Downscaling of general circulation model (GCM) outputs extracted from CMIP5 datasets to monthly precipitation for the Gediz Basin, Turkey, under Representative Concentration Pathways (RCPs) was performed by statistical downscaling models, multi‐GCM ensemble and bias correction. The output databases from 12 GCMs were used for the projections. To determine explanatory predictor variables, the correlation analysis was applied between precipitation observed at 39 meteorological stations located over the Basin and potential predictors of ERA‐Interim reanalysis data. After setting both artificial neural networks and least‐squares support vector machine‐based statistical downscaling models calibrated with determined predictor variables, downscaling models producing the most suitable results were chosen for each meteorological station. The selected downscaling model structure for each station was then operated with historical and future scenarios RCP4.5, RCP6.0 and RCP8.5. Afterwards, the monthly precipitation forecasts were obtained from a multi‐GCM ensemble based on Bayesian model averaging and bias correction applications. The statistical significance of the foreseen changes for the future period 2015–2050 was investigated using Student's t test. The projected decrease trend in precipitation is significant for the RCP8.5 scenario, whereas it is less significant for the RCP4.5 and RCP6.0 scenarios.

Due to climatological changes, a study was conducted in the Gediz Basin, Turkey, where agricultural production holds an important place. In the study prepared, 12 general circulation models (GCMs) were utilized under representative concentration pathway (RCP)4.5, RCP6.0, and RCP8.5 scenarios of the fifth assessment report (AR5) of IPCC for the period 2015–2050. The statistical downscaling methods were employed and the projections were derived right after applying the weighted-averaged ensemble mean by the Bayesian Model Averaging (BMA) method and bias correction by equidistant quantile mapping (EDQM). The temperature-based potential evapotranspiration (PET) formulas were modified in accordance with the Penman–Monteith method and the aridity indexes were calculated by UNEP's formula. According to the projections, the mean annual temperature increases between 1.5 and 2.2 °C and the mean total annual PET increases between 5 and 8% are foreseen in the Gediz Basin for the near future. It is foreseen that a semi-arid climate regime may predominate over the region for all of the RCP scenarios under the increasing dryness in basin climate. In addition, it was obtained in the study that sub-humid climate state occurrence for all of the regions included by the basin may be unexpected in the future for the RCP8.5 scenario. The presence of semi-arid climate conditions may be more potent with the increasing trend of radiative forcing over time.

İstatistiksel ölçek indirgeme modelleri kaba çözünürlüklü iklim modellerinin yerel ölçeğe indirgenmesinde oldukça etkili araçlar olup, iklim değişikliği çalışmalarında sıklıkla yararlanılmaktadır. Çeşitli hidro-meteorolojik değişkenlerin projeksiyonlarında kullanılan farklı iklim modelleri kendi bünyesinde barındırdıkları yanlılık sebebiyle ölçek indirgeme modellerinin performanslarını etkilemekte ve tahminlere ait hassasiyeti azaltabilmektedir. Bu nedenle, ölçek indirgeme modellerinin yanında yanlılık düzeltme işlemlerine de ihtiyaç duyulmaktadır. Bu çalışmada, Hükümetlerarası İklim Değişikliği Paneli’ne (IPCC) ait 5. Değerlendirme Raporu’na göre farklı emisyon senaryoları çerçevesinde hazırlanmış iklim modelleri ve farklı yanlılık düzeltme yöntemleri ile Gediz Havzası’na ait yağış projeksiyonları elde edilmiş ve bunu takiben farklı yanlılık düzeltme yöntemlerinin yağış tahminlerine olan etkileri araştırılmıştır. Bunun için öncelikle, Gediz Havzası yağışlarını temsil eden tahminleyici seçimi yapılmış, daha sonra ilgili yağış tahminleyicileri ile kaba çözünürlüklü iklim modelleri istasyon ölçeğine indirgenmiştir. Çalışmada 2015-2050 gelecek dönemine ait kaba çıktıları bulunan 12 adet farklı küresel iklim modelinden faydalanılmış ve bu iklim modellerinden türetilen projeksiyonlar birleştirilerek daha kuvvetli tahminler elde edilmesi amaçlanmıştır. Çoklu iklim modellerinin birleşiminden sonra tahminlerde var olan yanlılıklar Kantil Haritalama (QM), Eş Oran Kantil Haritalama (ERQM), Trendsizleştirilmiş Kantil Haritalama (DQM) ve Kantil Delta Haritalama (QDM) yöntemleri ile ayrı ayrı düzeltilmiştir. Tüm performans indislerini kapsayan bulgulara göre, QM yönteminin en büyük hata değerlerini veren yaklaşım olduğu görülmüştür. Diğer yandan, QDM yöntemininise rölatif değişimleri diğer yöntemlere göre daha iyi yansıtabildiği sonucuna varılmıştır. Ekstrem süreçleri temsil eden performans indisleri incelendiğinde de, QDM’nin ortalama tabanlı yağış projeksiyonlarının değerlendirilmesinde daha üstün olduğu gözlenmiştir.

In the rapidly evolving landscape of urbanization, cities face unprecedented challenges due to climate change. As frontline battlegrounds against global warming, urban areas increasingly rely on AI to bolster resilience and sustainability. This chapter explores AI's role in shaping urban resilience, drawing from research and real-world applications. AI revolutionizes climate modeling, using vast datasets and machine learning to create predictive models that anticipate and mitigate impacts like extreme weather and sea-level rise, enabling proactive urban planning.AI also enhances smart infrastructure and resource management, optimizing energy use, water resources, and transportation to minimize ecological footprints. Through real-time monitoring and adaptive systems, cities can respond to environmental changes, ensuring infrastructure resilience. AI democratizes decision-making by empowering citizen participation in climate efforts. Open data, cross-sector partnerships, and collaborative research drive innovation, accelerating the transition to climate-resilient urban futures.

In the phases of hydrological model calibration, the impact of control parameters of optimization algorithms on the related fitness (cost) function (reaching the global solution correctly and expeditiously) is rather essential. These control parameters’ dynamic structure and interactions can force the quantification of the mentioned influence. In recent years, both the decomposition of the uncertainties of variables representing any process and searching parameter sensitivities were conducted by means of variance analysis termed as ANOVA. In the study, the success of a hybrid PSO (HPSO) algorithm, which was composed of particle swarm optimization (PSO) and a gradient-type algorithm, was shown compared to a standard PSO for a monthly rainfall-runoff model example. In addition to the measures such as reaching stable results under each run and fast convergence, individual and interactive effects of parameters of employed algorithms on simulations were also investigated by ANOVA. In the application, different combinations were assigned for the coefficients c1 and c2 that were defined in both PSO and HPSO, and then, algorithms were run 10 times in Acisu sub-basin of Gediz Basin. The evaluations have shown that the parameters’ uncertainties due to their individual behaviors and their interactions with each other are fairly reduced in HPSO implementation. In this sense, the fact that HPSO is not excessively sensitive to its control parameters has made it a preferred choice in the hydrological model calibration process.