Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model
Abstract
:1. Introduction
2. Materials and Methods
2.1. Detection of Precipitation Type and Visibility from Camera Images
- Precipitation: rain, melting snow, snow, hail, no precipitation;
- Visibility: fog, normal (no fog)
2.2. Calibration of Sensor Measurements
2.3. Road Weather Model
3. Results
3.1. Detection of Precipitation Type and Visibility from Camera Images
- Automatic gain functions take time to settle on initial captures and on big lighting changes e.g., coming out of a tunnel.
- Over/underexposure in certain outside conditions
- A lot of image noise in low lighting conditions, e.g., during the night (which the WeathercAIm model seems to confuse with rain/snow, as also a human could).
3.2. Calibration of Sensor Measurements
3.3. Road Weather Model
4. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
AUC | Area Under (the ROC) Curve |
AWD | Adverse Weather Dataset |
AWS | Automatic Weather Station |
CNN | Convolutional Neural Network |
CV | Computer Vision |
DNN | Deep Neural Network |
GDPR | General Data Protection Regulation |
GPS | Global Positioning System |
ICSSN | In-Car Smart Sensor Node |
INCA | Integrated Nowcasting through Comprehensive Analysis |
INCA-BE | INCA Belgium |
ML | Machine Learning |
NWP | Numerical Weather Prediction |
RH | Relative humidity |
RMI | Royal Meteorological Institute of Belgium |
RMSE | Root-Mean-Square Error |
ROC | Receiver Operating Characteristic |
RWM | Road Weather Model |
RWS | Road Weather Station |
SARWS | Secure and Accurate Road Weather Services |
SGD | Stochastic Gradient Descent |
T2M | Air temperature at 2 m |
TD2M | Dewpoint temperature at 2 m |
RST | Road surface temperature |
VMM | De Vlaamse Milieumaatschappij |
ZAMG | Zentralanstalt für Meteorologie und Geodynamik |
References
- Malin, F.; Norros, I.; Innamaa, S. Accident risk of road and weather conditions on different road types. Accid. Anal. Prev. 2019, 122, 181–188. [Google Scholar] [CrossRef] [PubMed]
- Roh, C.G.; Kim, J.; Im, I. Analysis of Impact of Rain Conditions on ADAS. Sensors 2020, 20, 6720. [Google Scholar] [CrossRef] [PubMed]
- Dixit, V.V.; Chand, S.; Nair, D.J. Autonomous vehicles: Disengagements, accidents and reaction times. PLoS ONE 2016, 11, e0168054. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Parmenter, B.; Thornes, J.E. The Use of a Computer Model to Predict the Formation of Ice on Road Surfaces; Research Report; Transport and Road Research Laboratory: Wokingham, UK, 1986. [Google Scholar]
- Chapman, L.; Thornes, J.E.; Bradley, A.V. Modelling of road surface temperature from a geographical parameter database. Part 2: Numerical. Meteorol. Appl. A J. Forecast. Pract. Appl. Train. Tech. Model. 2001, 8, 421–436. [Google Scholar] [CrossRef]
- Crevier, L.P.; Delage, Y. METRo: A new model for road-condition forecasting in Canada. J. Appl. Meteorol. 2001, 40, 2026–2037. [Google Scholar] [CrossRef]
- Kangas, M.; Heikinheimo, M.; Hippi, M. RoadSurf: A modelling system for predicting road weather and road surface conditions. Meteorol. Appl. 2015, 22, 544–553. [Google Scholar] [CrossRef]
- Yin, Z.; Hadzimustafic, J.; Kann, A.; Wang, Y. On statistical nowcasting of road surface temperature. Meteorol. Appl. 2019, 26, 1–13. [Google Scholar] [CrossRef] [Green Version]
- Hippi, M.; Kangas, M.; Ruuhela, R.; Ruotsalainen, J.; Hartonen, S. RoadSurf-Pedestrian: A sidewalk condition model to predict risk for wintertime slipping injuries. Meteorol. Appl. 2020, 27, e1955. [Google Scholar] [CrossRef]
- Dey, K.C.; Mishra, A.; Chowdhury, M. Potential of intelligent transportation systems in mitigating adverse weather impacts on road mobility: A review. IEEE Trans. Intell. Transp. Syst. 2014, 16, 1107–1119. [Google Scholar] [CrossRef]
- Sukuvaara, T.; Mäenpää, K.; Stepanova, D.; Karsisto, V. Vehicular networking road weather information system tailored for arctic winter conditions. Int. J. Commun. Netw. Inf. Secur. 2020, 12, 281–288. [Google Scholar]
- Karsisto, V.; Lovén, L. Verification of road surface temperature forecasts assimilating data from mobile sensors. Weather Forecast. 2019, 34, 539–558. [Google Scholar] [CrossRef]
- Minge, E.; Gallagher, M.; Hanson, Z.; Hvizdos, K. Mobile Technologies for Assessment of Winter Road Conditions; Technical Report; Department of Transportation, Clear Roads Pooled Fund: St. Paul, MN, USA, 2019. [Google Scholar]
- Stepanova, D.; Sukuvaara, T.; Karsisto, V. Intelligent Transport Systems–Road weather information and forecast system for vehicles. In Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 25–28 May 2020; pp. 1–5. [Google Scholar]
- Hellweg, M.; Acevedo-Valencia, J.W.; Paschalidi, Z.; Nachtigall, J.; Kratzsch, T.; Stiller, C. Using floating car data for more precise road weather forecasts. In Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 25–28 May 2020; pp. 1–3. [Google Scholar]
- Mahoney, W.P., III; O’Sullivan, J.M. Realizing the potential of vehicle-based observations. Bull. Am. Meteorol. Soc. 2013, 94, 1007–1018. [Google Scholar] [CrossRef]
- mAutomotive, G. Connected Car Forecast: Global Connected Car Market to Grow Threefold within Five Years. 2013. Available online: https://www.gsma.com/iot/wp-content/uploads/2013/06/cl_ma_forecast_06_13.pdf (accessed on 26 May 2021).
- Markets. Connected Car Market. 2019. Available online: https://www.marketsandmarkets.com/Market-Reports/connected-car-market-102580117.html (accessed on 26 May 2021).
- Hintz, K.S.; O’Boyle, K.; Dance, S.L.; Al-Ali, S.; Ansper, I.; Blaauboer, D.; Clark, M.; Cress, A.; Dahoui, M.; Darcy, R.; et al. Collecting and utilising crowdsourced data for numerical weather prediction: Propositions from the meeting held in Copenhagen, 4–5 December 2018. Atmos. Sci. Lett. 2019, 20, e921. [Google Scholar] [CrossRef] [Green Version]
- Bell, Z.; Dance, S.L.; Waller, J.A. Exploring the characteristics of a vehicle-based temperature dataset for convection-permitting numerical weather prediction. arXiv 2021, arXiv:2105.12526. [Google Scholar]
- SARWS, C.N. Real-Time Location-Aware Road Weather Services Composed from Multi-Modal Data. 2019. Available online: https://www.celticnext.eu/project-sarws/ (accessed on 26 May 2021).
- Mercelis, S.; Watelet, S.; Casteels, W.; Bogaerts, T.; Van den Bergh, J.; Reyniers, M.; Hellinckx, P. Towards detection of road weather conditions using large-scale vehicle fleets. In Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 25–28 May 2020; pp. 1–7. [Google Scholar]
- Ibrahim, M.R.; Haworth, J.; Cheng, T. WeatherNet: Recognising weather and visual conditions from street-level images using deep residual learning. ISPRS Int. J. Geo-Inf. 2019, 8, 549. [Google Scholar] [CrossRef] [Green Version]
- Tan, L.; Xuan, D.; Xia, J.; Wang, C. Weather recognition based on 3C-CNN. KSII Trans. Internet Inf. Syst. 2020, 14, 3567–3582. [Google Scholar]
- Palvanov, A.; Cho, Y.I. Visnet: Deep convolutional neural networks for forecasting atmospheric visibility. Sensors 2019, 19, 1343. [Google Scholar] [CrossRef] [Green Version]
- Zhao, B.; Li, X.; Lu, X.; Wang, Z. A CNN–RNN architecture for multi-label weather recognition. Neurocomputing 2018, 322, 47–57. [Google Scholar] [CrossRef] [Green Version]
- Guerra, J.C.V.; Khanam, Z.; Ehsan, S.; Stolkin, R.; McDonald-Maier, K. Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks. In Proceedings of the 2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), Edinburgh, UK, 6–9 August 2018; pp. 305–310. [Google Scholar]
- Tsigkanos, C.; Avasalcai, C.; Dustdar, S. Architectural Considerations for Privacy on the Edge. IEEE Internet Comput. 2019, 23, 76–83. [Google Scholar] [CrossRef]
- Wang, H.; Barriga, L.; Vahidi, A.; Raza, S. Machine Learning for Security at the IoT Edge-A Feasibility Study. In Proceedings of the 2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops (MASSW), Monterey, CA, USA, 4–7 November 2019; pp. 7–12. [Google Scholar] [CrossRef]
- Krishnasamy, E.; Varrette, S.; Mucciardi, M. Edge Computing: An Overview of Framework and Applications. Technical Report, PRACE Aisbl. 2020. Available online: https://prace-ri.eu/wp-content/uploads/Edge-Computing-An-Overview-of-Framework-and-Applications.pdf (accessed on 17 February 2022).
- González, J.P. Machine Learning Edge Devices: Benchmark Report. 2019. Available online: https://tryolabs.com/blog/machine-learning-on-edge-devices-benchmark-report (accessed on 17 February 2022).
- Véstias, M.P. A Survey of Convolutional Neural Networks on Edge with Reconfigurable Computing. Algorithms 2019, 12, 154. [Google Scholar] [CrossRef] [Green Version]
- Basler. Basler pulse puA1920-30uc-Area Scan Camera. 2021. Available online: https://www.baslerweb.com/en/products/cameras/area-scan-cameras/pulse/pua1920-30uc/ (accessed on 7 December 2021).
- He, K.; Zhang, X.; Ren, S.; Sun, J. Identity Mappings in Deep Residual Networks. In Computer Vision–ECCV 2016; Leibe, B., Matas, J., Sebe, N., Welling, M., Eds.; Springer International Publishing: Cham, Switzerland, 2016; pp. 630–645. [Google Scholar]
- Khan, A.; Sohail, A.; Zahoora, U.; Qureshi, A.S. A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 2020, 53, 5455–5516. [Google Scholar] [CrossRef] [Green Version]
- MLCommons. Inference: Edge Benchmark v0.7 Results. 2020. Available online: https://mlcommons.org/en/inference-edge-07/ (accessed on 17 February 2022).
- Google. Coral Edge TPU Performance Benchmarks. 2021. Available online: https://coral.ai/docs/edgetpu/benchmarks/ (accessed on 17 February 2022).
- Deng, J.; Dong, W.; Socher, R.; Li, L.J.; Li, K.; Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 20–25 June 2009; pp. 248–255. [Google Scholar]
- Rawashdeh Research Group. Adverse Weather Dataset. 2019. Available online: http://sar-lab.net/adverse-weather-dataset/ (accessed on 7 December 2021).
- Williams, D.E. Low cost sensor networks: How do we know the data are reliable? ACS Sens. 2019, 4, 2558–2565. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Lin, Y.; Dong, W.; Chen, Y. Calibrating low-cost sensors by a two-phase learning approach for urban air quality measurement. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2018, 2, 1–18. [Google Scholar] [CrossRef]
- Lovén, L.; Karsisto, V.; Järvinen, H.; Sillanpää, M.J.; Leppänen, T.; Peltonen, E.; Pirttikangas, S.; Riekki, J. Mobile road weather sensor calibration by sensor fusion and linear mixed models. PLoS ONE 2019, 14, e0211702. [Google Scholar] [CrossRef] [Green Version]
- Bogaerts, T.; Watelet, S.; Thoen, C.; Coopman, T.; Van den Bergh, J.; Reyniers, M.; Seynaeve, D.; Casteels, W.; Latré, S.; Hellinckx, P. Enhancement of road weather services using vehicle sensor data. In Proceedings of the 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, 8–11 January 2022; pp. 1–6. [Google Scholar]
- Karsisto, V.; Tijm, S.; Nurmi, P. Comparing the performance of two road weather models in the Netherlands. Weather Forecast. 2017, 32, 991–1006. [Google Scholar] [CrossRef]
- Haiden, T.; Kann, A.; Wittmann, C.; Pistotnik, G.; Bica, B.; Gruber, C. The Integrated Nowcasting through Comprehensive Analysis (INCA) system and its validation over the Eastern Alpine region. Weather Forecast. 2011, 26, 166–183. [Google Scholar] [CrossRef]
- Caluwaerts, S.; Top, S.; Vergauwen, T.; Wauters, G.; De Ridder, K.; Hamdi, R.; Mesuere, B.; Van Schaeybroeck, B.; Wouters, H.; Termonia, P. Engaging schools to explore meteorological observational gaps. Bull. Am. Meteorol. Soc. 2021, 102, E1126–E1132. [Google Scholar] [CrossRef]
In Car | Sensor Box |
---|---|
GPS-module | Gyroscope |
Camera | Accelerometer |
Thermal imaging sensor | Temperature sensor |
Humidity sensor |
Optimiser | Learning Rate | Dropout Rate | Batch Size | Loss | Accuracy | AUC | F1 |
---|---|---|---|---|---|---|---|
sgd | 64 | ||||||
sgd | 16 | ||||||
sgd | 16 | ||||||
nadam | 16 | ||||||
nadam | 16 | ||||||
nadam | 16 | ||||||
nadam | 16 |
Mean Squared Error | Mean Absolute Error | Mean Bias | ||||
---|---|---|---|---|---|---|
Train | Test | Train | Test | Train | Test | |
Temperature original | 3.680 C | 3.360 C | 2.916 °C | 3.023 °C | −2.780 °C | −3.003 °C |
Temperature corrected | 1.695 °C | 1.705 °C | 1.285 °C | 1.409 °C | 0.100 °C | 1.077 °C |
Humidity original | 7.248 | 7.259 | 5.718% | 5.732% | 1.167% | 1.176% |
Humidity corrected | 5.644 | 5.561 | 4.262% | 4.265% | 0.172% | 0.182% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Bogaerts, T.; Watelet, S.; De Bruyne, N.; Thoen, C.; Coopman, T.; Van den Bergh, J.; Reyniers, M.; Seynaeve, D.; Casteels, W.; Latré, S.; et al. Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model. Sensors 2022, 22, 2732. https://doi.org/10.3390/s22072732
Bogaerts T, Watelet S, De Bruyne N, Thoen C, Coopman T, Van den Bergh J, Reyniers M, Seynaeve D, Casteels W, Latré S, et al. Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model. Sensors. 2022; 22(7):2732. https://doi.org/10.3390/s22072732
Chicago/Turabian StyleBogaerts, Toon, Sylvain Watelet, Niko De Bruyne, Chris Thoen, Tom Coopman, Joris Van den Bergh, Maarten Reyniers, Dirck Seynaeve, Wim Casteels, Steven Latré, and et al. 2022. "Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model" Sensors 22, no. 7: 2732. https://doi.org/10.3390/s22072732
APA StyleBogaerts, T., Watelet, S., De Bruyne, N., Thoen, C., Coopman, T., Van den Bergh, J., Reyniers, M., Seynaeve, D., Casteels, W., Latré, S., & Hellinckx, P. (2022). Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model. Sensors, 22(7), 2732. https://doi.org/10.3390/s22072732