# Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas

arXiv: https://arxiv.org/abs/2411.14354 · HTML: https://mlsanity.com/paper/2411.14354/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 21 Nov 2024.

## Builds on (most cited first, 18 of 18)

- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [A high-resolution canopy height model of the Earth](https://mlsanity.com/paper/2204.08322/) (2022)
- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar](https://mlsanity.com/paper/2304.07213/) (2023)
- [Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It](https://mlsanity.com/paper/2312.06420/) (2023)
- [Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles](https://mlsanity.com/paper/2103.03975/) (2021)
- [Micro-Estimates of Wealth for all Low- and Middle-Income Countries](https://mlsanity.com/paper/2104.07761/) (2021)
- [Importance of spatial predictor variable selection in machine learning applications -- Moving from data reproduction to spatial prediction](https://mlsanity.com/paper/1908.07805/) (2019)
- [Better, Not Just More: Data-Centric Machine Learning for Earth Observation](https://mlsanity.com/paper/2312.05327/) (2023)
- [ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery](https://mlsanity.com/paper/2201.11192/) (2022)
- [Estimating Canopy Height at Scale](https://mlsanity.com/paper/2406.01076/) (2024)
- [Open-Canopy: Towards Very High Resolution Forest Monitoring](https://mlsanity.com/paper/2407.09392/) (2024)
- [OpenForest: A data catalogue for machine learning in forest monitoring](https://mlsanity.com/paper/2311.00277/) (2023)
- [How accurate are existing land cover maps for agriculture in Sub-Saharan Africa?](https://mlsanity.com/paper/2307.02575/) (2023)
- [Evaluation Challenges for Geospatial ML](https://mlsanity.com/paper/2303.18087/) (2023)
- [Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream policy](https://mlsanity.com/paper/2305.01783/) (2023)
- [Striving for data-model efficiency: Identifying data externalities on group performance](https://mlsanity.com/paper/2211.06348/) (2022)

## Built on by (most cited first, 6 of 6)

- [PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models](https://mlsanity.com/paper/2412.04204/) (2024)
- [TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis](https://mlsanity.com/paper/2506.20380/) (2025)
- [Measuring the Intrinsic Dimension of Earth Representations](https://mlsanity.com/paper/2511.02101/) (2025)
- [Localized, High-resolution Geographic Representations with Slepian Functions](https://mlsanity.com/paper/2602.00392/) (2026)
- [The first global agricultural field boundary map at 10m resolution](https://mlsanity.com/paper/2605.11055/) (2026)
- [Canopy Tree Height Estimation Using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing](https://mlsanity.com/paper/2604.06988/) (2026)

## Abstract (arXiv)

While advances in machine learning with satellite imagery (SatML) are facilitating environmental monitoring at a global scale, developing SatML models that are accurate and useful for local regions remains critical to understanding and acting on an ever-changing planet. As increasing attention and resources are being devoted to training SatML models with global data, it is important to understand when improvements in global models will make it easier to train or fine-tune models that are accurate in specific regions. To explore this question, we contrast local and global training paradigms for SatML through a case study of tree canopy height (TCH) mapping in the Karingani Game Reserve, Mozambique. We find that recent advances in global TCH mapping do not necessarily translate to better local modeling abilities in our study region. Specifically, small models trained only with locally-collected data outperform published global TCH maps, and even outperform globally pretrained models that we fine-tune using local data. Analyzing these results further, we identify specific points of conflict and synergy between local and global modeling paradigms that can inform future research toward aligning local and global performance objectives in geospatial machine learning.