Real-Time Black Ice Detection in Hilly Areas Using LoRa and IoT Network with a Machine Learning Algorithm
| International Journal of Electrical and Electronics Engineering |
| © 2025 by SSRG - IJEEE Journal |
| Volume 12 Issue 6 |
| Year of Publication : 2025 |
| Authors : Vishant Kumar, Rajesh Singh, Anita Gehlot, Sanjeev Kumar Shah, Roosha Shamoon |
10.14445/23488379/IJEEE-V12I6P120
How to Cite?
Vishant Kumar, Rajesh Singh, Anita Gehlot, Sanjeev Kumar Shah, Roosha Shamoon, "Real-Time Black Ice Detection in Hilly Areas Using LoRa and IoT Network with a Machine Learning Algorithm," SSRG International Journal of Electrical and Electronics Engineering, vol. 12, no. 6, pp. 224-237, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I6P120
Abstract:
Black ice is a serious road safety hazard, especially in cold and high-altitude areas, as it often forms silently and invisibly. Drivers often remain unaware of black ice until it's too late, leading to sudden and dangerous situations on the road. That’s why accurate and timely detection is essential to help prevent accidents and support effective traffic management. This research presents an intelligent black ice detection system that combines environmental sensors and a deep learning-based vision model. The system monitors critical weather parameters, temperature, humidity, dew point, wind speed, wind direction, and precipitation using real-time sensors, and classifies road conditions (dry, wet, saline, snow) using a trained ResNet101 model. A custom logic engine analyses sensor data and image predictions to determine the presence of black ice. The model achieved an accuracy of 95.6% and was validated using both Grad-CAM visualizations and confusion matrix analysis. Hardware implementation using LoRa network-enabled sensor nodes and a gateway, with integration of LoRa and Wi-Fi interfaces, enabled practical deployment. The results demonstrate that integrating sensor and vision systems enhances the reliability of black ice detection, offering significant potential to improve road safety during extreme winter conditions.
Keywords:
Black Ice Detection, IoT-based Monitoring, Multimodal Sensing, ResNet101, Road condition classification.
References:
[1] Hojun Lee et al., “The Detection of Black Ice Accidents for Preventative Automated Vehicles Using Convolutional Neural Networks,” Electronics, vol. 9, no. 12, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] C.S. Cheng et al., “Possible Impacts of Climate Change on Freezing Rain in South-Central Canada Using Downscaled Future Climate Scenarios,” Natural Hazards and Earth System Sciences, vol. 7, no. 1, pp. 71-87, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Matti Kämäräinen et al., “A Method to Estimate Freezing Rain Climatology from ERA-Interim Reanalysis Over Europe,” Natural Hazards and Earth System Sciences, vol. 17, no. 2, pp. 243-259, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Seok Bum Hong et al., “Development of Black Ice Prediction Model Using GIS-Based Multi-Sensor Model Validation,” Natural Hazards and Earth System Sciences, vol. 22, no. 10, pp. 3435-3459, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Vishant Kumar et al., “Various Computational Methods for Highway Health Monitoring in Terms of Detection of Black Ice: A Sustainable Approach in Indian Context,” Discover Sustainability, vol. 5, no. 1, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Sergey Bogdanov et al., “Calculation of Black Ice Thickness and Heat Fluxes inside the Ice and at the Water–Ice Boundary in a Boreal Lake,” Limnological Review, vol. 23, no. 3, pp. 138-156, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Hojun Lee et al., “The Detection of Black Ice Accidents for Preventative Automated Vehicles Using Convolutional Neural Networks,” Electronics, vol. 9, no. 12, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jaewook Kim, Eunkyung Kim, and Dongwan Kim, “A Black Ice Detection Method Based on 1-Dimensional CNN Using mmWave Sensor Backscattering,” Remote Sensing, vol. 14, no. 20, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Sang-Yum Lee, Je-Sung Jeon, and Tri Ho Minh Le, “Feasibility of Automated Black Ice Segmentation in Various Climate Conditions Using Deep Learning,” Buildings, vol. 13, no. 3, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Marco Esposito et al., “Recent Advances in Internet of Things Solutions for Early Warning Systems: A Review,” Sensors, vol. 22, no. 6, pp. 1-39, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Moon-Soo Park, Seung Jin Joo, and Young Tae Son, “Development of Road Surface Temperature Prediction Model Using the Unified Model Output (UM-Road),” Atmosphere, vol. 24, no. 4, pp. 471-479, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Jinhwan Jang, “Night Icing Prediction Using Vehicle-Mounted Pavement Temperature Sensor and Atmospheric Data,” Transportation Research Interdisciplinary Perspectives, vol. 21, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Taryn DiLorenzo, and Xinbao Yu, “Use of Ice Detection Sensors for Improving Winter Road Safety,” Accident Analysis & Prevention, vol. 191, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Mohamad Molavi Nojumi et al., “Application of Machine Learning for Temperature Prediction in a Test Road in Alberta,” International Journal of Pavement Research and Technology, vol. 15, pp. 303-319, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Jae-Kang Lee, Yong Huh, and Jisoo Park, “Geospatial Simulation System of Mountain Area Black Ice Accidents,” Applied Sciences, vol. 12, no. 11, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Maria Jokela, Matti Kutila, and Long Le, “Road Condition Monitoring System Based on a Stereo Camera,” 2009 IEEE 5th International Conference on Intelligent Computer Communication and Processing, Cluj-Napoca, Romania, pp. 423-428, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Traffic Cameras, The Ministry of Transport and Sustainable Mobility, 2025. [Online]. Available: https://www.quebec511.info/fr/Diffusion/EtatReseau/Cameras.aspx
[18] Qi Zhang, “A Novel ResNet101 Model Based on Dense Dilated Convolution for Image Classification,” SN Applied Sciences, vol. 4, pp. 1-13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Shuyuan Xu et al., “Vision-Based Pavement Marking Detection and Condition Assessment—A Case Study,” Applied Sciences, vol. 11, no. 7, pp. 1-16, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Oleg A. Alduchov, and Robert E. Eskridge, “Improved Magnus form Approximation of Saturation Vapor Pressure,” Journal of Applied Meteorology and Climatology, pp. 601-609, 1996.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Hitesh Upreti, and C.S.P. Ojha, “Estimation of Relative Humidity and Dew Point Temperature Using Limited Meteorological Data,” Journal of Irrigation and Drainage Engineering, vol. 143, no. 9, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Brent C. Christner et al., “Geographic, Seasonal, and Precipitation Chemistry Influence on the Abundance and Activity of Biological Ice Nucleators in Rain and Snow,” Proceedings of the National Academy of Sciences, vol. 105, no. 48, pp. 18854-18859, 2008.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Insan Arafat Jahan et al., “RoadSense: A Framework for Road Condition Monitoring Using Sensors and Machine Learning,” IEEE Transactions on Intelligent Vehicles, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Ján Čimo, and Bernard Šiška, “Design and Realization of Monitoring System for Measuring Air Temperature and Humidity, Wind Direction and Speed,” Journal of Environmental Engineering and Landscape Management, vol. 14, no. 3, pp. 127-134, 2006.
[Google Scholar] [Publisher Link]
[25] K.E. Ukhurebor et al., “A Cost-Effective Weather Monitoring Device,” Archives of Current Research International, vol. 7, no. 4, pp. 1-9, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Adhitya Bhawiyuga et al., “LoRa-MQTT Gateway Device for Supporting Sensor-to-Cloud Data Transmission in Smart Aquaculture IoT Application,” 2019 International Conference on Sustainable Information Engineering and Technology (SIET), Lombok, Indonesia, pp. 187-190, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Deeksha Srivastava, Awanish Kesarwani, and Shivani Dubey, “Measurement of Temperature and Humidity by Using Arduino Tool and DHT11,” International Research Journal of Engineering and Technology, vol. 5, no. 12, pp. 876-878, 2018.
[Google Scholar] [Publisher Link]
[28] Tong Qiang et al., “Nodemcu-Based Low-Cost Smart Home Node Design,” IOP Conference Series: Materials Science and Engineering, vol. 435, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Reza Ghanaatian et al., “LoRa Digital Receiver Analysis and Implementation,” ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, pp. 1498-1502, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Warren Gay, Custom Raspberry Pi Interfaces: Design and Build Hardware Interfaces for the Raspberry Pi, 1st ed., Apress Berkeley, CA, pp. 35-54, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Paul S.B. Macheso et al., “Environmental Parameter Monitoring System Based on NodeMcu ESP8266, MQTT and Node-Red,” 2022 International Conference on Computer Communication and Informatics, Coimbatore, India, pp. 1-4, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Ramprasaath R Selvaraju et al., “Grad-CAM: Why did you Say That?,” Arxiv, pp. 1-4, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Zijun Zhang, “Improved Adam Optimizer for Deep Neural Networks,” 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), Banff, AB, Canada, pp. 1-2, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Zhen Zhen et al., “Impact of Training and Validation Sample Selection on Classification Accuracy and Accuracy Assessment when Using Reference Polygons in Object-Based Classification,” International Journal of Remote Sensing, vol. 34, no. 19, pp. 6914-6930, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Robert Susmaga, “Confusion Matrix Visualization,” Intelligent Information Processing and Web Mining: Proceedings of the International IIS: IIPWM ‘04 Conference, Zakopane, Poland, pp. 107-116, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Reda Yacouby, and Dustin Axman, “Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models,” Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems, pp. 79-91, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Tingting Zhang et al., “An Improved ResNet101 Network Based Pavement Classification Method,” International Core Journal of Engineering, vol. 9, no. 9, pp. 78-87, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Krzysztof Górnicki et al., “Evaluation of Models for the Dew Point Temperature Determination,” Technical Sciences, vol. 20, no. 3, pp. 241-257, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Huang-Chen Lee, and Kai-Hsiang Ke, “Monitoring of Large-Area IoT Sensors Using a LoRa Wireless Mesh Network System: Design and Evaluation,” IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 9, pp. 2177-2187, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Thomas Foken, and Jens Bange, Wind Sensors, Springer Handbook of Atmospheric Measurements, Springer, Cham, pp. 243-272, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Santiago Pindado, Javier Cubas, and Félix Sorribes-Palmer, “The Cup Anemometer, A Fundamental Meteorological Instrument for the Wind Energy Industry,” Sensors, vol. 14, no. 11, pp. 21418-21452, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Martin Bor, John Vidler, and Utz Roedig, “LoRa for the Internet of Things,” Proceedings of the 2016 International Conference on Embedded Wireless Systems and Networks, Graz, Austria, pp. 361-366, 2016.
[Google Scholar] [Publisher Link]