Know the water before it arrives.

NexFlood builds the physics-based models, machine learning and surrogate modeling, forecast systems, and software behind flood risk decisions — coastal, riverine, and the compound cases where they arrive together.

Start a conversation See what we do

Most flood questions are two questions. How deep, and how often. Everything we build exists to answer one of them with the evidence still attached.

Where we work

Regions, and the physics behind each one.

Areas of active work and interest. Not a claim that a system is running in each — when one is, it will say so.

Scroll to zoom · pick a region to fly to it

Tropical cyclone surge on national-scale unstructured meshes, validated against NOAA and NDBC records.

ADCIRCSWAN

Tropical cyclone basins modelled

All seven IBTrACS basins. Hover or tap one to locate it.

Regions of work Cyclone basin

Currently flooding

What the world is dealing with today.

A live view of active flood and tropical cyclone alerts worldwide. We watch this because the problems we work on do not wait for a project to be scoped.

What we do

Five ways a flood problem lands on our desk.

01Flood risk modelingCoastal surge, riverine, pluvial, and the compound cases where more than one arrives at once. How deep, and how often — answered with the evidence still attached.

02Forecast and early warning systemsOperational chains that pull forcing, run the model, and publish on a schedule without anyone watching — and the threshold logic that turns the result into a warning somebody acts on.

03Machine learning and computer visionFlood extent from satellite imagery, surrogate models that put a screening answer in seconds instead of hours, and structure inventories built from aerial and street-level photography. Trained against physics, scored against ground truth.

04Modeling tools and softwareMesh generators, forcing builders, validation harnesses — the tools that take preparation off the critical path. Tools commissioned for you are delivered with source and tests; the platform we build them on is licensed, not handed over.

05Validation and independent reviewSkill assessment against gauges, buoys, and high water marks — per station and in aggregate, using metrics chosen up front. Also a second set of eyes on somebody else’s study.

Capabilities

Three things we do, and how.

All capabilities

Flood forecasting and early warning systems

Operational chains that run on a schedule, and warnings somebody acts on

Flood risk analysis studies

How deep, and how often — with the evidence still attached

Computer vision aided flood risk planning

Turning imagery into inputs a model can actually use

Where this matters

The places with the least data are the places with the most flooding.

A well-instrumented coastline gets a well-constrained model. Most of the world has neither. We build workflows that start from what is globally available — reanalysis forcing, global bathymetry, satellite-derived terrain — and are honest about the uncertainty that comes with it.

The alternative is not a better model. It is no warning at all.

How we work

Tell us what the water is doing.

Scoping conversations are free and usually short. Bring the problem, not a specification — the specification is part of the work.

Start a conversation Browse services