Weather Data Research Articles

The Effect of Diesel Vehicle Regulation on Air Quality in Seoul: Evidence from Seoul’s Low Emission Zone

This study investigates the effect of the low emission zone (LEZ), designed to restrict old diesel vehicles, on air quality in Seoul, Republic of Korea, using the regression discontinuity in time (RDiT) approach. While previous studies have examined LEZ impacts using traditional econometric models such as time series and panel data approaches, our research uniquely integrates high-frequency daily weather data to better control for confounding environmental variables and captures time-of-day effects on pollutant concentrations. Our findings reveal that the LEZ policy effectively reduced NO2 and SO2 concentrations by 4.7% and 11.6%, respectively. Notably, during daytime hours, when traffic is heaviest, NO2, SO2, and PM10 concentrations decreased by 7.1%, 14.8%, and 13.6%, respectively. These results suggest that the observed improvements can be attributed not only to reduced diesel vehicle registrations but also to significant declines in overall traffic volume.

Offshore wind project installations: an advanced approach for weather risk assessments

Abstract This paper presents the development of a sequence-based simulation tool for the weather risk assessment of offshore work processes. The approach developed at the Fraunhofer Institute for Wind Energy Systems is the Advanced Weather Time Series Scheduling (Ad-WATSS) method. For statistical significance, this method combines hindcast weather time series of many years with the weather restrictions associated with offshore activities. The method is incorporated into the software tool COAST, where a project plan schedule is simulated by placing activities according to their operational limits, constraints and relationships, and minimum-required time for each operation. A scenario of an offshore wind installation project in the North Sea is used as reference test case for a weather risk assessment using the developed tool and ERA5 weather data. The assessment is then compared with the weather window statistics approach, based on the same weather data sets. The results from both approaches are analysed and compared on a project and task level detail. The results from the sequence-based simulations show that the method is able to capture the long-term variability and extreme events in weather conditions, making it a reliable tool for the simplification of the weather data-based planning, validation, and assessment of offshore projects.

Development of Particulate Matter Concentration Estimation Models for Road Sections Based on Micro-Data

With increasing global concerns related to global warming, air pollution, and environmental health, South Korea is actively implementing various particulate matter (PM) reduction policies to improve air quality. Accurate data analysis, including the investigation of weather phenomena, monitoring, and integrated prediction, is essential for effective PM reduction. However, the factors influencing the PM generated from domestic road sections have not yet been systematically analyzed, and currently, no predictive models utilize weather and traffic data. This study analyzed the correlations among factors influencing PM to develop models for estimating fine and coarse PM (PM2.5 and PM10, respectively) concentrations in road sections. Regression analysis models were used to assess the sensitivity of PM2.5 and PM10 concentrations to the traffic volume, whereas machine learning-based models, including linear regression, convolutional neural networks, and random forest models, were constructed and compared. The random forest models outperformed the other models, with coefficients of determination of 0.74 and 0.71 and mean absolute errors of 5.78 and 9.60 for PM2.5 and PM10, respectively. These results indicate that the random forest model provides the most accurate PM concentration estimates for road sections. The practical applications of the developed models were considered to inform effective transportation policies aimed at reducing PM. The developed model has practical applications in the formulation of transportation policies aimed at reducing PM. In particular, the model will play an important role in data-driven policymaking for sustainable urban development and environmental protection. By analyzing the correlation between traffic volume and weather conditions, policymakers can formulate more effective and sustainable strategies for reducing air pollution.

Reinforcement Learning for EV Fleet Smart Charging with On-Site Renewable Energy Sources

In 2020, the transportation sector was the second largest source of carbon emissions in the UK and in Newcastle upon Tyne, responsible for about 33% of total emissions. To support the UK’s target of reaching net zero emissions by 2050, electric vehicles (EVs) are pivotal in advancing carbon-neutral road transportation. Optimal EV charging requires a better understanding of the unpredictable output from on-site renewable energy sources (ORES). This paper proposes an integrated EV fleet charging schedule with a proximal policy optimization method based on a framework for deep reinforcement learning. For the design of the reinforcement learning environment, mathematical models of wind and solar power generation are created. In addition, the multivariate Gaussian distributions derived from historical weather and EV fleet charging data are utilized to simulate weather and charging demand uncertainty in order to create large datasets for training the model. The optimization problem is expressed as a Markov decision process (MDP) with operational constraints. For training artificial neural networks (ANNs) through successive transition simulations, a proximal policy optimization (PPO) approach is devised. The optimization approach is deployed and evaluated on a real-world scenario comprised of council EV fleet charging data from Leicester, UK. The results show that due to the design of the rewards function and system limitations, the charging action is biased towards the time of day when renewable energy output is maximum (midday). The charging decision by reinforcement learning improves the utilization of renewable energy by 2–4% compared to the random charging policy and the priority charging policy. This study contributes to the reduction in battery charging and discharging, electricity sold to the grid to create benefits and the reduction in carbon emissions.

Cyber attacks detection and mitigation in hybrid power system using type-2 fuzzy controller

Abstract This paper presents a novel control technique using Fuzzy Type-2 controller for regulating the frequency deviations in an independent Hybrid Power System (HPS). The HPS comprises of a wind system and a solar photovoltaic (PV) system as primary energy sources, along with Fuel Cells (FCs) as additional generation systems and Double Layer Capacitor (DLC) Banks as storage devices to meet the load demand. The frequency variations occur in the HPS due to the intermittency in power outputs from the primary sources, the load changes as well as any attacks in the system. The frequency regulation is achieved by effective coordination control of FC and DLC with the aid of a Fuzzy Type-2 controller and a high pass filter (HPF). The DLC technology adequately satisfies the residual power of hybrid systems resulting from the slow dynamics of FCs. The Fuzzy Type-2 controller is trained using an input-output data set of a PID controller whose gains are tuned to their optimal values using Monte-Carlo state estimators. The proposed system is simulated using real weather data to validate the capability of the Hybrid Power System (HPS) in supplying isolated loads while maintaining power frequency balance conditions. Also the HPS is subjected to attacks in daily load variation and the results are compared with the system without attacks. The simulation results show that the peak over shoots are reduced considerably but the settling time is 0.2 seconds in the system with no attacks where as the settling time is prolonged to 1.2 seconds with the attacks. This paper demonstrates the effectiveness of the Fuzzy Type-2 controller for the coordination control of DLC and FC to achieve generation-load balance condition in comparison with that of the PID controller for HPS system with and without attacks.

A Temporal–Geospatial Deep Learning Framework for Crop Yield Prediction

With the rapid development of information technology, the demand for digital agriculture is increasing. As an important agricultural production topic, crop yield has always attracted much attention. Currently, artificial intelligence, particularly machine learning, has become the leading approach for crop yield prediction. As a result, developing a machine learning method that accurately predicts crop yield has become one of the central challenges in digital agriculture. Unlike traditional regression prediction problems, crop yield prediction has a significant time correlation. For example, weather data for each county show strong temporal correlations. Moreover, geographic information from different regions also impacts crop yield to a certain extent. For example, if a county’s neighboring counties have a good harvest, then this county is likely to have high yields as well. This paper introduces a novel hybrid deep learning framework that combines convolutional neural network (CNN), graph attention network (GAT) and long short-term memory (LSTM) modules to enhance prediction accuracy. Specifically, CNN is employed to extract the features from the input data for each county in each year. GAT is introduced to model the geographical relationships between neighboring counties, allowing the model to capture spatial dependencies more effectively. LSTM is used to extract the temporal information within many years. The proposed hybrid deep learning framework CNN-GAT-LSTM captures both the temporal and spatial relationships, thereby improving the accuracy of yield prediction. We conduct experiments on a nationwide dataset that includes data from 1115 soybean-producing counties in 13 states in the United States covering the years from 1980 to 2018. We evaluate the performance of our proposed CNN-GAT-LSTM model based on three metrics, namely root of the mean squared error (RMSE), R-squared (R2) and correlation coefficient (Corr). The experimental results demonstrate that the proposed model achieves significant performance improvements over the existing state-of-the-art model, with RMSE reduced by 5%, R2 improved by 6% and Corr enhanced by 4%.

Al-driven Precision Agriculture: Advancing Crop Yield Prediction

This article explores the integration of Artificial Intelligence (AI) in precision agriculture, focusing on its role in advancing crop yield prediction and improving overall agricultural productivity. It examines three key areas: satellite imagery analysis, soil health monitoring, and weather data integration. The paper discusses how AI techniques such as Convolutional Neural Networks, IoT sensor networks, and ensemble methods are revolutionizing farming practices. It highlights the technical implementations of these technologies, their applications, and their significant impact on yield optimization, resource efficiency, and decision-making in agriculture. The study emphasizes the crucial role of AI in addressing global food security challenges and improving agricultural resilience to climate change.

Multimodal Deep Learning Integration of Image, Weather, and Phenotypic Data Under Temporal Effects for Early Prediction of Maize Yield

Maize (Zea mays L.) has been shown to be sensitive to temperature deviations, influencing its yield potential. The development of new maize hybrids resilient to unfavourable weather is a desirable aim for crop breeders. In this paper, we showcase the development of a multimodal deep learning model using RGB images, phenotypic, and weather data under temporal effects to predict the yield potential of maize before or during anthesis and silking stages. The main objective of this study was to assess if the inclusion of historical weather data, maize growth captured through imagery, and important phenotypic traits would improve the predictive power of an established multimodal deep learning model. Evaluation of the model performance when training from scratch showed its ability to accurately predict ~89% of hybrids with high-yield potential and demonstrated enhanced explanatory power compared with previously published models. Shapley Additive explanations (SHAP) analysis indicated the top influential features include plant density, hybrid placement in the field, date to anthesis, parental line, temperature, humidity, and solar radiation. Including weather historical data was important for model performance, significantly enhancing the predictive and explanatory power of the model. For future research, the use of the model can move beyond maize yield prediction by fine-tuning the model on other crop data, serving as a potential decision-making tool for crop breeders to determine high-performing individuals from diverse crop types.

Deep Learning-Based Time Series Analysis for Environment Changes

The effects of weather alteration are generally cited as one of the most significant challenges facing conservation efforts. Recent research indicates that it is feasible to identify the consequences of a changing climate on biological systems. Environment change is a worldwide problem that requires quick attention. The topic of environmental change and how to adapt to it has been the topic of several studies. More efficient and effective variation and extenuation measures are needed, but only if new approaches are developed to investigate the intricacies of environmental change. In recent years, Deep Learning (DL) approaches have become more popular across a variety of industries, environmental change included. It is to examine the most widely used DL techniques for combating and familiarising to environmental change. The second goal is to classify the greatest widely-studied mitigation and adaptation measures across all locations, but especially in urban regions using DL techniques. According to the results, the most widely used DL approach is also the most effective in mitigating and adapting to environmental changes. Furthermore, geo-engineering and land surface temperature studies have employed DL algorithms more than any others in the field of environment change mitigation and reworking. The weather, including its temperature, humidity, clouds, and wind speed, are all potential contributors. This work analyses the major impacts of the local environment and climate on these characteristics. The study uses Indian state Haryana's local weather data (from January 1, 2012, to December 31, 2022). In the result, shows that this section’s highest winds speed are around 9 Km/h in the month of June.

Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model

We developed an internal environment prediction model for smart greenhouses using machine learning models. Machine learning models were developed by finding certain rules based on the data obtained from the target system and have the advantage of learning various characteristics that are difficult to define theoretically. However, the model accuracy and precision can change according to the model structure (hyperparameters, algorithms, epoch) and data characteristics. In this study, the analysis was performed according to the collected weather data characteristics. The model performance was low when the amount of training data was obtained over less than three days (4320 ea). The model performance improved with an increase in the amount of training data. Model performance stabilized when the training data volume exceeded seven days (10,080 ea). The optimal amount of data was determined to be between three and seven days, with an average model r2 of 0.8811 and an RMSE of 2.056 for the gated recurrent unit algorithm. This study verified the possibility of developing a predictive model for the internal environment of a greenhouse based on weather data from outside. This study is limited to a specific target greenhouse, and further analysis of data from various greenhouses and climates is necessary to achieve global optimization.

Reinforcement Learning Algorithm for Optimising Durian Irrigation Systems: Maximising Growth and Water Efficiency

This study presents a Reinforcement Learning-based algorithm designed to optimise irrigation for Durio Zibethinus (i.e., durian) trees, aiming to maximise tree growth and reduce water usage. Traditional irrigation methods, as well as current machine learning models, often focus only on soil moisture and weather data, neglecting critical factors like actual tree growth. This study proposed a reinforcement learning irrigation (RL-Irr) algorithm incorporating tree growth stages, soil moisture, and weather conditions to determine precise irrigation needs. The algorithm was developed by calibrating the AQUACROP model using data from actual durian plantations where rain-fed irrigation (rain-fed) was practised. Daily irrigation volumes were calculated based on real-time soil moisture, weather forecasts, and weekly tree growth measurements. The reinforcement learning method was used to optimise irrigation schedules, with rewards based on soil moisture, tree growth, rainfall, and weather conditions. The algorithm was tested using AQUACROP simulations and compared against soil moisture balance irrigation (SMB-Irr) and rain-fed. The results showed that the RL-Irr reduced water use by up to 75 percent while maintaining tree growth. These findings suggest the algorithm could significantly improve water efficiency in durian farming, though real-world applications should consider potential model limitations.

A novel modelling framework for real-time prediction of path travel times using both traffic and weather data

The problems of path travel time predictions have been studied over decades. Traditional approaches to this challenge have relied on different traffic data. However, in metropolitan cities with frequent rainfall, there is a need to consider the weather effects on real-time prediction of path travel times. Hence, this research integrates traffic data with weather data, including rainfall intensity data and weather forecast data to consider the temporal relationships between weather data and path travel times. The proposed modelling framework is evaluated with data from a major expressway and an urban arterial road in Hong Kong. Results unequivocally demonstrate that incorporating weather data significantly boosts prediction accuracy. This study also examines the impact of different frequencies on weather data, as well as weather forecast correctness, on prediction accuracy. Finally, the applicability of the proposed modelling framework has been verified without and with the input of ground truth on path travel times.

Integrating Thermal Infrared Imaging and Weather Data for Short-Term Prediction of Building Envelope Thermal Appearance

This study presents a novel deep-learning framework for predicting the thermal appearance of building envelopes under varying weather conditions based on a new dataset collected using a thermal infrared camera at 10 min intervals over a one-and-a-half-year period. Unlike existing studies that rely on simulated data or physical models that do not always accurately reflect the complex heat transfer processes in real buildings, we have collected a large dataset showing how a building behaves under different climatic conditions. We propose a novel deep-learning approach that integrates weather data and thermal imagery to predict the temperature distribution on the building façade for the next 24 and 48 h. The model uses a state-of-the-art recurrent neural network architecture, PredRNN V2, with an action conditioning mechanism to incorporate weather forecasting data into the prediction process. We evaluate this approach in terms of average accuracy, prediction accuracy in specific regions, and visual-perceptual performance of the images. The proposed framework achieves a prediction accuracy of 1.5 °C (root mean square error—RMSE) for the 24 h prediction and 2.04 °C (RMSE) for the 48 h prediction, outperforming baseline models in terms of temperature prediction accuracy and structural similarity of the predicted images.

Towards Sustainable Energy Solutions: Evaluating the Impact of Floating PV Systems in Reducing Water Evaporation and Enhancing Energy Production in Northern Cyprus

Floating photovoltaic systems (FPVSs) are gaining popularity, especially in countries with high population density and abundant solar energy resources. FPVSs provide a variety of advantages, particularly in situations where land is limited. Therefore, the main objective of the study is to evaluate the solar energy potential and investigate the techno-economic perspective of FPVSs at 15 water reservoirs in Northern Cyprus for the first time. Due to the solar radiation variations, solar power generation is uncertain; therefore, precise characterization is required to manage the grid effectively. In this paper, four distribution functions (Johnson SB, pert, Phased Bi-Weibull, and Kumaraswamy) are newly introduced to analyze the characteristics of solar irradiation, expressed by global horizontal irradiation (GHI), at the selected sites. These distribution functions are compared with common distribution functions to assess their suitability. The results demonstrated that the proposed distribution functions, with the exception of Phased Bi-Weibull, outperform the common distribution regarding fitting GHI distribution. Moreover, this work aims to evaluate the effects of floating photovoltaic systems on water evaporation rates at 15 reservoirs. To this aim, five methods were used to estimate the rate of water evaporation based on weather data. Different scenarios of covering the reservoir’s surface with an FPVS were studied and discussed. The findings showed that annual savings at 100% coverage can reach 6.21 × 105 m3 compared to 0 m3 without PV panels. Finally, technical and economic assessment of FPVSs with various scales, floating assemblies, and PV technologies was conducted to determine the optimal system. The results revealed that a floating structure (North orientation-tilt 6°) and bifacial panels produced the maximum performance for the proposed FPVSs at the selected sites. Consequently, it is observed that the percentage of reduction in electricity production from fossil fuel can be varied from 10.19% to 47.21% at 75% FPV occupancy.

Modelling Climate Change Impacts on Location Suitability for Cultivating Avocado and Blueberry in New Zealand

Regional suitability for growing avocados and blueberries may alter with climate change. Modelling can provide insights into potential climate change impacts, thereby informing industry and government policy decisions to ameliorate future risks and capitalise on future opportunities. We developed continuous/sliding-scale models that used soil, terrain and weather data to assess location suitability for cultivating avocado and blueberry, based on physiological and phenological considerations specific to each crop. Using geographical information system (GIS) data on soil, slope and weather, we mapped cultivation suitability for avocado and blueberry across New Zealand, and, for accuracy, “ground-truthed” these maps in an iterative process of expert validation and model recalibration. We modelled the incremental changes in location suitability that could occur through climate change using “future” GIS-based weather data from climate model simulations for different greenhouse gas (GHG) pathways that ranged from stringent GHG mitigation to unabated GHG emissions. Changes in maps over time showed where suitability would increase or decrease and to what extent. These results indicate where avocado and blueberry might replace other crops that become less suitable over time, and where avocado might displace blueberry. The approach and models can be applied to other countries or extended to other crops with similar growing requirements.

Effects of Rainfall Variability on Maize Production in Migori County, Kenya

Maize is the main staple food crop in Kenya and is of vital concern to agricultural policy decisions, food security, and the overall development of the sector and the economy. It is also the dominant staple food crop in Migori-County. However, there has been a declining trend in maize production among farmers in the study area threatening household food security. This study was conducted in Migori County using cross sectional survey research design. A sample size of 384 households was selected through stratified and systematic sampling techniques though just 310 households accepted to be interviewed. Data was collected using a structured questionnaire. Validated secondary weather data for the period 2011-2023 was obtained from the Migori Meteorological Station. The collected data was entered into SPSS software, version 20, and analysed using both descriptive and inferential statistical methods. The results indicated that 60% of households have an adequate food supply, while 40% face food shortages. Further, there was a strong positive and significant relationship between maize production (yield) and annual weather conditions from 2018 to 2023 (r = 0.845, p = 0.05). This indicates that changes in weather patterns, such as rainfall and temperature, had a significant influence on maize yields during the study period. Hence, farmers should be encouraged to use income from cash crops to purchase food stocks and engage in non-farm activities as alternative income sources to mitigate the effects of rainfall variability and climate change on food security.

Projection of land use and land cover changes based on land change modeler and integrating both land use land cover and climate change on the hydrological response of Big Creek Lake Watershed, South Alabama

Changing land use/land cover (LULC) and climate substantially affect the hydrological components of a watershed. This study explored the future impact of the hydrological responses due to the changing LULC and climate on the Big Creek Lake watershed in Alabama, USA, from 2021 to 2050 using the Soil and Water Assessment Tool (SWAT). Five climate model datasets were used under the moderate scenario (Representative Concentrative Pathways 4.5) and the extreme scenario (Representative Concentrative Pathways 8.5), and the datasets were downscaled and bias-corrected. In addition, changing the LULC of five categories was predicted by Cellular Automata Markov (CA- Markov). With these data combined with the elevation (Digital Elevation Model), soils, and weather data, the SWAT model was calibrated and validated for the studied watershed to quantify how climate change will affect streamflow, nitrogen, and phosphorus. Our results indicate streamflow will increase due to the 50-acre increase in urban LULC. As streamflow increases, the percolation, surface runoff, lateral flow, groundwater flow, and water yield will also increase because the streamflow impacts these hydrological components. Moreover, the increase rate in streamflow is the same for all the components for January, February, and March. Therefore, there is a strong correlation between these months. On the contrary, evaporation will be high in May, June, and July because of the increasing temperature and streamflow. However, the changes in the water hydrological parameters and total nitrogen and phosphorus will be more intense in RCP8.5 than in RCP4.5.

Multivariate stochastic generation of meteorological data for building simulation through interdependent meteorological processes

In recent years, the uncertainty of weather conditions and the impact of future climate change on building energy assessment has received increasing attention. As an important part of these studies, several types of methods for generating stochastic meteorological data have also been developed. Since solar radiation drops to zero at night, unlike the continuous 24-hour data for elements such as temperature and humidity, this has posed challenges for previous research to fully account for the simultaneity among multiple elements. Therefore, this study proposes a framework for meteorological data generation: First, perform multivariate time series modeling of meteorological data of air temperature, solar radiation and absolute humidity at 12:00 of each day of a typical year based on the S-vine copula method and simulating daily series data at 12:00 for 365 days. Then, based on the probability of change of each element evaluated from the historical meteorological observation data, the daily series data at 12:00 were expanded to 24 h, after which the yearly stochastic weather data were obtained. The analysis of 30 years of stochastic data generated by this method, compared with the original data, reveals that air temperature and solar radiation closely match the original distribution characteristics, except for a minor deviation in the absolute humidity’s kurtosis. Furthermore, the comparison of thermal load distributions for office buildings shows that the original data curve falls within the range of the generated data. This suggests that the generated data includes more information about uncertainty but still keeps the original data’s characteristics.

A Systematic Review of Features Forecasting Patient Arrival Numbers.

Adequate nurse staffing is crucial for quality healthcare, necessitating accurate predictions of patient arrival rates. These forecasts can be determined using supervised machine learning methods. Optimization of machine learning methods is largely about minimizing the prediction error. Existing models primarily utilize data such as historical patient visits, seasonal trends, holidays, and calendars. However, it is unclear what other features reduce the prediction error. Our systematic literature review identifies studies that use supervised machine learning to predict patient arrival numbers using nontemporal features, which are features not based on time or dates. We scrutinized 26 284 studies, eventually focusing on 27 relevant ones. These studies highlight three main feature groups: weather data, internet search and usage data, and data on (social) interaction of groups. Internet data and social interaction data appear particularly promising, with some studies reporting reduced errors by up to 33%. Although weather data are frequently used, its utility is less clear. Other potential data sources, including smartphone and social media data, remain largely unexplored. One reason for this might be potential data privacy challenges. In summary, although patient arrival prediction has become more important in recent years, there are still many questions and opportunities for future research on the features used in this area.

How a non harmonic-like tremor at a volcanic lake could be caused by sustained wind: A case of study of Taupō volcano

Taupō volcano lies underneath the largest lake in New Zealand. It undergoes unrest roughly every ten years, has minor eruptions every few hundred years, and has supereruptions. Understanding volcanic seismic signals provides insights into the volcano dynamics and helps to anticipate eruptions. Harmonic and non-harmonic volcanic tremor are common signals that indicate fluid mobilisation in volcanic systems. We observed a signal that resembled non-harmonic tremor during 2019 at Taupō volcano. Careful time-frequency analysis of seismic data and weather data from around the lake revealed that the signals were not magmatic in origin, but were most likely from lake microseisms caused by special conditions of the wind, which generates wind-driven waves in the lake. The frequency range of lake microseisms at Taupō starts and ends with a dominant frequency of 0.7–1.0 Hz, and during the maximum energy peak, the dominant frequency is of 0.50–0.56 Hz. Such signals may be common in caldera lakes, which need to be distinguished from tremor caused by volcanic activity, so as not to exaggerate the probability of eruptions.