Engines
Engines, platforms and models that twins are built with.
The third layer of the stack: the simulations and platforms that move a place forward in time, shelved by the task a person is trying to do. Each entry says who makes it, what it is used for, how it runs and what is open. The data they eat is on the Data shelf, the things they reason about on Ontologies, and the viewers that show their results on Presentation.
3D cities and mapping
Hosted web tool from Bmap that turns a drawn bounding box anywhere on Earth into a low-poly 3D model of that place, with terrain, buildings, roads, coastline and trees from open geographic data, viewable in the browser and exportable as GLB.
Cities & places closed sourceopen data
Esri's commercial geographic information system; creates, manages, analyses, maps and shares spatial data, and is the geographic base of many city and infrastructure twin projects.
Cities & places closed source
Research model from Seoul National University that generates a town-scale 3D scene from a single image, built on Microsoft's TRELLIS; code released with a CVPR 2026 paper.
Cities & places open source
Open-source streaming 3D reconstruction model from the Robbyant team at Ant Group; turns a video or image sequence into camera poses, depth and point clouds in one feed-forward pass.
Sensory landscape open source
Hosted mapping and visual positioning service from MultiSet AI that turns one drone flight over a site into a localisation map which drones, phones, headsets and robots then query for their position.
Sensory landscapeCities & places closed sourceAPI
Catalogue from Niantic Spatial of 100 real-world environments captured as simulation-ready USDZ scenes, for training and testing robot policies in Isaac Sim and other OpenUSD simulators.
Sensory landscapeCities & places partly open data
NVIDIA's family of world foundation models and tools for physical AI; generates and reasons over video of the physical world for robot training, simulation and synthetic sensor data.
Sensory landscape open sourceAPI
NVIDIA's open-source robotics simulator built on Omniverse and OpenUSD; used to train, test and validate robots in physically based virtual environments and to generate synthetic training data.
Sensory landscape open source
World model from Odyssey that generates an interactive 3D environment from a prompt and predicts how it changes as a person or agent moves and acts in it.
Sensory landscapeMovement & logistics closed source
Universal Scene Description, the open 3D scene format and software platform created by Pixar and now stewarded by the Alliance for OpenUSD; the scene layer under NVIDIA Omniverse and many simulation pipelines.
Sensory landscape open source
Real-time underwater SLAM from the University of Michigan field robotics group that fuses learned stereo depth with IMU, pressure and Doppler velocity log measurements; developed and tested on shipwreck surveys.
WaterSensory landscape partly open sourceopen data
Feed-forward 3D vision model from Meta AI and Oxford's Visual Geometry Group that predicts camera poses, depth and point clouds from video; used as a reconstruction backend in DeepReefMap for coral reef mapping.
Sensory landscape partly open source
-
VU.CITY Limited supplies 3D city models and planning tools for the built environment in UK and Irish cities and New York; CLARA Technologies simulates wind, air quality and temperature street by street from a 3D city model, live in Brussels.
Cities & places closed sourcepartly open dataAPI
World Labs' Atlas is a world model that generates, reconstructs and simulates 3D scenes from text, images and video, in early access with selected partners since September 2026.
Cities & places closed source
Agents and system dynamics
AnyLogic's simulation software combines agent-based, discrete-event and system-dynamics modelling in one model, with libraries for road traffic, pedestrians and rail and the option to place models on GIS maps.
People & society closed sourceAPI
Open-source environment for building and running spatially explicit agent-based simulations; used for urban mobility, evacuation, epidemics, climate adaptation and planning.
People & society open sourceopen participation
-
Open-source multi-agent simulation from the MiroFish team, incubated by Shanda Group; builds a population of LLM agents from a seed document such as a news report or policy draft, runs them against each other and writes a report on how the event could unfold.
People & society open sourceopen participation
-
Steve Coy's simulation platform for decision-making: composable causal models of a system, run faster than real time to predict the consequences of possible courses of action and pick among them.
People & society closed sourcepartly open participation
Earth observation and AI
-
Geospatial foundation models from Google DeepMind (AlphaEarth Foundations, released as an embeddings dataset in Google Earth Engine) and from NASA with IBM (Prithvi Geospatial, open source on Hugging Face), for mapping and land-change tasks.
Cities & placesLiving systems partly open sourcepartly open data
Earth Genome's hosted search tool for satellite imagery; a user labels a few known sites and it finds similar places anywhere on Earth, for detecting mines, cattle facilities, airstrips and other land change.
Food & land closed source
Experimental Gemini-based agent from Google Research that plans a multi-step spatial analysis, calls Earth AI models and geospatial data sources, and returns the result with its plan and sources shown.
Cities & placesPeople & societyWeather & climateEnergy closed sourceAPI
-
Google's family of geospatial AI models and agents, covering satellite imagery, weather, floods and population, reached through Google Earth, Earth Engine, BigQuery, Maps Platform and Google Cloud.
Cities & placesPeople & societyWeather & climateWaterEnergy partly open sourcepartly open dataAPI
Part of Google Earth AI; given a user's local outcome data such as disease rates or crop yields, it picks relevant population and satellite signals and trains models for spatial prediction, downscaling and forecasting.
People & societyFood & land closed sourceAPI
-
Google Research geospatial foundation model that turns aggregated search trends, place busyness, maps, weather and air quality into an embedding vector per postal code or county, for predicting local health, economic and environmental indicators.
People & societyCities & places partly open sourcepartly open data
The Amazon Conservation Team and the AARIMO network use Vantor satellite imagery to find and track illegal gold-mining dredges along the Puré River in the Colombian Amazon and pass the findings to enforcement agencies.
Living systemsPeople & society closed source
Ecosystems and land
Open platform from the GeoSense group at the University of Freiburg, with GFZ and partner institutes, where researchers upload laser scans of forests, have them processed into segmented trees, inspect them in the browser and download them.
Living systems partly open dataopen participation
-
Open-source program that borrows algorithms from electronic circuit theory to predict how animals, plants and genes move across a landscape, treating every possible path at once; written in Julia.
Living systems open sourceopen participation
-
DSSAT (Decision Support System for Agrotechnology Transfer) simulates crop growth, development and yield from daily weather, soil and management data, with models for over 45 crops; free to download.
Molecular atlas that links microbial genes and transcripts from wetland and coastal sediments to field measurements of methane, nitrous oxide and sulfur, as evidence for blue-carbon projects; contacts are at Ecosphere Blue, whose MethaNet product is built on it.
Living systemsWaterWeather & climate partly open data
-
Global Change Analysis Model from the Joint Global Change Research Institute; links energy, water, agriculture and land, the economy and climate in long-run global scenarios.
Food & land open sourceopen participation
Open-source suite of ecosystem-service models from the Natural Capital Alliance at Stanford; maps and values what nature provides in terrestrial, freshwater, marine, coastal and urban settings.
Food & land open sourceopen dataopen participation
-
Ecosphere Blue's planned assessment service for blue-carbon projects, rating project performance with methane-risk projections drawn from microbial genomic evidence in mangrove sediment.
Mycosoft's hosted 3D globe inside its NatureOS platform; it shows environmental layers, the positions of the company's field sensors, historical playback and forecast context, drawing on its MINDEX database of species and observation records.
Pilot by The Nature Conservancy Argentina and the startup ReForest Latam that seeds native trees from drones on degraded farmland in Argentina's Gran Chaco.
Energy and utilities
-
PyPSA is an open-source Python framework from TU Berlin for optimising power and energy systems; PyPSA-Eur is the open model of the European energy system built on it, covering electricity, transport, heating and industry.
Energy open sourceopen dataopen participation
Infrastructure and assets
-
Cloud services from Microsoft (Azure Digital Twins) and Amazon (AWS IoT TwinMaker) for describing the entities and relationships in a place and connecting them to live device data.
Cities & places closed sourceAPI
Bentley Systems' iTwin Platform and its open-source iTwin.js library combine engineering, reality, GIS and IoT data into infrastructure digital twins that developers build applications on.
Cities & places partly open sourceAPI
Land use and housing
Urbanly's CityCompass simulates the households, firms and developers of a region on its real parcels, month by month in a browser, to compare housing, zoning and transport scenarios.
Cities & places closed source
-
UrbanSim is a microsimulation land-use model from UrbanSim Inc., grown out of research led by Paul Waddell, that forecasts real-estate development, prices and household and firm location for regional transport planning.
Cities & places partly open source
Participation and learning
-
Open-source Android app from the non-profit Awana Digital for territory monitoring and mapping, co-designed with Indigenous communities; teams record observations on a map and share them peer to peer.
People & societyCities & places open sourcepartly open participation
-
Climate Interactive's global climate simulator, built with MIT Sloan and Ventana Systems; shows how choices in energy, land use and policy change emissions and temperature to 2100.
-
Geodesignhub's hosted map-based negotiation platform; groups sketch spatial proposals, bundle them into alternatives and trade them off in facilitated sessions until they agree a plan.
People & society closed sourceAPI
Research infrastructure
DAFNI is a UK computing platform for national-infrastructure research; SPARC and the CICI Lab at Arizona State University, led by Wenwen Li, do GeoAI and cyberinfrastructure research for environmental and disaster applications.
Cities & places partly open datapartly open participation
-
Two ways to connect separate simulators into one run; HELICS is an open-source co-simulation framework from US national laboratories, and FMI is the Modelica Association's standard for packaging and exchanging dynamic models.
Energy open source
Sensory landscape
-
Commercial software from DataKustik GmbH in Germany that calculates, maps and assesses environmental noise from roads, railways, industry and aircraft, from a single site to a whole city.
Sensory landscape closed source
The Graz Lagrangian Model from Graz University of Technology; simulates the dispersion of pollutants and odour in built-up areas and complex terrain, including low-wind conditions and road tunnel portals.
-
Open-source lighting simulation from Lawrence Berkeley National Laboratory; uses ray tracing to predict light levels and the appearance of a space before it is built, for daylight and electric light.
Sensory landscapeEnergy open sourcepartly open participation
A hosted service that rates the walkability of any address from 0 to 100 from the walking distance to nearby amenities and from street measures; its companions Transit Score and Bike Score rate public transport and cycling. Scores are served through a widget and an API.
Movement & logisticsPeople & society closed sourceclosed dataAPIpartly open participation
Transport and crowds
Aimsun's real-time traffic management twin, Aimsun Live, uses live and historical data to simulate a road network and forecast conditions; the same company makes the Aimsun Next transport simulation software.
Movement & logistics closed sourceclosed data
Open-source microscopic traffic simulator, an Eclipse Foundation project; models road vehicles, public transport, bicycles and pedestrians one by one on large networks.
Movement & logistics open sourceAPI
Open-source framework for large-scale agent-based transport simulation, maintained by its contributors and the MATSim Association; simulates every traveller's day on a road and public-transport network.
Movement & logistics open sourceopen participation
Replica supplies modelled travel activity for US regions and a Scenario service that re-runs its mobility model under changed population, employment or road-closure inputs for transport and regional planning.
Movement & logistics closed sourceclosed data
Water and flooding
-
-
Feature of Deltares' Delft-FEWS forecasting platform, from version 2026.02, that pulls Google Flood Hub river forecasts and flood status through Google's Flood Forecasting API so forecasters can compare them with their own models and observations.
Deltares' Delft3D FM Suite models water flow, transport of matter and morphology in coastal, estuarine and river environments.
-
Free public site from Google Research with riverine flood forecasts, flood maps and water trends for river basins in over 150 countries, updated daily; the same forecasts reach Search, Maps and Android and can be pulled by API.
WaterWeather & climate partly open sourceopen dataAPI
-
Google Research's open-source hydrology framework, a Python package that replicates the LSTM river-flow models behind Flood Hub so forecasters can train or fine-tune them on their own watersheds.
Water open source
Weather and climate
-
Knowledge graph of urban climate adaptation plans from the Urban Tech Hub at Cornell Tech; AI agents read city plans and extract actions, hazards, outcomes and costs, each traced to its source sentence.
Cities & placesWeather & climatePeople & society partly open sourcepartly open dataAPI
ECMWF's machine-learning global weather model, run operationally beside its physics-based system since 2025; weights published openly.
Weather & climate open source
Microsoft Research foundation model for the Earth system, fine-tuned for global weather, air pollution and ocean-wave forecasting; code and weights open under MIT.
Weather & climate open source
-
Open-source Python library by James Adams that computes drought, fire and flood-potential indices such as SPI, SPEI, the Palmer family and KBDI from station or gridded precipitation and temperature.
Weather & climateWaterFire open source
World Resources Institute's web tool that maps heat hazard, exposure and cooling opportunity in a city and estimates how much street trees, cool roofs or shade structures would lower air temperature and thermal stress, at neighbourhood and city scale.
Weather & climateCities & places open sourceopen dataAPI
The European Commission's Destination Earth builds digital twins of the Earth system, implemented by ECMWF with ESA and EUMETSAT, for climate change adaptation and weather-induced extremes.
Tropocen's browser-based GIS for urban heat adaptation, with a 3D model of a city district, PALM-4U microclimate simulation and a planning editor for comparing cooling measures.
Cities & placesWeather & climate closed source
-
AI weather model from Schmitt, Jain and co-authors that retrains ECMWF's AIFS on satellite precipitation observations to forecast rain more accurately at the local scale.
-
Two AI weather-forecasting stacks: Google DeepMind's WeatherNext 3, a hosted global model that forecasts hourly and feeds Google products and cloud datasets, and NVIDIA's Earth-2, a family of open models and tools that organisations run on their own GPUs.
Weather & climate partly open sourceopen dataAPI
Wildfire and risk
Two commercial climate-risk platforms: Climate X's Spectra turns physical climate hazards into asset-level financial loss figures worldwide; UrbanFootprint's Resilience Insights combine hazard, community and land-use data for any location in the United States.
Fire closed sourceclosed dataAPI
Wildfire risk platform from Opal AI Inc. of Marina del Rey, California, that combines imagery, lidar, GIS, weather and field data into risk rankings and mitigation recommendations for utilities, fire agencies and insurers.
Fire closed source
EarthDaily's wildfire risk model, which combines satellite observations, daily weather and other geospatial data into ignition likelihood, fuel hazard and directional vulnerability layers, sold to insurers in the western United States.
Fire closed sourceclosed data
-
Technosylva makes wildfire and extreme-weather risk software for electric utilities and fire agencies, modelling fire behaviour against weather, fuels, terrain and assets.
Fire closed source
Wildlife and oceans
-
Open single-class fish detector built by Filippo Varini and a group of contributors, trained on seventeen open datasets pooled into one; finds fish in underwater images and video from any camera or habitat.
Living systemsWater open sourceopen dataopen participation
Open-source pipeline from EPFL's ECEO lab that turns handheld underwater video of coral reefs into labelled 3D point clouds, orthomosaics and benthic cover statistics.
Living systemsWater open source
-
Project hosted at the Woods Hole Oceanographic Institution to build digital twins of coral reefs, so that the people who manage, conserve and restore reefs can explore a reef in 3D over time and test management options; a low-fidelity prototype exists.
-
Open object detector from the ConservationDronesAI group, built on RF-DETR, that finds people, mammals and vehicles in drone imagery for wildlife surveys and counts.
Living systemsSensory landscape open source
-
Prototype web app by Hannah Nisonson of Esri's Applications Prototype Lab that links a 3D map of species observations in the San Bernardino National Forest with a 3D food-web graph, and shows what else is affected when a species is removed.
Open-source family of wildlife detection models and tools from Microsoft's AI for Good Lab; MegaDetector finds animals, people and vehicles in camera-trap images, and PyTorch-Wildlife is the framework that runs it and its siblings for aerial and acoustic data.
Living systemsSensory landscape open sourcepartly open data
-
Open-source detector from the Microsoft AI for Good Lab that finds wildlife in aerial and drone survey imagery; ships the OWL model family and extends MegaDetector from camera traps to overhead views.
Living systems open sourcepartly open data
Open-source, solar-powered edge device from Microsoft's AI for Good Lab that runs camera-trap and bioacoustic AI models on site and sends the results out by satellite or GSM, for biodiversity monitoring in remote places.
Living systems open source
-
Caribbean project testing whether dense restored stands of elkhorn coral reduce wave energy and sediment movement along coasts, with sites in Jamaica, Barbados and Antigua & Barbuda; funded by the Caribbean Biodiversity Fund.
-
Wildflow's platform for coral reefs, where divers upload footage and get georeferenced 3D models, orthomosaics and bathymetry for tracking a reef over time, with the stated aim of a digital twin of any reef.
Living systems open sourcepartly open data
-
Robotic surface vehicle from Woods Hole Oceanographic Institution, built by Peter Traykovski and adapted for Anne Cohen's reef work, that photographs shallow coral reefs along GPS-tagged tracks so the same colonies can be checked again after each heat wave.