Search Results (78)

Extreme precipitation events severely impact agriculture, reducing yields and land use efficiency. The spatiotemporal distribution of Total Column Water Vapor (TCWV), the primary gaseous form of water, directly influences sustainable agricultural management. This study, through multi-source data fusion, employs methods including the Mann–Kendall test, sliding change-point detection, wavelet transform, pixel-scale trend estimation, and linear regression to analyze the spatiotemporal dynamics of global TCWV from 1959 to 2023 and its impacts on agricultural systems, surpassing the limitations of single-method approaches. Results reveal a global TCWV increase of 0.0168 kg/m²/year from 1959–2023, with a pivotal shift in 2002 amplifying changes, notably in tropical regions (e.g., Amazon, Congo Basins, Southeast Asia) where cumulative increases exceeded 2 kg/m² since 2000, while mid-to-high latitudes remained stable and polar regions showed minimal content. These dynamics escalate weather risks, impacting sustainable agricultural management with irrigation and crop adaptation. To enhance prediction accuracy, we propose a novel hybrid model combining wavelet transform with LSTM, TCN, and GRU deep learning models, substantially improving multidimensional feature extraction and nonstationary trend capture. Comparative analysis shows that WT-TCN performs the best (MAE = 0.170, R² = 0.953), demonstrating its potential for addressing climate change uncertainties. These findings provide valuable applications for precision agriculture, sustainable water resource management, and disaster early warning. Full article

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

Understanding the time-lagged response of land subsidence to groundwater level fluctuations and subsurface strain variations is crucial for uncovering its underlying mechanisms and enhancing disaster early warning capabilities. This study focuses on Dangshan County, Anhui Province, China, and systematically analyzes the spatio-temporal evolution of land subsidence from 2018 to 2024. A total of 207 Sentinel-1 SAR images were first processed using the Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technique to generate high-resolution surface deformation time series. Subsequently, the seasonal-trend decomposition using the LOESS (STL) model was applied to extract annual cyclic deformation components from the InSAR-derived time series. To quantitatively assess the delayed response of land subsidence to groundwater level changes and subsurface strain evolution, time-lagged cross-correlation (TLCC) analysis was performed between surface deformation and both groundwater level data and distributed fiber-optic strain measurements within the 5–50 m depth interval. The strain data was collected using a borehole-based automated distributed fiber-optic sensing system. The results indicate that land subsidence is primarily concentrated in the urban core, with annual cyclic amplitudes ranging from 10 to 18 mm and peak values reaching 22 mm. The timing of surface rebound shows spatial variability, typically occurring in mid-February in residential areas and mid-May in agricultural zones. The analysis reveals that surface deformation lags behind groundwater fluctuations by approximately 2 to 3 months, depending on local hydrogeological conditions, while subsurface strain changes generally lead surface subsidence by about 3 months. These findings demonstrate the strong predictive potential of distributed fiber-optic sensing in capturing precursory deformation signals and underscore the importance of integrating InSAR, hydrological, and geotechnical data for advancing the understanding of subsidence mechanisms and improving monitoring and mitigation efforts. Full article

Seasonal climate forecasts are an essential tool for providing early insight into weather-related impacts and supporting decision-making in sectors such as agriculture, energy, and disaster management. Accurate representation of atmospheric circulation at the seasonal scale is essential, especially in regions such as the Eastern Mediterranean, where complex synoptic patterns drive significant climate variability. The aim of this study is to perform a comparison of weather type classifications between ERA5 reanalysis and seasonal forecasts in order to assess the ability of seasonal data to capture the synoptic patterns over the Eastern Mediterranean. For this purpose, we introduce a regional seasonal forecasting framework based on the state-of-the-art Advanced Research WRF (WRF-ARW) model. A series of sensitivity experiments were also conducted to evaluate the robustness of the model’s performance under different configurations. Moreover, the ability of seasonal data to reproduce observed trends in weather types over the historical period is also examined. The classification results from both ERA5 and seasonal forecasts reveal a consistent dominance of anticyclonic weather types throughout most of the year, with a particularly strong signal during the summer months. Model evaluation indicates that seasonal forecasts achieve an accuracy of approximately 80% in predicting the daily synoptic condition (cyclonic or anticyclonic) up to three months in advance. These findings highlight the promising skill of seasonal datasets in capturing large-scale circulation features and their associated trends in the region. Full article

In the South Pacific, an increase in the frequency of climate hazards has resulted in worsened human and animal health outcomes, revealing the need for strengthened early warning to increase hazard preparedness. As Vanuatu is one of the most at-risk countries to natural disasters, an early warning system (EWS) for climate hazards is essential to support industries and communities. Notably, climate variability has been found to exacerbate communicable disease burden and compromise livestock health and productivity; however, forecasting of such hazards and their compounding effects has not been developed in Vanuatu. Therefore, our study aims to explore EWSs that monitor and predict the impact of climate variables on malaria incidence and cattle heat stress in Vanuatu. Using monthly precipitation and temperature, a Bayesian model was developed to predict provincial malaria case burden in Vanuatu. Additionally, this study developed a weekly forecasting model to predict periods of cattle heat stress. This model used the Heat Load Index (HLI) as a proxy for heat stress to identify periods of increased heat load and antecedent conditions for cattle heat stress across the provinces. This study was successful in establishing proof-of-concept risk forecasts during selected case study periods: January 2020 and January 2016 for malaria transmission and cattle heat stress, respectively. To contribute towards a future multi-hazard EWS framework for climate hazards in Vanuatu, bulletins for predicted climate-based malaria transmission and cattle heat stress risk were developed to inform key decision makers. Intended to enhance preparedness for malaria outbreaks and cattle heat stress events, this study’s exploration of EWSs can support the resilience of Vanuatu’s public health and agricultural sectors in the face of escalating climate challenges. Full article

Wind and humidity are two very vital climate variables that have received little attention by researchers regarding Uganda. This study sought to close this knowledge gap by exposing the dynamics and relationship of windspeed and humidity in Uganda from 1980 to 2023 as well as predicting the future trends from 2025 to 2040. Using high-resolution gridded windspeed and relative humidity (RH) data for the past and seven downscaled and bias-adjusted global climate models within the coupled model intercomparison project phase 6 framework under two shared socioeconomic pathways (SSPs), SPP245 and SSP585, we employed variability, trend, and correlational analyses to expose the wind–humidity nexus at a monthly scale. The results showed a domination of winds of the calm to gentle breeze category across the country, with a maximum magnitude of 6 knots centered over eastern Lake Victoria and eastern Uganda over the historical period. RH was characterized by high to very high magnitudes, except the northern tips of the country, where RH was low for the historical period. Seasonally, both windspeed and RH demonstrated modest variations, with June–July–August (JJA) and September–October–November (SON) having the highest magnitudes, respectively. Similarly, both variables are forecasted to have significant distribution and magnitude changes. For example, windspeeds will be dominated by decreasing trends, while RH will be dominated by increasing trends. Finally, the correlation analysis revealed a strong negative correlation between windspeeds and RH for both the past and future periods, except for the March–April–May (MAM) and September–October–November (SON) seasons, where positive correlations were observed. These findings have practical applications in agriculture, hydrology, thermal comfort, disaster management, and forecasting, especially in the northern, eastern, and Lake Victoria basin regions. The study recommends further finer-scale research at various atmospheric levels and for prolonged future periods and scenarios. Full article

Extreme weather prediction plays a crucial role in agricultural production and disaster prevention. This study proposes a lightweight extreme weather early warning model based on UAV cruise monitoring, a density-aware attention mechanism, and edge computing. Reinforcement learning is utilized to optimize UAV cruise paths, while a Transformer-based model is employed for weather prediction. Experimental results demonstrate that the proposed method achieves an overall prediction accuracy of 0.91, a precision of 0.93, a recall of 0.88, and an F1-score of 0.91. In the prediction of different extreme weather events, the proposed method attains an accuracy of 0.89 for strong wind conditions, 0.92 for hail, and 0.89 for late spring cold, all outperforming state-of-the-art methods. These results validate the effectiveness and applicability of the proposed approach in extreme weather forecasting. Full article

Accurate weather forecasting is essential for various industries, particularly in sectors like energy, agriculture, and disaster management. In Slovenia, weather predictions are crucial for estimating electrical current transmission efficiency through power lines and ensuring the reliable supply of electricity to consumers. This study focuses on quantifying measurement uncertainty in meteorological forecasts generated by the CALMET model, specifically addressing its impact on energy transmission reliability. The research highlights those local factors, such as topography, that contribute significantly to measurement uncertainty, which affects the accuracy of weather forecasts. The study examines meteorological parameters like temperature, wind speed, and solar radiation, identifying how environmental variations lead to fluctuations in forecast reliability. Understanding these uncertainties is critical for improving the precision of forecasts, especially for energy transmission, where even small errors can have substantial consequences. The primary goal of this study is to enhance forecast reliability by addressing measurement uncertainty. By improving the interpretation of data, refining measurement methods, and integrating advanced models, the study proposes ways to reduce uncertainty. These improvements could support better decision-making in energy transmission and other sectors that rely on accurate weather predictions. Ultimately, the findings suggest that addressing measurement uncertainty is key to ensuring more dependable and accurate forecasting in critical industries. Full article

The vulnerability of Social–Ecological Systems (SES) is a frontier research topic in the field of geography. Research on drought vulnerability has emerged as a key area of focus in the study of SES vulnerability, and it has increasingly been recognized as a critical step in formulating policies for drought prevention and mitigation. In this study, the indicator system for drought vulnerability evaluation of SES in the Three-River Headwaters Region (TRHR) was established. This paper revealed the drought vulnerability evolution process and characteristics, and key driving indicators of SES at county-town-village spatial scales in six time periods of 1990, 2000, 2010, 2015, 2020, and 2023, and predicted the drought vulnerability of SES in 2050 under two scenarios. Results indicate that the average drought vulnerability in the TRHR decreased from 0.526 in 1990 to 0.444 in 2023. Compared to 1990, among the 82 selected towns, 85.37% experienced a decline in 2023, and among the 152 selected villages, 95.39% showed a reduction in 2023. Hot spots of drought vulnerability were concentrated in the southeast of the TRHR, while cold spots were in the northwest. From 1990 to 2000, the drought vulnerability of counties and towns in the TRHR increased, but it decreased between 2000 and 2023. In 1990, Henan County exhibited the highest drought vulnerability at the county level. Waeryi Town in Jiuzhi County had the highest vulnerability among towns, while Suojia Town in Zhidoi County had the lowest. Of the 152 selected villages, 41.45% exhibited relatively high or high levels of drought vulnerability, while 23.68% showed relatively low levels. In 2023, Jiuzhi County became the most vulnerable county, with Baiyu Town in Jiuzhi County ranking highest among towns and Suojia Town in Zhidoi County remaining the least vulnerable. At the village level, 22.37% exhibited relatively high or high vulnerability, whereas 42.11% showed relatively low or low levels. Drought disaster records, the proportion of agricultural and animal husbandry output value, the proportion of grassland, the proportion of large livestock, and the per capita disposable income surface are the key factors influencing drought vulnerability in the TRHR. By 2050, under the first scenario, the average drought vulnerability of the TRHR is projected to be 0.428, indicating a medium level, while the second scenario predicts a further reduction to 0.350, representing a relatively low level. The adaptive governance strategies to mitigate drought vulnerability in the TRHR include developing an integrated drought management system; establishing an ecological management, protection, and financial support model; and so on. Overall, this paper can provide scientific references and policy recommendations for policymakers and researchers on the aspects of drought vulnerability and sustainable development of SES. Full article

In recent years, extreme weather events have become more frequent and severe, making it crucial to apply meteorological and climate information services to mitigate the associated losses. However, given limited resources, it is essential to assess the potential value these services can generate while considering uncertainties. Since the impact of disasters and weather prediction accuracy is uncertain, and end-users’ decisions of disaster prevention, resource allocation, and operational planning are costly, the expected returns of acting according to weather forecasting information need to outweigh the cost to make decision-makers act. This study evaluates the direct economic value of meteorological information services for agricultural disaster prevention, with a focus on typhoon preparedness, using the cost-loss model. The results show that the current annual economic value of these services is NTD 77.28 million. Significant benefits can be gained by increasing the proportion of avoidable losses and improving forecast accuracy. A 10% increase in the proportion of avoidable losses, possibly due to the application of innovative technology and the extension of leading time, results in an 8% rise in economic value, while a 50% increase leads to a 38% increase. Moreover, enhancing the forecast accuracy, which is currently at 73.18%, by an additional 50% could boost economic value by up to 34%. From a practical perspective, unless agricultural output is completely protected from weather events (such as indoor horticultural crops), the potential for reducing avoidable losses remains limited. Consequently, the findings underscore the importance of government efforts to promote the establishment of additional weather observation stations in order to improve forecast accuracy, boost farmers’ confidence of application from public meteorological information services, and maximize the impact of meteorological services in reducing agricultural losses and enhancing disaster preparedness. Full article

Monitoring river systems is crucial for understanding and managing water resources, predicting natural disasters, and maintaining ecological balance. Assessment of heavy metal pollution derived valuable data which are critical for the environmental management and regulatory compliance of the Jukskei River. Heavy elements were evaluated in the Jukskei River for seasonal impact, potential health risks, and contamination level with concentration levels ranging from 6900 mg/kg iron (Fe) to 0.85 mg/kg cadmium (Cd) in the dry sampling season and 6900 mg/kg Fe to 0.26 mg/kg Cd in the wet season. Enrichment factor analysis indicated high contamination levels of Fe and Pb in both dry and wet seasons. Moreover, pollution indicators revealed extremely high contamination of geo-accumulation and enrichment factors in the downstream to upstream in both seasons with a mild contamination factor for mercury (Hg). Principal Component Analysis revealed anthropogenic sources of arsenic (As), Cd, and Pb due to wastewater and agricultural pesticide application while Thorium (Th), uranium (U) and Hg were attributed as a results of gold mining activities. ANOVA and Pearson correlation analysis showed a high and moderate link between As–Pb, Cd–Pd, and As–Hg, which are significantly correlated. The potential ecological risk index assessment revealed a significant impact of heavy metals on the freshwater ecosystem. Full article

A farm-specific early warning system has been developed to mitigate agricultural damage caused by climate change. This system utilizes weather data at the farm level to predict crop growth, forecast weather disaster risks, and provide risk alerts to farmers and local governments. For effective implementation, local governments must lead operating early warning services that reflect regional agricultural characteristics and farmers’ needs, while the central government provides foundational data. The system connects data from each region to the cloud, enabling the establishment of a nationwide integrated service operation framework that includes the central government, metropolitan cities, municipalities, and farmers. Full article

China is the world’s largest agricultural country and is also deeply affected by extreme weather. Water infrastructure is a crucial solution to improve the climate adaptability of the agricultural industry. This study aimed to explore the above adaptive processes of the agricultural industry from a resilience perspective. This study builds a multi-level system dynamics (SD) model to assess the development of the agricultural industry and water infrastructure, predict the future resilience development trend, identify the key influencing factors, and simulate the effectiveness of different water infrastructure measures. The results show that (1) water infrastructure involving various climate adaptation measures significantly promotes the development of the agricultural industry. (2) Agricultural output, water infrastructure investment, and other fixed asset investments strongly improve the resilience, and the impact of the crop planting area is limited. (3) The resilience level is higher under the eco-friendly water conservation scenario than in the water supply security scenario and flood disaster prevention scenario. Such information will promote the sustainable development of the agricultural industry and future climate adaptation policy-making. Full article

The accuracy of monthly runoff predictions is crucial for decision-making and efficiency in various areas, such as water resources management, flood control and disaster mitigation, hydraulic engineering scheduling, and agricultural irrigation. Therefore, in order to further improve the accuracy of monthly runoff prediction, aiming at the problem that the traditional Stacking ensemble method ignores (the base model correlation between different folds in the prediction process), this paper proposes a novel Stacking multi-scale ensemble learning model (SWA–FWWS) based on random weight averaging and a K-fold cross-validation weighted ensemble. Then, it is evaluated and compared with base models and other multi-model ensemble models in the runoff prediction of two upstream and downstream reservoirs in a certain river. The results show that the proposed model exhibits excellent performance and adaptability in monthly runoff prediction, with an average RMSE reduction of 6.44% compared to traditional Stacking models. This provides a new research direction for the application of ensemble models in reservoir monthly runoff prediction. Full article

Agriculture is the backbone of a country and plays a vital role in shaping its economic performance. Factors such as natural disasters, extreme weather changes, pests, and soil quality significantly impact productivity, often leading to economic losses. Accurate predictions in agricultural practices, particularly crop recommendations, can substantially boost productivity and resource management. This research aims to develop a robust crop recommendation system using ensemble learning (EL), which integrates multiple machine learning (ML) models for improved performance. This study utilizes two datasets: a real-time dataset available on Kaggle, collected using IoT sensors, and a synthetic dataset generated using CTGAN. These datasets provide crop recommendations for 22 different crops, based on key features like nitrogen, phosphorus, potassium, soil pH, humidity, and rainfall. The performance of various ML models—such as linear regression (LR), support vector machine (SVM), decision tree (DT), naïve Bayes (NB), K-nearest neighbor (KNN), random forest (RF), extra tree classifier, XGBoost, and gradient boost—is compared with that of EL models, including voting, bagging, boosting, and stacking ensemble techniques. The stacking ensemble model achieved the highest accuracy at 99.36% across all ensemble techniques. By further optimizing this model using the Optuna hyper-parameter tuning technique, the accuracy was improved to 99.43%. Full article