论文标题
土地覆盖映射的深度学习应用中的模型概括
Model Generalization in Deep Learning Applications for Land Cover Mapping
论文作者
论文摘要
最近的工作表明，深度学习模型可用于从地理空间卫星图像中对土地利用数据进行分类。我们表明，当这些深度学习模型接受了来自特定大洲/季节的数据培训时，在样本外部/季节的模型性能差异很高。这表明，仅仅因为一个模型准确地预测一个大陆或季节的土地利用类并不意味着该模型将准确预测不同大陆或季节的土地利用类别。然后，我们在不同大陆的卫星图像上使用聚类技术来可视化景观的差异，从而使地理空间概括特别困难，并总结了我们为将来与卫星图像相关的应用程序的收获。
Recent work has shown that deep learning models can be used to classify land-use data from geospatial satellite imagery. We show that when these deep learning models are trained on data from specific continents/seasons, there is a high degree of variability in model performance on out-of-sample continents/seasons. This suggests that just because a model accurately predicts land-use classes in one continent or season does not mean that the model will accurately predict land-use classes in a different continent or season. We then use clustering techniques on satellite imagery from different continents to visualize the differences in landscapes that make geospatial generalization particularly difficult, and summarize our takeaways for future satellite imagery-related applications.
