Vehicle Data Research Articles

A novel state of health prediction method for battery system in real-world vehicles based on gated recurrent unit neural networks

State of health (SOH) is crucial to battery management system. However, SOH accuracy and reliability is difficult to be guaranteed owing to complex ageing mechanisms and driving conditions. This paper proposes a novel battery SOH prediction method based on gated recurrent unit (GRU) neural network for real-world vehicles. Firstly, real-vehicle operating data is extracted as well as cleaned and sliced to improve data reliability, then the Kalman filter and recursive least squares method are used to identify the ohmic internal resistance (OIR). The GRU neural network is established to realize the battery SOH prediction, and the average relative error of final validation set is less than 0.65 %. To further validate the reliability and applicability of the prediction method, four other vehicles data are set as input, and the SOH results indicate that all average relative errors are still within 4 %. This study demonstrates the feasibility of using OIR as a health factor for real-world vehicles, and also provides a new solution for accurately predicting battery SOH for real-world vehicles.

An improved deep reinforcement learning routing technique for collision-free VANET

Vehicular Adhoc Networks (VANETs) is an emerging field that employs a wireless local area network (WLAN) characterized by an ad-hoc topology. Vehicular Ad Hoc Networks (VANETs) comprise diverse entities that are integrated to establish effective communication among themselves and with other associated services. Vehicular Ad Hoc Networks (VANETs) commonly encounter a range of obstacles, such as routing complexities and excessive control overhead. Nevertheless, the majority of these attempts were unsuccessful in delivering an integrated approach to address the challenges related to both routing and minimizing control overheads. The present study introduces an Improved Deep Reinforcement Learning (IDRL) approach for routing, with the aim of reducing the augmented control overhead. The IDRL routing technique that has been proposed aims to optimize the routing path while simultaneously reducing the convergence time in the context of dynamic vehicle density. The IDRL effectively monitors, analyzes, and predicts routing behavior by leveraging transmission capacity and vehicle data. As a result, the reduction of transmission delay is achieved by utilizing adjacent vehicles for the transportation of packets through Vehicle-to-Infrastructure (V2I) communication. The simulation outcomes were executed to assess the resilience and scalability of the model in delivering efficient routing and mitigating the amplified overheads concurrently. The method under consideration demonstrates a high level of efficacy in transmitting messages that are safeguarded through the utilization of vehicle-to-infrastructure (V2I) communication. The simulation results indicate that the IDRL routing approach, as proposed, presents a decrease in latency, an increase in packet delivery ratio, and an improvement in data reliability in comparison to other routing techniques currently available.

Determination of Energy Savings via Fuel Consumption Estimation with Machine Learning Methods and Rule-Based Control Methods Developed for Experimental Data of Hybrid Electric Vehicles

In this study, a parallel hybrid electric vehicle produced within the scope of our project titled “Development of Fuel Efficiency Enhancing and Innovative Technologies for Internal Combustion Engine Vehicles” has been modeled. Firstly, a new rule-based control method is proposed to minimize fuel consumption and carbon emission values in driving cycles in the experimental model of the parallel hybrid electric vehicle produced within the scope of this project. The proposed control method ensures that the internal combustion engine (ICE) operates at the optimum point. In addition, the electric motor (EM) is activated more frequently at low speeds, and the electric motor can also work as a generator. Then, a new dataset was also created on a traffic-free racetrack with the proposed control method for fuel consumption estimation of a parallel hybrid electric vehicle using ECE-15 (Urban Driving Cycle), EUDC (Extra Urban Driving Cycle), and NEDC (New European Driving Cycle) driving cycles. The data set is dependent on 11 different input variables, which complicates the system. Afterward, the fuel estimation process is made with seven different machine learning methods (ML), and these methods are compared using the obtained data set. To avoid overfitting machine learning, two different test data sets were created. The Random Forest algorithm is the most suitable technique in terms of training and testing the fuel consumption model using correlation coefficient (R2), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) simulation appropriateness for both test datasets. Moreover, the random forest algorithm achieved an impressive accuracy of 97% and 90% for both test datasets, outperforming the other algorithms. Furthermore, the proposed method consumes 4.72 L of fuel per 100 km, while the gasoline-powered vehicle consumes 7 L of fuel per 100 km. The results show that the proposed method emits 4.69 kg less CO2 emissions. The effectiveness of the Random Forest Algorithm has been verified by both simulation results and real-world data.

Design of Parking Information System in Langsa City General Hospital, Aceh

This study designed and built a parking information system at the Langsa City General Hospital with the aim of facilitating the management of incoming and outgoing vehicle data at the Langsa City General Hospital parking lot in Aceh. With the rapid advancement of technology, previous data management was still done manually, so it was not effective and efficient, and officers found it very difficult to know the data of incoming and outgoing vehicles. Researchers designed a computer-based information system to facilitate the management of the parking system. Methods of data collection using descriptive qualitative methods, namely observation, interviews, and literature study, and software development methods using the waterfall as well as the PHP programming language and the MYSQL database The information system created aims to make it easier for officers to manage vehicle entry and exit data at the Langsa City Regional General Hospital in Aceh.

Simulation model of a vehicle in the Simulink environment for determining fuel consumption in driving cycles

BACKGROUND: The paper shows that the problem of determining objective indicators of fuel consumption in operation based on calculation methods remains relevant. One of these methods is simulation modeling. Current state of computer technology significantly simplifies building of system simulation models, for example, using the Simulink software by Mathworks. In the process of model development, it is necessary to keep the balance of generalization and detailing, since excessive detailing leads to an unreasonably deep consideration of individual elements of the system and to a significant increase in simulation time.
 AIMS: Search for a reasonable structure of model of the driver car environment system, which makes it possible to simulate the car in driving cycles or other driving scenarios.
 METHODS: The MATLAB/Simulink simulation environment was used in the study. Based on the analysis of the car design and the capabilities of individual Simulink tools, a block diagram to study fuel consumption using the example of a passenger vehicle was synthesized. The obtained model was debugged for the stable motion simulation of the vehicle in various driving cycles using graphical analysis.
 RESULTS: The obtained results show that the developed system simulation model is well behaved. Control systems ensure the vehicle motion according to the mixed driving cycle modes in compliance with the required tolerances. It is possible to register fuel consumption and other simulation results of interest.
 CONCLUSIONS: The model showed the relative simplicity of setting up and the ability of quick update for other vehicles. A minimal amount of vehicle data is required to bring the model to an operable condition. Particular unknown parameters are supposed to be refined using identification methods.

A Bayesian extreme value theory modelling framework to assess corridor-wide pedestrian safety using autonomous vehicle sensor data

Pedestrians are a vulnerable road user group, and their crashes are generally spread across the network rather than in a concentrated location. As such, understanding and modelling pedestrian crash risk at a corridor level becomes paramount. Studies on pedestrian crash risks, particularly with the traffic conflict data, are limited to single or multiple but scattered intersections. A lack of proper modelling techniques and the difficulties in capturing pedestrian interaction at the network or corridor level are two main challenges in this regard. With autonomous vehicles trialled on public roads generating massive (and unprecedented) datasets, utilising such rich information for corridor-wide safety analysis is somewhat limited where it appears to be most relevant. This study proposes an extreme value theory modelling framework to estimate corridor-wide pedestrian crash risk using autonomous vehicle sensor/probe data. Two types of models were developed in the Bayesian framework, including the block maxima sampling-based model corresponding to Generalised Extreme Value distribution and the peak over threshold sampling-based model corresponding to Generalised Pareto distribution. The proposed framework was applied to autonomous vehicle data from Argoverse—a Ford Motors subsidiary. This autonomous vehicle fleet of Agro AI (owner of Argoverse dataset) is equipped with two 64 beams synchronised LiDAR sensors, a cluster of seven high-resolution cameras, and a pair of stereo-vison high-resolution cameras to capture surrounding road users’ information within a range of 200 meters. A subset of the Argoverse dataset, focussing on an arterial corridor in Miami, USA, was used to extract pedestrian and vehicle trajectories. From these trajectories, vehicle–pedestrian conflicts were identified and measured using post encroachment time. The non-stationarity of extremes was captured by vehicle volume, pedestrian volume, average vehicle speed, and average pedestrian speed in the extreme value model. Both block maxima and peak over threshold sampling-based models were found to provide a reasonable estimate of historical pedestrian crash frequencies. Notably, the block maxima sampling-based model was more accurate than the peak over threshold sampling-based model based on mean crash estimates and confidence intervals. This study demonstrates the potential of using autonomous vehicle sensor data for network-level safety, enabling an efficient identification of pedestrian crash risk zones in a transport network.

Sustainable and Round-Optimized Group Authenticated Key Exchange in Vehicle Communication

Vehicle authentication is an essential component validating the vehicle’s identity and ensuring the integrity of transformed data for intelligent transport vehicles (ITS) in the vehicular ad hoc network (VANET). Easy to deploy and operate privacy-enhancing vehicle authentication mechanisms are the mainstay for the widespread ITS in the VANET. Very recently, VANET security architectures are constituting by IEEE 1609.2 group, NoW project, the SeVeCom project. However, these approaches heavily depend on the consuming public key infrastructure (PKI) and certification authorities (CA). In this work, walking along the research line, we attempt to design authentication protocols with two diverse factors for Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) networks, respectively, without depending on the stumbling block PKI/CA. In addition, a smooth projective hash function (SPHF) (a.k.a., a special case of the designated-verifier zero-knowledge proof system) guarantees any recipient can confirm the authenticity and integrity of the received messages without knowing the authentication factors. Thus, to optimize the communication round, SPHF is used to design a (group) two-factor authenticated key exchange (AKE) with low-interactive communication rounds. The proof-of-concept implementation indicates that the computation and communication overheads introduced by our solution are acceptable in real-world deployments. The security of the proposed approach is validated using Bellare-Pointcheval-Rogaway (BPR) model along with the experimental evaluation and the theoretical analysis.

Surface sediment classification using a deep learning model and unmanned aerial vehicle data of tidal flats

This study proposes a deep learning model, U-Net, to improve surface sediment classification using high-resolution unmanned aerial vehicle (UAV) images. We constructed training datasets with UAV images and corresponding labeling data acquired from three field surveys on the Hwangdo tidal flat. The labeling data indicated the distribution of surface sediment types. We compared the performance of the U-Net model trained in various implementation environments, such as surface sediment criteria, input datasets, and classification models. The U-Net trained with five class criteria—derived from previous classification criteria—yielded valid results (overall accuracy:65.6 %). The most accurate results were acquired from trained U-Net with all input datasets; in particular, the tidal channel density caused a significant increase in accuracy. The accuracy of the U-Net was approximately 20 % higher than that of other classification models. These results demonstrate that surface sediment classification using UAV images and the U-Net model is effective.

The mid‐latitude hydrolaccolith of the Spanish Central System (Southern Europe): A top‐to‐bottom integration of geomatic, geophysical and sedimentary datasets for characterising a singular periglacial landform

AbstractPermafrost study in the Spanish Central System (~41°N) has remained elusive in past decades. Although numerous periglacial features have been described, none has yielded conclusive information about the existence/distribution of permafrost across these mountains. This work focuses on integrating light detection and ranging and unmanned aerial vehicle data with geophysical methods and sedimentary records, along with preliminary thermal information, for the comprehensive study of a frost mound. The singularity of this feature resides in its location, currently dominated by a seasonal frost regime, and its size reaching 59 m long, 22.5 m wide and 4 m high, representing the largest landform of this type in Iberia. From top‐to‐bottom, the internal structure comprises three resistivity units (G1, G2 and G3). The most superficial unit (G1) consists of a sequence of burial soils alternating with sand and silts, with pebbles and gravel at the bottom, followed by a high porous layer that belongs to a landslide deposit (G2), likely composed of gravel and pebbles laying over unit G3 (bedrock). Calibrated 14C ages suggest this landform formed at least ~4300 years ago during the mid‐Holocene. Finally, the preliminary surface thermal map indicates the presence of sectors affected by strong thermal gradients likely driven by water table variations. Our results conclude that the dynamics are primarily controlled by the seasonal frost regime influencing local subsurface drainage, which allows us to classify this landform as a hydrodynamic pingo‐like structure. We also demonstrate that our approach is suitable for assessing the evolution of this type of periglacial landform. Implementing long‐lasting annual monitoring programmes would help to understand local periglacial dynamics better.

Impact of federated deep learning on vehicle-based speed control in mixed traffic flows

This study investigates the application of Federated Learning (FL) in an environment of mixed traffic flow with Connected and Automated Vehicles (CAVs). The focus of this study is set on the CAV cruise control speed adjustment which is enforced by the Intelligent Speed Adaptation (ISA) system. It is modelled as an Actor-Critic-based learning architecture with the goal of computing the vehicle speed based on the data of the nearby vehicles. Some CAVs achieve poor travel time performance in comparison to others. Thus, the proposed FL framework selects periodically best-performing CAVs which are local clients in the context of FL. The updated global model is computed based on the weighted averaging of the best-performing models of clients. The use case environment is modelled as a simulation of a synthetic motorway with an induced capacity drop in the form of a work-zone under moderate and high traffic demand. It is shown that the FL framework can stabilise the individual client learning convergence and reduce their travel time compared to the local learning approach. The overall motorway throughput is also increased by the proposed FL framework. This indicates that the global model of FL can utilise the optimal ratio between generalisation and bias towards the most effective control policy of individual speed control. Results show that those effects are more prominent under moderate traffic demand.

Anomalous vehicle recognition in smart cities using persistent bloom filter: Memory efficient and intelligent monitoring

AbstractGlobally, there is a rapid and significant change in the distribution of the urban population. Concerning which there is an increase in traffic rule violations in smart cities, resulting in traffic congestion and accidents. Anomalous vehicle recognition in smart cities is a critical issue that demands prompt and real‐time responsive solutions to address such situations. This article proposes an effective technique utilizing a persistent bloom filter to store and retrieve vehicle data, to improve road safety in urban locations. The technique employs distinct bloom filters to store vehicle data based on the hour, day, month, and year, which enables effective temporal membership queries on vast data. The proposed approach of anomalous vehicle recognition in smart cities using a persistent bloom filter is a memory‐efficient and intelligent monitoring technique. According to experimental analysis on large datasets such as “Montgomery County 911 Calls", “EMS and Fire Calls", “Seattle Fire Dept: 911", and “Traffic Violations in Montgomery County", the approach has the potential to boost query efficiency by up to 80% in comparison to conventional methods, in addition to decreasing storage space demands by up to 60%. The proposed approach has the potential to bridge the gap between research and practice in the field of urban safety and to enhance road safety while considering the dynamic changes in the road network. Employing traditional approaches to detect violations and monitor real‐time changes in a vast dataset of vehicles can be a laborious undertaking. The proposed technique provides a reliable and efficient approach to handling big data and improving traffic safety in smart cities.

Urban Road Lane Number Mining from Low-Frequency Floating Car Data Based on Deep Learning

Lane-level road information is especially crucial now that high-precision navigation maps are in more demand. Road information may be obtained rapidly and affordably by mining floating vehicle data (FCD). A method is proposed to extract the number of lanes on urban roads by combining deep learning and low-frequency FCD. Initially, the FCD is cleaned using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique. Then, the FCD is split into three categories based on the typical urban road types: one-way one-lane, one-way two-lane, and one-way three-lane, and the deep learning sample data is created using segmentation, rotation, and gridding. Lastly, the number of urban road lanes is obtained by training and predicting the sample data using the LeNet-5 model. The number of urban road lanes was effectively identified from the low-frequency FCD with a detection accuracy of 92.7% through the cleaning and classification of Wuhan FCD. Urban roads can be efficiently covered by the FCD on a regular basis, and lane information can be efficiently collected using deep learning techniques. This method can be used to generate and update lane number information for high-precision navigation maps.

An analysis of physiological responses as indicators of driver takeover readiness in conditionally automated driving

By the year 2045, it is projected that Autonomous Vehicles (AVs) will make up half of the new vehicle market. Successful adoption of AVs can reduce drivers’ stress and fatigue, curb traffic congestion, and improve safety, mobility, and economic efficiency. Due to the limited intelligence in relevant technologies, human-in-the-loop modalities are still necessary to ensure the safety of AVs at current or near future stages, because the vehicles may not be able to handle all emergencies. Therefore, it is important to know the takeover readiness of the drivers to ensure the takeover quality and avoid any potential accidents. To achieve this, a comprehensive understanding of the drivers’ physiological states is crucial. However, there is a lack of systematic analysis of the correlation between different human physiological responses and takeover behaviors which could serve as important references for future studies to determine the types of data to use. This paper provides a comprehensive analysis of the effects of takeover behaviors on the common physiological indicators. A program for conditional automation was developed based on a game engine and applied to a driving simulator. The experiment incorporated three types of secondary tasks, three takeover events, and two traffic densities. Brain signals, Skin Conductance Level (SCL), and Heart Rate (HR) of the participants were collected while they were performing the driving simulations. The Frontal Asymmetry Index (FAI) (as an indicator of engagement) and Mental Workload (MWL) were calculated from the brain signals to indicate the mental states of the participants. The results revealed that the FAI of the drivers would slightly decrease after the takeover alerts were issued when they were doing secondary tasks prior to the takeover activities, and the higher difficulty of the secondary tasks could lead to lower overall FAI during the takeover periods. In contrast, The MWL and SCL increased during the takeover periods. The HR also increased rapidly at the beginning of the takeover period but dropped back to a normal level quickly. It was found that a fake takeover alert would lead to lower overall HR, slower increase, and lower peak of SCL during the takeover periods. Moreover, the higher traffic density scenarios were associated with higher MWL, and a more difficult secondary task would lead to higher MWL and HR during the takeover activities. A preliminary discussion of the correlation between the physiological data, takeover scenario, and vehicle data (that relevant to takeover readiness) was then conducted, revealing that although takeover event, SCL, and HR had slightly higher correlations with the maximum acceleration and reaction time, none of them dominated the takeover readiness. In addition, the analysis of the data across different participants was conducted, which emphasized the importance of considering standardization or normalization of the data when they were further used as input features for estimating takeover readiness. Overall, the results presented in this paper offer profound insights into the patterns of physiological data changes during takeover periods. These findings can be used as benchmarks for utilizing these variables as indicators of takeover preparedness and performance in future research endeavors.

Battery defect detection for real world vehicles based on Gaussian distribution parameterization developed LCSS

Accurate detection of early faults in lithium-ion (Li-ion) battery packs plays an important role in preventing safety accidents and reducing property damage. At present, fault diagnosis research based on actual vehicle single-cell voltage consistency has become a hot topic, but the consistency evolution law is not uniform due to complex environmental conditions and operating conditions, so the generalization of current methods is poor. To this end, this paper proposes a multi-layer fault diagnosis framework, which first considers the evolution law of single-unit voltage difference to determine whether there is a potential risk, and proposes a flexible screening method for state of charge (SOC) interval segments, which improves the accuracy and efficiency of inspection. Next, the thresholds required by the developed longest common subsequence (DLCSS) algorithm are parameterized based on Gaussian distribution and combined with z-score to construct fault diagnosis indicators. The parameters of the framework are calculated from different segment data statistics, enhancing the objectivity and interpretability of the parameters. The results are validated using actual vehicle data and show that the proposed framework can greatly reduce the required time and identify faulty batteries more accurately with a 96.2 % precision and a 72.4 % detection rate, which is better than other algorithms and has better robustness.

DLPformer: A Hybrid Mathematical Model for State of Charge Prediction in Electric Vehicles Using Machine Learning Approaches

Accurate mathematical modeling of state of charge (SOC) prediction is essential for battery management systems (BMSs) to improve battery utilization efficiency and ensure a good safety performance. The current SOC prediction framework only considers battery-related features but ignores vehicle information. Additionally, in light of the emergence of time-series Transformers (TSTs) that harness the power of multi-head attention, developing a SOC prediction model remains a significant challenge. Therefore, we introduce a new framework that integrates laboratory battery data with mathematical vehicle model features to improve the accuracy of the SOC and propose a prediction model named DLPformer, which can effectively capture variations in the SOC attributed to both trend and seasonal patterns. First, we apply Matlab/Simulink to simulate a mathematical model of electric vehicles and process the generated vehicle data with Spearman correlation analysis to identify the most relevant features, such as the mechanical losses of the electric motor, differential, and aerodynamic drag. Then, we employ a data fusion method to synchronize the heterogeneous datasets with different frequencies to capture the sudden changes in electric vehicles. Subsequently, the fused features are input into our prediction model, DLPformer, which incorporates a linear model for trend prediction and patch-input attention for seasonal component prediction. Finally, in order to effectively evaluate the extrapolation and adaptability of our model, we utilize different driving cycles and heterogeneous battery datasets for training and testing. The experimental results show that our prediction model significantly improves the accuracy and robustness of SOC prediction under the proposed framework, achieving MAE values of 0.18% and 0.10% across distinct driving cycles and battery types.

Analysis of Connected Vehicle Data to Quantify National Mobility Impacts of Winter Storms for Decision Makers and Media Reports

Traditional techniques of monitoring roadway mobility during winter weather have relied on embedded road sensors, roadside cameras, radio reports from public safety staff, or public incident reports. However, widely available connected vehicle (CV) data provides government agencies and media with a unique opportunity to monitor the mobility impact of inclement weather events in near real-time. This study presents such a use case that analyzed over 500 billion CV records characterizing the spatial and temporal impact of a winter storm that moved across the country from 21 to 26 December 2022. The analysis covered 97,000 directional miles of interstate roadway and processed over 503 billion CV records. At the storm’s peak on 22 December at 5:26 PM Eastern Time, nearly 4800 directional miles of interstate roadway were operating under 45 mph, a widely accepted indicator of degraded interstate conditions. The study presents a methodological approach to systematically assess the mobility impact of this winter event on interstate roadways at a national and regional level. The paper then looks at a case study on Interstate 70, a 4350 directional mile route passing through ten states. Statewide comparison showed Ohio was most impacted, with 9% of mile-hours operating below 45 mph on 23 December. High-Resolution Rapid Refresh weather data provided by the National Oceanic and Atmospheric Administration was integrated into the analysis to provide a visualization of the storm’s temporal path and severity. We believe the proposed metrics and visualizations are effective tools for communicating the severity and geographic impact of extreme weather events to broad non-technical audiences.

Measuring data access and re-use in the European Legal Framework for Data, from the General Data Protection Regulation (GDPR) law to the Proposed Data Act: the case of vehicle data.

This article delves into the difficulties and opportunities associated with the acquisition, sharing, and re-purposing of vehicle data, particularly information derived from black boxes used by insurance companies and event data recorders installed by manufacturers. While this data is usually utilized by insurers and car makers, it may benefit consumers, rival firms, and public institutions profiting from access to data for objectives such as data portability between insurance companies, traffic and transportation management, and the development of intelligent mobility solutions. Among other regulations, the authors examine the proposed Data Act as the European chosen champion to address the legal and technical hurdles surrounding the reuse of privately held corporate data, including privacy and intellectual property, competition, and data interoperability issues. The text also offers an overview of the sorts of data obtained through vehicle recording systems and their potential benefits for various stakeholders. This paper presents a methodology for comparing and evaluating, in an ordinal fashion, the degree of access conferred by various regulations and put it to practical use to assess how much data is currently left out from access by the existing legislation, how much of such data is covered by the Data Act, and ultimately, how much still remains inaccessible for reuse.

Detection of Beach–Dune Geomorphic Changes by Means of Satellite and Unmanned Aerial Vehicle Data: The Case of Altamura Island in the Gulf of California

Although sandy islands in arid environments are vital protection sites for endemic species, they face constant natural and anthropogenic hazards, such as storm surge impacts and the occasional presence of off-road vehicles. Monitoring the sedimentary dune-beach displacement and balance is essential because sediment transportation usually does not depend on external sources, such as rivers. The latest generation of geomatic applications may be relevant to understanding coastal vulnerability due to their ability to acquire and process spatial data at unprecedented scales. The objective of this study was to analyze the sedimentary dynamics of a distinctive dune corridor on Altamura Island in the Gulf of California, Mexico. We compared three ultra-high spatial resolution digital surface models (DSMs) with geomorphic change detection (DoD), covering the 1150 m coastal stretch. We used light detection and ranging (LiDAR) data and analyzed changes in the coastline with the semi-automatic CoastSat tool. Although the orthomosaics and the DSM collected in April, June, and October 2021 show different conditions in sediment distribution along the beach-dune interface, depending on the direction and intensity of the wind, the two DoDs showed a constant sediment distribution balance of ~13 M m3 between April and June and June and October. LiDAR data along the 40-km length of the sandy island indicate that the entire island could present a similar sedimentation pattern between the dune and beach interface. The CoastSat data indicate a constant accretion of 125 m in the beach-ocean interface between 2015 and 2022. This study demonstrates that the sediment balance between the dune and the beach on arid sandy islands is vital for conserving their shoreline and all associated coastal ecosystems.

Road Pattern Classification Using Deep Learning for Noise Data for Autonomous Driving Vehicle

Tire-pavement Interaction Noise (TPIN) is noise caused by interactions between rolling tires and road surfaces. After measuring the TPIN using a microphone, transform TPIN to images using continuous wavelet transform (CWT). The transformed images are used to classify the driving road and tire using convolutional neural network (CNN). The road and tire classification network using CNN is required for braking systems in autonomous vehicle. The CNN in this paper can classify snow road, asphalt road, and two types of tires with over 97% accuracy.

Monitoring the annual geodetic mass balance of Bordu and Sary-Tor glaciers using UAV data

Abstract The geodetic mass balance of a glacier corresponds to glacier-wide volume changes, converted to mass changes using density assumptions. It is typically calculated by differencing multi-temporal digital elevation models. In this study, we show how the annual geodetic mass balance of a glacier can be derived from uncrewed aerial vehicle (UAV) data. The presented workflow is applied to two small- to medium-sized glaciers in the Kyrgyz Tien Shan (Central Asia): Bordu glacier and Sary-Tor glacier. The obtained geodetic mass balance is compared with the glaciological mass balance derived from a network of ablation stakes and snow pits. A previously calibrated mass-balance model is used to correct for the difference in acquisition dates. The results show that the determined geodetic mass balance matches closely with the glaciological mass balance. Besides, for both glaciers the geodetic mass balance does not seem to be particularly sensitive to the assumptions regarding volume-to-mass conversion. Therefore, our results demonstrate that UAVs can serve as a valuable instrument to quantify the annual geodetic mass balance and to validate the glaciological mass balance. The conventional glaciological mass-balance estimation often relies on interpolation and extrapolation methods, whereas UAVs offer the potential for direct data acquisition over the entire glacier surface.