Detection of War-Caused Agricultural Field Damages Using Sentinel-2 Satellite Data with Machine Learning and Anomaly Detection
Вантажиться...
Дата
2024
Автори
Науковий керівник
Назва журналу
Номер ISSN
Назва тому
Видавець
ACM Special Interested Group on Applied Computing (SIGAPP)
Анотація
This research aims to detect war-caused damages on agricultural fields in Ukraine using Sentinel-2 satellite data. To achieve this, a Random Forest-based classification and an anomaly detection method deployed in the GEE cloud environment are applied. Two spectral bands - blue (B2) and green (B3) and two vegetation indices - NDVI and GCI - were used as input parameters. According to the results, the f1-score of classification reach 0.9. Using the developed methodology, more than 1.5 millions ha of fields were identified as damaged during the period of 2022--2023.
Опис
Ключові слова
War-caused agricultural field damages, Sentinel-2 satellite data, Random Forest-based classification, anomaly detection
Бібліографічний опис
Drozd, S. Detection of War-Caused Agricultural Field Damages Using Sentinel-2 Satellite Data with Machine Learning and Anomaly Detection / Sofiia Drozd // SAC ’24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, April 8 –April 12, 2024, Avila, Spain. - Avila, 2024. - P. 701-703.