# Developing a Sequential Deep Learning Pipeline to Model Alaskan Permafrost Thaw Under Climate Change

arXiv: https://arxiv.org/abs/2510.06258 · HTML: https://mlsanity.com/paper/2510.06258/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 40 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)

## Abstract (arXiv)

Changing climate conditions threaten the natural permafrost thaw-freeze cycle, leading to year-round soil temperatures above 0degC. In Alaska, the warming of the topmost permafrost layer, known as the active layer, signals elevated greenhouse gas release due to high carbon storage. Accurate soil temperature prediction is therefore essential for risk mitigation and stability assessment; however, many existing approaches overlook the numerous factors driving soil thermal dynamics. This study presents a proof-of-concept latitude-based deep learning pipeline for modeling yearly soil temperatures across multiple depths. The framework employs dynamic reanalysis feature data from the ERA5-Land dataset, static geologic and lithological features, sliding-window sequences for seasonal context, a derived scenario signal feature for long-term climate forcing, and latitude band embeddings for spatial sensitivity. Five deep learning models were tested: a Temporal Convolutional Network (TCN), a Transformer, a 1-Dimensional Convolutional Long-Short Term Memory (Conv1DLSTM), a Gated-Recurrent Unit (GRU), and a Bidirectional Long-Short Term Memory (BiLSTM). Results showed solid recognition of latitudinal and depth-wise temperature discrepancies, with the GRU performing best in sequential temperature pattern detection. Bias-corrected CMIP5 RCP data enabled recognition of sinusoidal temperature trends, though limited divergence between scenarios were observed. This study establishes an end-to-end framework for adopting deep learning in active layer temperature modeling, offering seasonal, spatial, and vertical temperature context without intrinsic restrictions on feature selection.