Buket İşLer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Buket İşLer has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Zafer Aslan
İstanbul Aydın University
7 shared publications - Ahmet Tokgözlü
Süleyman Demirel University
3 shared publications - Uğur Şener
Metropolitan State University of Denver
3 shared publications - Enrico Feoli
Department of Life Sciences, University of Trieste, Trieste, Italy
2 shared publications - Fahhreddin Raşit Kiliç
Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Konya Technical University, Konya 42250, Türkiye
2 shared publications - Şükrü Mustafa Kaya
İstanbul Aydin Universitesi
2 shared publications
Latest Publications
- Open Access
- 20 April 2026
- Published by Politeknik Dergisi in Journal of Polytechnic
- Vol. 29 (4) , 1-13
Deep Learning-Based Speech Emotion Recognition for IoT Edge Devices: A Comparative Study
With advancements in artificial intelligence (AI), particularly in pattern recognition, significant progress has been made in recognising human emotions from speech characteristics, facial activity, and physiological responses. However, the expansion of Internet of Things (IoT)-based infrastructures has increased pressure on conventional cloud systems due to the high volume of transmitted data and the need for real-time responsiveness. As a remedy, edge computing has emerged as a distributed alternative, enabling localised data processing and reducing dependency on remote servers. In this context, the present study evaluates the classification performance of three hybrid deep learning (DL) models—Convolutional Neural Network–Dense Neural Network (CNN-Dense), Long Short-Term Memory–Convolutional Neural Network (LSTM-CNN), and Dense–Long Short-Term Memory (Dense-LSTM) —within a simulated edge-based environment. The Toronto Emotional Speech Set (TESS) dataset was employed, and experimental workflows were implemented via Amazon Web Services (AWS) to simulate edge resource limitations. Accuracy was assessed using macro-averaged metrics, including precision, recall, and F1-score. Among the models, CNN-Dense showed the highest performance, achieving an F1-score of 96%, followed by LSTM-CNN (95%) and Dense-LSTM (93%). The findings suggest that CNN–Dense may offer feature extraction advantages, and that hybrid models could be promising for emotion classification in decentralised systems.
- 20 April 2026
- Published by Politeknik Dergisi in Journal of Polytechnic
- Vol. 29 (4) , 1-13
Open AccessDeep Learning-Based Speech Emotion Recognition for IoT Edge Devices: A Comparative Study
With advancements in artificial intelligence (AI), particularly in pattern recognition, significant progress has been made in recognising human emotions from speech characteristics, facial activity, and physiological responses. However, the expansion of Internet of Things (IoT)-based infrastructures has increased pressure on conventional cloud systems due to the high volume of transmitted data and the need for real-time responsiveness. As a remedy, edge computing has emerged as a distributed alternative, enabling localised data processing and reducing dependency on remote servers. In this context, the present study evaluates the classification performance of three hybrid deep learning (DL) models—Convolutional Neural Network–Dense Neural Network (CNN-Dense), Long Short-Term Memory–Convolutional Neural Network (LSTM-CNN), and Dense–Long Short-Term Memory (Dense-LSTM) —within a simulated edge-based environment. The Toronto Emotional Speech Set (TESS) dataset was employed, and experimental workflows were implemented via Amazon Web Services (AWS) to simulate edge resource limitations. Accuracy was assessed using macro-averaged metrics, including precision, recall, and F1-score. Among the models, CNN-Dense showed the highest performance, achieving an F1-score of 96%, followed by LSTM-CNN (95%) and Dense-LSTM (93%). The findings suggest that CNN–Dense may offer feature extraction advantages, and that hybrid models could be promising for emotion classification in decentralised systems.
- 23 January 2026
- Published by Springer Nature in Acta Geophysica
- Vol. 74 (1) , 62
Correction: Hybrid wavelet–ANN modelling for LAI forecasting under climatic variability: comparative case studies from the mediterranean basin
- 23 January 2026
- Published by Springer Nature in Acta Geophysica
- Vol. 74 (1) , 62
Correction: Hybrid wavelet–ANN modelling for LAI forecasting under climatic variability: comparative case studies from the mediterranean basin
- 17 December 2025
- Published by Springer Nature in Acta Geophysica
- Vol. 74 (1) , 34
Hybrid wavelet–ANN modelling for LAI forecasting under climatic variability: comparative case studies from the mediterranean basin
- 17 December 2025
- Published by Springer Nature in Acta Geophysica
- Vol. 74 (1) , 34
Hybrid wavelet–ANN modelling for LAI forecasting under climatic variability: comparative case studies from the mediterranean basin
- Open Access
- 7 October 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Evaluating urbanization effects on biomass density using a hybrid AI model: a case study
Urbanisation profoundly influences both socioeconomic structures and ecological systems worldwide, highlighting the critical need for integrated approaches to sustainable urban planning and environmental management. This study investigates the effects of population growth and urban expansion on natural vegetation cover in Fethiye, Muğla, Turkey—a coastal region exemplifying the delicate balance between urban development and ecological preservation. To model vegetation dynamics, Normalised Difference Vegetation Index (NDVI) values are projected up to the year 2032 using Long Short-Term Memory (LSTM) networks applied to time series data. Land Surface Temperature (LST) and Normalised Difference Built-up Index (NDBI), derived from MODIS and Landsat satellite imagery spanning 2013–2023, are used as input parameters. The predictions are interpreted within the framework of anticipated urban growth, demographic trends, and stable climate assumptions. Furthermore, a hybrid model combining Discrete Wavelet Transform with LSTM (DWT-LSTM) is proposed to enhance predictive performance, resulting in a 9.1% improvement in NDVI accuracy. This improvement has been validated against CORINE land cover data, demonstrating the model’s robustness and generalisability. The findings offer crucial insights for urban planners and environmental policymakers. By quantitatively linking urbanisation indicators with ecological degradation, this study provides a data-driven foundation for mitigating the adverse environmental impacts of rapid urban development. The results underscore the utility of advanced AI-based models in forecasting ecological change and supporting informed, sustainable land-use strategies.
- 7 October 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Open AccessEvaluating urbanization effects on biomass density using a hybrid AI model: a case study
Urbanisation profoundly influences both socioeconomic structures and ecological systems worldwide, highlighting the critical need for integrated approaches to sustainable urban planning and environmental management. This study investigates the effects of population growth and urban expansion on natural vegetation cover in Fethiye, Muğla, Turkey—a coastal region exemplifying the delicate balance between urban development and ecological preservation. To model vegetation dynamics, Normalised Difference Vegetation Index (NDVI) values are projected up to the year 2032 using Long Short-Term Memory (LSTM) networks applied to time series data. Land Surface Temperature (LST) and Normalised Difference Built-up Index (NDBI), derived from MODIS and Landsat satellite imagery spanning 2013–2023, are used as input parameters. The predictions are interpreted within the framework of anticipated urban growth, demographic trends, and stable climate assumptions. Furthermore, a hybrid model combining Discrete Wavelet Transform with LSTM (DWT-LSTM) is proposed to enhance predictive performance, resulting in a 9.1% improvement in NDVI accuracy. This improvement has been validated against CORINE land cover data, demonstrating the model’s robustness and generalisability. The findings offer crucial insights for urban planners and environmental policymakers. By quantitatively linking urbanisation indicators with ecological degradation, this study provides a data-driven foundation for mitigating the adverse environmental impacts of rapid urban development. The results underscore the utility of advanced AI-based models in forecasting ecological change and supporting informed, sustainable land-use strategies.
- Open Access
- 23 July 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (15) , 6696
Spatio-Temporal Variation in Solar Irradiance in the Mediterranean Region: A Deep Learning Approach
In response to the global imperative of reducing greenhouse gas emissions, the optimisation of renewable energy systems under regionally favourable conditions has become increasingly essential. Solar irradiance forecasting plays a pivotal role in enhancing energy planning, grid reliability, and long-term sustainability. However, in the context of Turkey, existing studies on solar radiation forecasting often rely on traditional statistical approaches and are limited to single-site analyses, with insufficient attention to regional diversity and deep learning-based modelling. To address this gap, the present study focuses on Turkey’s Mediterranean region, characterised by high solar potential and diverse climatic conditions and strategically relevant to national clean energy targets. Historical data from 2020 to 2023 were used to forecast solar irradiance patterns up to 2026. Five representative locations—Adana, Isparta, Fethiye, Ulukışla, and Yüreğir—were selected to capture spatial and temporal variability across inland, coastal, and high-altitude zones. Advanced deep learning models, including artificial neural networks (ANN), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM), were developed and evaluated using standard performance metrics. Among these, BiLSTM achieved the highest accuracy, with a correlation coefficient of R = 0.95, RMSE = 0.22, and MAPE = 5.4% in Fethiye, followed by strong performance in Yüreğir (R = 0.90, RMSE = 0.12, MAPE = 7.2%). These results demonstrate BiLSTM’s superior capacity to model temporal dependencies and regional variability in solar radiation. The findings contribute to the development of location-specific forecasting frameworks and offer valuable insights for renewable energy planning and grid integration in solar-rich environments.
- 23 July 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (15) , 6696
Open AccessSpatio-Temporal Variation in Solar Irradiance in the Mediterranean Region: A Deep Learning Approach
In response to the global imperative of reducing greenhouse gas emissions, the optimisation of renewable energy systems under regionally favourable conditions has become increasingly essential. Solar irradiance forecasting plays a pivotal role in enhancing energy planning, grid reliability, and long-term sustainability. However, in the context of Turkey, existing studies on solar radiation forecasting often rely on traditional statistical approaches and are limited to single-site analyses, with insufficient attention to regional diversity and deep learning-based modelling. To address this gap, the present study focuses on Turkey’s Mediterranean region, characterised by high solar potential and diverse climatic conditions and strategically relevant to national clean energy targets. Historical data from 2020 to 2023 were used to forecast solar irradiance patterns up to 2026. Five representative locations—Adana, Isparta, Fethiye, Ulukışla, and Yüreğir—were selected to capture spatial and temporal variability across inland, coastal, and high-altitude zones. Advanced deep learning models, including artificial neural networks (ANN), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM), were developed and evaluated using standard performance metrics. Among these, BiLSTM achieved the highest accuracy, with a correlation coefficient of R = 0.95, RMSE = 0.22, and MAPE = 5.4% in Fethiye, followed by strong performance in Yüreğir (R = 0.90, RMSE = 0.12, MAPE = 7.2%). These results demonstrate BiLSTM’s superior capacity to model temporal dependencies and regional variability in solar radiation. The findings contribute to the development of location-specific forecasting frameworks and offer valuable insights for renewable energy planning and grid integration in solar-rich environments.
- Open Access
Fog-Enabled Machine Learning Approaches for Weather Prediction in IoT Systems: A Case Study
Temperature forecasting is critical for public safety, environmental risk management, and energy conservation. However, reliable forecasting becomes challenging in regions where governmental institutions lack adequate measurement infrastructure. To address this limitation, the present study aims to improve temperature forecasting by collecting temperature, pressure, and humidity data through IoT sensor networks. The study further seeks to identify the most effective method for the real-time processing of large-scale datasets generated by sensor measurements and to ensure data reliability. The collected data were pre-processed using Discrete Wavelet Transform (DWT) to extract essential features and reduce noise. Subsequently, three wavelet-processed deep-learning models were employed: Wavelet-processed Artificial Neural Networks (W-ANN), Wavelet-processed Long Short-Term Memory Networks (W-LSTM), and Wavelet-processed Bidirectional Long Short-Term Memory Networks (W-BiLSTM). Among these, the W-BiLSTM model yielded the highest performance, achieving a test accuracy of 97% and a Mean Absolute Percentage Error (MAPE) of 2%. It significantly outperformed the W-LSTM and W-ANN models in predictive accuracy. Forecasts were validated using data obtained from the Turkish State Meteorological Service (TSMS), yielding a 94% concordance, thereby confirming the robustness of the proposed approach. The findings demonstrate that the W-BiLSTM-based model enables reliable temperature forecasting, even in regions with insufficient governmental measurement infrastructure. Accordingly, this approach holds considerable potential for supporting data-driven decision-making in environmental risk management and energy conservation.
Open AccessFog-Enabled Machine Learning Approaches for Weather Prediction in IoT Systems: A Case Study
Temperature forecasting is critical for public safety, environmental risk management, and energy conservation. However, reliable forecasting becomes challenging in regions where governmental institutions lack adequate measurement infrastructure. To address this limitation, the present study aims to improve temperature forecasting by collecting temperature, pressure, and humidity data through IoT sensor networks. The study further seeks to identify the most effective method for the real-time processing of large-scale datasets generated by sensor measurements and to ensure data reliability. The collected data were pre-processed using Discrete Wavelet Transform (DWT) to extract essential features and reduce noise. Subsequently, three wavelet-processed deep-learning models were employed: Wavelet-processed Artificial Neural Networks (W-ANN), Wavelet-processed Long Short-Term Memory Networks (W-LSTM), and Wavelet-processed Bidirectional Long Short-Term Memory Networks (W-BiLSTM). Among these, the W-BiLSTM model yielded the highest performance, achieving a test accuracy of 97% and a Mean Absolute Percentage Error (MAPE) of 2%. It significantly outperformed the W-LSTM and W-ANN models in predictive accuracy. Forecasts were validated using data obtained from the Turkish State Meteorological Service (TSMS), yielding a 94% concordance, thereby confirming the robustness of the proposed approach. The findings demonstrate that the W-BiLSTM-based model enables reliable temperature forecasting, even in regions with insufficient governmental measurement infrastructure. Accordingly, this approach holds considerable potential for supporting data-driven decision-making in environmental risk management and energy conservation.
- 30 May 2025
- Published by Springer Nature
- p. 11-25
Prediction of Solar Energy Potential with Machine Learning and Deep Learning Models
- 30 May 2025
- Published by Springer Nature
- p. 11-25
Prediction of Solar Energy Potential with Machine Learning and Deep Learning Models
- Open Access
- 24 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (3) , 1201
Urban Sound Recognition in Smart Cities Using an IoT–Fog Computing Framework and Deep Learning Models: A Performance Comparison
Rapid urbanization presents significant challenges in energy consumption, noise control, and environmental sustainability. Smart cities aim to address these issues by leveraging information technologies to enhance operational efficiency and urban liveability. In this context, urban sound recognition supports environmental monitoring and public safety. This study provides a comparative evaluation of three machine learning models—convolutional neural networks (CNNs), long short-term memory (LSTM), and dense neural networks (Dense)—for classifying urban sounds. The analysis used the UrbanSound8K dataset, a static dataset designed for environmental sound classification, with mel-frequency cepstral coefficients (MFCCs) applied to extract core sound features. The models were tested in a fog computing architecture on AWS to simulate a smart city environment, chosen for its potential to reduce latency and optimize bandwidth for future real-time sound-recognition applications. Although real-time data were not used, the simulated setup effectively assessed model performance under conditions relevant to smart city applications. According to macro and weighted F1-score metrics, the CNN model achieved the highest accuracy at 90%, followed by the Dense model at 84% and the LSTM model at 81%, with the LSTM model showing limitations in distinguishing overlapping sound categories. These simulations demonstrated the framework’s capacity to enable efficient urban sound recognition within a fog-enabled architecture, underscoring its potential for real-time environmental monitoring and public safety applications.
- 24 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (3) , 1201
Open AccessUrban Sound Recognition in Smart Cities Using an IoT–Fog Computing Framework and Deep Learning Models: A Performance Comparison
Rapid urbanization presents significant challenges in energy consumption, noise control, and environmental sustainability. Smart cities aim to address these issues by leveraging information technologies to enhance operational efficiency and urban liveability. In this context, urban sound recognition supports environmental monitoring and public safety. This study provides a comparative evaluation of three machine learning models—convolutional neural networks (CNNs), long short-term memory (LSTM), and dense neural networks (Dense)—for classifying urban sounds. The analysis used the UrbanSound8K dataset, a static dataset designed for environmental sound classification, with mel-frequency cepstral coefficients (MFCCs) applied to extract core sound features. The models were tested in a fog computing architecture on AWS to simulate a smart city environment, chosen for its potential to reduce latency and optimize bandwidth for future real-time sound-recognition applications. Although real-time data were not used, the simulated setup effectively assessed model performance under conditions relevant to smart city applications. According to macro and weighted F1-score metrics, the CNN model achieved the highest accuracy at 90%, followed by the Dense model at 84% and the LSTM model at 81%, with the LSTM model showing limitations in distinguishing overlapping sound categories. These simulations demonstrated the framework’s capacity to enable efficient urban sound recognition within a fog-enabled architecture, underscoring its potential for real-time environmental monitoring and public safety applications.
- Open Access
- 1 January 2025
- Published by Dicle Universitesi Muhendislik Fakultesi Muhendislik Dergisi in Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
- Vol. 16 (1) , 59-67
Duygu tanımada akustik verilerle derin öğrenme modellerinin karşılaştırılması: LSTM ve DenseNet üzerine bir inceleme
Ses tanıma teknolojileri, insan-makine etkileşiminde önemli bir rol oynamakta olup, özellikle duygu tanıma sistemleri bu alandaki en kritik uygulamalardan biridir. İnsan davranışlarının daha iyi analiz edilmesi ve çeşitli alanlarda daha duyarlı sistemlerin geliştirilmesi amacıyla kullanılmaktadır. Bu çalışma, sesli duygu tanıma alanında iki farklı derin öğrenme modeli olan Uzun Kısa Süreli Bellek (LSTM) ve Dense modellerini karşılaştırmayı amaçlamaktadır. Ses verileri üzerinde daha etkili duygu tanıma performansı elde edebilmek için farklı derin öğrenme yöntemlerinin nasıl sonuçlar verdiği incelenmiştir. Çalışmada, Emotion Speech Dataset (ESD) kullanılmış ve her iki modelin genel doğruluk oranları karşılaştırılmıştır. Araştırma sonuçları F1-Score kriterine göre, LSTM modelinin %92 genel doğruluk oranına ulaştığı, DenseNet modelinin ise %88 genel doğruluk oranı sağladığı gözlemlenmiştir. Bu bulgular, zamansal verilerle çalışmada başarılı olan LSTM modelinin, duygu tanıma açısından daha üstün performans sergilediğini göstermektedir.
- 1 January 2025
- Published by Dicle Universitesi Muhendislik Fakultesi Muhendislik Dergisi in Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
- Vol. 16 (1) , 59-67
Open AccessDuygu tanımada akustik verilerle derin öğrenme modellerinin karşılaştırılması: LSTM ve DenseNet üzerine bir inceleme
Ses tanıma teknolojileri, insan-makine etkileşiminde önemli bir rol oynamakta olup, özellikle duygu tanıma sistemleri bu alandaki en kritik uygulamalardan biridir. İnsan davranışlarının daha iyi analiz edilmesi ve çeşitli alanlarda daha duyarlı sistemlerin geliştirilmesi amacıyla kullanılmaktadır. Bu çalışma, sesli duygu tanıma alanında iki farklı derin öğrenme modeli olan Uzun Kısa Süreli Bellek (LSTM) ve Dense modellerini karşılaştırmayı amaçlamaktadır. Ses verileri üzerinde daha etkili duygu tanıma performansı elde edebilmek için farklı derin öğrenme yöntemlerinin nasıl sonuçlar verdiği incelenmiştir. Çalışmada, Emotion Speech Dataset (ESD) kullanılmış ve her iki modelin genel doğruluk oranları karşılaştırılmıştır. Araştırma sonuçları F1-Score kriterine göre, LSTM modelinin %92 genel doğruluk oranına ulaştığı, DenseNet modelinin ise %88 genel doğruluk oranı sağladığı gözlemlenmiştir. Bu bulgular, zamansal verilerle çalışmada başarılı olan LSTM modelinin, duygu tanıma açısından daha üstün performans sergilediğini göstermektedir.
- 23 February 2024
- Published by Journal of the Faculty of Engineering and Architecture of Gazi University in Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi
- Vol. 40 (1) , 467-486
Makine öğrenme yöntemleriyle nehir akım tahmininde farklı tekniklerinin karşılaştırılması
Su yeryüzünün %75’ini kaplamaktadır ve bu oran toplam dünya kütlesinin sadece yaklaşık 4500 de 1’ini oluşturmaktadır. Dünya üzerindeki bütün canlıların varlığını sürdürebilmesi için gerekli olan en temel maddelerden biri sudur. Ayrıca su tarımsal faaliyetlerle, ekonomiyle, sağlıkla, enerji kaynaklarının kullanımı ve hijyen gibi unsurlarla karmaşık bir ilişki içinde bulunmaktadır. İklim değişiklikleri ve artan nüfus ile paralel olarak gelecek yıllarda su kaynaklarımızın yetersiz kalması, yaşanması olası başlıca büyük problemlerdendir. Temiz su kaynaklarının korunması ve geliştirilmesi, canlı yaşamı açısından büyük önem taşımaktadır. Mevcut su potansiyelinin tasarruflu kullanılması su ve kullanımının verimli hale getirilmesi gerekmektedir. Buna dayanarak mevcut suyun ne kadarını kullanılabileceği ve gelecekte su potansiyelinin ne derece değişeceğini önceden tahmin etmek su planlaması yapılması açısından şarttır. Akım ölçümleri gözlem istasyonlarında günlük olarak yapılmaktadır. Bu verilere dayalı olarak, matematik modellerle ve makine öğrenmesi sistemleri ile tahmin çalışmaları yapılabilmektedir. Bu araştırmada inceleme bölgesi olarak seçilen Yukarı Fırat havzası Tagar çayı Küçükkumluk ve Sakarya Havzası Kütahya Porsuk çayı Porsuk Çiftliği istasyonuna ait günlük ortalama akım, bölgeye ait günlük toplam yağış miktarı ve günlük ortalama hava sıcaklığı değerleri birlikte analiz edilmiş ve inceleme istasyonlarına ait nehir akım hızı tahmini yapılmıştır. Akış tahmini için Lineer Regresyon (Linear Regression-LR), Destek Vektör Regresyonu (Support Vector Regression-SVR), Karar Ağaçları (Decision Tree- DT), Rasgele Orman (Random Forest- RF) ve Ekstra Ağaçlar Regresyon (Extra Tree Regressor- ETR) yöntemleri uygulanmıştır. Ayrıca, uygulanan modellerin her birinin başarı performansları artırmak amacıyla Dalgacık Dönüşümü (Wavelet Transform- WT) kullanarak hibrit bir yöntem geliştirilmiştir. Veri setinin yaklaşık % 65’i eğitim, %15 doğrulama ve % 20’si test verisi olarak ayrılmıştır. Tagar Çayi Küçükkumluk için %70.8 ve Porsuk çayı Porsuk Çiftliği için %67.67 oranıyla ETR en başarılı tahmin yöntemi olarak saptanmıştır. Geliştirilen hibrit modelin tahmin başarısını bütün yöntemler için başarı oranını arttırmış; en yüksek artış oranlarını Tagar çayi Küçükkumluk için %20.82, Porsuk çayı Porsuk Çiftliği için %30.64 oranında artarak SVR yönteminde elde edilmiş; En başarılı yöntem olarak ETR yöntemi olup sırası ile %89.61 ve %86.39 oranlarında başarı elde edilmiştir. Üstel düzleştirme yöntemi ileri dönük 2030 yılına kadar tahmin değerleri elde edilmiştir.
- 23 February 2024
- Published by Journal of the Faculty of Engineering and Architecture of Gazi University in Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi
- Vol. 40 (1) , 467-486
Makine öğrenme yöntemleriyle nehir akım tahmininde farklı tekniklerinin karşılaştırılması
Su yeryüzünün %75’ini kaplamaktadır ve bu oran toplam dünya kütlesinin sadece yaklaşık 4500 de 1’ini oluşturmaktadır. Dünya üzerindeki bütün canlıların varlığını sürdürebilmesi için gerekli olan en temel maddelerden biri sudur. Ayrıca su tarımsal faaliyetlerle, ekonomiyle, sağlıkla, enerji kaynaklarının kullanımı ve hijyen gibi unsurlarla karmaşık bir ilişki içinde bulunmaktadır. İklim değişiklikleri ve artan nüfus ile paralel olarak gelecek yıllarda su kaynaklarımızın yetersiz kalması, yaşanması olası başlıca büyük problemlerdendir. Temiz su kaynaklarının korunması ve geliştirilmesi, canlı yaşamı açısından büyük önem taşımaktadır. Mevcut su potansiyelinin tasarruflu kullanılması su ve kullanımının verimli hale getirilmesi gerekmektedir. Buna dayanarak mevcut suyun ne kadarını kullanılabileceği ve gelecekte su potansiyelinin ne derece değişeceğini önceden tahmin etmek su planlaması yapılması açısından şarttır. Akım ölçümleri gözlem istasyonlarında günlük olarak yapılmaktadır. Bu verilere dayalı olarak, matematik modellerle ve makine öğrenmesi sistemleri ile tahmin çalışmaları yapılabilmektedir. Bu araştırmada inceleme bölgesi olarak seçilen Yukarı Fırat havzası Tagar çayı Küçükkumluk ve Sakarya Havzası Kütahya Porsuk çayı Porsuk Çiftliği istasyonuna ait günlük ortalama akım, bölgeye ait günlük toplam yağış miktarı ve günlük ortalama hava sıcaklığı değerleri birlikte analiz edilmiş ve inceleme istasyonlarına ait nehir akım hızı tahmini yapılmıştır. Akış tahmini için Lineer Regresyon (Linear Regression-LR), Destek Vektör Regresyonu (Support Vector Regression-SVR), Karar Ağaçları (Decision Tree- DT), Rasgele Orman (Random Forest- RF) ve Ekstra Ağaçlar Regresyon (Extra Tree Regressor- ETR) yöntemleri uygulanmıştır. Ayrıca, uygulanan modellerin her birinin başarı performansları artırmak amacıyla Dalgacık Dönüşümü (Wavelet Transform- WT) kullanarak hibrit bir yöntem geliştirilmiştir. Veri setinin yaklaşık % 65’i eğitim, %15 doğrulama ve % 20’si test verisi olarak ayrılmıştır. Tagar Çayi Küçükkumluk için %70.8 ve Porsuk çayı Porsuk Çiftliği için %67.67 oranıyla ETR en başarılı tahmin yöntemi olarak saptanmıştır. Geliştirilen hibrit modelin tahmin başarısını bütün yöntemler için başarı oranını arttırmış; en yüksek artış oranlarını Tagar çayi Küçükkumluk için %20.82, Porsuk çayı Porsuk Çiftliği için %30.64 oranında artarak SVR yönteminde elde edilmiş; En başarılı yöntem olarak ETR yöntemi olup sırası ile %89.61 ve %86.39 oranlarında başarı elde edilmiştir. Üstel düzleştirme yöntemi ileri dönük 2030 yılına kadar tahmin değerleri elde edilmiştir.