# Post-Fire Forest Pulse Recovery: Superiority of Generalized Additive Models (GAM) in Long-Term Landsat Time-Series Analysis

## TL;DR

Generalized Additive Models (GAMs) are better at tracking post-fire forest recovery than other methods, especially in capturing complex recovery patterns in different ecosystems.

## Contribution

GAMs are shown to be superior for modeling nonlinear post-fire recovery, offering a new methodological framework for assessing forest resilience.

## Key findings

- GAMs outperformed linear and logistic models in capturing post-fire recovery dynamics.
- Australian forests recovered faster (~2 years) compared to California forests, which showed incomplete recovery after 9 years.
- GAMs had the lowest AIC and RMSE values, indicating strong performance in modeling recovery patterns.

## Abstract

What are the main findings?
Generalized Additive Models (GAMs) consistently outperformed other methods in modeling nonlinear post-fire vegetation recovery across two contrasting ecosystems. This model exhibited the lowest AIC and RMSE values, demonstrating an unparalleled ability to capture multiphase recovery patterns.Post-fire recovery trajectories are inherently nonlinear and ecosystem-specific. Australian (MDSF) forests rapidly returned to baseline levels (within ~2 years), whereas California (SMM) forests with a history of recurrent fires failed to fully recover even after 9 years.

Generalized Additive Models (GAMs) consistently outperformed other methods in modeling nonlinear post-fire vegetation recovery across two contrasting ecosystems. This model exhibited the lowest AIC and RMSE values, demonstrating an unparalleled ability to capture multiphase recovery patterns.

Post-fire recovery trajectories are inherently nonlinear and ecosystem-specific. Australian (MDSF) forests rapidly returned to baseline levels (within ~2 years), whereas California (SMM) forests with a history of recurrent fires failed to fully recover even after 9 years.

What are the implications of the main findings?
This study provides a transferable methodological framework for monitoring forest resilience under intensifying global fire regimes. Integrating Landsat time series with flexible semi-parametric models like GAM offers a powerful approach for recovery assessment.Simple linear and logistic models are insufficient for accurately estimating vegetation recovery time, as the findings emphasize the need for adopting more complex methods capable of capturing the heterogeneity of recovery pathways.

This study provides a transferable methodological framework for monitoring forest resilience under intensifying global fire regimes. Integrating Landsat time series with flexible semi-parametric models like GAM offers a powerful approach for recovery assessment.

Simple linear and logistic models are insufficient for accurately estimating vegetation recovery time, as the findings emphasize the need for adopting more complex methods capable of capturing the heterogeneity of recovery pathways.

Wildfires are increasing globally and pose major challenges for assessing post-fire vegetation recovery and ecosystem resilience. We analyzed long-term Landsat time series in two contrasting fire-prone ecosystems in the United States and Australia. Vegetation area was extracted using the Enhanced Vegetation Index (EVI) with Otsu thresholding. Recovery to pre-fire baseline levels was modeled using linear, logistic, locally estimated scatterplot smoothing (LOESS), and generalized additive models (GAM), and their performance was compared using multiple metrics. The results indicated rapid recovery of Australian forests to baseline levels, whereas this was not the case for forests in the United States. Among climatic factors, temperature was the dominant parameter in Australia (Spearman ρ = 0.513, p < 10−8), while no climatic variable significantly influenced recovery in California. Methodologically, GAM consistently performed best in both regions due to its success in capturing multiphase and heterogeneous recovery patterns, yielding the lowest values of AIC (United States: 142.89; Australia: 46.70) and RMSE_cv (United States: 112.86; Australia: 2.26). Linear and logistic models failed to capture complex recovery dynamics, whereas LOESS was highly sensitive to noise and unstable for long-term prediction. These findings indicate that post-fire recovery is inherently nonlinear and ecosystem-specific and that simple models are insufficient for accurate estimation, with GAM emerging as an appropriate method for assessing vegetation recovery using remote sensing data. This study provides a transferable approach using remote sensing and GAM to monitor forest resilience under accelerating global fire regimes.