The planning and management of water resources are affected by streamflow. The analysis of the sustainability of water resources has used well-grounded methods such as artificial neural networks, used for streamflow forecasting by researchers in recent years. The main aim of this study is to evaluate the performance of various methods for long-term forecasting from the data of the mean monthly streamflows between 1981 and 2017 from the Kucukmuhsine station on the Meram Stream in the Turkish province of Konya. For that reason, the multilayer perceptron (MLP), long short-term memory (LSTM), and adaptive neuro-fuzzy inference system (ANFIS) artificial intelligence techniques were employed in this study for the long-term forecasting of streamflow for 12 months, 24 months, and 36 months. The mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²) were used to evaluate the performance of the models developed to make predictions using the data from 1981 to 2017, and the Mann-Whitney test was applied to examine the differences between the actual data from 2018 to 2020 and each model’s forecasted results for those three years. The LSTM model showed superiority based on the values of R² (calculated as 0.730) and RMSE (lowest value of 0.510), whereas the MLP yielded better prediction accuracy as reflected by the value of MAE (lowest value of 0.519). The ANFIS model did not have the best prediction ability for any of the criteria. In accordance with the Mann-Whitney test results, LSTM and MLP indicated no significant difference between the actual data from 2018 to 2020 and the forecasted values; whereas, there was a significant difference for the ANFIS model at a confidence level of 95%. The results showed that the LSTM model had a better prediction performance, surpassing the MLP and ANFIS models, when comparing mean monthly streamflow forecasts.

Konya ili ekilebilir arazi bakımından yüksek bir orana sahip olduğu için ve Konya ilinde yağışın mevsimsel değişkenlik göstermesinden dolayı bu çalışmada Konya ili için bağıl nem ve yağış trend analizi araştırılmıştır. Türkiye Devlet Meteoroloji Dairesi, 1929'dan 2020'ye kadar 91 yıllık dönemi kapsayan bağıl nem ve yağış miktarına ilişkin istatistikler sağlanmıştır. Yağışın ve bağıl nemin içinde bulunduğu meteorolojik verilerin trend analizinin incelenmesi için Mann Kendall Testi ve Sen’in Trend Eğim Metodu kullanılmıştır. Yapılan analizler sonucunda yağış verileri için Kendall'ın tau değerlerinin Ocak'tan Aralık ayına kadar −0,087 ile 0,121 arasında değiştiği ve değerlerin çoğunluğunun sıfıra yakın olduğu belirlenmiştir Çoğu p değeri 0,05'ten büyük olarak hesaplanmıştır ve Sen'in eğimi değerlerinin aylık yağış için-0,087 ila 0,121 arasında değiştiği belirlenmiştir. Sonuçlara bağlı olarak Kendall'ın tau ve Sen' in eğimi değerleri sıfıra yakın ve p değerleri yüksektir; bu durum aylık ortalama yağış eğilimlerinde istatistiksel anlamlılık eksikliğine işaret etmektedir. Bağıl nem verileri için Kendall'ın tau değer aralığı-0,007 ila -0,248 olarak hesaplanmıştır ve p değerleri birkaç ayda (Ocak, Haziran, Aralık) 0,05'ten az olarak bulunmuştur. Sen'in eğimi değerleri ise 0,076 ila 0,000 aralığında değiştiği saptanmıştır. Sen'in eğimi ve Mann-Kendall testi, istatistik açısından üç ay boyunca (Ocak, Haziran ve Aralık) bağıl nemin azalma yönünde önemli bir eğilim olduğunu, ancak ortalama bağıl nem için diğer aylarda bu eğilimin olmadığını göstermektedir. İklim değişikliği tahmin edilirken, Konya'nın bağıl nem ve yağış oranlarında önemli farklılıklar öngörmeyen senaryo ve iklim modellerinin yol gösterici olabileceği söylenebilir.

Accurate precipitation forecasting is essential for water resource management, agricultural planning, and climate resilience, particularly in semiarid regions such as Konya Province, Türkiye, which receives approximately 300 to 350 mm of rainfall annually and is highly vulnerable to drought. This study presents a systematic comparative evaluation of eight forecasting models applied to monthly precipitation data spanning the period from 1958 to 2025. The models evaluated include SARIMAX, LASSO, CatBoost, LightGBM, XGBoost, Multilayer Perceptron (MLP), Long Short Term Memory (LSTM), and a hybrid LSTM and XGBoost framework. Model inputs comprise six key meteorological variables, namely temperature, humidity, evaporation, sunshine duration, wind speed, and precipitation, supplemented by sinusoidal seasonal encodings and lagged or rolling features depending on the model structure. A chronological 70/10/20 train, validation, and test split was applied to all machine learning models, while SARIMAX used the full dataset with exogenous regressors. Performance was evaluated using seven complementary metrics: R2, RMSE, MAE, NSE, MAPE, KGE, and PBIAS. The results reveal a clear three tier performance hierarchy. The hybrid LSTM and XGBoost framework achieved the highest accuracy (R2 = 0.945, RMSE = 5.46 mm), demonstrating that combining temporal feature extraction with nonlinear residual learning substantially improves predictive performance. Tree based ensemble models, including CatBoost, LightGBM, and XGBoost, formed an intermediate tier with R2 values around 0.70, effectively capturing seasonal variability but tending to underestimate extreme rainfall events. Linear and standalone deep learning models, including SARIMAX, LASSO, MLP, and LSTM, constituted the weakest tier. These findings confirm that hybrid architectures offer the most reliable framework for precipitation forecasting in semiarid regions, with direct implications for sustainable water management and climate adaptation planning.

This study examines key bioprocess parameters influencing the reduction in hydraulic conductivity in porous media via Microbially-Induced Calcite Precipitation (MICP), highlighting its relevance to environmental engineering applications such as bio-barriers and landfill liners. Sporosarcina pasteurii was utilized as the ureolytic bacterium to induce calcium carbonate precipitation under controlled laboratory conditions. Experimental variables included bacterial cell density (OD₆₀₀), diameter of glass beads, concentrations of precipitation solution, bentonite, and yeast extract. A total of 42 experimental runs were conducted based on a custom design in Design-Expert software. Hydraulic conductivity was selected as the response variable to evaluate treatment performance. Response surface methodology (RSM) was applied to develop a second-order polynomial model, with statistical analyses indicating a strong model fit (R² = 0.948, adjusted R² = 0.929, predicted R² = 0.868). ANOVA confirmed the significance of the main effects and interactions, particularly those involving glass bead diameter and OD₆₀₀. Among the tested factors, the precipitation solution exhibited the strongest individual effect, while bentonite and yeast extract demonstrated supportive roles. Optimization revealed that a balanced combination of microbial density and chemical inputs minimized hydraulic conductivity to 0.0399 cm/s (≈95% reduction), with an overall desirability score of 1.000. Laboratory-scale experiments demonstrated field-scale applicability, underscoring the potential of biotechnological soil treatment and empirical modeling for developing sustainable low-permeability barriers.