Breakthrough technology for a secure future
Synthetik Applied Technologies is an agile research and development company specializing in risk, security, and protection.
Synthetik creates breakthrough technology to mitigate significant threats to the world around us, including terrorism, extreme events, and global environmental impacts.
Providing insurers with better data and the right tools to address the challenge of global strikes, riots, and civil commotion
Through generation of realistic event footprints based on likely target points and a robust, granular property-level data pipeline, Synthetik’s srccQuantum provides dynamic, high-resolution insights into potential SRCC scenarios, empowering market participants to make informed decisions regardless of portfolio complexity.
Unlike traditional approaches that rely on concentric risk zones or simplified geographic overlays, srccQuantum evaluates the dynamic relationships between high-risk locations and the pathways that connect them, ensuring that underwriting and portfolio management decisions are aligned with actual exposure at location, individual property or portfolio scale.
Urban heat islands
A physics-informed deep learning framework for the generation of high-resolution urban temperature data
Overview:
Urban areas are home to 55% of the world’s population and use up to 76% of global energy according to the UN’s Department of Economic and Social Affairs. This is due in part to the significant energy consumption in heating and cooling occupied spaces. The combination of the urban phenomena, heat-island effect, and the increased reliance on critical infrastructure increases the vulnerability of these areas to climate change. Understanding urban heat islands is an important step in identifying areas most at risk and their required mitigation strategies.
01. Objective
Develop a software platform capable of calculating urban heat to better inform governmental agencies of areas most at risk from global rising temperatures
02. Process
Due to the complexity of the urban environment and the extent to which it drives environmental behavior, existing techniques used for modeling rural areas/natural terrain may not be effective. To generate high-resolution predictions of surface temperatures in urban spaces, Synthetik is developing and evaluating several physics-informed neural networks (PINNs) to harness deep learning while conforming to the governing physical equations.
Flood modeling
State-of-the-art flood modeling capability
Overview
Synthetik leveraged their physics-based modeling and simulation web-based platform to three discreet and critically important areas: improved characterization of flood hazard data, enhancing insured building stock information, and quantifying anticipated flood damage.
01. Objective
Develop a flood modeling capability to support the U.S. National Flood Insurance Program (NFIP), the Federal Emergency Management Agency (FEMA) and Department of Homeland Security.
02. Process
Synthetik developed and deployed physics-informed neural networks (PINNs) to enable accurate high-resolution analysis of historical, current, and predicted flood data. Synthetik then leveraged existing open source building stock data and geo-spatial information to train and deploy a machine learning algorithm to ascertain costs associated with flood-damaged buildings.
03. Results
Synthetik’s solution aids FEMA in quantifying flood impact with greater accuracy and has also been incorporated into CityScape – an insurance modeling platform originally designed for terrorism modeling but now also incorporates many environmental-based impact events.
Synthetik AI | Segmentastic
An automated AI-based platform for 3D object recognition, segmentation, annotation, and synthetic data generation
Segmentastic is an ‘on-the-fly’ machine-assisted annotation capability – as new unknown objects are scanned, identified, and classified, the system will ‘learn’ the new object, thus increasing system accuracy and reducing false positives over time.
A collaborative annotation platform for both 2D images and 3D scans, Segmentastic allows teams to jointly create bounding box and label annotations for objects in 2D and 3D media for use in later machine learning projects. Suitable for multiple applications, Segmentastic has already been deployed to the TSA (U.S. Transportation Security Administration) for scanning passenger baggage.
Custom solutions to fit your needs
Not seeing what you’re looking for? We create solutions for a variety of needs in insurance, global environment, energy, and defense & security. Reach out and we’ll be in touch.