Search Results (18,089)

Rainstorms and blizzards are common extreme weather events occurring in the eastern Tibet region. Their complex dynamic and thermodynamic mechanisms present challenges for regional meteorological research and forecasting. Based on station observation data and ERA5 atmospheric reanalysis datasets, a diagnostic analysis of the heavy rain and snow event in eastern Tibet from 24 to 27 October 2022 was conducted. The results indicate that (1) the influence of the cloud systems surrounding the Bay of Bengal storm “Sitrang” was a significant factor contributing to the occurrence of this heavy rain and snow weather. (2) Sustained stability of the southern branch trough and the western Pacific subtropical high favored the establishment and maintenance of the mid-level jet stream ahead of the storm. Storm “Sitrang” transported warm and moist air to eastern Tibet through the southwest mid-level jet stream, providing favorable moisture, dynamic, and thermal conditions for the heavy rain and snow. (3) Most importantly, symmetrical instability generated by the inclined motion of the storm’s warm and moist air emerged as the decisive mechanism driving the occurrence and development of the heavy rain and snow. Full article

Erosive rainfall is essential for initiating surface runoff and soil erosion to occur. The analysis on its temporal and spatial distribution characteristics is crucial for calculating rainfall erosivity, predicting soil erosion, and implementing soil and water conservation. This study utilized daily rainfall observation data from 90 meteorological stations in Henan from 1981 to 2020, and conducted geostatistical analysis, M-K mutation test analysis, and wavelet analysis on erosive rainfall to reveal the spatiotemporal distribution characteristics over the past 40 years. Building on this foundation, the correlation between erosive rainfall, rainfall, and rainfall erosivity were further explored. The findings indicated that the average annual rainfall in Henan Province varied between 217.66 mm and 812.78 mm, with an average yearly erosive rainfall of 549.24 mm and a standard deviation of 108.32 mm. Erosive rainfall constitutes for 77% of the average annual rainfall on average, and the analysis found that erosive rainfall is highly correlated with rainfall volume. The erosive rainfall increased from northwest to southeast, and had the same spatial distribution characteristics as the total rainfall. The number of days with erosive rainfall was 20.5 days and the annual average sub-erosive rainfall was 26.86 mm. The average annual rainfall erosivity in Henan Province ranged from 1341.81 to 6706.64 MJ·mm·ha⁻¹·h⁻¹, averaging at 3264.63 MJ·mm·ha⁻¹·h⁻¹. Both the erosive rainfall and the rainfall erosivity are influenced by the monsoon, showing a unimodal trend, with majority of the annual total attributed to rainfall erosivity from June to September, amounting to 80%. The results can provide a basis for forecasting of heavy rainfall events, soil conservation and planning, ecological treatment, and restoration. Full article

Due to the supply problems of fossil-based energy sources, the tendency towards alternative energy sources is relatively high. For this reason, the use of solar energy systems is increasing today. This study combines experimental data and machine learning algorithms to evaluate the energy performance of four different photovoltaic (PV) panel designs (monocrystalline, polycrystalline, flexible, and transparent) under harsh environmental conditions on Horseshoe Island (Antarctica). In this research, the effects of environmental factors, such as solar radiation, temperature, humidity, and wind speed, on the panels were analyzed. Electrical power output of the PV panels are analyzed using six machine learning models. Random forest (RF) and CatBoost (CB) models showed the highest accuracy and reliability among these models. According to the experimental results, Monocrystalline PV provided the highest electrical power (20.5 Watts on average), and Flexible PV provided the highest energy efficiency (19.67%). However, Flexible PV was observed to have higher surface temperatures compared to the other panel types. Furthermore, using Monocrystalline PV resulted in an average reduction of 4.1 tons of CO₂ emissions per year, demonstrating the positive environmental impact of renewable energy systems. Thanks to this study, renewable energy research for temporary stations in Antarctica will focus on explainable and interpretable artificial intelligence models that will provide an understanding of the factors affecting the energy performance of PV panels. The research results will be an important guide for optimizing energy consumption, management, and demand forecasting in temporary research stations in Antarctica. Full article

In the context of global warming, climate strongly affects forest fires. With long-term and strict fire prevention policies, China has become a unique test arena for comprehending the role of climatic variables in affecting forest fires. Here, using GIS spatial analysis, Pearson correlation, and geographical detector, the climate drivers of forest fires in China are revealed using the 2003–2022 active fire data from the MODIS C6 and climate products from CHELSA (Climatologies at high resolution for the Earth’s land surface areas). The main conclusions are as follows: (1) In total, 82% of forest fires were prevalent in the southern and southwestern forest regions (SR and SWR) in China, especially in winter and spring. (2) Forest fires were mainly distributed in areas with a mean annual temperature and annual precipitation of 14~22 °C (subtropical) and 800~2000 mm (humid zone), respectively. (3) Incidences of forest fires were positively correlated with temperature, potential evapotranspiration, surface downwelling shortwave flux, and near-surface wind speed but negatively correlated with precipitation and near-surface relative humidity. (4) Temperature and potential evapotranspiration dominated the roles in determining spatial variations of China’s forest fires, while the combination of climate variables complicated the spatial variation. This paper not only provides new insights on the impact of climate drives on forest fires, but also offers helpful guidance for fire management, prevention, and forecasting. Full article

Background: Diabetes is a metabolic disorder characterized by increased blood sugar levels. Early detection of diabetes could help individuals to manage and delay the progression of this disorder effectively. Machine learning (ML) methods are important in forecasting the progression and diagnosis of different medical problems with better accuracy. Although they cannot substitute the work of physicians in the prediction and diagnosis of disease, they can be of great help in identifying hidden patterns based on the results and outcome of disease. Methods: In this research, we retrieved the PIMA dataset from the Kaggle repository, the retrieved dataset was further processed for applied PCA, heatmap, and scatter plot for exploratory data analysis (EDA), which helps to find out the relationship between various features in the dataset using visual representation. Four different ML algorithms Random Forest (RF), Decision Tree (DT), Naïve Bayes (NB), and Logistic regression (LR) were implemented on Rattle using Python for the prediction of diabetes among the female population. Results: Results of our study showed that RF performs better in terms of accuracy of 80%, precision of 82%, error rate of 20%, and sensitivity of 88% as compared to other developed models DT, NB, and LR. Conclusions: Diabetes is a common problem prevailing across the globe, ML-based prediction models can help in the prediction of diabetes much earlier before the worsening of the condition. Full article

The research initiatives envisaged by the PNRR (Italian National Recovery and Resilience Plan) include the creation of innovation ecosystems to promote collaboration between universities, research centers, and local institutions with a focus on territorial integration and sustainability. The NODES Project (Nord-Ovest Digitale E Sostenibile) is part of this research. In this context, the Laboratory of Geomatics of the University of Pavia, in collaboration with other partners, deals with the study of the suitability maps for the renowned Pinot Noir wine. To achieve this, we considered different thematic input layers: elevation, slope, aspect, soil depth and type, Land Use Land Cover maps, NDVI, and current and forecast climatic aspects. An important thematic layer is concerned with the air temperature, which requires high spatial and temporal resolution. In the selected study area, the Lombardy Region has some accurate and reliable weather stations with high temporal resolution but low spatial resolution (7 stations in 648.5 square kilometers, i.e., one every 92 square kilometers). In addition, we considered Land Surface Temperature (LST) MODIS maps: these maps have good spatial resolution but present some voids and low temporal resolution. From the first evaluations made, the temperatures reported by MODIS are not always in excellent agreement with the ones from monitoring stations. To evaluate MODIS as a data source, we decided to use Kriging spatio-temporal interpolation. Starting from multitemporal MODIS data matrices, we interpolate them to estimate the temperature of the weather stations, in order to compare the estimation with the real weather station data, thus allowing the validation of MODIS data. Full article

Time series forecasting, particularly within the Internet of Things (IoT) and hydrological domains, plays a critical role in predicting future events based on historical data, which is essential for strategic decision making. Effective flood forecasting is pivotal for optimal water resource management and for mitigating the adverse impacts of flood events. While deep learning methods have demonstrated exceptional performance in time series prediction through advanced feature extraction and pattern recognition, they encounter significant limitations when applied to scenarios with sparse data, especially in flood forecasting. The scarcity of historical data can severely hinder the generalization capabilities of traditional deep learning models, presenting a notable challenge in practical flood prediction applications. To address this issue, we introduce MetaTrans-FSTSF, a pioneering meta-learning framework that redefines few-shot time series forecasting. By innovatively integrating MAML and Transformer architectures, our framework provides a specialized solution tailored for the unique challenges of flood prediction, including data scarcity and complex temporal patterns. This framework goes beyond standard implementations, delivering significant improvements in predictive accuracy and adaptability. Our approach leverages Model-Agnostic Meta-Learning (MAML) to enable rapid adaptation to new forecasting tasks with minimal historical data. Our inner architecture is a Transformer-based meta-predictor capable of capturing intricate temporal dependencies inherent in flood time series data. Our framework was evaluated using diverse datasets, including a real-world hydrological dataset from a small catchment area in Wuyuan, China, and other benchmark time series datasets. These datasets were preprocessed to align with the meta-learning approach, ensuring their suitability for tasks with limited data availability. Through extensive evaluation, we demonstrate that MetaTrans-FSTSF substantially improves predictive accuracy, achieving a reduction of up to 16%, 19%, and 8% in MAE compared to state-of-the-art methods. This study highlights the efficacy of meta-learning techniques in overcoming the limitations posed by data scarcity and enhancing flood forecasting accuracy where historical data are limited. Full article

Air pollution in Jakarta, one of the most polluted cities globally, has reached critical levels, with PM_2.5 concentrations exceeding the WHO guidelines and posing significant health risks. Accurate forecasting of PM_2.5 is crucial for effective air quality management and public health interventions. PM_2.5 exhibits significant nonlinear fluctuations; thus, this study employed two machine learning approaches: self-exciting threshold autoregressive tree (SETAR-Tree) and long short-term memory (LSTM). The SETAR-Tree model integrates regime-switching capabilities with decision tree principles to capture nonlinear patterns, while LSTM models long-term dependencies in time-series data. The results showed that: (1) SETAR-Tree outperformed LSTM, achieving lower RMSE (0.1691 in-sample, 0.2159 out-sample) and MAPE (2.83% in-sample, 2.98% out-sample) compared to LSTM’s RMSE (0.2038 in-sample, 0.2399 out-sample) and MAPE (3.48% in-sample, 4.05% out-sample); (2) SETAR-Tree demonstrated better responsiveness to sudden regime changes, capturing complex pollution patterns influenced by meteorological and anthropogenic factors; (3) PM_2.5 in Jakarta often exceeds the WHO limits, highlighting this study’s importance in supporting strategic planning and providing an early warning system to reduce outdoor activity during extreme pollution. Full article

Food and water security are critical challenges in Pakistan, exacerbated by rapid population growth, climate variability, and limited resources. This study explores the application of machine learning techniques to address these issues. We specifically examine the dimensions of food and water security in Pakistan, employing data-driven methods to enhance crop yield predictions, food production forecasting, and water resource management. Using secondary data, we refine machine learning models, such as random forest and linear regression, to analyze water availability, crop yield, and crop production. These models aim to optimize resource distribution, improve irrigation efficiency, and minimize water waste. We propose developing AI-based predictions to address food and water crises proactively. Our findings indicate that food insecurity persists in Pakistan, worsened by uneven distribution. Given the country’s high dependence on irrigation for crop production, we analyze the impact of population growth on food production and water demand. We recommend a comprehensive strategy that includes infrastructure development, improved water use efficiency in agriculture, and policy adjustments to balance food imports and exports. Full article

The time series of agricultural prices exhibit brevity and considerable volatility. Considering that traditional time series models and machine learning models are facing challenges in making predictions with high accuracy and robustness, this paper proposes a Light gradient boosting machine model based on the boosting ensemble learning algorithm to predict prices for three representative types of fresh agricultural products (bananas, beef, crucian carp). The prediction performance of the Light gradient boosting machine model is evaluated by comparing it against multiple benchmark models (ARIMA, decision tree, random forest, support vector machine, XGBoost, and artificial neural network) in terms of accuracy, generalizability, and robustness on different datasets and under different time windows. Among these models, the Light gradient boosting machine model is shown to have the highest prediction accuracy and the most stable performance across three different datasets under both long-term and short-term time windows. As the time window length increases, the Light gradient boosting machine model becomes more advantageous for effectively reducing error fluctuation, demonstrating better robustness. Consequently, the model proposed in this paper holds significant potential for forecasting fresh agricultural product prices, thereby facilitating the advancement of precision and sustainable farming practices. Full article

Climate prediction is of fundamental importance to various sectors of society and the economy, as it can predict the likelihood of droughts or excessive rainfall in vulnerable regions. Climate models are useful tools in producing reliable climate forecasts, which have become increasingly vital due to the rising impacts of climate change. As global temperatures rise, changes in precipitation patterns are expected, increasing the importance of reliable seasonal forecasts to support planning and adaptation efforts. In this study, we evaluated the performance of NOAA/GFDL models from CMIP6 simulations in representing the climate of South America under three configurations: atmosphere-only, coupled ocean-atmosphere, and Earth system. Our analysis revealed that all three configurations successfully captured key climatic features, such as the South Atlantic Convergence Zone (SACZ), the Bolivian High, and the Intertropical Convergence Zone (ITCZ). However, coupled models exhibited larger errors and lower correlation (below 0.6), particularly over the ocean and the South American Monsoon System, which indicates a poor representation of precipitation compared with atmospheric models. The coupled models also overestimated upward motion linked to the southern Hadley cell during austral summer and underestimated it during winter, whereas the atmosphere-only models more accurately simulated the Walker circulation, showing stronger vertical motion around the Amazon. In contrast, the coupled models simulated stronger upward motion over Northeast Brazil, which is inconsistent with reanalysis data. Moreover, we provided insights into how model biases may evolve under climate change scenarios. Future climate projections for the mid-century period (2030–2060) under the SSP2-4.5 and SSP5-8.5 scenarios indicate significant changes in the global energy balance, with an increase of up to 0.9 W/m². Additionally, the projections reveal significant warming and drying in most of the continent, particularly during the austral spring, accompanied by increases in sensible heat flux and decreases in latent heat flux. These findings highlight the risk of severe and prolonged droughts in some regions and intensified rainfall in others. By identifying and quantifying the biases inherent in climate models, this study provides insights to enhance seasonal forecasts in South America, ultimately supporting strategic planning, impact assessments, and adaptation strategies in vulnerable regions. Full article

Intelligent logistical systems are crucial for adapting to technological advancements and global supply chains, particularly at seaports. Automation can maximize port efficiency and adapt to changing circumstances, but port digitalisation is challenging due to the various parties and information flows involved. The port of Sines in Portugal is undergoing a digital transformation, specifically about the Smart Gate concept. The port administration and partners have developed a pre-gate, which is being examined for operations, technologies, and information models. This work uses simulation to analyse the pre-gate model dynamically. The discrete-event simulation model, using Anylogic software (version 8.9.0), forecasts possible problems and predicts pre-gate behaviour, facilitating ongoing enhancement of pre-gate procedures. The considered scenarios vary in two factors: the processing time at the bottleneck process and the number of active lanes at the same point. Four of the twenty tested alternatives were identified as balanced. Results allow drawing conclusions on the number of lanes to be open to prevent congestion, particularly when processing times increase. The study highlights the benefits of simulating complex systems to improve operations. Future work could involve adjusting parameters, incorporating advanced optimisation techniques, and expanding evaluated metrics. The ultimate goal is to develop a reliable digital twin for the port. Full article

Weather radar plays a critical role in flash flood forecasting, providing an effective and comprehensive guide for the identification of possible flood-prone areas. However, the utilization of radar precipitation data remains limited in current research and applications, particularly in addressing flash flood hazards in complex environments such as in Athens, Greece. To address this gap, this study introduces the Gridded Flash Flood Guidance (GFFG) method, a short-term flash flood forecasting and warning technology based on radar precipitation and hydrological model coupling, and implements it in the region of Athens, Greece. The GFFG system improves upon the traditional flash flood guidance (FFG) concept by better integrating the weather radar dataset’s spatial and temporal flexibility, leading to increased resolution results. Results from six flood events underscore its ability to identify high-risk areas dynamically, with urban regions frequently flagged for flooding unless initial soil moisture conditions are low. Moreover, the sensitivity analysis of the system showed that the most crucial parameter apart from rainfall input is the soil moisture conditions, which define the amount of effective rainfall. This study highlights the significance of incorporating radar precipitation and real-time soil moisture assessments to improve flood prediction accuracy and provide valuable flood risk assessments. Full article

Urban rail transit passenger flow forecasting often relies on the traditional “four-step” method, where the division of traffic analysis zones (TAZs) is critical to ensuring prediction accuracy. As the fundamental units for describing trip origins and destinations, TAZs also encompass socioeconomic attributes such as land use, population, and employment. However, traditional TAZs, typically based on administrative boundaries, fail to reflect evolving urban travel behavior, particularly when transit stations are located near TAZ boundaries. Additionally, the emergence of urban big data allows for more refined spatial analyses based on individual travel patterns, addressing the limitations of administrative divisions. This study proposes an innovative TAZ aggregation model based on travel similarity, integrating public transit smart-card data and GIS data from bus networks. First, individual spatiotemporal travel patterns are mapped and discretized in both the spatial and temporal dimensions. Travel characteristic data are then extracted for spatial grid units. The TAZ division problem is defined as a multiobjective optimization problem, including factors such as travel similarity, the homogeneity of travel intensity, the statistical accuracy of the area, geographic information preservation, travel ratio constraints, and shape constraints. Multiple TAZ division schemes are produced and assessed using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), resulting in the selection of the optimal scheme. The proposed method is implemented on bus passenger travel data in Beijing, showing that the optimized scheme significantly reduces the number of zones with travel ratios exceeding 10%. Compared with existing schemes, the optimized division yields more uniform distributions of travel ratios, area, and travel density, while significantly minimizing the number of zones with a high travel concentration. These results demonstrate that the proposed method better reflects residents’ actual travel behaviors, offering a notable improvement over traditional approaches. This research provides a novel and practical framework for data-driven TAZ optimization. Full article

Soybean yield prediction is one of the most critical activities for increasing agricultural productivity and ensuring food security. Traditional models often underestimate yields because of limitations associated with single data sources and simplistic model architectures. These prevent complex, multifaceted factors influencing crop growth and yield from being captured. In this line, this work fuses multi-source data—satellite imagery, weather data, and soil properties—through the approach of multi-modal fusion using Convolutional Neural Networks and Recurrent Neural Networks. While satellite imagery provides information on spatial data regarding crop health, weather data provides temporal insights, and the soil properties provide important fertility information. Fusing these heterogeneous data sources embeds an overall understanding of yield-determining factors in the model, decreasing the RMSE by 15% and improving R² by 20% over single-source models. We further push the frontier of feature engineering by using Temporal Convolutional Networks (TCNs) and Graph Convolutional Networks (GCNs) to capture time series trends, geographic and topological information, and pest/disease incidence. TCNs can capture long-range temporal dependencies well, while the GCN model has complex spatial relationships and enhanced the features for making yield predictions. This increases the prediction accuracy by 10% and boosts the F1 score for low-yield area identification by 5%. Additionally, we introduce other improved model architectures: a custom UNet with attention mechanisms, Heterogeneous Graph Neural Networks (HGNNs), and Variational Auto-encoders. The attention mechanism enables more effective spatial feature encoding by focusing on critical image regions, while the HGNN captures interaction patterns that are complex between diverse data types. Finally, VAEs can generate robust feature representation. Such state-of-the-art architectures could then achieve an MAE improvement of 12%, while R² for yield prediction improves by 25%. In this paper, the state of the art in yield prediction has been advanced due to the employment of multi-source data fusion, sophisticated feature engineering, and advanced neural network architectures. This provides a more accurate and reliable soybean yield forecast. Thus, the fusion of Convolutional Neural Networks with Recurrent Neural Networks and Graph Networks enhances the efficiency of the detection process. Full article