Normal Weather Research Articles

DLW-Net model for traffic flow prediction under adverse weather

To predict traffic flow under adverse weather, a hybrid deep learning model concerning adverse weather (DLW-Net) is formulated. The DLW-Net model consists of the target and global analysis parts. For the target analysis part, the spatio-temporal characteristics of traffic flow data are analyzed using the convolutional neural network (CNN), the long short-term memory (LSTM) and gated recurrent unit (GRU) neural networks. For the global analysis part, the variation rules of traffic flow and weather data are extracted using the LSTM model. Additionally, the characteristics of traffic flow under normal and adverse weather are also discussed. The developed model is verified using three cases. The results show that traffic volume and speed would reduce under heavy rain compared to normal weather, however, drizzle has little impact on traffic flow patterns; the rules of traffic speed data are disturbed by strong wind; and the DLW-Net model performs best under all the conditions.

Energy efficiency path planning for a quadrotor aerial vehicle

Unmanned aerial vehicles are used today in many real-world applications. In all these applications, the vehicle endurance (flight time) is an important constraint that affects mission success. This study investigates the limitations of embedded energy for a quadrotor aerial vehicle. We consider a quadrotor simple tasked to travel from an initial hover configuration to a final hover configuration. In order to have a precise approximation of the consumed energy, we propose a power consumption model with battery dynamic, motor dynamic, and rotor efficiency function. We then introduce an optimization algorithm to minimize the energy consumption during quadrotor aerial vehicle mission. The proposed algorithm is based on an optimal control problem formulated for the quadrotor model and solved using nonlinear programming. In the optimal control problem, we seek to find control inputs (rotor velocity) and vehicle trajectory between initial and final configurations that minimize the consumed energy during a point-to-point mission. We extensively test in simulation experiments the proposed algorithm under normal and windy weather conditions. We compare the proposed optimization method with a nonlinear adaptive control approach to highlight the saved amount of energy.

A Method Based on Numerical Wind Field and Extreme Learning Machine for Typhoon Wind Speed Prediction of Wind Farm

Typhoon wind speed prediction is of great significance for it can help prevent wind farms from damages caused by frequent typhoon disasters in coastal areas. However, most researches on wind forecast are either for meteorological application or for normal weather. Therefore, this paper proposes a systematic method based on numerical wind field and extreme learning machine for typhoon wind speed prediction of wind farms. The proposed method mainly consists of three parts, IGA-YanMeng typhoon numerical simulation model, typhoon status prediction model, and wind speed simulation model based on an extreme learning machine. The IGA-YanMeng typhoon numerical simulation model can greatly enrich typhoon wind speed data according to historical typhoon parameters. The typhoon status prediction model can predict the status of typhoons studied in the next few hours. And wind speed simulation model simulates the average wind speed magnitude/direction at 10 m height of each turbine in the farm according to the predicted status. The end of this paper presents a case study on a wind farm located in Guangdong province that suffered from the super typhoon Mangkhut landed in 2018. The results verified the feasibility and effectiveness of the proposed method.

Understanding Plum Rain’s Effects on Urban Public Bicycle Unavailability Considering Both Place Semantics and Riding Distance

The effect of the plum rain weather event on cycling trips reflects the climate resilience of the public bicycle system. However, quantitative studies regarding the impact of plum rain on public bicycle users and corresponding spatial heterogeneity have not been paid much attention. This paper explores the spatial pattern of affected levels from the perspective of cyclist number, place semantics and riding distance. Corresponding public bicycle trips in normal weather are predicted by spatial-temporal random forest prediction. GIS neighborhood statistics and clustering algorithms are adapted to analyze and visualize the affected levels using origin-destination data of public bicycle trips and point of interest data of city public facilities. It is proved that there is an obvious spatial difference in affected levels by plum rain from three dimensions. In the dimension of the number of cyclists, the docking stations with different affected levels are distributed across the whole urban area. In the place semantic dimension, the docking stations with high affected levels show a clustered zonal distribution in the city center. In the dimension of cycling distance, the docking stations with high affected levels are mainly distributed in the periphery of the central urban area. The study theoretically expands the impact mechanism of environment and active transport. It is beneficial for the early monitoring, warning and assessment of climate change risks for public bicycle planning and management.

Sedimentological and microfossil records of modern typhoons in a coastal sandy lagoon off southern China coast

To determine the characteristics and potential indicators of modern typhoon deposition in a sandy lagoon off the coast of Guangdong Province (southern China), we analysed the 210Pb, sedimentology, and microfossils of samples from ten cores obtained before and after the passage of Typhoon Rammasun in 2014. Typhoon deposition showed a thinning trend from internal areas of the lagoon to its mouth, with the maximum thickness inside the lagoon of ∼35 cm. These typhoon deposits are dominated by overwash and differ from sediments deposited under normal weather conditions. Under normal weather conditions, lagoon sediment has a 210Pb curve that follows a model of exponential decay, has a unimodal granularity frequency curve, and lacks organic matter and microfossils (diatoms and foraminifera). However, 210Pb is low in the typhoon deposits, the grain size is coarse, and the granularity frequency curve is obviously bimodal. There are also abundant foraminifera in the typhoon deposits. We found a clear double-layered structure in the typhoon deposits, which was caused by strong hydrodynamic disturbance that mixed sediments originally from the offshore area with those of the lagoon. The lower layer has coarse-grained particles with medium sorting, low organic matter content, and low diatom content. The upper layer has fine-grained particles with poor sorting, high organic matter content, and abundant diatoms. The rate of fragmentation of diatoms in the upper layer was very high (40%–60%). The diatom assemblage contained offshore and freshwater species carried by storm runoff. Therefore, we believe that the sediments of this typical sand bar–lagoon environment retain evidence of typhoon events along the southern China coast that is displayed in the marked sedimentological and microfossil characteristics.

Comparative study of prospective variety numbers of meadow clover in the conditions of the Smolensk region

The purpose of the work was to study the best populations of meadow clover in comparison with the control variety in a competitive variety trial and select the best ones to create a new variety. When summarizing the breeding work from 2011 to 2017, the most productive populations of meadow clover were identified during the selection. Their comparative characteristics are given, morphological characteristics and economically useful indicators and properties are described. In the conditions of the Smolensk region, under normal weather and climatic conditions during the studied period, on sod-podzolic light loamy medium acid soil with a high level of mobile phosphorus and medium mobile potassium, in the nursery of the competitive trial from 6 varieties, a population under the number U-6 emerged in terms of indicators yield of green mass and air-dry matter. The control was the Novichok variety, released since 2000. The cultivar of meadow clover U-6 has increased winter hardiness (99.2%), the yield of green mass is 53.9 t / ha, while the Novichok control is 42.5 t / ha, and the high collection of air-dry matter is 12.4 t / ha (control - 10.6 t / ha). The leafiness of the variety was 42.38% (control - 40.2%), the content of crude protein - 16.58%, which is 5.6% higher than the control variety. The average seed yield for two years is 3.7 centners / ha; this figure exceeds the control by 19.4%.

The Effect of Weather Conditions on Fertilizer Applications: A Spatial Dynamic Panel Data Analysis

AbstractGiven the extreme dependence of agriculture on weather conditions, this paper analyses the effect of climatic variations on this economic sector, by considering both a huge data set and a flexible spatiotemporal model specification. In particular, we study the response of N-fertilizer application to abnormal weather conditions, while accounting for other relevant control variables. The data set consists of gridded data spanning over 21 years (1993–2013), while the methodological strategy makes use of a spatial dynamic panel data (SDPD) model that accounts for both space and time fixed effects, besides dealing with both space and time dependences. Time-invariant short- and long-term effects, as well as time-varying marginal effects are also properly defined, revealing interesting results on the impact of both GDP and weather conditions on fertilizer utilizations. The analysis considers four macroregions—Europe, South America, Southeast Asia and Africa—to allow for comparisons among different socio-economic societies. In addition to finding both spatial (in the form of knowledge spillover effects) and temporal dependences as well as a good support for the existence of an environmental Kuznets curve for fertilizer application, the paper shows peculiar responses of N-fertilization to deviations from normal weather conditions of moisture for each selected region, calling for ad hoc policy interventions.

Topological Modeling Research on the Functional Vulnerability of Power Grid under Extreme Weather

The large-scale interconnection of the power grid has brought great benefits to social development, but simultaneously, the frequency of large-scale fault accidents caused by extreme weather is also rocketing. The power grid is regarded as a representative complex network in this paper to analyze its functional vulnerability. First, the actual power grid topology is modeled on the basis of the complex network theory, which is transformed into a directed-weighted topology model after introducing the node voltage together with line reactance. Then, the algorithm of weighted reactance betweenness is proposed by analyzing the characteristic parameters of the power grid topology model. The product of unit reliability and topology model’s characteristic parameters under extreme weather is used as the index to measure the functional vulnerability of the power grid, which considers the extreme weather of freezing and gale and quantifies the functional vulnerability of lines under wind load, ice load, and their synergistic effects. Finally, a simulation using the IEEE-30 node system is implemented. The result shows that the proposed method can effectively measure the short-term vulnerability of power grid units under extreme weather. Meanwhile, the example analysis verifies the different effects of normal and extreme weather on the power grid and identifies the nodes and lines with high vulnerability under extreme weather, which provides theoretical support for preventing and reducing the impact of extreme weather on the power grid.

Enhancing the Performance of Vehicle Passenger Detection under Adverse Weather Conditions Using Augmented Reality-Based Machine Learning Approach

In response to extreme traffic congestion in metropolitan areas that causes unnecessarily long travel times, high fuel consumption, and excessive greenhouse gas emissions, transportation agencies have implemented various strategies to mitigate traffic congestion. Managed lanes—one of the measures applied worldwide—provide benefits to road users and operating agencies by integrating advanced technologies such as electronic and dynamic tolling systems. However, those agencies already implementing or considering implementing the managed lane strategy are seeking a solution to effectively and properly charge toll rates based on vehicle occupancy and penalize violating vehicles. Vehicle passenger detection systems (VPDSs) have been developed and evaluated worldwide, but limitations still inhibit their full implementation. This study confirms that the performance of the deep learning algorithm, a core VPDS technology, declines under certain adverse weather conditions because of lack of training data sets. The performance of the “you only look once” (YOLOv3) model trained with a normal weather data set decreased by as much as 8.5% when it was tested for adverse weather conditions. In this study, augmented reality (AR) models are developed to enhance the accuracy of vehicle passenger detection (VPDA) by the VPDS by training the algorithm with AR images representing virtual adverse weather conditions. Models trained with AR image sets of various weather categories (fog, rain, and snow) attained VPDA enhanced by up to 7.9%. The final model significantly improves VPDA under adverse weather conditions. The proposed models could be considered for implementation with road weather information systems under adverse weather conditions.

FISS GAN: A Generative Adversarial Network for Foggy Image Semantic Segmentation

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather (clear images), it is difficult to extract and express their texture. No method has previously been developed to directly explore the relationship between foggy images and semantic segmentation images. We investigated this relationship and propose a generative adversarial network (GAN) for foggy image semantic segmentation (FISS GAN), which contains two parts: an edge GAN and a semantic segmentation GAN. The edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation GAN. The semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation images. Experiments on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

Urban tree growth and ecosystem services under extreme drought

Urban trees are supposed to have an important regulating function for the urban microclimate, carbon sequestration and a number of other ecosystem services. Vice versa, urban trees suffer from droughts that are typically enhanced within the urban heat island. In the present study, we examined how ecosystem services cooling and carbon sequestration by urban trees were impaired due to the extreme Central European drought periods in the years 2018 and 2019. The analysis was based on continuous measurements of tree growth, sap flow and meteorological characteristics along a transect of five sites of Tilia cordata and three sites of Robinia pseudoacacia spread over the urban area of Würzburg, Germany. The biomass increment of both tree species was reduced up to 50 % with respect to normal weather conditions, especially in the extreme drought year 2018. The studied tree species revealed contrasting growth strategies with T. cordata being more prone to droughts than R. pseudoacacia. Under drought conditions R. pseudoacacia showed twice as much carbon sequestration as T. cordata, which means that R. pseudoacacia is much more water use efficient than T. cordata. In drought years the water use efficiency increases up to 4.4 kg (kg H2O)−1 for R. pseudoacacia, while it remains at 0.83–0.86 kg (kg H2O)−1 for T. cordata. Whereas both species have shown substantially reduced transpiration rates in both years, T. cordata had a higher transpiration activity than R. pseudoacacia, Hence, T. cordata made a larger contribution to microclimatic cooling in drought and normal years. These findings are systematically depending on the specific sites within the urban area.

A Deep Learning Model for Forecasting Sea Surface Height Anomalies and Temperatures in the South China Sea

AbstractThe field of forecasting oceanic variables has traditionally relied on numerical models, which effectively consider the ocean's dynamic evolution and are of physical importance. However, to make the models more realistic, complicated processes need to be considered, which is difficult because their calculations are complex. In fact, information on the internal dynamic mechanisms and external driving forces of the ocean are already embedded in the time series of observations. Therefore, we can determine the patterns of ocean variations through data mining of these series to achieve forecasting. Furthermore, to predict variations in ocean processes more realistically, interactions between variables and spatial correlations should be effectively considered. Thus, inspired by available remote sensing data and advancements in deep learning technologies, we develop a hybrid model based on a statistical method and a deep learning model to predict multiple sea surface variables. A case study in the South China Sea shows that this model is highly promising for short‐term daily forecasts of the sea surface height anomaly (SSHA) and sea surface temperature (SST). When the forecast time is 10 days, the root mean square errors of this model forecasts for SSHA and SST are approximately 0.0276 m and 0.46°C, respectively, which are much smaller than those of persistence, climatology and linear regression predictions. The anomaly correlation coefficients for SSHA and SST are approximately 0.864 and 0.633, respectively. The model performs satisfactorily under both normal and typhoon weather conditions.

NOVA: Rendering Virtual Worlds with Humans for Computer Vision Tasks

AbstractToday, the cutting edge of computer vision research greatly depends on the availability of large datasets, which are critical for effectively training and testing new methods. Manually annotating visual data, however, is not only a labor‐intensive process but also prone to errors. In this study, we present NOVA, a versatile framework to create realistic‐looking 3D rendered worlds containing procedurally generated humans with rich pixel‐level ground truth annotations. NOVA can simulate various environmental factors such as weather conditions or different times of day, and bring an exceptionally diverse set of humans to life, each having a distinct body shape, gender and age. To demonstrate NOVA's capabilities, we generate two synthetic datasets for person tracking. The first one includes 108 sequences, each with different levels of difficulty like tracking in crowded scenes or at nighttime and aims for testing the limits of current state‐of‐the‐art trackers. A second dataset of 97 sequences with normal weather conditions is used to show how our synthetic sequences can be utilized to train and boost the performance of deep‐learning based trackers. Our results indicate that the synthetic data generated by NOVA represents a good proxy of the real‐world and can be exploited for computer vision tasks.

Analytical Solution of FSO-Mimo System Peformance Using DWDM Optical Communication

Now days, in optical communication network challenge requirement are a high quality factor, good performance in terms of parameters like Bit Error Rate (BER), Eye Diagram. An objective of this paper, to analysis the attenuation value for a haze and normal weather condition respectively, and analysis, performance result of the different optical system has been compared in terms of received signal strength and quality factor of the different haze atmosphere. In this proposed paper used FSO with SISO and FSO-MIMO system for measuring the Q-factor and BER for various data link in different atmosphere. Finally, simulation result shows that the improved FSO link over the existing technique in terms of both the parameter signal power strength and quality factor.

Silane treatment of drop-on glass-beads and their performance in two-component traffic paints

In this research, the surface of drop-on glass beads (GBs) was first etched, then modified using 3- trimethoxy silyl propyl methacrylate (MS) and trimethoxy vinyl silane (VS) through a sol-gel process to improve GBs’ adhesion to the two-component methyl methacrylate-based traffic paints (known as cold plastic paints). The etching was conducted in acidic, neutral, and basic conditions. Acidic etching condition was selected for the further experiments considering the highest number of OH groups provided by etching reaction on the surface of GBs. The FTIR and 13C-NMR spectroscopy were utilized to characterize chemical composition, and Atomic Force Microscopy (AFM) was used to evaluate the surface roughness / topography of the pretreated and silane-treated GBs. The amount of silane coated on the surface of the GBs was determined using thermogravimetric analysis (TGA). The dispersion of silane compounds on the surface of the treated GBs was assessed using Energy Dispersive X-Ray Analysis (EDXA). Neat and silane-treated GBs were then sprayed on freshly applied cold plastic paint samples using a designed lab spray device. Optical microscopy was used to evaluate the proper embedment depth of the GBs onto the surface of the paint samples. The abrasion test was performed in dry and wet conditions to evaluate the adhesion strength of neat and silane-treated GBs to the paint surface in normal and rainy weather. The coefficient of retroreflected luminance (RL) and the luminance coefficient under diffuse illumination (Qd) were measured to characterize the night and day retroreflective performance of cold plastic paints containing treated and untreated GBs. The abrasion test results showed the least weight loss in the paint markings containing drop-on VS-treated GBs (VS.GBs) in comparison to neat and MS-treated GBs (MS.GBs). This was assigned to increase in adhesion strength and interfacial interactions between VS.GBs and the polymeric matrix. The measured values of RL and Qd also confirmed the excellent maintenance of drop on VS.GBs on the surface of the two-component traffic paints.

Road Obstacle Detection in Bad Weather Based on Deep Learning

With the progress of the scientific era, people’s way of travel has become more diverse, not like the ancient carriage travel, but now the car, bus, train, high-speed rail, aircraft and so on for people to choose more, but the emergence of science and technology is like a double-edged sword, the convenience of travel mode will lead to traffic congestion, especially in bad weather In this paper, the deep learning method is used as the basic prediction algorithm to realize the road obstacle detection in bad weather. Under the influence of bad weather, people cannot judge the obstacles clearly, and 87 traffic accidents have occurred in two and a half years, The average number of accidents per day is 1.2, which is higher than that of 1.1 accidents / day in normal weather. The average number of accidents increases by about 20%.

Multivariate weather anomaly detection using DBSCAN clustering algorithm

Weather is highly influential for human life. Weather anomalies describe conditions that are out of the ordinary and need special attention because they can affect various aspects of human life both socially and economically and also can cause natural disasters. Anomaly detection aims to get rid of unwanted data (noise, erroneous data, or unwanted data) or to study the anomaly phenomenon itself (unusual but interesting). In the absence of an anomaly-labeled dataset, an unsupervised Machine Learning approach can be utilized to detect or label the anomalous data. This research uses the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to separate between normal and anomalous weather data by considering multiple weather variables. Then, PCA is used to visualize the clusters. The experimental result had demonstrated that DBSCAN is capable of identifying peculiar data points that are deviating from the ‘normal’ data distribution.

Impact of weather changes on the potato cultivation quality with the LEISA system

The aspect of potato cultivation well known to most farmers is closely related to the climatology of the cultivated site. Therefore, this study aims to obtain the basic information on climatic change in potato cultivation quality using the LEISA system or in potato cultivation, compost is used as fertilizer at a dose of 10-30 tonnes/ha. The experiment was designed based on four treatments namely, (1) cultivation in normal weather conditions from April - June 2019, (2) in foggy air conditions from July to September 2019, (3) in extremely hot conditions from October to December 2019, and (4) in extremely rainy conditions from January to March 2020. The parameters observed were (1) microclimates around the plants, (2) the condition of the growing media depth 0-30 cm, (3) plant growth, and (4) productivity. The changes from normal to foggy, extremely rainy, and hot weather had impacts on soil temperature by 22.1±5.2%, 8.6±2.2%, and 10.3±5.9% respectively. In extremely hot and rainy weather, the cation exchange capacity (CEC) value was low by 22.1±0.16 and 23.8±0.21 meq/100g of dry soil. The extremely hot, rainy, and foggy weather reduced the productivity of potato plants by 32.13–60.2%, 19.5– 43.0%, and 16.7–18.0% respectively. In addition, they also reduced the quality of potato tubers by 19.9–94.7%, 26.0–62.9%, and 8.8–15.9% respectively.

Application of Kalman Filter to Improve 3D LiDAR Signals of Autonomous Vehicles in Adverse Weather

A worldwide increase in the number of vehicles on the road has led to an increase in the frequency of serious traffic accidents, causing loss of life and property. Autonomous vehicles could be part of the solution, but their safe operation is dependent on the onboard LiDAR (light detection and ranging) systems used for the detection of the environment outside the vehicle. Unfortunately, problems with the application of LiDAR in autonomous vehicles remain, for example, the weakening of the echo detection capability in adverse weather conditions. The signal is also affected, even drowned out, by sensory noise outside the vehicles, and the problem can become so severe that the autonomous vehicle cannot move. Clearly, the accuracy of the stereo images sensed by the LiDAR must be improved. In this study, we developed a method to improve the acquisition of LiDAR data in adverse weather by using a combination of a Kalman filter and nearby point cloud denoising. The overall LiDAR framework was tested in experiments in a space 2 m in length and width and 0.6 m high. Normal weather and three kinds of adverse weather conditions (rain, thick smoke, and rain and thick smoke) were simulated. The results show that this system can be used to recover normal weather data from data measured by LiDAR even in adverse weather conditions. The results showed an effective improvement of 10% to 30% in the LiDAR stereo images. This method can be developed and widely applied in the future.

Weather prediction system and recommendation of plant varieties as an effort to minimize harvest failure with android-based Backpropagation Artificial Neural Networks

Based on Malang Regency agriculture data in 2017 presented by the Head of the Agriculture and Food Crops and Horticulture Office (DPTPH), there was a 2.5% decrease in yields. One hectare of paddy land can produce 7.71 tons during normal weather, but currently only produces 6.9 tons per hectare. Three farmers’ groups in Malang Regency (2018), are of the opinion that the current weather greatly influences crop failure. Weather prediction used so far using conventional benchmarks for planting, is no longer relevant to current reality. These estimates are often incorrect, resulting in crop failures, which have an impact on the farmer’s economy. This study aims to make the application of weather prediction systems and recommendations for suitable planting varieties based on data on temperature, humidity, time of sun exposure, wind speed, and rainfall using Backpropagation ANN method. Data used for Karangploso District weather prediction from 2009-2018. While the variables used in the application of Backpropagation ANN: temperature, humidity, time of sun exposure, wind speed, and rainfall. For output, the prediction of rainfall in the next 12 months and planting of varieties in accordance with the predicted rainfall, OPT and land type. From the calculation results of this application the MSE error value of 0.0299 is obtained.