METIS

<p>Autonomous driving can be challenging especially in winter conditions when road surface is covered by icy and snow or visibility is low due to precipitation, fog or blowing snow. These harsh weather and road conditions set up very important requirements for the guidance systems of autonomous cars. In the normal conditions autonomous cars can drive without limitations but otherwise the speed must be reduced, and the safety distances increased to ensure safety on the roads. </p><p>Autonomous driving needs very precise and real-time weather and road condition information. Data can be collected from different sources, like (road) weather models, fixed road weather station network, weather radars and vehicle sensors (for example Lidars, radars and dashboard cameras). By combining the all relevant weather and road condition information a weather-based autonomous driving mode system is developed to help and guide autonomous driving. The driving mode system is dividing the driving conditions from perfect conditions to very poor conditions. In between there are several steps with slightly alternate driving modes depending for example snow intensity and friction. In the most challenging weather conditions, automatic driving must be stopped because the sensors guiding the driving are disturbed by for example heavy snowfall or icy road.</p><p>Finnish Meteorological Institute is testing autonomous driving in the Arctic vehicular test track in Sodankylä, Northern Finland. The test track is equipped with road weather observation system network including road weather stations, IoT sensors measuring air temperature and humidity along with various communication systems. Also, tailored road weather services are produced to the test track, like precise road weather model calculations and very accurate radar precipitation observations and nowcasting. The developed weather-based autonomous driving system is tested on Sodankylä test track among other arctic autonomous driving testing.</p><p>This study presents the Sodankylä Arctic vehicular test track environment and weather-based autonomous driving mode system that is developed at the Finnish Meteorological Institute.</p>

PURPOSES : This study demonstrates the need for the collection of road weather information in order to perform efficient snow removal works during the winter season. Snow removal operations are usually dependent upon weather information obtained from the Automatic Weather Station provided by the Korea Meteorological Administration. However, there are some difference between road weather and weather forecasts in their scope. This is because general weather forecasts are focused on macroscopic standpoints rather than microscopic perspectives. METHODS : In this study, the relationship between snow removal works and historical weather forecasts are properly analyzed to prove the importance of road weather information. We collected both weather data and snow removal works during winter season at "A" regional offices in Gangwon areas. RESULTS : Results showed that the validation of weather forecasts for snow removal works were depended on the height difference between AWS location and its neighboring roadway. CONCLUSIONS : Namely, it appears that road weather information should be collected where AWS location and its neighboring roadway have relatively big difference in their heights.

A major challenge that all law-enforcement and intelligence-gathering organizations are facing is to accurately and efficiently analyze the growing volumes of crime data. In many fields, video surveillance can be used for that purpose. Video surveillance systems are now commonly used at various places like banks, hotels, schools, supermarkets. These systems are applicable for real-time monitoring or post checking. Current video surveillance systems have lower intelligence and it need people to monitor them. Today, video surveillance systems are used for traffic cameras, too. Traffic cameras are an innovative and extremely functional application of video surveillance technology. Whether they are recording traffic patterns for the future study and observation or monitoring traffic and issuing tickets for moving violations, traffic cameras are an explosively popular form of video surveillance. One way to find traffic patterns or to prevent traffic accidents and provide better road security is to use data mining techniques. With data mining, stream from many traffic cameras can be processed in real time. Property like this could provide some intelligence upgrade within systems, so they could make decision on their own without the need of people to monitor them. In this paper the authors described the data mining techniques for stream processing, pattern and abnormality detection in traffic surveillance systems. Each video recording and the use of recorded video on the court must be covered by legal regulations. The authors investigated and extracted the appropriate articles from concrete Laws of Republic Serbia, covering this kind of problems.

Electrical energy losses increase in modern grids. The losses are connected with an increase in consumption. Existing models of electric power losses estimation considering climatic factors do not allow estimating the cable temperature in real time. Considering weather and mode factors in real time allows to meet effectively and safely the consumer’s needs to minimize energy losses during transmission, to use electric power equipment effectively. These factors increase an interest in the evaluation of the dynamic thermal mode of overhead transmission lines conductors. The article discusses an approximate analytic solution of the heat balance equation in the transient operation mode of overhead lines based on the least squares method. The accuracy of the results obtained is comparable with the results of solving the heat balance equation of transient thermal mode with the Runge-Kutt method. The analysis of mode and climatic factors effect on the cable temperature in a dynamic thermal mode is presented. The calculation of the maximum permissible current for variation of weather conditions is made. The average electric energy losses during the transient process are calculated with the change of wind, air temperature and solar radiation. The parameters having the greatest effect on the transmission capacity are identified.

Urban taxi systems struggle to manage their fleets in real time and often cannot integrate with other modes of transportation or adapt to changing conditions. We propose a hybrid reinforcement learning framework that includes Q-learning and rule-based optimization to schedule a taxis fleet optimization that can utilize multiple modes of the transportation. The framework contains real-time weather’s fluctuations and the behaviour of the passengers how they are acting to make fixed-route transit work in a better way. The experimental demonstrations illustrate a 23.4% increase in performance over random scheduling technique, with which vehicle utilisation and an average wait time of 0.42 hours are improved, even when the environment is uncertain.

The Southeast region in the United States has a high risk for tornadoes and tornado-related losses (e.g., fatalities, injuries, damages). For the public in tornado-vulnerable areas, receiving warning information is essential for seeking protective action during a tornado event. However, for Latinx/e households in the Southeast, social, cultural, and political factors pertaining to language barriers, cultural differences, and trust in public officials often inhibit the effectiveness of warning communication strategies. The current study utilized a survey among 820 Latinx/e adults across 11 states in the U.S. Southeast. Using the Wilcoxon–Mann–Whitney (WMW) test, we examined if language, nativity, and immigration status impacted how Latinx/e populations receive, understand, and act upon severe weather information in the Southeast region. Results found intraethnic disparities related to tornado hazard understanding, reception, and response among Latinx/e adults based on language, nativity, and U.S. citizenship status. These findings suggest that NWS and its partners work with Latinx/e communities to adjust their communication strategies to consider ethnic heterogeneity in future hazard research, alert systems, and targeted outreach campaigns. Significance Statement We sought to determine if Latinx/e populations in the Southeast United States face distinct social and systematic challenges and exhibit varying levels of preparedness and awareness in the face of tornado hazards. We analyzed tornado warning comprehension, weather information sources, and barriers to protective actions among 820 Latinx/e participants, along with intraethnic disparities or vulnerabilities that may impact an individual’s or community’s ability to prepare for, respond to, and adapt to tornado hazards. These findings are important for forecasters, broadcasters, emergency managers, and others responsible for alerting the public during severe weather situations in the Southeast. Understanding differences in human vulnerability in the face of tornado threats can help inform better disaster planning and response for vulnerable and underrepresented populations.

The cities are the largest emitters of the greenhouse gas (GHG) emissions in the world, with close to a quarter of the total energy‐related CO 2 emissions occurring in urban places. As urbanization and demand to move surge in transiting, traditional monomodal transport systems, especially the ones that rely on the use of personal vehicles, are inefficient given the low efficiency, and thus unaffordable to support the goal of sustainability. The current article suggests the idea of an artificial intelligence (AI)‐powered, Internet of Things (IoT)‐compatible real‐time multimodal optimization tool to minimize urban emissions yet improve the efficient mobility of people and goods. The system unites AI algorithms, such as reinforcement learning (RL) and graph neural networks (GNNs), and the data streams based on the IoT devices connected to road sensors, GPS, mobile apps, and the public transportation systems. It actively suggests the best paths and combinations of methods of transport (e.g., walking, biking, bus, metro) according to the traffic, weather, user preferences, and emission characteristics in real time. Through simulations that have been carried out in the simulation of urban mobility (SUMO) platform on a modeled city, average CO 2 emissions per trip have been reduced by 45% compared with baseline routing strategies. Further findings indicate the use of suggested alternatives with high user acceptance rate (83%) and efficient modal shifts of the avoided use of a private car. The suggested framework provides a data‐driven and scalable framework of sustainable urban mobility. Considering that it integrates modeling of emissions into the central optimization engine, enables real‐time, personalized decision‐making, it can help achieve climate action as well as aid in the smart city development. The proposed AI–IoT framework demonstrably reduces CO 2 emissions and supports the United Nations Sustainable Development Goals (SDGs), specifically SDG 11 (cities, targets 11.2/11.6), SDG 13 (climate, target 13.2), and SDG 9 (infrastructure, targets 9.1/9.4) with secondary alignment to SDG 7.3 on energy efficiency.

A real time functional Near-InfraRed Imager (fNIRI) was presented in this paper. We developed a continuous wave (cw) light imaging probe which includes 9 light sources and 4 pairs detectors (each pair has one 850 nm filtered detector and one 760 nm filtered detector). There are 16 measurement sections and total detection area is 9 cm X 4 cm. The detector- source uses 2.5 cm spacing. The light sources are controlled by a computer and the signals from the detectors are converted and processed in real time by the computer. The user-friendly software was programmed with Visual C++ language. Relative changes of oxy-Hb, Hb, and total blood concentration in 16 channels and the corresponding images combined by 16 channels could be displayed in real time on computer. With this cw imaging probe, we have measured motor function in motor cortex area, visual function in occipital area, and cognitive activity in frontal forehead area of the human brain when the subjects are stimulated by moving fingers, viewing a flashing light and doing an analogy test, respectively. The experimental results show that the cw imaging probe can be used for functional images of brain activity, based upon changes of oxygenation and blood volume due to the stimulus.

The inaccuracy of non-real-time macro-regional weather forecasts creates an information gap for MSME actors in the agricultural sector who need updates on actual weather conditions at their business locations. This study aims to develop a real-time weather monitoring system based on ESP32 and an LSTM rainfall prediction model, the results of which can be accessed via a web interface by MSME actors such as farmers. The system was developed using an ESP32 microcontroller, DHT22 sensor, and Hall-effect 3144, with an LSTM model trained using historical BMKG data and field data. Our findings show that the system is capable of monitoring weather conditions in real time while generating microspatial rainfall predictions through full integration between IoT devices and the LSTM model. Test results show stable system performance with a transmission delay of 5 seconds, an initial fetch latency of 48 ms, and prediction performance RMSE of 17.05 mm, MAE of 12.40 mm, and F1-score of 0.175, which is adequate for detecting extreme rainfall intensity. These findings demonstrate the potential for developing an affordable, easily replicable, and adaptable microspatial weather forecasting system to support early warning systems or smart irrigation in agricultural areas.

Intelligent vehicles or smart cars are considered to be capable of reducing the high mortality rate that occurs on roads globally. The different applications of intelligent vehicles i.e., vehicle-to-vehicle (V2V) or vehicle-to-infrastructure networks (V2I), are collectively called vehicle-to-everything (V2X) communications which has the endorsement of the international standard IEEE 802.11p. It is widely expected that V2X can diminish traffic gridlocks and aid the drivers with information such as road status and weather forecast in order to prevent traffic accidents. The aim of this paper is to generate viable mm-Wave channel parameters for V2V scenario in a specific urban area in London as a benchmark for future development. Thus, a thorough evaluation of the implemented V2V mm-Wave propagation channel is performed so as to determine the main constraint factors, such as the signal fading, shadowing, reflection, refraction, scattering and Doppler effect, that can affect V2V communication and connectivity. We analyse comparatively the simulation results of V2V channel propagation parameters using the geometry-based efficient propagation simulator for V2V communications with the experimental measurements conducted using our testbed setup in Hendon area of London UK, which is a combination of urban and suburban streets, with hill top and express way in terms of roadside environments. It is found that i) the simulation results are consistent with the practical measurement; and ii) the simulation at higher mmWave frequencies shows that signal can be detected up to 200m in the urban area irrespective of it being highly non-line of sight environment.

This paper examines the interactive aerodynamic effects of road topography and meteorological conditions on time-trialling cycling performance. Aerodynamics and cycling performance were modelled using a fictitious cyclist completing a 40-km time-trial with simulated power outputs of 164 W (recreational level), 255 W (well-trained) and 394 W (elite) Virtual topographical conditions encompassed altitudes of up to 2500 m and ±2% road gradients. Meteorological variations incorporated 970–1040 mb barometric pressures, 0–40°C air temperatures, 0–100% relative humidity levels and ±2 m/s wind velocities. Interactions between physical altitude and weather were expressed in terms of the associated air density Drag force was calculated, and aerodynamic power, cycling speed and finishing time were estimated using mathematical modelling. Prediction equations were developed using curve fitting. Non-standard atmospheric conditions alter the pressure altitude and density altitude of a particular race location. With increasing air density, drag force rises rapidly in direct proportion, but aerodynamic power increases and cycling performance declines in a non-linear fashion. Windy conditions and hilly terrain add to race time exponentially with air density. An Excel spreadsheet was developed which may be used by time-triallists to predict cycling performance and adjust pacing according to road topography and forecast weather.

Historically, weather forecasting was unreliable and imprecise, relying on intuition and local knowledge. Inaccurate weather forecasts can cause severe impacts on agriculture, construction, and daily life. Existing methods struggle with rural and urban weather prediction, requiring faster and more accurate solutions. This research proposes a deep learning system using real- time images to address this challenge. This research employs a deep learning model fully convolutional network-long short-term memory (FCN-LSTM) to analyze images and predict weather conditions. In this case, the model forecasts a sunny and cloudy environment, which facilitates defining the ideal conditions for every given climatic zone in the weather classification model. The model is trained on a dataset of weather images obtained from Kaggle. The performance of the proposed model FCN-LSTM achieves an accuracy of 96.88% and a validation accuracy of 91.22%. Also, the mean squared error (MSE) is 7.11, which is significantly lower and supports efficient enhancement in weather forecasting. This significant improvement demonstrates the potential of deep learning for real-time weather forecasting. The model provides efficient weather classification, enabling informed decision-making across various sectors. This research lays the foundation for automated weather analysis using deep learning, eliminating human bias and improving accuracy.

Solar irradiance prediction is significant for maximizing energy-saving effects in the predictive control of buildings. Several models for solar irradiance prediction have been developed; however, they require the collection of weather data over a long period in the predicted target region or evaluation of various weather data in real time. In this study, a long short-term memory algorithm–based model is proposed using limited input data and data from other regions. The proposed model can predict solar irradiance using next-day weather forecasts by the Korea Meteorological Administration and daily solar irradiance, and it is possible to build a model with one-time learning using national and international data. The model developed in this study showed excellent predictive performance with a coefficient of variation of the root mean square error of 12% per year even if the learning and forecast regions were different, assuming that the weather forecast was correct.

Winter storms making landfall in western North America can generate heavy precipitation and other significant weather, leading to floods, landslides, and other hazards that cause significant damage and loss of life. To help alleviate these negative impacts, the California Land-falling Jets (CALJET) and Pacific Land-falling Jets (PACJET) experiments took extra meteorological observations in the coastal region to investigate key research questions and aid operational West Coast 0–48-h weather forecasting. This article presents results from a study of how information provided by CALJET and PACJET was used by National Weather Service (NWS) forecasters and forecast users. The primary study methodology was analysis of qualitative data collected from observations of forecasters and from interviews with NWS personnel, CALJET–PACJET researchers, and forecast users. The article begins by documenting and discussing the many types of information that NWS forecasters combine to generate forecasts. Within this context, the article describes how forecasters used CALJET–PACJET observations to fill in key observational gaps. It then discusses researcher–forecaster interactions and examines how weather forecast information is used in emergency management decision making. The results elucidate the important role that forecasters play in integrating meteorological information and translating forecasts for users. More generally, the article illustrates how CALJET and PACJET benefited forecasts and society in real time, and it can inform future efforts to improve human-generated weather forecasts and future studies of the use and value of meteorological information.

We propose a real time simulation for window frost formation on mobile devices that uses both particles and grids. Previous ice formation methods made heavy demands on both memory and computational capacity because they were designed for a desktop environment. In this paper, a frost skeleton grows around a location touched by the user using particles, and the ice surfaces are constructed using a grid. Using a nonlattice random-walk technique, the frost skeleton grows freely and naturally. A hash grid technique is used to search efficiently for neighbor particles during the crystallization process. Finally, some 2.5D details are added to the ice skeleton by adjusting the height of the grid vertices around the skeleton. Experiments show that our method creates realistic frost in real time. Our method can be used to express ice formation effects in touch-based mobile device applications such as weather forecasts or games.