Weather and climate extremes have been varying and changing on many different time scales. In recent decades, heat waves have generally become more frequent across the United States, while cold waves have been decreasing. While this is in keeping with expectations in a warming climate, it turns out that decadal variations in the number of U.S. heat and cold waves do not correlate well with the observed U.S. warming during the last century. Annual peak flow data reveal that river flooding trends on the century scale do not show uniform changes across the country. While flood magnitudes in the Southwest have been decreasing, flood magnitudes in the Northeast and north-central United States have been increasing. Confounding the analysis of trends in river flooding is multiyear and even multidecadal variability likely caused by both large-scale atmospheric circulation changes and basin-scale “memory” in the form of soil moisture. Droughts also have long-term trends as well as multiyear and decadal variability. Instrumental data indicate that the Dust Bowl of the 1930s and the drought in the 1950s were the most significant twentieth-century droughts in the United States, while tree ring data indicate that the megadroughts over the twelfth century exceeded anything in the twentieth century in both spatial extent and duration. The state of knowledge of the factors that cause heat waves, cold waves, floods, and drought to change is fairly good with heat waves being the best understood.

Climate forecasting is essential for energy production, agricultural activities, transportation, and civil defense sectors, serving as a foundation for decision-making and risk management. This study addresses the challenge of accurately predicting extreme droughts in South America, a region highly vulnerable to climate variability. By employing a supervised neural network (NN) within a machine learning framework, we developed a methodology to forecast precipitation and subsequently calculate the Standardized Precipitation Index (SPI) for predicting drought conditions across the continent. The proposed model was trained with precipitation data from the Global Precipitation Climatology Project (GPCP) for the period 1983–2023. It provided monthly drought forecasts, which were validated against observational data and compared with predictions from the North American Multi-Model Ensemble (NMME). Key findings indicate the neural network’s ability to capture complex precipitation patterns and predict drought conditions. The model’s architecture effectively integrates precipitation data, demonstrating superior performance metrics compared to traditional approaches like the NMME. This study reinforces the relevance of using machine learning algorithms as a robust tool for drought prediction, providing critical information that can assist in decision-making for sustainable water resource management.

Abstract Background: Drought Indices has an important role to assess drought over the surfaces of the Earth. Drought is one of the most complex and severe catastrophes in the study area that causes damage in different ways. The main objective of this study is to assess the spatiotemporal variation of meteorological drought using Reconnaissance Drought Index (RDIst) and Standardized Precipitation Index (SPI) in Boricha District. The study used the long-term gridded rainfall and temperature data in six stations covering the period of (1985-2016). The spatial distribution of drought was mapped using ArcGIS 10.3 spatial analysis tool and interpolated using Inverse Distance Weight (IDW) method.Results: The spatiotemporal variation of meteorological drought was analyzed by using both SPI and RDIst at seasonal and annual timescale. In spring season two extreme droughts were observed in station-2 and 3 with the same SPI value of (-2.26). During summer season in station-3 extreme drought was detected with SPI values of (-2.32), in station-4 one extreme drought was observed with SPI values of (-2.14). In 12 month RDIst time scale, one extreme drought was identified in station-4 during 2012 with RDIst value of (-2.25), and in station-6 one extreme drought has been occurred during 2009 with RDIst value of (-2.23). The study area was affected by drought of slight/mild to extreme droughts at all time scale. MK trend test indicates the tendency of drought was decreased and statistically insignificant in spring and annual timescales except station-1 (12 months SPI) in the study period of (1985-2016). The temporal correlation analysis of SPI and RDIst was applied with the correlation coefficient at seasonal (spring, summer) and annual timescale (r = 0.99) and it’s significant at P = 0.01 levels was achieved, which indicates very strong positive correlation. Conclusion: The study area was more affected by meteorological drought. There is no a station without drought in all parts of the district. The substantial parts of the district are under severe and extreme drought risk, calling for an immediate intervention by the regional and federal disaster risk preparedness and natural resource office to save people and Natural resource.

<p><strong>Abstract</strong></p><p>In this study, droughts were assessed for the Uremia Lake Basin located in the North West of Iran which is facing the risk of drying over the last decades. Since long-term and spatially dense observational data are not available, in particular for the mountainous part of the Uremia lake basin, we successfully tested the performance of the ERA5 reanalysis data set for our purpose. By comparing time series plots of drought indices (SPI, SPEI), both indices were able to capture the temporal variation of droughts. SPIE identified more drought events but SPI, as it uses precipitation only as input, fails to show the increasing number of evaporation driven droughts in the Uremia Lake Basin, which were observed in particular for the most recent decade. SPEI was calculated using the monthly temperature and precipitation, the extremely dry conditions of the basin were observed in the mountainous area, it seems that based on SPEI index, the highest values of actual evapotranspiration happens near the lake and in high mountains. Moreover, in recent years, drought has become more extreme in higher elevated areas, then we focused on Snow cover which has a significant role in surface runoff and groundwater recharge in mountainous and semi-arid areas, like within the Uremia lake basin. In recent years climate change impact snow variations distribution, snow cover, and runoff in different scales. Therefore, spatial and temporal monitoring of the snow-covered surface and the impact of these changes is necessary. Consequently, the chances of snow cover (SCA) in the study area were studied using MODIS images by the NDSI index and snow cover data from the ERA5 dataset. Finally, we came to this conclusion that the temperature rise in recent decades led to a high amount of evaporation and consequently the snow surface area has decreased so that it could affect the region’s water reservoir in the future.</p><p>Key words: Drought monitoring,ERA5,MODIS,SPI,SPEI,NDSI</p>

This study aims to evaluate meteorological drought predictions for Türkiye in 2024 using the SEAS5 seasonal forecast system developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). The motivation behind this research is to assess the applicability of SEAS5 for drought forecasting and its potential contribution to drought management and early warning systems. Drought analysis was performed using the Standardized Precipitation-Evapotranspiration Index (SPEI) on a 3-month timescale, while the model’s predictive performance was evaluated through categorical verification metrics. The forecast data used were the monthly anomaly outputs of the SEAS5 system for 2024, combined with station-based reference normals from the 1991-2020 period to produce station-specific forecast series. Long-term precipitation and temperature data from 190 meteorological observation stations, with records starting from 1969, were employed to identify climate trends using the Mann-Kendall rank correlation method. The study presents spatial and temporal distributions of drought conditions and assesses the SEAS5 model’s success in predicting droughts across different months and seasons. The findings suggest that SEAS5 can be effectively used for drought forecasting in Türkiye and can contribute significantly to improving drought management and early warning systems.

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.

Meteorological droughts, which occur due to deviations in the average precipitation amount, are the type of drought that living beings suffer from the most. Just as every part of the world is affected by this natural phenomenon, almost all regions of Türkiye are also impacted. Acıpayam is one of the regions located in western Türkiye that is affected by droughts. Therefore, monitoring and forecasting droughts in this region is paramount of important. In this study, the Acıpayam region was chosen as the study area, and monthly precipitation data from the meteorological station in the region covering the period 1967–2020 was used. Based on the obtained data, the Standardized Precipitation Index (SPI) values were first calculated and then analyzed using the Long Short-Term Memory Network (LSTM). Moreover, four different model input structures were created. In addition, to enrich the model performance results, Variational Mode Decomposition (VMD) was employed. To evaluate the model results, the correlation coefficient (r), the Nash–Sutcliffe efficiency (NSE), and the root mean square error (RMSE) were calculated for each model. According to the results, the best performance metrics were obtained in M04 (r=0.9271, NSE=0.9234, and RMSE=0.2762). For future drought forecasting studies, this model input structure should be preferred. This study will contribute to supporting decision-making authorities in determining drought-related policies in the region.

Abstract Climate change could cause changes in temperature and precipitation patterns that may increase the probability of drought. Climate change could enormously affect arid regions, and many countries may suffer from drought. This study aims to monitor the historical drought in Syria. Monthly data were collected from 71 land stations for the period (1991-2009). After 2010, the field data were not available due to the civil war in Syria. The satellite images for monthly precipitation were collected for the period (1983-2020). RS and GIS were used to correct the satellite images using the land stations data for the period (1991-2009) and correction equation was developed for each station that was used to correct the data for the period (1983-2020). Drought risk analysis was carried out utilizing Standardized Precipitation Index (SPI) in the period (1983-2020). Three types of droughts have been detected; agricultural, hydrological and groundwater drought. The results showed that significant drought struck Syria and the highest drought events were recorded in 1989, 2013 and 2016. The results of SPI trend analysis showed decreasing trends at all the stations. This highlights the impact of climate change on Syria that may suffer from more droughts in the future which in turn affect the availability of water resources. The results of this research could help to manage water resources and adapt to climate change risks in Syria. The results approved that SPI is a useful tool to monitor drought that could help decision-makers for putting efficient plans for drought risk management.

Regional Climate Models (RCMs) work at finer resolution over a limited region and are presumed to perform better at regional scales. RCMs need thorough evaluation before being used for any climate change impact assessment study due to the biases associated with the observed data. While few studies used RCM outputs for understanding the spatio-temporal variability of precipitation and temperature over India, application of RCMs in drought assessment has been overlooked. Here, the study aims to perform drought analysis using RCMs over India with Standardized Precipitation Evapotranspiration Index (SPEI) as the drought index. About 10 RCMs from the Coordinated Regional Climate Downscaling Experiment program (CORDEX) have been considered in the analysis. To remove the systematic biases, a Quantile based bias correction method has been used. The study evaluated the performance of bias-corrected RCMs to simulate rainfall over India for each grid using the statistical measures such as correlation and Nash-Sutcliffe Efficiency coefficients. The monthly precipitation for all over India was best represented by the experiment LMDz-IITMRegCM4 (Regional Climatic Model version 4). Based on the performance evaluation in the study, ICHEC-EC-EARTH-SMHI-RCA4 and MPI-CSC-REMO2009 were used along with LMDz-IITMRegCM4 for drought assessment over India. The results reveal that for West and North-East zones, the drought frequencies and intensities increase for the periods of 2001-2050 and 2051-2100 with Representative Concentration Pathways (RCP) 4.5 for all three considered RCMs. All over India, the average drought intensities were observed to be increasing for ICHEC-EC-EARTH-SMHI-RCA4 and LMDz-IITMRegCM4 while there is no change for MPI-CSC-REMO2009.

Droughts typically develop gradually, and early prediction is crucial for the government to formulate effective mitigation plans. Our approach does not involve predicting specific drought index values. Instead, we forecast whether a particular year will experience drought. Insufficient investigation has been carried out regarding variations in additional climatic indicators like shortwave radiation, wind speed, sea level, and pollution in the context of droughts in the state of Tamil Nadu, India. In the study period taken from 1995 to 2020, only three years (2002, 2009, and 2017) experienced drought occurrences, resulting in an imbalanced dataset. To enhance the classification performance of this imbalanced dataset, a weighted dataset is constructed using a feature weighting approach known as the Single Objective Scorer (SOS) based Multi-objective PSO(MPSO) in conjunction with the Gradient Boosting Classifier. The proposed model facilitates objective-based multi-population formation and neighborhood learning. Precision and recall are crucial metrics, particularly in measuring imbalanced dataset classification performance. The application of multi-objective optimization techniques helps to strike a suitable balance between precision and recall. In addition to the Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI), 14 climatic indicators based on land, atmosphere, and sea are utilized. By employing the weighted dataset created