利用高分辨率卫星影像比较不丹水稻制图的深度学习模型
Comparing Deep Learning Models for Rice Mapping in Bhutan Using High Resolution Satellite Imagery
AI总结：
本文针对不丹帕罗地区水稻制图，基于 NICFI 高分辨率影像比较 DNN 与 U-Net 及多源特征组合，发现 U-Net RGBNES 独立评估表现最佳，并验证弱标签土地覆盖产品可改善抽样。
摘要：
不丹政府正在加强对技术方法的利用，例如将基于遥感的知识纳入其决策过程。本研究聚焦不丹水稻高产区之一帕罗的作物类型和作物范围，并采用来自 Planet 的公开可用 NICFI 高分辨率卫星影像。研究结合云计算平台，使用了两种深度学习（DL）方法：基于点的 DNN 和基于影像块的 U-Net 模型。每种深度学习方法（DNN 和 U-Net）均训练了三种不同模型：1）来自 Planet 的 RGBN 通道；2）RGBN 与高程数据（RGBNE）；3）RGBN 与 Sentinel-1（S1）数据（RGBNS），以及结合 RGBN、E 和 S1 数据的 RGBNES。综合分析表明，U-Net 在模型训练和模型验证两方面均表现出更高的性能指标。在 U-Net 模型组中，RGBN、RGBNE、RGBNS 和 RGBNES 模型的 F1 分数分别为 0.8546、0.8563、0.8467 和 0.8500。研究还开展了独立模型评估，发现所有指标均存在较大性能差异。在该独立模型评估中，U-Net RGBN、RGBNE、RGBNES 和 RGBN 模型的 F1 分数分别为 0.5935、0.6154、0.5882 和 0.6582，表明 U-Net RGBNES 为最佳模型。研究表明，深度学习方法能够预测水稻。此外，深度学习方法可与不丹农业部目前采用的基于调查的方法结合使用。进一步而言，本研究展示了将 SERVIR RLCMS 等区域土地覆盖产品作为弱标签方法的用途，以捕捉不同分层、解决类别不平衡问题并改进深度学习应用的抽样设计。最后，通过初步模型测试和所列比较表明，使用 NDVI、EVI 和 NDWI 等附加特征并未显著提升模型性能。
英文摘要：
The Bhutanese government is increasing its utilization of technological approaches such as including Remote Sensing-based knowledge in their decision-making process. This study focuses on crop type and crop extent in Paro, one of the top rice-yielding districts in Bhutan, and employs publicly available NICFI high-resolution satellite imagery from Planet. Two Deep Learning (DL) approaches, point-based (DNN) and patch-based (U-Net), models were used in conjunction with cloud-computing platforms. Three different models per DL approaches (DNN and U-Net) were trained: 1) RGBN channels from Planet; 2) RGBN and elevation data (RGBNE); 3) RGBN and Sentinel-1 (S1) data (RGBNS), and RGBN with E and S1 data (RGBNES). From this comprehensive analysis, the U-Net displayed higher performance metrics across both model training and model validation efforts. Among the U-Net model sets, the RGBN, RGBNE, RGBNS, and RGBNES models had an F1-score of 0.8546, 0.8563, 0.8467, and 0.8500 respectively. An independent model evaluation was performed and found a high level of performance variation across all the metrics. For this independent model evaluation, the U-Net RGBN, RGBNE, RGBNES, and RGBN models displayed the F1-scores of 0.5935, 0.6154, 0.5882, and 0.6582, suggesting U-Net RGBNES as the best model. The study shows that the DL approaches can predict rice. Also, DL methods can be used with the survey-based approaches currently utilized by the Bhutan Department of Agriculture. Further, this study demonstrated the usage of regional land cover products such as SERVIR's RLCMS as a weak label approach to capture different strata addressing the class imbalance problem and improving the sampling design for DL application. Finally, through preliminary model testing and comparisons outlined it was shown that using additional features such as NDVI, EVI, and NDWI did not drastically improve model performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
