# Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass Distribution for Deep Learning Biomass Estimation

arXiv: https://arxiv.org/abs/2607.05260 · HTML: https://mlsanity.com/paper/2607.05260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [Survey on Publicly Available Sinhala Natural Language Processing Tools and Research](https://mlsanity.com/paper/1906.02358/) (2019)
- [SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods](https://mlsanity.com/paper/1610.03771/) (2016)
- [InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2302.08624/) (2023)
- [Sentiment Analysis for Sinhala Language using Deep Learning Techniques](https://mlsanity.com/paper/2011.07280/) (2020)
- [BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification](https://mlsanity.com/paper/2110.00171/) (2021)
- [Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons & Dragons](https://mlsanity.com/paper/2212.09080/) (2022)
- [EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks](https://mlsanity.com/paper/2508.17008/) (2025)
- [Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content](https://mlsanity.com/paper/2504.13545/) (2025)
- [Linguistic Analysis of Sinhala YouTube Comments on Sinhala Music Videos: A Dataset Study](https://mlsanity.com/paper/2501.18633/) (2025)
- [Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content](https://mlsanity.com/paper/2504.10679/) (2025)
- [Text classification using machine learning methods](https://mlsanity.com/paper/2502.19801/) (2025)
- [GeeSanBhava: Sentiment Tagged Sinhala Music Video Comment Data Set](https://mlsanity.com/paper/2511.18146/) (2025)
- [DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2601.23022/) (2026)

## Abstract (arXiv)

Conventional modeling approaches for LiDAR-based above-ground biomass (AGB) estimation rely on discrete plot-level inventory aggregates. This methodology introduces boundary-effect uncertainties that may severely degrade model performance within small field plots. To solve this limitation, we evaluate a Horizontal Biomass Distribution (HBD) reference mapped continuously from Quantitative Structure Models (QSMs). We trained a sparse 3D U-Net on simulated broadleaved forest structures using three AGB reference types: a standard forest inventory (FI) plot-level aggregate, an edge-effect-free QSM plot-level aggregate, and a continuous HBD mapping. Evaluating training plot sizes scaling from 100 to 2500 m2 , QSM-based models systematically outperformed FI approaches at small plot sizes. Specifically, for 100 m2 plots, the HBD reference reduced the relative root mean square error (RRMSE) by 16.84 ± 4.37 % and increased R2 by 0.22 ± 0.05 against the FI baseline. By replacing plot level aggregates with HBDs as AGB reference, this methodology corrects for edge-effects and shows that using an HBD-based reference enhances model performance for small plot sizes.