USE OF HISTORICAL DATA TO IMPROVE THE ACCURACY OF ILLEGAL LANDFILL DETECTION IN REMOTE SENSING IMAGERY
DOI:
https://doi.org/10.34185/1991-7848.itmm.2026.01.081Keywords:
illegal landfills, aerospace imagery, satellite data, historical data, temporal analysis, change detection, YOLO, environmental monitoring, agent-based feature modelAbstract
The paper considers the use of historical satellite data to improve the accuracy of illegal landfill detection in aerospace imagery. It is shown that temporal context has independent diagnostic value for such objects, since landfills are usually formed gradually and manifest themselves not only in the spectral characteristics of a current scene, but also in the dynamics of land-surface changes over time. The study analyzes the approaches of satellite image time series, change detection, temporal modeling, and historical prior maps. It is argued that the most promising solution is a hybrid approach in which primary candidate detection is performed by a YOLO-like detector, while further refinement is carried out using historical observations, change maps, and an agent-based feature model. Such an approach makes it possible to improve detection robustness, reduce false positives, and increase the interpretability of environmental
monitoring results.
References
Fraternali P., Cazzaniga P., Dell’Acqua F. et al. Solid waste detection, monitoring and mapping in remote sensing: a review // Waste Management. 2024.
Jiang W., Sun Y., Lei L. et al. Change detection of multisource remote sensing images: a review // International Journal of Digital Earth. 2024. Vol. 17, No. 1. DOI: 10.1080/17538947.2024.2398051.
Vincent E., Ponce J., Aubry M. Satellite Image Time Series Semantic Change Detection: Novel Architecture and Analysis of Domain Shift // arXiv. 2024. DOI: 10.48550/arXiv.2407.07616.
Wang R., Ma L., He G. et al. Transformers for Remote Sensing: A Systematic Review and Analysis // Sensors. 2024. Vol. 24, No. 11. Art. 3495. DOI: 10.3390/s24113495.
Gui S., Song S., Qin R., Tang Y. Remote Sensing Object Detection in the Deep Learning Era—A Review // Remote Sensing. 2024. Vol. 16, No. 2. Art. 327. DOI: 10.3390/rs16020327.
Sakti A. D., Sembiring E., Rohayani P. et al. Identification of illegally dumped plastic waste in a highly polluted river in Indonesia using Sentinel-2 satellite imagery // Scientific Reports. 2023. Vol. 13. Art. 5039. DOI: 10.1038/s41598-023-32087-5.
Scharf N., Ducry B., Sy B. et al. Integrating Remote Sensing, GIS, and Citizen Science to Map Illegal Waste Dumping Susceptibility in Dakar, Senegal // Sustainability. 2025. Vol. 17, No. 24. Art. 11137. DOI: 10.3390/su172411137.
El Hafyani H., Pasdeloup B., Yver C., Romenteau P. Multimodal Object Detection via Probabilistic a priori Information Integration // arXiv. 2024. DOI: 10.48550/arXiv.2405.15596.
Lytvynov, Ye., Hnatushenko, V., & Udovyk, I. (2026). Detection of illegal landfills in satellite images using a multi-agent approach. Herald of Khmelnytskyi National University. Technical Sciences, 361(1), 523–530. https://doi.org/10.31891/2307-5732-2026-361-73
