CVIVJun 19, 2023

Forest Parameter Prediction by Multiobjective Deep Learning of Regression Models Trained with Pseudo-Target Imputation

arXiv:2306.11103v13 citationsh-index: 80
Originality Incremental advance
AI Analysis

This work addresses the challenge of limited ground reference data in forest monitoring for environmental scientists and remote sensing practitioners, offering an incremental improvement through semi-supervised learning.

The paper tackles the problem of predicting forest parameters from remote sensing data by imputing a small sample of ground reference data with pseudo-targets from existing prediction maps, which increases training data and enables deep learning for semi-supervised regression. The result shows that this approach surpasses traditional airborne laser scanning-based regression models in above-ground biomass and stem volume predictions across diverse forest types.

In prediction of forest parameters with data from remote sensing (RS), regression models have traditionally been trained on a small sample of ground reference data. This paper proposes to impute this sample of true prediction targets with data from an existing RS-based prediction map that we consider as pseudo-targets. This substantially increases the amount of target training data and leverages the use of deep learning (DL) for semi-supervised regression modelling. We use prediction maps constructed from airborne laser scanning (ALS) data to provide accurate pseudo-targets and free data from Sentinel-1's C-band synthetic aperture radar (SAR) as regressors. A modified U-Net architecture is adapted with a selection of different training objectives. We demonstrate that when a judicious combination of loss functions is used, the semi-supervised imputation strategy produces results that surpass traditional ALS-based regression models, even though \sen data are considered as inferior for forest monitoring. These results are consistent for experiments on above-ground biomass prediction in Tanzania and stem volume prediction in Norway, representing a diversity in parameters and forest types that emphasises the robustness of the approach.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes