# Global Flood Prediction: a Multimodal Machine Learning Approach

arXiv: https://arxiv.org/abs/2301.12548 · HTML: https://mlsanity.com/paper/2301.12548/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 29 Jan 2023.

## Builds on (most cited first, 4 of 4)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis](https://mlsanity.com/paper/1807.07814/) (2018)
- [On the Sentence Embeddings from Pre-trained Language Models](https://mlsanity.com/paper/2011.05864/) (2020)
- [Flood Prediction Using Machine Learning Models: Literature Review](https://mlsanity.com/paper/1908.02781/) (2019)

## Built on by (most cited first, 4 of 4)

- [On the Foundations of Earth and Climate Foundation Models](https://mlsanity.com/paper/2405.04285/) (2024)
- [Graph Transformer Network for Flood Forecasting with Heterogeneous Covariates](https://mlsanity.com/paper/2310.07631/) (2023)
- [Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach](https://mlsanity.com/paper/2304.04308/) (2023)
- [Harnessing Diverse Data for Global Disaster Prediction: A Multimodal Framework](https://mlsanity.com/paper/2309.16747/) (2023)

## Abstract (arXiv)

Flooding is one of the most destructive and costly natural disasters, and climate changes would further increase risks globally. This work presents a novel multimodal machine learning approach for multi-year global flood risk prediction, combining geographical information and historical natural disaster dataset. Our multimodal framework employs state-of-the-art processing techniques to extract embeddings from each data modality, including text-based geographical data and tabular-based time-series data. Experiments demonstrate that a multimodal approach, that is combining text and statistical data, outperforms a single-modality approach. Our most advanced architecture, employing embeddings extracted using transfer learning upon DistilBert model, achieves 75%-77% ROCAUC score in predicting the next 1-5 year flooding event in historically flooded locations. This work demonstrates the potentials of using machine learning for long-term planning in natural disaster management.