Scholarlink

<p>Accurate identification of airfields and their components; especially runways are critical for both civil aviation planning and military operations, particularly in emergency landing scenarios and defence-related reconnaissance. This study focuses on detecting runways and associated airfield features using open-source Sentinel-1 (SAR) and Sentinel-2 (optical) satellite imagery through three data pathways: PW1 (SAR), PW2 (optical), and PW3 (fused SAR-optical). Six machine learning (ML) classifiers; Random Forest (RF), Extra Trees Classifier (ETC), Light Gradient Boosting Machine (LGBM), Gradient Boosting (GB), Decision Tree (DT), and K-Nearest Neighbors (KNN) were implemented and evaluated based on both qualitative and quantitative metrics, including accuracy, Area Under Curve (AUC), recall, precision, F1-score, kappa, Mathews Correlation Coefficient (MCC), and training time. The ET classifier in PW3 achieved the highest accuracy (97.98%), followed by LGBM in PW2 (96.24%) and RF in PW1 (73.24%). The results demonstrate that integrating SAR and optical data enhances classification performance, and RF offers a balance between accuracy and training efficiency. This research underscores the effectiveness of moderate-resolution multi-sensor fusion and ML techniques in mapping strategic targets like runways, with practical implications for defence, disaster response, and remote sensing applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

“Runway and airfield associated feature detection from optical and SAR data using machine learning Algorithms”

  • 期刊论文

  • 发表日期：

    2025年10月8日

查看全文
  • Puja Jha,
  • C. Jeganathan

摘要

Accurate identification of airfields and their components; especially runways are critical for both civil aviation planning and military operations, particularly in emergency landing scenarios and defence-related reconnaissance. This study focuses on detecting runways and associated airfield features using open-source Sentinel-1 (SAR) and Sentinel-2 (optical) satellite imagery through three data pathways: PW1 (SAR), PW2 (optical), and PW3 (fused SAR-optical). Six machine learning (ML) classifiers; Random Forest (RF), Extra Trees Classifier (ETC), Light Gradient Boosting Machine (LGBM), Gradient Boosting (GB), Decision Tree (DT), and K-Nearest Neighbors (KNN) were implemented and evaluated based on both qualitative and quantitative metrics, including accuracy, Area Under Curve (AUC), recall, precision, F1-score, kappa, Mathews Correlation Coefficient (MCC), and training time. The ET classifier in PW3 achieved the highest accuracy (97.98%), followed by LGBM in PW2 (96.24%) and RF in PW1 (73.24%). The results demonstrate that integrating SAR and optical data enhances classification performance, and RF offers a balance between accuracy and training efficiency. This research underscores the effectiveness of moderate-resolution multi-sensor fusion and ML techniques in mapping strategic targets like runways, with practical implications for defence, disaster response, and remote sensing applications.