The air temperature difference is an essential indicator to measure weather and climate change. The Tibetan Plateau (TP) is a sensitive area to global climate change. The study on its temperature difference variations is of great significance for further understanding the evolution of weather and climate systems, and scientific disaster prevention and mitigation. In this study, the spatio‐temporal evolution characteristics of the temperature difference on daily, monthly, seasonal and annual scales and their possible causes are analysed based on the daily observations at 59 meteorological stations over the TP from 1961 to 2020 and the circulation indexes such as the East Asian summer monsoon, South Asian summer monsoon, midlatitude westerly and TP summer monsoon. The results indicate that the diurnal temperature range (DTR) on the TP tends to decrease from 1961 to 2020. Compared with the situation in the late 20th century, the annual average of the DTR in the eastern TP turns from a nonsignificant increasing trend into a pronounced decreasing trend, while that in the western TP maintains a decreasing trend. This phenomenon is primarily influenced by the minimum and maximum temperature, precipitation and atmospheric circulations. The standardized temperature difference at different temporal scales shows decreasing trends and is distributed in north–south and east–west distribution patterns. The annual temperature range is mainly influenced by the remarkable increase of the minimum temperature, especially in the northern and southeastern TP. Besides, the increases of maximum temperature and precipitation also affect the annual temperature range. In terms of the seasonal temperature range, it is dramatically influenced by different meteorological factors, especially in the northern TP. The monthly temperature range (Mon‐TR) is dramatically influenced by the maximum and minimum temperature in the first and second half years, respectively. Moreover, the circulation systems, such as the midlatitude westerly, South Asian summer monsoon and TP summer monsoon, are the main influencing factors of the temperature difference variations on the TP. The midlatitude westerly have a large influence on Mon‐TR in June and September, and the significantly influenced stations reaches 54.2% and 35.6%. The impact stations of the TP summer monsoon on Mon‐TR is the largest in August, and the significantly influenced stations is 39%. In July, the influenced stations of the TP summer monsoon and South Asian summer monsoon on the Mon‐TR reaches 30.5%–33.9%. The influenced area of the Mon‐TR in June is largest affected by single summer monsoon or westerly index. Previous studies have shown that the warming mechanisms and their influencing factors have changed in the TP since the 21st century. The study results might provide the foundation for a scientific understanding of climate warming on the TP.

The frequent occurrence of meteorological disasters in China has caused huge losses to agriculture. Risk assessment serves as a bridge from disaster crisis management to disaster risk management. Therefore, it is necessary to carry out a refined comprehensive risk assessment of meteorological disasters in typical areas. However, several limitations remain in the disaster loss risk research, such as too coarse resolution and too single risk indicator. Additionally, less research has examined geographical information on risk clustering and barycenter migration, as well as temporal information on the sustainability of trends. Consequently, it is significant to unearth the geographical and temporal information on disaster loss and identify the refined spatial and temporal evolution pattern of crop risk. For this reason, we evaluated the risk of corn production in Gansu Province. First, based on maize yield data, a risk evaluation index system was constructed using the characteristics of variation trends, fluctuations, and extreme values of disaster losses. Then, the spatial distribution patterns and temporal evolution characteristics of maize production risks on a county scale in Gansu Province were determined using spatial analysis and climate diagnosis technology. The results show that there is a large interdecadal fluctuation in risk. In the 1980s, 1990s, 2000s, and 2010s, the average yield reduction rates of maize in Gansu Province were −11.8%, −12.6%, −8.7%, and −8.5%, and the proportions of counties with severe yield reduction were 34.8%, 44.4%, 20.8%, and 9.7%, respectively. Second, most counties belong to medium-low or low-risk areas for maize production. High-risk counties are primarily located in eastern and southern Gansu, whereas low-risk counties are mostly found along the Hexi Corridor. Third, most risk indicators exhibit some geographical aggregation. The Jiuquan region falls within the low-low-risk aggregation zone. In contrast, the Qingyang region is a high-high aggregation zone with a gradual expansion trend. Four, each risk indicator’s geographical barycenter migrates over a complicated path, but the direction and distance vary considerably. The comprehensive risk migrates along the south-northwest-southeast trajectory, albeit at a shorter distance. Five, the proportion of counties with a medium, medium-severe, severe, and total yield reduction tended to decline. In addition, the annual precipitation is significantly or very significantly correlated with most risk indicators and the comprehensive risk level. The results can guide agricultural production processes at all levels, as well as government disaster prevention.

Food security is crucial for human survival and national economic development, but frequent meteorological disasters have caused great harm to agricultural production. Therefore, it is very important and meaningful to study how to quickly and accurately predict the loss rate of disasters. Only based on historical loss sequence, the time series prediction method can effectively predict future loss. Therefore, this paper first briefly describes the main means of time series prediction, namely statistical methods and machine learning algorithms. Secondly, the commonly used machine learning algorithms for disaster loss time series prediction, and its application cases and existing problems, were introduced in detail. To address the issue of small sample sizes for loss predication, data augmentation techniques can be used; To address the issue of data non-stationarity, Empirical Mode Decomposition (EMD) can be used to decompose the original sequence into relatively stationary sub-sequences. In addition, exploratory solutions have been proposed, such as ensemble learning strategies for multiple machine learners, and combining machine learning algorithms with optimization algorithms, strong prediction strategies, or attention mechanisms. Finally, a summary solution for conventional disaster damage prediction was proposed.

This study evaluates the spatio-temporal variations in vegetation ecological quality (EQI) on the Tibetan Plateau (TP) from 2001 to 2020 by integrating net primary productivity (NPP) and fractional vegetation cover (FVC). The results show that annual EQI increased at 0.8 decade⁻¹, with 65.6% of areas exhibiting improvement, particularly in sparse grasslands and mixed forests. NPP and FVC rose by 5.4 g C m⁻² decade⁻¹ and 0.008 decade⁻¹, respectively, displaying southeast–northwest spatial gradients. Climate warming (0.18 °C decade⁻¹) and wetting (27.5 mm decade⁻¹) drove EQI trends, with temperature positively correlating with EQI in eastern forests (29% mixed forests) but negatively in southern grasslands. Atmospheric circulation further modulated EQI: enhanced zonal water vapor flux and monsoon indices (IVarea, EMI) significantly impacted 10–25% of areas. Despite persistent improvement trends (13.9% of TP), 5.9% of regions face sustained degradation risks, emphasizing the need for climate-adaptive vegetation management. This synthesis of ecological-climate coupling provides actionable insights for conservation on the warming TP.