講座主題：Analysis of SENTINEL-2 image series based on neural networks
專家姓名：Fedorov Roman K
工作單位：Russian Academy of Sciences
講座時間：2025年06月04日 10:30-11:30
講座地點：數學院大會議室341
主辦單位：煙臺大學數學與信息科學學院
內容摘要：
This study presents a neural network-based analysis of Sentinel-2 satellite image series, focusing on land cover classification and temporal change detection. The methodology involves six key stages: (1) image markup, where satellite images are cataloged and annotated using polygon objects; (2) image preparation, including resolution standardization (10x10 m) and terrain feature extraction; (3) sample creation, generating 64x64-pixel tensor samples from non-background pixels; (4) clustering and balancing to homogenize sample distribution across classes; (5) model training using Random Forest, ConvNet, ResNet50, and LSTM architectures; and (6) large-scale classification of over 22,000 images (May–September, multi-year) on a GPU cluster (3090/4090/A100). The output, saved in GeoTIFF format, enables analysis of crop dynamics and land transitions. The workflow emphasizes automation, parallel processing, and multi-temporal evaluation, demonstrating scalable applications for environmental monitoring.
主講人介紹：
Fedorov R.K. 的全名為 Roman K. Fedorov（羅曼·K·費多羅夫），是俄羅斯科學院西伯利亞分院計算中心（IDSCT SB RAS）的研究人員，主要研究方向為遙感圖像處理與人工智能應用。其工作聚焦衛星影像的智能解析與大規模計算，成果直接服務于農業監測及生態變遷分析，體現了較強的工程落地能力。Fedorov R.K. 作為主要作者之一，參與開發了基于神經網絡的哨兵-2（Sentinel-2）衛星影像時序分析技術。該技術通過六階段流程實現高效處理，包括影像標注、多模態特征融合（光譜+紋理+地形）、動態樣本生成、聚類平衡、多模型訓練（如ResNet50、LSTM）及大規模并行分類，最終應用于農作物動態監測與地表覆蓋變遷分析。
