Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach
Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach
复制标题
DOI：
10.1145/3466688
复制
发表时间：
2021-11-01
影响因子：
5
通讯作者：
Shekhar, Shashi
中科院分区：
文献类型：
--
作者：
Gupta, Jayant;Molnar, Carl;Shekhar, Shashi
空间变异性是各种地理现象的一个显著特征，如气候带、USDA植物抗寒带和陆地栖息地类型（如森林、草原、湿地和沙漠）。然而，目前的深度学习方法采用空间一刀切（OSFA）方法来训练单个深度神经网络模型，这些模型不考虑空间可变性。由于许多地球物理因素的影响，空间变异性的量化具有挑战性。在初步工作中，我们提出了一种空间可变性感知神经网络（SVANN- i，以前称为SVANN）方法，其中权重是位置的函数，但神经网络结构与位置无关。在这项工作中，我们探索了一种更灵活的SVANNE方法，其中神经网络架构因地理位置而异。此外，我们还提供了SVANN类型的分类和物理启发的解释模型。基于航空影像的湿地制图实验表明，svann - 1优于OSFA，而SVANN-E表现最好。
Spatial variability is a prominent feature of various geographic phenomena such as climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all (OSFA) approach to train single deep neural network models that do not account for spatial variability. Quantification of spatial variability can be challenging due to the influence of many geophysical factors. In preliminary work, we proposed a spatial variability aware neural network (SVANN-I, formerly called SVANN) approach where weights are a function of location but the neural network architecture is location independent. In this work, we explore a more flexible SVANNE approach where neural network architecture varies across geographic locations. In addition, we provide a taxonomy of SVANN types and a physics inspired interpretation model. Experiments with aerial imagery based wetland mapping show that SVANN-I outperforms OSFA and SVANN-E performs the best of all.