Transformer-Based Wildlife Species Classification from Daily Movement Trajectories

TL;DR

This study demonstrates that Transformer models significantly outperform traditional sequence models in wildlife species classification from GPS movement data, with improved accuracy especially under data-limited conditions.

Contribution

The paper introduces Transformer-based models for wildlife classification from movement trajectories and compares their performance to other neural network architectures.

Findings

Transformers achieve 8-22% higher accuracy than LSTM, CNN, and TCN models.

Feature augmentation improves performance for underrepresented species.

Finer temporal resolution captures short-term patterns but reduces overall performance due to data sparsity.

Abstract

Inferring the identity of wildlife species from daily movement data alone is a challenging task. We train sequence models on large-scale, 7-species GPS trajectories from the Movebank platform. Trajectories models are evaluated using a protocol in which entire telemetry studies or regions are heldout during testing. We compare Transformer-based sequence models to LSTM, CNN, and Temporal Convolutional Networks, and find that Transformers consistently achieve higher balanced accuracy with gains of approximately 8 to 22 percentage points, depending on the species and experimental setting. In an elephant binary classification task with 1-hour resolution, the Transformer achieves a balanced accuracy of 0.83 and an AUC of 0.92, substantially outperforming all baseline models. We examine, under data-limited conditions, feature representations by analyzing the differences between a basic displacement-based encoding and an expanded range of movement descriptors that include speed, direction, and turning behavior. With feature augmentation, we see clear performance gains, especially for underrepresented and sparsely represented species, such as large carnivores, lions, and Zebras. Finally, experiments comparing 1-hour and 30-minutetemporal resolutions show that while finer sampling can capture short-term movement patterns for some species, a unified 1-hour resolution yields more promising performance across studies by reducing missing data and ensuring consistent temporal coverage.