ML framework for global river flood predictions based on the Caravan dataset

TL;DR

This paper introduces a global river flood prediction framework using the Caravan dataset, proposing a novel two-path LSTM model and evaluating its generalizability across African and Asian locations to aid early flood warning efforts.

Contribution

It presents the first global flood prediction framework based on Caravan dataset and introduces a novel 2P-LSTM architecture for improved accuracy.

Findings

2P-LSTM outperforms baseline models in flood prediction accuracy.

The framework serves as a benchmark for future global flood prediction research.

Models generalize well to unseen locations in Africa and Asia.

Abstract

Reliable prediction of river floods in the first 72 hours can reduce harm because emergency agencies have sufficient time to prepare and deploy for help at the scene. Such river flood prediction models already exist and perform relatively well in most high-income countries. But, due to the limited availability of data, these models are lacking in low-income countries. Here, we offer the first global river flood prediction framework based on the newly published Caravan dataset. Our framework aims to serve as a benchmark for future global river flood prediction research. To support generalizability claims we include custom data evaluation splits. Further, we propose and evaluate a novel two-path LSTM architecture (2P-LSTM) against three baseline models. Finally, we evaluate the generated models on different locations in Africa and Asia that were not part of the Caravan dataset.