Oil Pollution Detection in Aquatic Ecosystems Using UAVS and Multispectral Imaging Based on Deep Learning Technologies
( Pp. 152-160)
More about authors
Gladkikh Tatiana Ya.
научный сотрудник, аспирант
Institute of Management Problems named after V.A. Trapeznikova Russian Academy of Sciences
Moscow, Russian Federation
Institute of Management Problems named after V.A. Trapeznikova Russian Academy of Sciences
Moscow, Russian Federation
Abstract:
This paper presents a deep learning-based algorithm for identifying oil pollution on water surfaces using multispectral images from a 5-channel camera obtained from unmanned aerial vehicles (UAVs). The algorithm, based on the Unet architecture with the efficientnet-b0 encoder, demonstrates high segmentation accuracy and is part of an environmental monitoring system. Using data on natural and controlled oil spills, as well as organic discharges, the method has been field tested on various water bodies, which confirms its efficiency and reliability in the prompt detection of pollution. Particular attention in the article is paid to the accuracy and speed of the algorithm. The developed method has a high data processing speed and can be successfully applied in various climatic conditions. The results demonstrate that the proposed algorithm is able to automatically detect even minor pollution of water surfaces, which allows for a prompt response to environmental disasters and minimize their consequences. The proposed algorithm has shown high results. With the selected model configuration, the Dice Loss metrics were achieved at the level of 0.00265 and the IoU Score equal to 0.9971. These high values confirm the reliability and accuracy of the proposed approach, ensuring accurate identification of oil spills.
How to Cite:
Gladkikh T.Ya. Oil Pollution Detection in Aquatic Ecosystems Using UAVS and Multispectral Imaging Based on Deep Learning Technologies. Computational Nanotechnology. 2024. Vol. 11. No. 5. Pp. 152–160. (In Rus.). DOI: 10.33693/2313-223X-2024-11-5-152-160. EDN: CGGJDP
Reference list:
Amani M. et al. Remote sensing systems for ocean: A review. Part 1: Passive systems. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2022. Vol. 15. Pp. 210–234.
Cheng K., Chan S., Lee J.H. Remote sensing of coastal algal blooms using unmanned aerial vehicles (UAVs). Marine Pollution Bulletin. 2020. Vol. 152. P. 110889.
Ding H., Li R., Lin H., Wang X. Monitoring and evaluation on water quality of Hun River based on landsat satellite. In: Progress in Electromagnetic Research Symposium (PIERS). 2016. Pp. 1532–1537.
Eljabri A., Gallagher C. Developing integrated remote sensing and GIS procedures for oil spills monitoring at Libyan coast. WIT Transactions on Ecology and the Environment. 2012. Vol. 44. Pp. 17–20.
Garcia-Pineda O., Hu Ch., Sun Sh., Garsia D. Classification of oil spill thicknesses using multispectral UAS and satellite remote sensing for oil spill response. In: IGARSS. IEEE International Geoscience and Remote Sensing Symposium. 2019. Pp. 5863–5866.
Huang L., Miron A., Hone K., Li Y. Segmenting medical images: From UNet to Res-UNet and nnUNet. In: IEEE 37th International Symposium on Computer-Based Medical Systems (CBMS). 2024. Pp. 483–489.
Kirillov A. et al. Segment Anything. arXiv. 2019. DOI: 10.48550/arXiv.2304.02643.
Maashri A., Ghommam J., Saleem A., Nasiri N. A multi-drone system for oil spill detection: A simulation and emulation platform. In: 22nd International Conference on Control, Automation and Systems (ICCAS). 2022. Pp. 397–402.
Mityagina M., Lavrova O. Satellite monitoring of the Black Sea surface pollution. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2015. Pp. 2291–2294.
Ofitserov V., Konushin A. High resolution image segmentation with deep learning models. International Journal of Open Information Technologies. 2024. Vol. 12 (6). Pp. 57–64. (In Rus.)
Oliveira A., Pedrosa D., Santos T., Dias A. Design and development of a multi rotor UAV for oil spill mitigation. In: OCEANS. Marsel, 2019. Pp. 1–7.
Prochazka A. et al. Satellite image processing and air pollution detection. In: IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100). 2000. Vol. 6. Pp. 2282–2285.
Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI). 2015. Vol. 9351. Pp. 234–241. DOI: 10.1007/978-3-319-24574-4_28.
Saleem A. et al. Detection of oil spill pollution in seawater using drones: Simulation & Lab-based experimental study. In: IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS). 2021. Pp. 1–5.
Tan M., Le Q.V. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning. 2019. Pp. 6105–6114.
Vytovtov K.A. et al. Remote monitoring of water pollution with oil products in the visible range by using UAV multispectral camera. In: International Conference on Information, Control, and Communication Technologies (ICCT). 2022. Pp. 1–5.
Ying H. et al. Evaluation of water quality based on UAV images and the IMP-MPP algorithm. Ecological Informatics. 2021. Vol. 61. P. 101239.
Antonets K.V. et al. Integrated monitoring of oil and gas pollution. International Agricultural Journal. 2021. No. 1. Pp. 49–54.
Vytovtov K.A., Barabanova E.A., Gladkikh T.Ya., Novochadova A.V. Identification of oil pollution of the water surface using UAVs. Automation in Industry. 2024. No. 6. Pp. 52–56. (In Rus.)
Cheng K., Chan S., Lee J.H. Remote sensing of coastal algal blooms using unmanned aerial vehicles (UAVs). Marine Pollution Bulletin. 2020. Vol. 152. P. 110889.
Ding H., Li R., Lin H., Wang X. Monitoring and evaluation on water quality of Hun River based on landsat satellite. In: Progress in Electromagnetic Research Symposium (PIERS). 2016. Pp. 1532–1537.
Eljabri A., Gallagher C. Developing integrated remote sensing and GIS procedures for oil spills monitoring at Libyan coast. WIT Transactions on Ecology and the Environment. 2012. Vol. 44. Pp. 17–20.
Garcia-Pineda O., Hu Ch., Sun Sh., Garsia D. Classification of oil spill thicknesses using multispectral UAS and satellite remote sensing for oil spill response. In: IGARSS. IEEE International Geoscience and Remote Sensing Symposium. 2019. Pp. 5863–5866.
Huang L., Miron A., Hone K., Li Y. Segmenting medical images: From UNet to Res-UNet and nnUNet. In: IEEE 37th International Symposium on Computer-Based Medical Systems (CBMS). 2024. Pp. 483–489.
Kirillov A. et al. Segment Anything. arXiv. 2019. DOI: 10.48550/arXiv.2304.02643.
Maashri A., Ghommam J., Saleem A., Nasiri N. A multi-drone system for oil spill detection: A simulation and emulation platform. In: 22nd International Conference on Control, Automation and Systems (ICCAS). 2022. Pp. 397–402.
Mityagina M., Lavrova O. Satellite monitoring of the Black Sea surface pollution. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2015. Pp. 2291–2294.
Ofitserov V., Konushin A. High resolution image segmentation with deep learning models. International Journal of Open Information Technologies. 2024. Vol. 12 (6). Pp. 57–64. (In Rus.)
Oliveira A., Pedrosa D., Santos T., Dias A. Design and development of a multi rotor UAV for oil spill mitigation. In: OCEANS. Marsel, 2019. Pp. 1–7.
Prochazka A. et al. Satellite image processing and air pollution detection. In: IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100). 2000. Vol. 6. Pp. 2282–2285.
Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI). 2015. Vol. 9351. Pp. 234–241. DOI: 10.1007/978-3-319-24574-4_28.
Saleem A. et al. Detection of oil spill pollution in seawater using drones: Simulation & Lab-based experimental study. In: IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS). 2021. Pp. 1–5.
Tan M., Le Q.V. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning. 2019. Pp. 6105–6114.
Vytovtov K.A. et al. Remote monitoring of water pollution with oil products in the visible range by using UAV multispectral camera. In: International Conference on Information, Control, and Communication Technologies (ICCT). 2022. Pp. 1–5.
Ying H. et al. Evaluation of water quality based on UAV images and the IMP-MPP algorithm. Ecological Informatics. 2021. Vol. 61. P. 101239.
Antonets K.V. et al. Integrated monitoring of oil and gas pollution. International Agricultural Journal. 2021. No. 1. Pp. 49–54.
Vytovtov K.A., Barabanova E.A., Gladkikh T.Ya., Novochadova A.V. Identification of oil pollution of the water surface using UAVs. Automation in Industry. 2024. No. 6. Pp. 52–56. (In Rus.)
Keywords:
environmental monitoring, UAVs, multispectral images, oil spills, deep learning, neural networks, information processing.
Related Articles
Artificial intelligence and machine learning Pages: 9-18 DOI: 10.33693/2313-223X-2022-9-3-9-18 Issue №21873
Artificial Intelligence Elements for the Task of Determining the Position of the Vehicle in the Image
YOLO
computer vision
neural networks
convolutional neural networks
image recognition
Show more
5.2.3. REGIONAL AND SECTORAL ECONOMICS Pages: 16-22 Issue №21250
The Impact of artificial Intelligence on the Investment Climate and Socio-Economic Development of Russia
artificial intelligence
investment climate
digital economy
neural networks
additive method
Show more
Mathematical Modeling, Numerical Methods and Complex Programs Pages: 20-36 DOI: 10.33693/2313-223X-2024-11-5-20-36 Issue №172073
Machine Learning Methods for Determining Optimal Irrigation Timing for Corn
artificial intelligence
neural networks
computer vision
hyperspectral imaging
corn classification
Show more
THEORETICAL AND HISTORICAL LEGAL SCIENCES Pages: 20-24 Issue №24576
Possibilities of Neural Networks in Legal Regulation of Land Management and Land Registry
legal regulation of land management
land registry
neural networks
digital technologies
rational use of land.
Show more
Calculative modeling of high-tech production processes Pages: 46-58 DOI: 10.33693/2313-223X-2021-8-1-46-58 Issue №18588
Application of modeling tools in the framework of smart petrochemical production
BPMN
IDEF0
“smart” manufacturing
petrochemical enterprise
modeling
Show more
Informatics and Information Processing Pages: 64-80 DOI: 10.33693/2313-223X-2024-11-3-64-80 Issue №143798
Algorithm for identifying abnormal actions
deep learning
human behavior
video surveillance
Show more
New Issues in Law Pages: 108-114 DOI: 10.33693/2223-0092-2024-14-3-108-114 Issue №113934
Electronic Digital Virtualization in Criminology: Objects and Forms of Research; Criminalistic Significance for the Criminal Process
virtualization
virtual reality
digitalization
digital reconstruction
rendering
Show more
5.2.2. MATHEMATICAL, STATISTICAL AND INSTRUMENTAL METHODS OF ECONOMICS Pages: 150-155 Issue №20468
About Some Specific Limitations of Data Mining Application
Big data
information technology
data mining
classification
clustering
Show more
MATHEMATICAL, STATISTICAL AND INSTRUMENTAL METHODS OF ECONOMICS Pages: 190-199 Issue №22019
Building a Neural Network to Predict the Option Price
Financial market
options execution
neural networks
loss function
option value models
Show more
4. CRIMINAL LAW (5.1.4.) Pages: 216-221 Issue №22457
Modern possibilities of examining the scene of a traffic accident using robotics and artificial intelligence systems
accident
inspection of the scene
technical and forensic means
innovative technologies
artificial intelligence
Show more