Low-Resource Crop Classification from Multi-Spectral Time Series Using Lossless Compressors

TL;DR

This paper introduces a non-training, compressor-based method for crop classification from multispectral time series data, outperforming deep learning models especially in low-resource scenarios, by using symbolic representations and normalized compression distances.

Contribution

The paper proposes a novel non-parametric framework that replaces deep learning with symbolic representations and compression-based similarity measures for crop classification.

Findings

Outperforms 7 advanced deep learning models on benchmark datasets.

Effective in few-shot, sparse-label scenarios.

Lightweight and ready-to-use, no training required.

Abstract

Deep learning has significantly improved the accuracy of crop classification using multispectral temporal data. However, these models have complex structures with numerous parameters, requiring large amounts of data and costly training. In low-resource situations with fewer labeled samples, deep learning models perform poorly due to insufficient data. Conversely, compressors are data-type agnostic, and non-parametric methods do not bring underlying assumptions. Inspired by this insight, we propose a non-training alternative to deep learning models, aiming to address these situations. Specifically, the Symbolic Representation Module is proposed to convert the reflectivity into symbolic representations. The symbolic representations are then cross-transformed in both the channel and time dimensions to generate symbolic embeddings. Next, the Multi-scale Normalised Compression Distance (MNCD) is designed to measure the correlation between any two symbolic embeddings. Finally, based on the MNCDs, high quality crop classification can be achieved using only a k-nearest-neighbor classifier kNN. The entire framework is ready-to-use and lightweight. Without any training, it outperformed, on average, 7 advanced deep learning models trained at scale on three benchmark datasets. It also outperforms more than half of these models in the few-shot setting with sparse crop labels. Therefore, the high performance and robustness of our non-training framework makes it truly applicable to real-world crop mapping. Codes are available at: https://github.com/qinfengsama/Compressor-Based-Crop-Mapping.