature. For this, daily rainfall raw data from three rainfall observation stations located in Turkey are used. The results show that the proposed hybrid MODWT models can effectively improve the accuracy of precipitation forecasting, based on model evaluation measures such as mean square error (MSE) and Nash‐Sutcliffe coefficient of efficiency (CE). Accordingly, it can be concluded that the integration of MODWT and machine learning algorithms have the potential to revolutionize the field of daily rainfall prediction.


  • Open Access

    Application of Maximum Overlap Discrete Wavelet Transform and Machine Learning to Improved Daily Rainfall Prediction Modeling

    by Kübra Küllahci, Abdüsselam Altunkaynak

    Rainfall is an important phenomenon for various aspects of human life and the environment. Accurate prediction of rainfall is crucial for a wide range of sectors, including agriculture, water resources management, energy production, disaster management, and many more. The ability to predict rainfall in an accurate fashion enables stakeholders to make informed decisions and take necessary actions to mitigate the impacts of natural disasters, water scarcity, and other issues related to rainfall. In addition, advances in rainfall prediction technologies have the potential to contribute to sustainable water management and the preservation of water resources by providing the necessary information for decision-makers to plan and implement effective water management strategies. Hence, it is important to continuously improve the accuracy of rainfall prediction. In this paper, the integration of the Maximum Overlap Discrete Wavelet Transform (MODWT) and machine learning algorithms for daily rainfall prediction is proposed. The main objective of this study is to investigate the potential of combining MODWT with various machine-learning algorithms to increase the accuracy of rainfall prediction and extend the forecast time horizon to three days. In addition, the performances of the proposed hybrid models are contrasted with the models hybridized with commonly used discrete wavelet transform (DWT) algorithms in the literature. For this, daily rainfall raw data from 3 rainfall observation stations located in Türkiye are used. The results show that the proposed hybrid MODWT models can effectively improve the accuracy of precipitation forecasting, based on model evaluation measures such as mean square error (MSE) and Nash-Sutcliffe coefficient of efficiency (CE). Accordingly, it can be concluded that the integration of MODWT and machine learning algorithms have the potential to revolutionize the field of daily rainfall prediction.


  • Enhanced rainfall prediction performance via hybrid empirical-singular-wavelet-fuzzy approaches

    by Kübra Küllahcı, Abdüsselam Altunkaynak

    Rainfall is a vital process in the hydrological cycle of the globe. Accessing reliable and accurate rainfall data is crucial for water resources operation, flood control, drought warning, irrigation, and drainage. In the present study, the main objective is to develop a predictive model to enhance daily rainfall prediction accuracy with an extended time horizon. In the literature, various methods for the prediction of daily rainfall data for short lead times are presented. However, due to the complex and random nature of rainfall, in general, they yield inaccurate prediction results. Generically, rainfall predictive models require many physical meteorological variables and consist of challenging mathematical processes that require high computational power. Furthermore, due to the nonlinear and chaotic nature of rainfall, observed raw data typically has to be decomposed into its trend cycle, seasonality, and stochastic components before being fed into the predictive model. The present study proposes a novel singular spectrum analysis (SSA)-based approach for decomposing observed raw data into its hierarchically energetic pertinent features. To this end, in addition to the stand-alone fuzzy logic model, preprocessing methods SSA, empirical mode decomposition (EMD), and commonly used discrete wavelet transform (DWT) are incorporated into the fuzzy models which are named as hybrid SSA-fuzzy, EMD-fuzzy, W-fuzzy models, respectively. In this study, fuzzy, hybrid SSA-fuzzy, EMD-fuzzy, and W-fuzzy models are developed to enhance the daily rainfall prediction accuracy and improve the prediction time span up to 3 days via three (3) stations’ data in Turkey. The proposed SSA-fuzzy model is compared with fuzzy, hybrid EMD-fuzzy, and widely used hybrid W-fuzzy models in predicting daily rainfall in three distinctive locations up to a 3-day time horizon. Improved accuracy in predicting daily rainfall is provided by the SSA-fuzzy, W-fuzzy, and EMD-fuzzy models compared to the stand-alone fuzzy model based on mean square error (MSE) and the Nash-Sutcliffe coefficient of efficiency (CE) model assessment metrics. Specifically, the advocated SSA-fuzzy model is found to be superior in accuracy to hybrid EMD-fuzzy and W-fuzzy models in predicting daily rainfall for all time spans. The results reveal that, with its easy-to-use features, the advocated SSA-fuzzy modeling tool in this study is a promising principled method for its possible future implementations not only in hydrological studies but in water resources and hydraulics engineering and all scientific disciplines where future state space prediction of a vague nature and stochastic dynamical system is important.