Search Results (37)

Accurate short-term weather forecasting plays a vital role in disaster response, agriculture, and energy management, where timely and reliable predictions are essential for decision-making. Graph neural networks (GNNs), known for their ability to model complex spatial structures and relational data, have achieved remarkable success in meteorological forecasting by effectively capturing spatial dependencies among distributed weather stations. However, most existing GNN-based approaches rely on pairwise station connections, limiting their capacity to represent higher-order spatial interactions. Moreover, their dependence on supervised learning makes them vulnerable to spatial heterogeneity and temporal non-stationarity. This paper introduces a novel spatial–temporal pretraining framework, Hypergraph-enhanced Meteorological Pretraining (HyMePre), which combines hypergraph neural networks with self-supervised learning to model high-order spatial dependencies and improve generalization across diverse climate regimes. HyMePre employs a two-stage masking strategy, applying spatial and temporal masking separately, to learn disentangled representations from unlabeled meteorological time series. During forecasting, dynamic hypergraphs group stations based on meteorological similarity, explicitly capturing high-order dependencies. Extensive experiments on large-scale reanalysis datasets show that HyMePre outperforms conventional GNN models in predicting temperature, humidity, and wind speed. The integration of pretraining and hypergraph modeling enhances robustness to noisy data and improves generalization to unseen climate patterns, offering a scalable and effective solution for operational weather forecasting. Full article

Cotton (Gossypium spp.) is an important industrial crop, but it is vulnerable to waterlogging stress. The relationship between cotton yields and waterlogging indicators (CY-WI) is fundamental for waterlogging disaster reduction. This review systematically summarized and analyzed literature containing CY-WI relations across 1970s–2020s. China conducted the most CY-WI experiments (67%), followed by Australia (17%). Recent decades (2010s, 2000s) contributed the highest proportion of CY-WI works (49%, 15%). Surface waterlogging form is mostly employed (74%) much more than sub-surface waterlogging. The flowering and boll-forming stage, followed by the budding stage, performed the most CY-WI experiments (55%), and they showed stronger negative relations of CY-WI than other stages. Some compound stresses enhance negative relations of CY-WI, such as accompanying high temperatures, low temperatures, and shade conditions, whereas some others weaken the negative CY-WI relations, such as prior/post drought and waterlogging. Anti-waterlogging applications significantly weaken negative CY-WI relations. Regional-scale CY-WI research is increasing now, and they verified the influence of compound stresses. In future CI-WI works, we should emphasize the influence of compound stresses, establish regional CY-WI relations regarding cotton growth features, examine more updated cotton cultivars, focus on initial and late cotton stages, and explore the consequence of high-deep submergence. Full article

In recent years, the increasing frequency and intensity of climate-related disasters have underscored the urgent need for resilient urban development. In cold-region cities, low temperatures pose a distinct and underexplored threat, with serious implications for human well-being, infrastructure performance, and ecological stability. Despite growing attention to climate resilience, existing urban risk assessments have largely focused on heatwaves and flooding, leaving a notable gap in research on cold-weather vulnerability. To address this gap, this study develops a fine-scale cold-climate vulnerability assessment framework grounded in the widely recognized “Exposure–Sensitivity–Adaptive Capacity” (ESA) model. Using subdistricts as the basic units of analysis, we integrate multi-source spatial data—including demographics, built environment, services, and ecological indicators—to construct a comprehensive evaluation system tailored to low-temperature conditions. The model is applied to the central urban area of Harbin, China, a representative cold-region city. The results reveal distinct spatial disparities in vulnerability: older urban districts exhibit higher vulnerability due to high population density and inadequate public services, while newly developed areas show relatively greater adaptive capacity. Further analysis identifies key drivers of vulnerability in different zones. Based on these insights, the study proposes differentiated, subdistrict-level planning strategies aimed at reducing exposure, mitigating sensitivity, and enhancing adaptive capacity. By extending the ESA model to cold-climate scenarios and operationalizing it at the subdistrict scale, this research contributes both methodologically and practically to the field of urban climate resilience. The findings offer actionable strategies for policymakers and provide a replicable framework applicable to other cold-region cities facing similar challenges. Full article

The Western Sichuan Plateau, an ecologically critical transition zone between the Qinghai–Tibet Plateau and the Sichuan Basin, is also a typical fragile and sensitive area in China’s ecological security. This study established a multi-process evaluation model using the Spatial Distance Index Method, integrating cluster analysis, Sen–Mann–Kendall trend detection, and OWA-based scenario simulations to assess composite ecological sensitivity dynamics. The optimal geodetector was further applied to quantitatively determine the driving mechanisms underlying these sensitivity dynamics. The research showed the following findings: (1) From 2000 to 2020, the ecological environment of the Western Sichuan Plateau exhibited a phased pattern characterized by significant improvement, partial rebound, and overall stabilization. The composite ecological sensitivity grading index showed a declining trend, indicating a gradual reduction in ecological vulnerability. The effectiveness of ecological restoration projects became evident after 2010, with the area of medium- to high-sensitivity zones decreasing by 24.29% at the regional scale compared to the 2010 baseline. (2) The spatial pattern exhibited a gradient-decreasing characteristic from west to east. Scenario simulations under varying decision-making behaviors prioritized Jiuzhaigou, Xiaojin, Jinchuan, Danba, and Yajiang counties as ecologically critical. (3) Driving force analysis revealed a marked increase in the explanatory power of freeze-thaw erosion, with its q-value rising from 0.49 to 0.80. Moreover, its synergistic effect with landslide disasters spans 74.19% of county-level units. Dominant drivers ranked: annual temperature range (q = 0.32) > distance to faults (q = 0.17) > slope gradient (q = 0.16), revealing a geomorphic-climatic-tectonic interactive mechanism. This study provided methodological innovations and decision-making support for sustainable environmental development in plateau transitional zones. Full article

Fire, whether wild or urban, depends on the triad of oxygen, fuel, and heat. Urban fires, although smaller in scale, have devastating impacts, as evidenced by the 2018 wildfire in Mati, Attica (Greece), which claimed 104 lives. The elderly and children are the most vulnerable due to mobility and cognitive limitations. This study applies Grammatical Evolution (GE), a machine learning method that generates interpretable classification rules to predict the consequences of urban fires. Using historical data (casualties, containment time, and meteorological/demographic parameters), GE produces classification rules in human-readable form. The rules achieve over 85% accuracy, revealing critical correlations. For example, high temperatures (>35 °C) combined with irregular building layouts exponentially increase fatality risks, while firefighter response time proves more critical than fire intensity itself. Applications include dynamic evacuation strategies (real-time adaptation), preventive urban planning (fire-resistant materials and green buffer zones), and targeted awareness campaigns for at-risk groups. Unlike “black-box” machine learning techniques, GE offers transparent human-readable rules, enabling firefighters and authorities to make rapid informed decisions. Future advancements could integrate real-time data (IoT sensors and satellites) and extend the methodology to other natural disasters. Protecting urban centers from fires is not only a technological challenge but also a moral imperative to safeguard human lives and societal cohesion. Full article

Based on the rapid development of urbanization and the increasing severity of extreme heat disasters caused by global warming, it has become increasingly important to enhance the assessment of heat risk. In this study, in response to the urgent need for fine-grained assessment of urban heat risk in arid zones in the context of climate change, an analytical method of dividing Local Climate Zones (LCZs) into street blocks combined with the Hazard–Exposure–Vulnerability–Adaptability (HEVA) heat risk assessment framework is used in Urumqi, a representative city of China’s arid zones. In addition, Shapley Additive Explanations (SHAP) was introduced to quantitatively resolve the driving mechanisms of heat risk in different types of LCZs. The results show that the study area has the largest proportion of bare soil (LCZ F) (37.6%), which is distributed around the built-up types of LCZs, while water (LCZ G) has a very small proportion (0.39%) and only exists in the outskirts of the city. Heat risk was significantly higher in the urban core than in the peri-urban areas, but LCZ F had a very high hazard due to the unique surface characteristics of arid zones, which elevated the heat risk in the peri-urban desertification fringe; SHAP analyses demonstrated that in arid zones, land surface temperature (LST) became a determinant of heat risk for all low-density built-up types of LCZs. This study proposes targeted mitigation strategies for heat risk in arid zones based on the LCZ framework. Full article

One of the important effects of global warming is the use of fossil fuels. Disadvantaged individuals may be affected by fossil fuel use more than others. In this study, the Kepez district of Antalya province, where the Social Vulnerability Index (SVI) is high, was selected as the study area. Five-year (2019–2023) NO₂, SO₂, and CO concentrations were extracted from the Sentinel-5P TROPOMI satellite with open-source code. These values were combined and compared with Land Use Land Cover (LULC) land classes obtained from the Sentinel-2 satellite. The same process was performed for Land Surface Temperature (LST) obtained from MODIS Terra and Aqua satellites, and interpretation was made according to the LST-LULC map and surface temperature. The integrated SVI was calculated with population, age, education, and gender data from the Turkish Statistical Institute and NO₂, SO₂, and CO concentrations from the Sentinel-5P TROPOMI satellite. It was mapped on a neighborhood basis with zonal statistics. Accordingly, 20.6% of the neighborhoods in Kepez were categorized as very high risk, and 16.2% were categorized as high risk. Integrated SVI with the determination made by evaluating only air pollution gave different neighborhood results. This revealed the importance of using the SVI in disaster risk assessments. This study has the potential to shed light on the social vulnerability-supported disaster risk information system that is likely to be created in the following years. Full article

With the advancement of urbanization and acceleration of global warming, extreme weather and climate events are becoming increasingly frequent and severe, and climate risk continues to rise. Each community is irreplaceable and important in coping with extreme climate risk and improving urban resilience. In this study, the Dongsi Community in the functional core area of Beijing was explored, and the risk assessment of high temperatures and rainstorm waterlogging was implemented at the community scale. Local navigation observations were integrated into a theoretical framework for traditional disaster risk assessment. The risk assessment indicator system for community-scale high-temperature and rainstorm waterlogging disasters was established and improved from a microscopic perspective (a total of 22 indicators were selected from the three dimensions of hazard, exposure, and vulnerability). Geographic Information Systems (GIS) technology was used to integrate geographic information, meteorological, planning, municipal, socioeconomic and other multisource information layers, thus enabling more detailed spatial distribution characteristics of the hazard, exposure, vulnerability, and risk levels of community-scale high temperatures and rainstorm waterlogging to be obtained. The results revealed that the high-risk area and slightly high-risk area of high-temperature disasters accounted for 13.5% and 15.1%, respectively. The high-risk area and slightly high-risk area of rainstorm waterlogging disasters accounted for 9.8% and 31.6%, respectively. The high-risk areas common to high temperatures and waterlogging accounted for 3.9%. In general, the risk of high-temperature and rainstorm waterlogging disasters at the community scale showed obvious spatial imbalances; that is, the risk in the area around the middle section of Dongsi Santiao was the lowest, while a degree of high temperatures or rainstorm waterlogging was found in other areas. In particular, the risk of high-temperature and rainstorm waterlogging disasters along Dongsi North Street, the surrounding areas of Dongsi Liutiao, and some areas along the Dongsi Jiutiao route was relatively high. These spatial differences were affected to a greater extent by land cover (buildings, vegetation, etc.) and population density within the community. This study is a useful exploration of climate risk research for resilient community construction, and provides scientific support for the planning of climate-adaptive communities, as well as the proposal of overall adaptation goals, action frameworks, and specific planning strategies at the community level. Full article

The increasing global population and in-country migration have a significant impact on global land use land cover (LULC) change, which reduces green spaces and increases built-up areas altering the near-surface radiation and energy budgets, as well as the hydrological cycle over an urban area. The LULC change can lead to a combination of hazards such as increasing urban temperatures and intensified rainfall, ultimately resulting in increased flooding. This present study aims to discuss the changing pattern in urban temperature, daily rainfall, and flooding in Jakarta. The daily urban temperature and daily rainfall were based on a 30-year dataset from three meteorological stations of Jakarta in the period between 1987 and 2013. The changing trend was analyzed by using the Mann–Kendall and the Pettitt’s tests. The relation between daily rainfall and flooding was analyzed using a 30-year flooding dataset collected from several sources including the international disaster database, research, and newspaper. The results show that there was an increasing trend in the daily temperature and the daily rainfall in Jakarta. The annual maximum daily temperature showed that an increasing trend started in 2001 at the KMY station, and in 1996 at the SHIA station. In general, the highest annual maximum daily temperature was about 37 °C, while the lowest was about 33 °C. Moreover, the maximum daily rainfall started increasing from 2001. An increase in the maximum daily rainfall was observed mainly in January and February, which coincided with the flood events recorded in these months in Jakarta. This indicates that Jakarta is not only vulnerable to high urban temperature but also to flooding. While these two hazards occur in distinct timeframes, there is potential for their convergence in the same geographical area. This study provides new and essential insights to enhance urban resilience and climate adaptation, advocating a holistic approach required to tackle these combined hazards. Full article

Kazakhstan is historically a livestock-producing country. For the first time in this study, we attempted to assess the vulnerability of nomadic pastoralists in Kazakhstan to climate change using the Livelihood Vulnerability Index (LVI). To collect data, a survey of 100 household heads was conducted on fourteen main components and fifty-six sub-components. The study was conducted in the period from May to July 2022 in the Panfilov (PD) and Kerbulak (KD) districts of the Zhetysu region, where the Altyn-Emel State National Nature Park is located. The results of the study were combined using a composite index method and comparing different vulnerability indicators. Natural disasters, which manifest as the effects of drought, temperature fluctuations, and precipitation, contribute most to the vulnerability of nomads living in remote mountain areas with a complex infrastructure. According to the results of the study, nomads of both regions have high vulnerability in such components as natural resources, human–wildlife conflict, housing type, agriculture and food security, and social networks. High vulnerability in the “Finances and incomes” component was found only in the pastoralists of the PD. Identifying the levels of vulnerability of nomadic households to climate change, as well as understanding their adaptation strategies, will enable pastoralists to gain access to new ways of reducing the vulnerability of their livelihoods. Currently, the country practices a strategy to reduce the vulnerability of pastoral nomads’ livelihoods by insuring livestock against natural or natural hazards and other risks; involving the population in environmental-protection activities and helping them to obtain sustainable financial resources when they refuse to hunt endangered animals; non-agricultural diversification of high-altitude ecotourism in rural areas in their area of residence; and improving financial literacy by providing training and providing information on low-interest loans under state projects and livestock subsidy mechanisms, as well as training in organizing cooperatives within the framework of legal status, which will ensure them stable sales of products and income growth. The results of software research serve as a basis for taking measures within the framework of the development and implementation of state programs for climate change adaptation of the Environmental Code of the Republic of Kazakhstan, where agriculture is one of the priority areas of management. Full article

It is necessary to alleviate the high temperatures and heat wave disasters in cities in southwest China that are beginning to occur because of global warming. During this study, the spatial and temporal characteristics of heat waves in Nanchong from 1961 to 2022 are analyzed by using the signal smooth method and mutation test. Based on the meteorological data and socioeconomic statistics, the entropy value method is used to obtain the indicator weights to construct a heat wave social vulnerability evaluation index system and conduct vulnerability assessments and classifications. The results show that: ① The heat wave indicators in Nanchong show an increasing trend, although there is a low period of heat waves from 1980 to 1995. Additionally, there are significant mutations in the number of days, frequency, and intensity of high-temperature heat waves from 2009 to 2011, which may be caused by the abnormal high-pressure belt in the mid-latitude. ② The distribution of exposure, sensitivity, and adaptability in Nanchong City, under high temperatures, is uneven in space. Generally, the indicators in the north are lower than those in the south. ③ The high-vulnerability counties are mainly distributed in the east and west of Nanchong, the proportion of the medium social vulnerability index areas are more than a half, while the dominant factor in the distribution pattern is natural factors. ④ The Western Pacific Subtropical High (WPSH) anomaly directly led to the extremely high temperature in Nanchong in the summer of 2022, and the urbanization process index shows a significant positive correlation with the trend of high temperatures and heat waves in Nanchong. Full article

Desertification vulnerability and contributing factors are of global concern. This study analyzed the spatial and temporal distribution of net primary productivity (NPP), precipitation, and temperature from 1985 to 2015. The rain use efficiency (RUE) of vegetation was selected as an indicator; and desertification vulnerability and contributors were evaluated with the Mann–Kendall test (M–K test) and the Thornthwaite–Memorial model. The results showed that NPP was lower in that years that had lower precipitation and higher temperatures, and vice versa. NPP was spatially consistent with precipitation distribution and roughly opposite to the spatial distribution of the annual change rate of temperature. The desertification vulnerability decreased from west to east, among which both the western sub–region (WSR) and the central sub–region (CSR) had the largest proportion of regions with high desertification vulnerability. On the other hand, the eastern sub–region (ESR) mostly comprises areas with extremely low or low desertification vulnerability. The vulnerability contributors for desertification differed among each sub–region. The desertified regions in WSR and ESR were mainly influenced by human activity (HA), but primarily driven by the combined impact of Precipitation–Temperature (PT) and HA in CSR. The south–east part of the CSR was only affected by HA, whereas the lesser affected regions in the study area were affected by PT and HA simultaneously. The study provides recommendations for the improvement of regional ecological environments to prevent future disasters. Full article

The frequent occurrence and spread of wildfires pose a serious threat to the ecological environment and urban development. Therefore, assessing regional wildfire susceptibility is crucial for the early prevention of wildfires and formulation of disaster management decisions. However, current research on wildfire susceptibility primarily focuses on improving the accuracy of models, while lacking in-depth study of the causes and mechanisms of wildfires, as well as the impact and losses they cause to the ecological environment and urban development. This situation not only increases the uncertainty of model predictions but also greatly reduces the specificity and practical significance of the models. We propose a comprehensive evaluation framework to analyze the spatial distribution of wildfire susceptibility and the effects of influencing factors, while assessing the risks of wildfire damage to the local ecological environment and urban development. In this study, we used wildfire information from the period 2013–2022 and data from 17 susceptibility factors in the city of Guilin as the basis, and utilized eight machine learning algorithms, namely logistic regression (LR), artificial neural network (ANN), K-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM), and eXtreme gradient boosting (XGBoost), to assess wildfire susceptibility. By evaluating multiple indicators, we obtained the optimal model and used the Shapley Additive Explanations (SHAP) method to explain the effects of the factors and the decision-making mechanism of the model. In addition, we collected and calculated corresponding indicators, with the Remote Sensing Ecological Index (RSEI) representing ecological vulnerability and the Night-Time Lights Index (NTLI) representing urban development vulnerability. The coupling results of the two represent the comprehensive vulnerability of the ecology and city. Finally, by integrating wildfire susceptibility and vulnerability information, we assessed the risk of wildfire disasters in Guilin to reveal the overall distribution characteristics of wildfire disaster risk in Guilin. The results show that the AUC values of the eight models range from 0.809 to 0.927, with accuracy values ranging from 0.735 to 0.863 and RMSE values ranging from 0.327 to 0.423. Taking into account all the performance indicators, the XGBoost model provides the best results, with AUC, accuracy, and RMSE values of 0.927, 0.863, and 0.327, respectively. This indicates that the XGBoost model has the best predictive performance. The high-susceptibility areas are located in the central, northeast, south, and southwest regions of the study area. The factors of temperature, soil type, land use, distance to roads, and slope have the most significant impact on wildfire susceptibility. Based on the results of the ecological vulnerability and urban development vulnerability assessments, potential wildfire risk areas can be identified and assessed comprehensively and reasonably. The research results of this article not only can improve the specificity and practical significance of wildfire prediction models but also provide important reference for the prevention and response of wildfires. Full article

As drought vulnerability assessment is fundamental to risk management, it is urgent to develop scientific and reasonable assessment models to determine such vulnerability. A vulnerability curve is the key to risk assessment of various disasters, connecting analysis of hazard and risk. To date, the research on vulnerability curves of earthquakes, floods and typhoons is relatively mature. However, there are few studies on the drought vulnerability curve, and its application value needs to be further confirmed and popularized. In this study, on the basis of collecting historical disaster data from 52 drought events in China from 2009 to 2013, three drought remote sensing indexes were selected as disaster-causing factors; the affected population was selected to reflect the overall disaster situation, and five typical regional drought vulnerability curves were constructed. The results showed that (1) in general, according to the statistics of probability distribution, most of the normalized difference vegetation index (NDVI) and the temperature vegetation drought index (TVDI) variance ratios were concentrated between 0 and ~0.15, and most of the enhanced vegetation index (EVI) variance ratios were concentrated between 0.15 and ~0.6. From a regional perspective, the NDVI and EVI variance ratio values of the northwest inland perennial arid area (NW), the southwest mountainous area with successive years of drought (SW), and the Hunan Hubei Jiangxi area with sudden change from drought to waterlogging (HJ) regions were close and significantly higher than the TVDI variance ratio values. (2) Most of the losses (drought at-risk populations, DRP) were concentrated in 0~0.3, with a cumulative proportion of about 90.19%. At the significance level, DRP obeys the Weibull distribution through hypothesis testing, and the parameters are optimal. (3) The drought vulnerability curve conformed to the distribution rule of the logistic curve, and the line shape was the growth of the loss rate from 0 to 1. It was found that the arid and ecologically fragile area in the farming pastoral ecotone (AP) region was always a high-risk area with high vulnerability, which should be the focus of drought risk prevention and reduction. The study reduces the difficulty of developing the vulnerability curve, indicating that the method can be widely used to other regions in the future. Furthermore, the research results are of great significance to the accurate drought risk early warning or whether to implement the national drought disaster emergency rescue response. Full article

The impact of global climate change has intensified, and the frequent occurrence of meteorological disasters has posed a serious challenge to crop production. This article conducts an integrated risk assessment of agricultural drought disasters in the main grain-producing areas of Jilin Province using the temperature and precipitation data of the study area from 1955 to 2020, the sown area of crops, historical disaster data, regional remote sensing images, and statistical yearbook data. The agricultural drought integrated risk assessment model was built around four factors: drought hazards, vulnerability of hazard-bearing bodies, sensitivity of disaster-pregnant environments, and stability of disaster mitigation capacity. The results show that the study area has shown a trend of changing from wet to dry and then wet over the past 66 years, with the occasional occurrence of severe drought, and a decreasing trend at a rate of −0.089. (10a)⁻¹ overall. The integrated risk of drought in the study area exhibits regional clustering, and the overall risk level has some relationship spatially with the regional geological tectonic units, with the high-risk level concentrated in the central area of Song Liao Basin and close to the geological structure of Yishu Graben and the low risk level concentrated in the marginal area of Song Liao Basin. Based on the results of the risk factor analysis, integrated risk prevention suggestions for drought in the main grain-producing areas of Jilin Province were put forward from four aspects. Fine identification and evaluation of high-risk areas of agricultural drought can provide a quantitative basis for effective drought resistance activities in relevant areas. Full article