In this study, the latest release of all available Coupled Model Intercomparison Project Phase 6 (CMIP6) climate models with two future scenarios of Shared Socio-Economic Pathways, SSP2-4.5 and SSP5-8.5, over the period 2015–2100 are utilized in diagnosing climate extremes in Türkiye. Coarse-resolution climate models were downscaled to a 0.1° × 0.1° (~9 km) spatial resolution using the European Centre for Medium-Range Weather Forecasts Reanalysis 5-Land (ERA5-Land) dataset based on three types of quantile mapping: quantile mapping, detrended quantile mapping, and quantile delta mapping. The temporal variations of the 12 extreme precipitation indices (EPIs) and 12 extreme temperature indices (ETIs) from 2015 to 2100 consistently suggest drier conditions, in addition to more frequent and severe precipitation extremes and warming temperature extremes in Türkiye, under the two future scenarios. The SSP5-8.5 scenario indicates more severe water stress than the SSP2-4.5 scenario; the total precipitation decreases up to 20% for Aegean and Mediterranean regions of Türkiye. Precipitation extremes indicate a decrease in the frequency of heavy rains but an increase in very heavy rains and also an increasing amount of the total precipitation from very heavy rain days. Temperature extremes such as the coldest, warmest, and mean daily maximum temperature are expected to increase across all regions of Türkiye, indicating warming conditions by up to 7.5 °C by the end of the century. Additionally, the coldest daily maximums also exhibit higher variability to climate change in the subregions Aegean, Southeastern Anatolia, Marmara, and Mediterranean regions of Türkiye while the mean daily maximum temperature showed greater sensitivity in the Black Sea, Central Anatolia, and Eastern Anatolia regions.

A serious natural disaster that poses a threat to people and their living spaces is drought, which is difficult to notice at first and can quickly spread to wide areas through subtle progression. Numerous methods are being explored to identify, prevent, and mitigate drought, and distinct metrics have been developed. In order to contribute to the research on measures to be taken against drought, the Standard Precipitation Evaporation Index (SPEI), one of the drought indices that has been developed and accepted in recent years and includes a more comprehensive drought definition, was chosen in this study. Machine learning and deep learning algorithms, including support vector machine (SVM), random forest (RF), long short-term memory (LSTM), and Gaussian process regression (GPR), were used to model the droughts in six regions of Norway: Bodø, Karasjok, Oslo, Tromsø, Trondheim, and Vadsø. Four distinct model architectures were employed for this goal, and as a novel approach, the models’ output was enhanced by using discrete wavelet decomposition/transformation (WT). The model outputs were evaluated using the correlation coefficient (r), Nash–Sutcliffe efficiency (NSE), and root mean square error (RMSE) as performance evaluation criteria. When the findings were analyzed, the GPR model (W-GPR), which was acquired after WT, typically produced the best results. Furthermore, it was discovered that, out of all the recognized models, M04 had the most effective model structure. Consequently, the most successful outcomes were obtained with W-SVM-M04 for Bodø and W-GPR-M04 for Karasjok, Oslo, Tromsø, Trondheim, and Vadsø. Furthermore, W-GPR-M04 in the Oslo region had the best results across all regions (r: 0.9983, NSE: 0.9966 and RMSE:0.0539).

There are specific construction operations that require weather forecast data to make short-term decisions regarding construction; however, most resource-related decision making and all project management plans must be carried out to anticipate weather conditions beyond the capabilities of the currently available forecasting technologies. In this study, a series of single- and multi-risk analyses were performed with ~9 km grid resolution over Türkiye using combinations of weather and climate variables and their threshold values which have an impact on the execution and performance of construction activities. These analyses will improve the predictability of potential delays, enable the project to be scheduled on a future-proof basis by considering the calculated normal and periodic predictions on the grid scale, and serve as a dispute resolution tool for related claims. A comprehensive case study showcasing the methodology and illustrating its application shows that the project duration is expected to be extended because of the impact of climate on both historical and future periods. While the original project duration was 207 days, when climate effects were considered, the optimum mean and median values increased to 255 and 238 days, respectively, for the historical period. The optimum duration mean and median change to 239 days by the end of the century, according to the SSP5-8.5 scenario, if the construction schedules consider climate change. The change in duration was mainly due to rising temperatures, which increased winter workability and reduced summer workability. However, if the historical practices are carried over to future schedules, the mean and median increase to 258 days and 244 days, respectively, which may cause unavoidable direct, indirect, or overhead costs.

Meteorological drought, defined as a decrease in the average amount of precipitation, is among the most insidious natural disasters. Not knowing when a drought will occur (its onset) makes it difficult to predict and monitor it. Scientists face significant challenges in accurately predicting and monitoring global droughts, despite using various machine learning techniques and drought indices developed in recent years. Optimization methods and hybrid models are being developed to overcome these challenges and create effective drought policies. In this study, drought analysis was conducted using The Standard Precipitation Index (SPI) with monthly precipitation data from 1920 to 2022 in the Tromsø region. Models with different input structures were created using the obtained SPI values. These models were then analyzed with The Adaptive Neuro-Fuzzy Inference System (ANFIS) by means of different optimization methods: The Particle Swarm Optimization (PSO), The Genetic Algorithm (GA), The Grey Wolf Optimization (GWO), and The Artificial Bee Colony (ABC), and PSO optimization of Support Vector Machine (SVM-PSO). Correlation coefficient (r), Root Mean Square Error (RMSE), Nash–Sutcliffe efficiency (NSE), and RMSE-Standard Deviation Ratio (RSR) served as performance evaluation criteria. The results of this study demonstrated that, while successful results were obtained in all commonly used algorithms except for ANFIS-GWO, the best performance values obtained using SPI12 input data were achieved with ANFIS-ABC-M04, exhibiting r: 0.9516, NSE: 0.9054, and RMSE: 0.3108.

Drought is a natural disaster that often remains unnoticed until ecosystem impacts become severe. Therefore, monitoring and detecting droughts are important research topics. Consequently, drought indices with different focuses, such as precipitation or soil moisture, have been developed. Yet, the utility of the indices is limited before the beginning of the drought. To overcome this shortcoming, drought forecasting and providing decision-makers with an early warning to mitigate the effects is an important research topic. This study aims to take on the forecasting of the droughts with its novelty on the spatial focus, Norway (Drammen, Hamar, and Lillehammer). We forecast the Effective Drought Index (EDI) across spatially diverse Norwegian regions without hydrological constraints. To achieve this, we have utilized precipitation data between 1980 and 2025 and trained our machine learning models, namely, Support Vector Machine (SVM), Multi-layer Perceptron (MLP), Extreme Gradient Boosting (XGboost), Long-Short Term Memory network (LSTM), and Categorical Boosting Algorithm (Catboost). Moreover, the latent feature space is extended by wavelet transformation (WT). The innovative aspect of this study and its contribution to the literature is its novel application of the WT to some algorithms. Furthermore, unlike the literature, EDI was chosen as the drought index in this study, further increasing its innovative nature. Our results indicate that long short-term memory networks enhanced by wavelet transformation provide the best forecasts. Here, the best performance, LSTMW-M04, is achieved over Drammen ( r = 0.9765, NSE = 0.9510, KGE = 0.8641, PI = 0.3211, and RMSE = 0.2207). Although LSTM is already an innovative and successful algorithm, we have further improved the model performance. This result will help decision-makers in a future drought study with both the model input structure and the algorithm used.