用知识增强的深度学习模型，精准识别遥感图像中的灌溉方式。
Knowledge-Informed Deep Learning for Irrigation Type Mapping from Remote Sensing
- 融合作物信息与遥感图像，通过注意力机制捕捉多源互补特征。
- 在5个美国州测试中，整体精度提升22.9%（IoU），滴灌识别提升71.4%。
- 仅需40%数据即可达基线性能，适合小样本、大规模农业监测场景。
精确绘制灌溉方式对可持续农业和粮食系统至关重要。然而，仅依赖卫星影像光谱特征的现有模型因农田景观复杂且训练数据有限，效果不佳。本文提出知识引导的灌溉制图方法（KIIM），基于Swin-Transformer架构，采用：(i) 专用投影矩阵编码作物到灌溉概率；(ii) 空间注意力图区分农用地与非农用地；(iii) 双向交叉注意力融合多模态信息；(iv) 加权集成结合图像与作物信息预测结果。在五个美国州的实验表明，相比基线模型，整体指标提升最高达22.9%（IoU），难以分类的滴灌识别提升71.4%。此外，提出的两阶段迁移学习策略显著提升跨州映射能力，在标注数据少的州实现51%的IoU提升。仅需40%训练数据即可达到基线性能，大幅降低人工标注成本，推动大规模自动化灌溉制图的可行性与经济性。
原文摘要 · Abstract (English)
Accurate mapping of irrigation methods is crucial for sustainable agricultural practices and food systems. However, existing models that rely solely on spectral features from satellite imagery are ineffective due to the complexity of agricultural landscapes and limited training data, making this a challenging problem. We present Knowledge-Informed Irrigation Mapping (KIIM), a novel Swin-Transformer based approach that uses (i) a specialized projection matrix to encode crop to irrigation probability, (ii) a spatial attention map to identify agricultural lands from non-agricultural lands, (iii) bi-directional cross-attention to focus complementary information from different modalities, and (iv) a weighted ensemble for combining predictions from images and crop information. Our experimentation on five states in the US shows up to 22.9\% (IoU) improvement over baseline with a 71.4% (IoU) improvement for hard-to-classify drip irrigation. In addition, we propose a two-phase transfer learning approach to enhance cross-state irrigation mapping, achieving a 51% IoU boost in a state with limited labeled data. The ability to achieve baseline performance with only 40% of the training data highlights its efficiency, reducing the dependency on extensive manual labeling efforts and making large-scale, automated irrigation mapping more feasible and cost-effective.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。