PhD Thesis: Hybrid Physical–Machine Learning Models Improve High Streamflow Prediction for Flood Early Warning
Summary
This PhD thesis defense by Sergio Ricardo López Chacón focuses on enhancing short-term prediction of high streamflow by combining physically based models with machine learning. It addresses key limitations of ML models in hydrology: accuracy degradation on high (flood-relevant) streamflow values, uncertainty estimation, and hydrological interpretability. The work aims to improve early warning systems for flood mitigation by tackling the challenge of scarce high-flow data that reduces predictive accuracy, especially in extrapolated scenarios.
Source
bskyPhD Thesis: Hybrid Physical–Machine Learning Models Improve High Streamflow Prediction for Flood Early Warningcimne.comKey quotes
· 3 pulledMachine learning models have demonstrated a strong potential in the recent decade for streamflow prediction purposes.
High streamflow values are the most relevant for early warning systems of flood mitigation.
These records are scarce in the data. Hence, a decrease in accuracy is seen, which gets deeper in extrapolated scenarios.
You might also wanna read
Comparing Machine Learning Models of Raindrop Formation
General Physics Transformer Achieves Foundation Model Capabilities for Multiple Physical Systems
Researchers present the General Physics Transformer (GPhyT), a physics foundation model trained on 1.8 TB of diverse simulation data that ca
arxiv.org·9mo ago
Reflections on 2024 Bio-ML Predictions: Generative Chemistry and Molecular Dynamics Challenges
The article reflects on the author's 2024 predictions about bio-ML (biological machine learning) from a 2026 perspective, focusing on genera
owlposting.com·5mo ago
I have just published a new research paper titled: “AI Driven Urban Heat Equity Atlas Integrating Machine Learning for Climate Risk Assessment.” This research applies artificial intelligence and machi
Core Principles and Mathematical Foundations of Diffusion Models
This monograph presents the core principles of diffusion models, explaining how they work through three complementary mathematical perspecti
arxiv.org·8mo ago
Statistical Challenges in Machine Learning Model Calibration and Isotonicity Constraints
The article discusses the challenges of post-hoc calibration in machine learning models, specifically addressing the 'deadweight costs of st
gojiberries.io·9mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.