Symbiotic Artificial Intelligence and satellite imagery for rapid assessment of war-induced agricultural damage in Ukraine

• Autorzy: Parkhomchuk Oleksandr , Drozd Sofiia , Shelestov Andrii , Mikava Polina

Identyfikatory

DOI

10.24425/agg.2025.150688

• Języki publikacji: EN

Abstrakty

EN

This study aims to enhance damage detection methods for the agricultural sector in Ukraine, which has been severely affected by ongoing conflict. While existing approaches, such as the method by Kussul et al. (2023), are among the best for monitoring damage, they are limited by the use of static threshold coefficients that can lead to inaccurate results, particularly false positives. To address these issues, we introduce a new approach using Symbiotic Artificial Intelligence (SAI), which integrates human oversight with machine learning to enable real-time adjustments to detection sensitivity based on field-specific characteristics. The proposed SAI-based method was tested using high-resolution satellite imagery from MAXAR for fields in Donetsk and Kherson. Results demonstrated a significant reduction in false positive rates, from 8.5% to approximately 1%, while maintaining a high rate of correctly identified undamaged areas. However, a slight decrease in true positive detections was observed, indicating a necessary balance between false positive reduction and sensitivity to actual damage. The SAI method effectively minimized false detections at field boundaries and other non-damage-related anomalies. This approach showcases the potential of combining human expertise with AI to improve accuracy and adaptability in damage detection. While the results are promising, further research should focus on automating the adjustment of detection thresholds for broader application, such as developing regression models to optimize field-specific coefficients.

Słowa kluczowe

EN

remote sensing; symbiotic artificial intelligence; human interaction; agricultural field anomaly detection; agricultural damage

PL

teledetekcja; sztuczna inteligencja; szkody rolnicze

• Wydawca: Komitet Geodezji PAN
• Czasopismo: Advances in Geodesy and Geoinformation
• Rocznik: 2025
• Tom: Vol. 74, no. 1
• Strony: art. no. e59, 2025
• Opis fizyczny: Bibliogr. 21 poz., rys., tab., wykr.

Twórcy

autor

Parkhomchuk Oleksandr

• Space Research Institute NASU-SSAU, Kyiv, Ukraine

• https://orcid.org/0009-0000-9184-5604

autor

Drozd Sofiia

• Space Research Institute NASU-SSAU, Kyiv, Ukraine
• National Technical University of Ukraine, Kyiv, Ukraine

• https://orcid.org/0000-0002-5149-5520

autor

Shelestov Andrii

• Space Research Institute NASU-SSAU, Kyiv, Ukraine
• National Technical University of Ukraine, Kyiv, Ukraine

• https://orcid.org/0000-0001-9256-4097

autor

Mikava Polina

• National Technical University of Ukraine, Kyiv, Ukraine

• https://orcid.org/0009-0002-6242-5218

Bibliografia

• 1. Alvarez, M.D. (2003). Forests in the time of violence: conservation implications of the Colombian war. J. Sustain. For., 16(3–4), 47–68. DOI: 10.1300/J091v16n03_03.
• 2. Aslan, M.F., Sabanci, K., Aslan, B. (2024). Artificial Intelligence Techniques in Crop Yield Estimation Based on Sentinel-2 Data:AComprehensive Survey. Sustainability, 16(18), 8277. DOI: 10.3390/su16188277.
• 3. Avtar, R., Kouser, A., Kumar, A. et. al. (2021). Remote sensing for international peace and security: its role and implications. Remote Sens., 13(3), 439. DOI: 10.3390/rs13030439.
• 4. Becker-Reshef, I., Vermote, E., Lindeman, M. Et al.(2010). A generalized regression-based model for forecasting winter wheat yields in Kansas and Ukraine using MODIS data. Remote sensing of environment, 114(6), 1312–1323.
• 5. Bennett, M.M., van Den Hoek, J., Zhao, B. et al. (2022). Improving satellite monitoring of armed conflicts. Earth’s Future, 10(9), e2022EF002904. DOI: 10.1029/2022EF002904.
• 6. Butsic, V., Baumann, M., Shortland, A. et al. (2015). Conservation and conflict in the Democratic Republic of Congo: The impacts of warfare, mining, and protected areas on deforestation. Biol. Conserv., 191, 266–273. DOI: 10.1016/j.biocon.2015.06.037.
• 7. Calabrese, A., Costa, R., Tiburzi, L. et al. (2023). Merging two revolutions: A human-artificial intelligence method to study how sustainability and Industry 4.0 are intertwined. Technol. Forecast. Soc. Change, 188, 122265. DOI: 10.1016/j.techfore.2022.122265.
• 8. Duncan, E.C., and Skakun, S. (2023). Detection and mapping of artillery craters in agricultural areas of Donetsk Oblast using a U-Net-based deep neural network and ultra-high spatial resolution satellite imagery. Int. J. Appl. Earth Obs. Geoinf., 125, 103562. DOI: 10.1016/j.jag.2023.103562.
• 9. Eklund, L., Degerald, M., Brandt, M. et al. (2017). How conflict affects land use: agricultural activity in areas seized by the Islamic State. Environ. Res. Lett., 12(5), 054004. DOI: 10.1088/1748-9326/aa673a.
• 10. Garzón, F.A.M., and Valánszki, I. (2020). Environmental armed conflict assessment using satellite imagery. J. Environ. Geogr., 13(3-4), 1–14. DOI: 10.2478/jengeo-2020-0007.
• 11. Gitelson, A., Viña, A., Solovchenko, A. et al. (2019). Derivation of canopy light absorption coefficient from reflectance spectra. Remote Sens. Environ., 231, 111276. DOI: 10.1016/j.rse.2019.111276.
• 12. Goswami, B., and Nayak, P. (2022). Optimization in Agricultural Growth Using AI and Satellite Imagery. In: Rautaray, S.S., Pandey, M., Nguyen, N.G. (eds) Data Science in Societal Applications. Studies in Big Data, 114. Springer, Singapore. DOI: 10.1007/978-981-19-5154-1_7.
• 13. Kussul, N., Shelestov, A., Yailymov, B. et al. (2022). Analysis of Cultivated Areas in Ukraine During theWar. In 12th International Conference on Dependable Systems, Services and Technologies (DESSERT) (pp. 1–4). IEEE.
• 14. Kussul, N., Drozd, S., Yailymova, H. et.al. (2023b). Assessing damage to agricultural fields from military actions in Ukraine: An integrated approach using statistical indicators and machine learning. Int. J. Appl. Earth Obs. Geoinf., 125, 103562. DOI: 10.1016/j.jag.2023.103562.
• 15. Mueller, H., Groeger, A., Hersh, J. et al. (2021). Monitoring war destruction from space using machine learning. In Proceedings of the National Academy of Sciences, 118(23), e2025400118.
• 16. Shammi, S.A., and Meng, Q. (2021). Use time series NDVI and EVI to develop dynamic crop growth metrics for yield modeling. Ecol. Indicators, 121, 107124. DOI: 10.1016/j.ecolind.2020.107124.
• 17. Shelestov, A., Drozd, S., Mikava, P. et al. (2023). War damage detection based on satellite data. In Proceedings of the 11th International Conference on Applied Innovations in IT, (ICAIIT).
• 18. Sticher, V., Wegner, J.D., and Pfeifle, B. (2023). Toward the remote monitoring of armed conflicts. PNAS NEXUS, 2(6), pgad181. DOI: 10.1093/pnasnexus/pgad181.
• 19. Taggio, F., Rossi, M., and Bianchi, L. (2024). SAI4EO: Symbiotic Artificial Intelligence for Earth Observation. In Proceedings of the International Conference on Artificial Intelligence Applications (pp. 509-518). CEUR Workshop Proceedings.
• 20. Wu, B., Zhang, M., Zeng, H. et al. (2023). Challenges and opportunities in remote sensing-based crop monitoring: A review. National Sci. Rev., 10(4), nwac290. DOI: 10.1093/nsr/nwac290.
• 21. Zhu, Q., Sun, X., Zhong, Y. et al.. (2019). High-resolution remote sensing image scene understanding: A review. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, 28 July–2 August 2019, Yokohama, Japan, p. 3061–3064. DOI: 10.1109/IGARSS.2019.8899293.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025)