# Time-Space tradeoff in deep learning models for crop classification on satellite multi-spectral image time series

## TL;DR

This paper evaluates various deep learning architectures for crop classification using satellite multi-spectral time series, highlighting the importance of temporal modeling and providing design guidelines.

## Contribution

It systematically compares structured deep learning models, emphasizing the significance of temporal structures in crop classification from satellite data.

## Key findings

- Hybrid models with a focus on temporal structure perform best.
- Most model parameters (up to 90%) are dedicated to temporal modeling.
- Guidelines for designing effective deep learning models for crop classification.

## Abstract

In this article, we investigate several structured deep learning models for crop type classification on multi-spectral time series. In particular, our aim is to assess the respective importance of spatial and temporal structures in such data. With this objective, we consider several designs of convolutional, recurrent, and hybrid neural networks, and assess their performance on a large dataset of freely available Sentinel-2 imagery. We find that the best-performing approaches are hybrid configurations for which most of the parameters (up to 90%) are allocated to modeling the temporal structure of the data. Our results thus constitute a set of guidelines for the design of bespoke deep learning models for crop type classification.