Artificial light at night (ALAN) is a growing global concern, with poorly managed lighting linked to significant health and environmental impacts. Although streetlighting in urban areas has been studied extensively, the contribution of major roads - long-distance connectors between cities - remains unstudied. In this study, we combined global geospatial datasets with VIIRS/DNB and SDGSAT-1 satellite imagery to identify and quantify lit roads outside urban areas across all countries. We then explored their relationships with socio-economic, environmental, and governance indicators. We found that the extent of lit roads outside urban areas at the country level was closely related to urban brightness, reliance on fossil fuels for development, and levels of environmental regulation and awareness. Although most countryside roads remain unlit, we identified 27 countries where more than 2% of the roads outside urban areas were lit, accounting for up to 5.3% of the country's total nighttime surface radiance. Most countries with illuminated rural roads included oil- and gas- producers with high GDP per capita, located in the Middle East, as well as highly urbanized, high GDP per capita nations in South East Asia. Conversely, even among wealthy countries, those with strong environmental policies and carbon-pricing mechanisms exhibit minimal countryside road illumination. This study is the first to quantify contribution of major roads outside urban areas to night-time radiance and highlights the value of nighttime sensors for advancing ALAN research.

Abstract This study presents a machine learning framework for predicting pedestrian accident severity using Amman, Jordan's first complete 10-year traffic dataset (2014–2023). Addressing the critical class imbalance where minor injuries predominate (85%), causing standard models to poorly detect severe cases (< 25% recall), we implement cost-sensitive algorithms and specialized undersampling techniques, such as XGBoost with Balancing the Loss Function (XGBLF) and Random Data Partitioning with Voting Rule (RDPVR), which enhanced learning from underrepresented Major/Fatal cases while maintaining data authenticity. Through mixed-type correlation analysis and statistical testing, vehicle speed, road illumination, vehicle type, driver age, and road conditions emerged as the most significant predictive factors. RDPVR achieved a 63% true positive rate for Major/Fatal injuries, a 2.78-fold improvement over standard classifiers, and XGBLF achieved 95%, but this achievement was on account of the accuracy of the minor cases. Comprehensive interpretability analysis (SHAP, LIME, and Permutation Importance) revealed that heavy vehicles, poor lighting, and high-speed driving strongly predict Major/Fatal outcomes. Notably, the analysis demonstrates Jordan's improved safety trajectory, with 2020–2023 showing reduced severe accidents compared to 2014–2016, indicating measurable policy impact. This study delivers the first interpretable, context-sensitive AI framework for Amman/Jordan pedestrian safety, translating technical insights into actionable recommendations for targeted interventions, urban planning, and data-driven enforcement strategies to reduce pedestrian injury severity in high-risk zones.

Road illumination and nighttime pedestrian deaths: Evidence from moonlight

• Performed extensive photometric simulation of metal halide-based public road lighting systems. • Propounded models based on multiple regression analysis and artificial neural networking (ANN). • Luminaire power per unit road length and standard specular factor were the most important predictor variables. • The 50-neuron ANN model had the lowest mean square error and highest coefficient of correlation. • ANN-based models performed much better than the multiple regression analysis-based model. Public road illumination systems shape the urban landscape and are ineluctable to ensuring the nocturnal safety of motorists, wayfarers, and pedestrians. In developing nations including India, various local bodies still rely on time-honoured discharge lamps including metal halide (MH) lamps for road lighting. This study aimed to develop practicable models for predicting luminance and energy efficiency parameters of MH-based public road illumination systems. Photometric simulations were conducted for 80,000 installation combinations considering single-sided arrangements of MH luminaires and candidate models of predicting luminance and energy efficiency parameters were propounded with multiple regression analysis and two-layer feed-forward artificial neural networks (ANNs). Luminaire power per unit road length (τ, W/km) and standard specular factor (S 1 ) were found to be the most important predictor variables for the prediction of photometric parameters and installation energy efficiency respectively. For some conventional design configurations, the performances of the models were assessed and the 50-neuron ANN model performed well with an error margin of – 1.45 % to + 1.71 % for the prediction of average luminance, of – 8.67 % to + 9.08 % for the prediction of overall uniformity, of – 8.31 % to + 16.40 % for the prediction of longitudinal uniformity and of – 1.56 % to + 1.52 % for the prediction of installation energy efficiency. Through extensive photometric simulation and data analysis, this study provides useful insights for the commissioning of road lighting projects especially pertaining to the usefulness of ANN models for the planning and optimization of public road illumination systems in developing countries.

Dynamic weighing systems, an advanced technology for traffic management, are designed to measure the weight of moving vehicles without obstructing traffic flow. These systems play a critical role in monitoring freight vehicle overloading, collecting weight-based tolls, and assessing the structural health of roads and bridges. However, due to the complex road traffic environment in real-world applications of dynamic weighing systems, some vehicles cannot be accurately weighed, even though precise parameter calibration was conducted prior to the system's official use. The variation in driving behaviors among different drivers contributes to this issue. When different types and sizes of vehicles pass through the dynamic weighing area simultaneously, changes in the vehicles' motion states are the main factors affecting weighing accuracy. This study proposes an improved SSD vehicle detection model to address the high sensitivity to vehicle occlusion and frequent vehicle ID changes in current multi-target tracking methods. The goal is to reduce detection omissions caused by vehicle occlusion. Additionally, to obtain more stable trajectory and speed data, a Gaussian Smoothing Interpolation (GSI) method is introduced into the DeepSORT algorithm. The fusion of dynamic weighing data is used to analyze the impact of changes in vehicle size and motion states on weighing accuracy, followed by compensation and experimental validation. A compensation strategy is implemented to address the impact of speed fluctuations on the weighing accuracy of vehicles approximately 12.5 m in length. This is completed to verify the feasibility of the compensation method proposed in this paper, which is based on vehicle information. A dataset containing vehicle length, width, height, and speed fluctuation information in the dynamic weighing area is constructed, followed by an analysis of the key factors influencing dynamic weighing accuracy. Finally, the improved dynamic weighing model for extracting vehicle motion state information is validated using a real dataset. The results demonstrate that the model can accurately detect vehicle targets in video footage and shows strong robustness under varying road illumination conditions.

ABSTRACT Nighttime illuminated roads (NTIRs) are closely related to residents' nighttime travel and activities. However, traditional nighttime light (NTL) data are not highly applicable for large-scale NTIR extraction tasks because of challenges such as low resolution and data acquisition. In contrast, the open-sourced SDGSAT-1 NTL data released in 2021 which contains a panchromatic band (PAN) of 10-m resolution and red, green, blue bands (RGB) of 40-m resolution, are more suitable for this task. To date, research on NTIR extraction methods is still insufficient, and the application potential of NTIR products has not been fully explored. In this work, a deep learning model called DSC-UNet was proposed for NTIR extraction via SDGSAT-1 NTL imagery of 10-m spatial resolution. The proposed model uses UNet as the basic architecture and incorporates a dynamic snake convolution module to increase the sensitivity of the NTIR pixels. Our experimental results showed that DSC-UNet outperformed seven baseline models. Using the proposed model and vectorization tools, a high-accuracy NTIR centerline product of the BTH region was generated. By applying spatial statistics, the road illumination rate of the BTH region was assessed. The assessment results revealed an imbalance in road lighting levels among different cities in the BTH region.

This paper presents Adaptive Headlight Management Information System for Optimized Intensity and Direction in Electric Vehicles, aimed at optimizing road illumination while minimizing glare for other road users. The system integrates three primary components: the Vital Illumination Sensing System (VISS), the Headlight Adjusting System (HAS), and the Light Intensity Adjusting System (LIAS). The CISS, which consists of a PIXY2 microcontroller and a camera, detects oncoming vehicles and evaluates their headlight intensity using machine learning algorithms. The microcontroller then adjusts the intensity of the vehicle's own headlights through the LIAS, which uses a DC-DC boost chopper to vary the duty cycle according to the required light intensity.The HAS controls the headlight’s direction by using a servo mechanism to adjust its angle, ensuring that the light is directed precisely on the road, especially during turns or inclines. The system dynamically predicts the necessary adjustments by processing data from the PIXY2 microcontroller and applying image processing algorithms. Additionally, the integration of IoT communication protocols, such as Wi-Fi and GPRS, enables real-time data transmission to the user interface, allowing the rider to receive notifications about headlight status, intensity adjustments, and anomalies.By continuously adjusting the headlight intensity and direction based on real-time vehicle and road conditions, the system enhances road safety, conserves energy, and reduces glare for other road users. This innovative approach represents a significant step forward in the development of intelligent lighting systems for electric vehicles.

This paper examines the road lighting design practice in Indonesia’s urban kampung, which is one of the important elements that shape and define an Indonesian city. However, it appears that the current road illumination standard disregards its existence and creates regulations based on the requirements of motorist. In contrast, urban kampung roads are more intricate due to their frequent use as shared spaces. The research explains the issue by utilizing a literature review and a case study of urban kampung Siwalankerto as an illustration. Even though the placement of streetlights and the measurement of average illuminance comply with SNI standards, there is no significant correlation between the perception of safety and the quantity of light deemed adequate by residents. This finding contradicts the primary function of street illumination, which is to promote night-time safety. Keywords: urban kampung, road lighting, illumination, lighting regulation

This paper presents a UAV-based road illumination measurement system and evaluates its performance through experiments. The system employs a HUBSAN Zino 2+ UAV, STM32F103RCT6 microcontroller, BH1750 illuminance sensor, and GPS and integrates flight, processing, measurement, cloud platform, obstacle avoidance, communication, and power supply units via the OneNET cloud platform. Both hardware and software designs were implemented, using the Z-score algorithm to handle outliers in illumination data. The system showed a single-point measurement error rate of 1.14% and a MAPE of 5.08% for multi-point measurements. In experiments, the system’s horizontal and vertical illuminance RMSE were 1.92 lx and 1.75 lx, respectively. The real-time visualization interface improved operational efficiency, cutting labor costs by half and time costs by nearly four-fifths. UAV control and monitoring from the roadside ensured safety during measurements. The system’s efficiency and wide measurement range enabled extended experiments, collecting illuminance data across multiple horizontal and vertical planes. This resulted in the creation of both horizontal and innovative vertical-plane illuminance distribution maps. These findings provide valuable data for evaluating road lighting quality, enhancing road traffic safety, and improving road illumination design.

The construction and installation of street lighting is an important element in the modernization of China’s cities. Besides, it also plays an important role in raising the living standards of the people. In recent years, with the technological and economic development, smart street lighting has gradually emerged. Key functions of smart street lighting include road illumination, cultural promotion, meteorological monitoring, public broadcasting, and 5G micro-base stations. The overall quality of smart street lighting construction directly impacts the effectiveness of urban development and the city’s comprehensive growth. This paper analyzes the concept of smart street lighting, its advantages and disadvantages, the functionalities of smart street light systems, and the application of smart street lighting in urban road illumination.

An assessment of general road illumination system simulation methods and comparison of simulation outcomes with photometric measurements conducted on a public road with anthropogenic sources of peripheral illumination

Predictive modelling of lighting quality parameters and energy efficiency of light emitting diode-based general road illumination systems with special emphasis on luminaire tilt and bracket length

Driving at night poses a serious risk due to the momentary blindness brought on by oncoming traffic’s headlights. Traditional headlight designs impair vision temporarily, which increases the risk of accidents. Manual headlight settings and inadequate lighting make the issue worse. An in-depth review of the various sensors-based headlight control systems used by various automaker firms has been conducted. This study discusses a system for detecting vehicles that makes use of a camera and a regression-based machine-learning model. Using a grid formation technique on video that the on-board camera has processed, the position of the approaching vehicle is determined. A signal is then sent to a reflector system that has been specially designed to enable precise beam control with the help of a control unit made up of several electronic components, such as an Arduino UNO, a relay, and a battery. The proposed technology can increase nighttime driving safety by eliminating the Troxler effect on drivers of opposing vehicles while retaining adequate road illumination for the driver on-board.

To drive safely and comfortably, an adequate contrast between the road surface and road markings is needed. This contrast can be improved by using optimized road illumination designs and luminaires with dedicated luminous intensity distributions, taking advantage of the (retro)reflective characteristics of the road surface and road markings. Since little is known about road markings' (retro)reflective characteristics for the incident and viewing angles relevant for street luminaires, bidirectional reflectance distribution function (BRDF)-values of some retroreflective materials are measured for a wide range of illumination and viewing angles using a luminance camera in a commercial near-field goniophotometer setup. The experimental data are fitted to a new and optimized "RetroPhong" model, which shows good agreement with the data [root mean squared error (R M S E)<0.13, normalized root mean squared error (N R M S E)<0.04, and the normalized cross correlation ratio (N C C)>0.8]. The RetroPhong model is benchmarked with other relevant (retro)reflective BRDF models, and the results suggest that the RetroPhong model is most suitable for the current set of samples and measurement conditions.

Purpose Properly planned road illumination systems are collectively a public wealth and the commissioning of such systems may require extensive planning, simulation and testing. The purpose of this simulative work is to offer a simple approach to facilitate luminance-based road lighting calculations that can be easier to comprehend and apply to practical designing problems when compared to complex multi-objective algorithms and other convoluted simulative techniques. Design/methodology/approach Road illumination systems were photometrically simulated with a created model in a validated software platform for specified system design configurations involving high-pressure sodium (HPS) and light-emitting diode (LED) luminaires. Multiple regression analyses were conducted with the simulatively obtained data set to propound a linear model of estimating average luminance, overall uniformity of luminance and energy efficiency of lighting installations, and the simulatively obtained data set was used to explore luminaire power–road surface average luminance characteristics for common geometric design configurations involving HPS and LED luminaires, and four categories of road surfaces. Findings The six linear equations of the propounded linear model were found to be well-fitted with their corresponding observation sets. Moreover, it was found that the luminaire power–road surface average luminance characteristics were well-fitted with linear trendlines and the increment in road surface average luminance level per watt increment of luminaire power was marginally higher for LEDs. Originality/value This neoteric approach of estimating road surface luminance parameters and energy efficiency of lighting installations, and the compendia of luminaire power–road surface average luminance characteristics offer new insights that can prove to be very useful for practical purposes.

In recent years, there has been a trend towards energy-efficient, long-lasting, environmentally friendly, and technology-compatible LED road luminaires. In this study, the optical design and analysis of the LED road luminaire model for the M1 and M2 illumination classes roads, which are the roads with the highest importance, have been carried out. In the research, the unique reflector design was made using SolidWorks 3D design software. XLamp CXA1520 LED light source by Cree company was preferred during the design. 21 LEDs were placed on the reflector at the ideal distance and LED luminaire model was created in LightTools illumination design software. A simulation study was performed for the LED luminaire model created on LightTools software and the distribution curve of luminous intensity was obtained. At the same time, the EULUMDAT (.ldt) file, which is required for road illumination analysis, was produced with LightTools software. The obtained .ldt file was transferred to DIALux illumination calculation program and simulated for M1 and M2 class roads. Illumination parameters obtained from DIALux analysis have been optimized by comparing them with the road illumination criteria accepted by International Commission on Illumination (CIE). It has been observed that the designed LED luminaire model significantly meets the M1 and M2 class road illumination criteria defined by CIE. In the study, it was also discussed what changes can be made in the optical material to meet all criteria.

In this study, numerical analysis was made for 7 different road scenarios, which are called functional illumination in the architectural field. In functional illumination (road illumination) within the scope of the lighting masterplan, optimum illumination was provided in the simulation environment according to the criteria of the International Illumination Commission (CIE). According to the criteria of the CIE, the illumination system that does not adversely affect living things and the environment has been proposed by providing the limit values for the illuminance level, luminance, overall (resultant) uniformity, and longitudinal uniformity. In the architectural field, it is thought that functional illumination will increase the attractiveness of the city and contribute to architectural aesthetics by providing visual comfort.

Diffuse reflection-based lighting calculation model and particle swarm optimization algorithm for road tunnels

The fundamental goal of this research is to create something that is long-lasting, environmentally friendly, and energyefficient for everyday consumers. As a result, the concept of an automatic green street lighting system was proposed, addressing the issue of needless road illumination and, in particular without energy wastage. Street lighting when it is not required is a waste of resources and electrical energy in general. Modern civilization has adopted the philosophy of "Going Green," which is emphasized at all times, particularly in the engineering field. Engineers come up with novel ways to save energy while improving the efficiency of their goods. One of these methods is to use a smart system, which has applications in numerous areas of society, such as at home, at work, and so on. Our main goal is to reduce energy while maintaining user-friendliness. Smart systems, created years ago, are still the foundation and are used to this day, improving as time goes on and striving for even greater development.

As the demand for electrical energy increases daily, it has become inevitable to use electrical energy more efficiently and economically. To reduce foreign dependency in energy in our country, various steps are taken to bring the areas where energy is used under the focus and to bring the existing systems to a better level with technology. 20 % of the energy consumed in our country is used in illumination. The share of road illumination is high illumination. Besides, since the control and observability of the road illumination inside the external illumination are easy, it is easier for countries to work in this field. New generation technologies are rapidly adopted, followed, and applied in our country. Light sources and luminaires used in road illumination have constantly changed with technology. High-pressure sodium vapor lamps are primarily used in road illumination in our country. In addition, LED luminaires, which are considered a new generation illumination technology, have startedto find wide use in this market. A comparative analysis of luminaires with high-pressure sodium vapor lamps and LED luminaires used in road illumination was made in this study. DIALux program was used to compare these analyses.