Kussul, NatalliaDrozd, SofiiaSkakun, SergiiDuncan, ErikBecker-Reshef, Inbal2024-02-232024-02-232023Fusion of very high and moderate spatial resolution satellite data for detection and mapping of damages in agricultural fields / N. Kussul, S. Drozd, S. Skakun, E. Duncan, I. Becker-Reshef // The 13th IEEE International Conference on Dependable Systems, Services and Technologies, DESSERT’2023, [Athens], 13-15 October, 2023. - Athens, 2023. - P. 1-7.https://ela.kpi.ua/handle/123456789/64922The war in Ukraine has resulted in significant losses in the agricultural sector due to damages to farmlands posing a threat to global food security. To restore the prosperity of the agricultural sector it is essential to detect and assess damages in agricultural fields and monitor their evolution. Commercial satellite data at very high spatial resolution $(\lt3 \mathrm{m})$ such as sub-meter imagery acquired by Maxar’s WorldView and Planet Labs’ SkySat platforms allow detection and mapping of artillery craters at fine scale. However, the frequency of acquisition and geographical coverage of this type of data is limited and may be quite low, e.g., 1-2 scenes per agriculture season. With the aim to continuously monitor the state of the fields over large areas in Ukraine we must compliment the analysis with satellite data at lower spatial resolution, e.g., daily PlanetScope at $\sim 3-\mathrm{m}$ and 10-m Sentinel-2/MSI. Here, we propose a data fusion approach to monitor artillery craters in agricultural fields using combination of satellite images acquired at different spatial and temporal resolution. Specifically, we use a single-date SkySat image at 0.5-m resolution with crater detection using previously developed deep learning approach along with multi-temporal data acquired by PlanetScope and Sentinel-2 images. For the latter, we detect anomalies of refelecant signal in the blue and green spectral bands and the Normalized Difference Water Index (NDWI). This approach is applied to a test area of 8,800 ha in Donetsk oblast. We found that with PlanetScope images at 3-m we were able to identify 202 ha of craters, or 63% of those in SkySat imagery; with Sentinel-2 at 10-m we detected 165 ha (or 51%) of craters. Craters with an area smaller than $100 \mathrm{m}{2}$ were poorly detected. By analyzing anomalies in multi-temporal PlanetScope and Sentinel-2 images, we were able to identify craters that were not detected in SkySat data highlighting the importance of temporal component in the data. Furthermore, with daily PlanetScope data combined with Sentinel-2 data (3-5 days), we were able to estimate the dates of crater appearances and analyze the dynamics of craters and their evolution.P. 1-7endamage on agricultural fieldsfreely and commercial satellite dataSentinel-2PlanetScopeSkySatmachine learninganomaly detectionhistory of cratersArticlehttps://doi.org/10.1109/DESSERT61349.2023.10416533