Upscaling Global Hourly GPP with Temporal Fusion Transformer (TFT)

TL;DR

This study develops a novel machine learning approach using Temporal Fusion Transformer and tree algorithms to upscale GPP estimates globally at high temporal resolution, overcoming data limitations.

Contribution

Introduces a hybrid model combining TFT with tree algorithms for global GPP upscaling without relying on past GPP data, enhancing interpretability and accuracy.

Findings

Model achieved 0.704 NSE and 3.54 RMSE.

Feature importance analysis improved understanding of temporal dynamics.

Hybrid approach outperformed individual models.

Abstract

Reliable estimates of Gross Primary Productivity (GPP), crucial for evaluating climate change initiatives, are currently only available from sparsely distributed eddy covariance tower sites. This limitation hampers access to reliable GPP quantification at regional to global scales. Prior machine learning studies on upscaling \textit{in situ} GPP to global wall-to-wall maps at sub-daily time steps faced limitations such as lack of input features at higher temporal resolutions and significant missing values. This research explored a novel upscaling solution using Temporal Fusion Transformer (TFT) without relying on past GPP time series. Model development was supplemented by Random Forest Regressor (RFR) and XGBoost, followed by the hybrid model of TFT and tree algorithms. The best preforming model yielded to model performance of 0.704 NSE and 3.54 RMSE. Another contribution of the study was the breakdown analysis of encoder feature importance based on time and flux tower sites. Such analysis enhanced the interpretability of the multi-head attention layer as well as the visual understanding of temporal dynamics of influential features.