A changing climate has been posing significant impacts on vegetation growth, especially in the Yellow River Basin (YRB) where agriculture and ecosystems are extremely vulnerable. In this study, the data for normalized difference vegetation index (NDVI) obtained from moderate-resolution imaging spectroradiometer (MODIS) sensors and climate data (precipitation and temperature) derived from the national meteorological stations were employed to examine the spatiotemporal differences in vegetation growth and its reaction to climate changes in the YRB from 2000–2019, using several sophisticated statistical methods. The results showed that both NDVI and climatic variables exhibited overall increasing trends during this period, and positive correlations at different significant levels were found between temperature/precipitation and NDVI. Furthermore, NDVI in spring had the strongest response to temperature/precipitation, and the correlation coefficient of NDVI with temperature and precipitation was 0.485 and 0.726, respectively. However, an opposite situation was detected in autumn (September to November) since NDVIs exhibited the weakest responses to temperatures/precipitation, and the NDVI’s correlation with both temperature and precipitation was 0.13. This indicated that, compared to other seasons, increasing the temperature and precipitation has the most significant effect on NDVI in spring (March to May). Except for a few places in the northern, southern, and southwestern regions of the YRB, NDVI was positively correlated with precipitation in most areas. There was an inverse relationship between NDVI and temperature in most parts of the central YRB, especially in summer (June to August) and growing season (May to September); however, there was a positive correlation in most areas of the YRB in spring. Finally, continuous attention must be given to the influence of other factors in the YRB.

Global warming and rapid socioeconomic development increased the risk of regional and global disasters. Particularly in China, annual heatwaves (HWs) caused many fatalities and substantial property damage, with an increasing trend. Therefore, it is of great scientific value and practical importance to analyze the spatiotemporal changes of HW in China for the sustainable development of regional socioeconomic and disaster risk management. In this study, based on gridded maximum temperature product and specific humidity dataset, an HW evaluation algorithm, considering the impact of humidity on the human body and the characteristics of HW in China, was employed to generate daily HW state at light, moderate, and severe levels for the period 1979–2018. Consequently, the regional differences at three HW levels were revealed, and the changing trend of HW onset, termination, and duration in each subregion was analyzed. The results show that in the three levels, the frequency and duration of HW in China had a significant increasing trend, generally characterized by the advancement of HW onset and the postponement of HW termination. The HW influence at light, moderate and severe levels decreased gradually, with the light level occurring the earliest and terminating the latest. Among the seven subregions, the largest HW frequency happened to be mainly in XJ (Xinjiang), SC (Southern China), and NC (Northern China), while the variations of HW onset and termination had noticeable regional differences at the three levels. The findings presented in this study can provide the essential scientific and technological support for national and regional disaster prevention mitigation and adaptation to extreme climate events.

This study assessed the drought susceptibility in Golestan Province, Northeastern Iran, using land use change modeling and climate projections from the CMIP6 framework, under three Shared Socioeconomic Pathways (SSP1-2.6, SSP2-4.5, and SSP5-8.5) for 2030–2050. The development of current (2022) and future drought susceptibility maps was based on agrometeorological sample points and 14 environmental factors—such as land use, precipitation, mean temperature, soil moisture, and remote sensing-driven vegetation indices—used as inputs into a machine learning model, maximum entropy. The model showed a very robust predictive capacity, with AUCs for the training and test data of 0.929 and 0.910, thus certifying the model’s reliability. The current analysis identified major hotspots in Gomishan and Aqqala, where 66.12% and 36.12% of their areas, respectively, exhibited “very high” susceptibility. Projections under the SSP scenarios, particularly SSP5-8.5, indicate that the risk of drought will be the most severe in Maraveh Tappeh, where 72.09% of the area exhibits a “very high” risk. The results revealed that Golestan Province is at a crossroads. Rising temperatures, exceeding 35 °C in summer, combined with declining rainfall, intensify agricultural and hydrological droughts. These aggravated risks are compounded with land use transitions from rangelands to bare land, mostly in Aqqala and Gomishan, besides urban expansion in Bandar-e Torkman and Bandar Gaz, all of which face less groundwater recharge and increased surface runoff. Golestan’s drought vulnerability has both local and regional impacts, with its increased susceptibility affecting neighboring communities and ecosystems. Trade, migration, and ecological stresses linked to declining water resources may emerge as critical challenges, requiring regional collaboration for mitigation. Targeted interventions prioritizing sustainable land use practices, regional cooperation, and collaborative strategies are essential to address and mitigate these cascading risks and safeguard vulnerable communities.

The source region of the Yellow River Basin (SRYRB) is not only sensitive to climate change and the vulnerable region of the ecological environment but also the primary runoff generating region of the Yellow River Basin (YRB). Its changes of drought and wetness profoundly impact water resources security, food production and ecological environment in the middle and downward reaches of YRB. In the context of global warming, based on daily precipitation, maximum and minimum temperature of 12 national meteorological stations around and within SRYRB during 1960–2015, this study obtained standardized precipitation index (SPI) and reconnaissance drought index (RDI) on 1-, 3-, 6- and 12-month scales, and then compared the consistency of SPI and RDI in many aspects. Finally, the temporal and spatial variation characteristics of drought and wetness in the SRYRB during 1960–2015 were analyzed in this study. The results showed that SPI and RDI have high consistency on different time scales (correlation coefficient above 0.92). According to the average distribution and change trend of the RDI, SRYRB presented an overall wetness state on different time scales. We found an increasing trend in wetness since the early 1980s. In terms of wetness events of different magnitudes, the highest frequency for moderate and severe ones was in June (12.7%) and February (5.5%), respectively, and for extreme wetness events, both September and January had the highest frequency (1.8%). Among the four seasons, the change rate of RDI in spring was the largest with a value of 0.38 decade⁻¹, followed by winter (0.36 decade⁻¹) and autumn (0.2 decade⁻¹) and the smallest in summer (0.1 decade⁻¹). There was a greater consistency between RDI values of larger time scales such as annual and vegetation growing seasonal (VGS) scales in SRYRB. There was generally a growing trend in wetness in the VGS time scale. These findings presented in this study can provide data support for drought and wetness management in SRYRB.

In the context of global warming, the general increase in temperature has led to an increase in heatwave events, as well as a dramatic intensification of economic losses and social risks. This study employs the latest intensity–area–duration (IAD) framework that takes into account the temporal continuity and spatial dynamics of extreme events to identify regional heatwave events, and extracts key parameters of heatwave events to study the associated changes in frequency, intensity, influence area, and duration in seven geographic subregions of China in the 1979–2018 period. Heatwaves of all durations increased in frequency and intensity during the research period, with shorter heatwaves increasing in frequency and intensity at a faster rate than longer heatwaves. Among the seven geographic subregions, Xinjiang (XJ) and Southern China (SC) are the regions with the most frequent heatwave occurrence, while the Southwest (SW) and SC have the highest increase in heatwave frequency. In terms of regional distributions, XJ has the strongest heatwave event intensity and the largest affected area, while SC has the longest duration. However, in terms of spatial trends, SC, XJ, and the SW have the highest rates of intensity growth, influence area, and duration, respectively. In addition, heatwaves with extended durations and vast influence areas are more likely to occur in SC, and their frequency is on the rise. During the study period, the intensity, influence area, and length of heatwave occurrences in China exhibited an upward tendency, and it was shown that the longer the duration, the greater the intensity and the broader the influence area. In addition, the evolutionary characteristics of heatwave events with the longest duration indicate a certain consistency in their intensity and influence. These findings can contribute to the development of strategies to prepare for and mitigate the adverse effects of heatwave occurrences.

Droughts are increasingly threatening ecological balance, agricultural productivity, and socio-economic resilience—especially in semi-arid regions like the Inner Mongolia segment of China’s Yellow River Basin. This study presents a hybrid drought forecasting framework integrating machine learning (ML) and deep learning (DL) models with high-resolution historical and downscaled future climate data. TerraClimate observations (1985–2014) and bias-corrected CMIP6 projections (2030–2050) under SSP2-4.5 and SSP5-8.5 scenarios were utilized to develop and evaluate the models. Among the tested ML algorithms, Random Forest (RF) demonstrated the best trade-off between accuracy and interpretability and was selected for feature importance analysis. The top-ranked predictors—precipitation, solar radiation, and maximum temperature—were used to train a Long Short-Term Memory (LSTM) network. The LSTM outperformed all ML models, achieving high predictive skill (R² = 0.766, CC = 0.880, RMSE = 0.885). Scenario-based projections revealed increasing drought severity and variability under SSP5-8.5, with mean PDSI values dropping below −3 after 2040 and deepening toward −4 by 2049. The high-emission scenario also exhibited broader uncertainty bands and amplified interannual anomalies. These findings highlight the value of hybrid AI–climate modeling approaches in capturing complex drought dynamics and supporting anticipatory water resource planning in vulnerable dryland environments.