# Uncertainty estimation of machine learning spatial precipitation predictions from satellite data

arXiv: https://arxiv.org/abs/2311.07511 · HTML: https://mlsanity.com/paper/2311.07511/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 84 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [Generalized Random Forests](https://mlsanity.com/paper/1610.01271/) (2016)
- [A comparison of some conformal quantile regression methods](https://mlsanity.com/paper/1909.05433/) (2019)
- [Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problems](https://mlsanity.com/paper/1808.08798/) (2018)
- [A review of predictive uncertainty estimation with machine learning](https://mlsanity.com/paper/2209.08307/) (2022)
- [Boosting algorithms in energy research: A systematic review](https://mlsanity.com/paper/2004.07049/) (2020)
- [A review of machine learning concepts and methods for addressing challenges in probabilistic hydrological post-processing and forecasting](https://mlsanity.com/paper/2206.08998/) (2022)
- [Comparison of machine learning algorithms for merging gridded satellite and earth-observed precipitation data](https://mlsanity.com/paper/2301.01252/) (2022)
- [Merging satellite and gauge-measured precipitation using LightGBM with an emphasis on extreme quantiles](https://mlsanity.com/paper/2302.03606/) (2023)
- [Comparison of tree-based ensemble algorithms for merging satellite and earth-observed precipitation data at the daily time scale](https://mlsanity.com/paper/2301.01214/) (2022)
- [Ensemble learning for blending gridded satellite and gauge-measured precipitation data](https://mlsanity.com/paper/2307.06840/) (2023)
- [Quantification of predictive uncertainty in hydrological modelling by harnessing the wisdom of the crowd: Methodology development and investigation using toy models](https://mlsanity.com/paper/1909.00244/) (2019)

## Built on by (most cited first, 2 of 2)

- [Ensemble learning for uncertainty estimation with application to the correction of satellite precipitation products](https://mlsanity.com/paper/2403.10567/) (2024)
- [Combinations of distributional regression algorithms with application in uncertainty estimation of corrected satellite precipitation products](https://mlsanity.com/paper/2407.01623/) (2024)

## Abstract (arXiv)

Merging satellite and gauge data with machine learning produces high-resolution precipitation datasets, but uncertainty estimates are often missing. We addressed the gap of how to optimally provide such estimates by benchmarking six algorithms, mostly novel even for the more general task of quantifying predictive uncertainty in spatial prediction settings. On 15 years of monthly data from over the contiguous United States (CONUS), we compared quantile regression (QR), quantile regression forests (QRF), generalized random forests (GRF), gradient boosting machines (GBM), light gradient boosting machine (LightGBM), and quantile regression neural networks (QRNN). Their ability to issue predictive precipitation quantiles at nine quantile levels (0.025, 0.050, 0.100, 0.250, 0.500, 0.750, 0.900, 0.950, 0.975), approximating the full probability distribution, was evaluated using quantile scoring functions and the quantile scoring rule. Predictors at a site were nearby values from two satellite precipitation retrievals, namely PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and IMERG (Integrated Multi-satellitE Retrievals), and the site's elevation. The dependent variable was the monthly mean gauge precipitation. With respect to QR, LightGBM showed improved performance in terms of the quantile scoring rule by 11.10%, also surpassing QRF (7.96%), GRF (7.44%), GBM (4.64%) and QRNN (1.73%). Notably, LightGBM outperformed all random forest variants, the current standard in spatial prediction with machine learning. To conclude, we propose a suite of machine learning algorithms for estimating uncertainty in spatial data prediction, supported with a formal evaluation framework based on scoring functions and scoring rules.