Crop Classification Under Varying Cloud Cover With Neural Ordinary Differential Equations
| Autor: | Nando Metzger, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler, Mehmet Ozgur Turkoglu |
|---|---|
| Přispěvatelé: | University of Zurich, Turkoglu, Mehmet Ozgur |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer science 530 Physics Cloud cover Computer Vision and Pattern Recognition (cs.CV) 2208 Electrical and Electronic Engineering 1900 General Earth and Planetary Sciences Computer Science - Computer Vision and Pattern Recognition Image (mathematics) Convolution Recurrent neural network Ordinary differential equation 10231 Institute for Computational Science General Earth and Planetary Sciences Node (circuits) Time series Electrical and Electronic Engineering Representation (mathematics) Algorithm |
| DOI: | 10.5167/uzh-223348 |
| Popis: | Optical satellite sensors cannot see the Earth's surface through clouds. Despite the periodic revisit cycle, image sequences acquired by Earth observation satellites are therefore irregularly sampled in time. State-of-the-art methods for crop classification (and other time series analysis tasks) rely on techniques that implicitly assume regular temporal spacing between observations, such as recurrent neural networks (RNNs). We propose to use neural ordinary differential equations (NODEs) in combination with RNNs to classify crop types in irregularly spaced image sequences. The resulting ODE-RNN models consist of two steps: an update step, where a recurrent unit assimilates new input data into the model's hidden state; and a prediction step, in which NODE propagates the hidden state until the next observation arrives. The prediction step is based on a continuous representation of the latent dynamics, which has several advantages. At the conceptual level, it is a more natural way to describe the mechanisms that govern the phenological cycle. From a practical point of view, it makes it possible to sample the system state at arbitrary points in time, such that one can integrate observations whenever they are available, and extrapolate beyond the last observation. Our experiments show that ODE-RNN indeed improves classification accuracy over common baselines such as LSTM, GRU, and temporal convolution. The gains are most prominent in the challenging scenario where only few observations are available (i.e., frequent cloud cover). Moreover, we show that the ability to extrapolate translates to better classification performance early in the season, which is important for forecasting. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|