Multimodal Machine Learning Lab
Multimodal ML for Climate Forecasting

Multimodal
Machine Learning
Lab

Multimodal ML for
Climate Forecasting

Fusing data to predict and mitigate climate extremes

What is Multimodal Machine Learning (MML) Architecture?

Synthesize wide range of data for accurate forecasting

DATA SOURCES

Satellite Imagery

News & Reports

Weather Data

More data

Our MML Models

How it works

Most AI systems focus on a single modality, but human understanding is multimodal. Our MML architecture fuses data across domains.

We combine vision, language, and time series to produce accurate forecasts—from minutes to years—with state-of-the-art reliability.

PREDICTIONS

Flood

Drought

Snowfall

Wildfire

Hurricane

Heat

Read our blogs

Stay updated with the latest insights, research findings, and developments in climate science and environmental data analysis. Our team shares cutting-edge research, methodologies, and real-world applications of our work.

July 8, 20255 min read

MML - Flood

Flooding is one of the most damaging natural disasters we face—and with climate change, the risks are only growing. In our latest research, we’ve developed a machine learning model that combines different types of data—like geographic information and past disaster records—to predict where floods are likely to happen over the next 1 to 5 years. By using both text and numbers together, our model performs significantly better than traditional methods, reaching up to 77% accuracy. It’s a step forward in using AI to plan ahead and reduce the impact of natural disasters.

by Nicole Zhang & Zein Mukhanov

Flood PredictionMachine Learning

July 8, 20255 min read