# Migrating in a Warming World: A Deep Learning Approach to Predict Pan‐American Seasonal Shifts in the Monarch Butterfly Niche

## TL;DR

This paper uses deep learning to predict how climate change will shift the monarch butterfly's seasonal range across the Americas.

## Contribution

A time-aware deep learning model is introduced to better capture seasonal and spatial dynamics of migratory species under climate change.

## Key findings

- Climatic factors like humidity, temperature, and precipitation strongly influence the monarch butterfly's ecological niche.
- The model predicts a northwestward shift in the monarch's range by the end of the XXI century.
- Decreased precipitation and increased temperature are key drivers of overwintering site contractions in California and Mexico.

## Abstract

Climate change is driving biodiversity loss, disrupting ecosystem functioning, and altering species distributions. Migratory species, whose range varies across seasons depending on specific climatic conditions, are particularly sensitive to environmental changes and serve as indicators of ecosystem health. However, current species distribution models often fail to capture the temporal dynamics critical for migratory species, limiting their ability to provide accurate future range estimations. In this study, we address this gap by developing a time‐aware deep learning species distribution model for the monarch butterfly (
Danaus plexippus
), an iconic species for biodiversity conservation. Using monarch occurrence records across the Americas gathered from scientific and citizen science sources, we incorporate the effect of monthly climatic variables in a sequential framework. We compare the performance of our concatenated seasonal model to conventional time‐static baselines, showing not only better performance in the present, where the models have been trained and validated, but also in the past. Our findings show that climatic factors such as humidity, temperature, precipitation and cloud coverage strongly influence the ecological niche of the monarch butterfly, with notable seasonal and spatial variability. Applying our model under climate change scenarios, we predict a northwestward shift in the monarch range by the end of the XXI century, with expansion in Canada and significant contraction in California and Mexico, key sites for overwintering that also host resident monarch populations. These changes could severely impact the species' migratory cycle and population stability. Using Shapley values, an explainable AI technique, we identify the decrease in precipitation and an increase in temperature as important environmental drivers responsible for the contraction of overwintering sites. By focusing on a species of high ecological relevance through a time‐aware modeling approach, this work brings novel insights for the conservation of migratory species in the face of the challenges posed by climate change.

Migratory species are highly sensitive to environmental changes, making them useful indicators of how ecosystems respond to global change. To address the limitations of time‐static species distribution models, which fail to capture dynamic range shifts, we develop a time‐aware deep learning model to study the monarch butterfly migration across the Americas. Beyond improving model performance, our approach links expected changes in environmental conditions to a northwestward distribution shift and highlights range contractions in California and Mexico, threatening overwintering sites and long‐term population stability.