Accelerating the shift towards a sustainable economy using HPC on AWS

Accelerating the shift towards a sustainable economy using HPC on AWSThe transition to a sustainable economy is a major goal of many organizations today. To accomplish this goal, organizations are turning to High Performance Computing (HPC) on Amazon Web Services (AWS). HPC on AWS has enabled a wide range of sustainability initiatives, from clean energy solutions and new materials design, to increased efficiency in manufacturing and operations.

With the help of HPC on AWS, organizations can leverage the power of cloud computing to achieve their sustainability goals and create a positive impact on the lives of humans, other species, and the environment.

In this blog post, we’ll explore how HPC on AWS is enabling the shift towards a sustainable future.

The shift towards a sustainable future

The world is waking up to the risks of climate change. Because of that, the European Commission has put sustainability reporting on an equal footing with financial reporting, meaning that it will require companies to report on their environmental, social, and governance (ESG) practices. This effort can lead to higher reporting costs but also to new opportunities.

The value of new market opportunities driven by the transition away from a carbon-intensive economy is projected by the UN to reach €10T per year by 2030, and the EU is promising €1B in annual funding to help develop the reporting infrastructure needed to take advantage of these opportunities. Furthermore, the Commission’s Sustainable Corporate Reporting Directive (CSRD) allows companies other than the usual auditors to meet due diligence requirements for reported sustainability data, making it easier to comply with the new regulations.

Simulation in Service of Sustainability

Companies can use HPC on AWS to tackle massive datasets quickly and efficiently while remaining compliant. In this context, simulation has become an essential tool across industries to reduce their environmental impact and move towards a more sustainable economy. Businesses can harness the power of simulation to make informed decisions that support the environment and meet their sustainability goals.

The energy sector is using simulations to reduce greenhouse gas emissions and find more efficient green energy solutions. Automakers use HPC and digital twins to develop lighter electric vehicles and improve aerodynamics. And aerospace companies use advanced manufacturing techniques to develop new propulsion and fuel storage solutions.

MHP (a Porsche Company) and AWS are working together to develop a digital twin solution that use the connectivity of modern vehicles to enable entirely new business models. This solution brings the capabilities of digital twins to a new level and allows dynamic monitoring, analytics, and optimizations of the corresponding physical entity.

High-tech is coming up with eco-friendly electronics and advanced devices to take apart e-waste. With the industrial internet of things, even heavy industry is saving energy, reducing pollution, and optimizing operations through digital workflows.

Customers from virtually every industry can also design and test new materials faster, discover new opportunities for circularity, and ultimately move closer to achieving a clean environment. The search for an affordable, scalable, and zero-waste solution for PFAS pollution, for example, is an ongoing effort across the globe. In this context, quantum chemistry opens the door for studying this and many other challenging problems. However, the computational complexity of highly accurate quantum chemistry has always been a prohibitive factor for its application to real-world problems.

The introduction of new algorithms, like iFCI, and new cloud-based HPC technology enables affordable and accurate calculations for many computational chemistry problems. In fact, Good Chemistry, AWS, Accenture, and Intel joined forces to massively scale-up the QEMIST Cloud to run on Spot compute instances with more than a million CPU cores. This approach successfully calculated the C–F bond breaking energy in three PFAS molecules, TFA, PFBA, and PFOA.

HPC on AWS gives customers the computing power they need to run complex models, experiment with different inputs, and optimize systems in near real-time, allowing customers to simulate at scale, which helps them make better decisions in less time, resulting in increased efficiencies and cost savings that are necessary for sustainability initiatives.

How AWS High-Performance Computing can help?

With HPC services like AWS ParallelCluster and AWS Batch, businesses can accelerate their sustainability workloads and make use of huge datasets while maintaining compliance standards. This accelerates their ability to adhere to ESG (Environmental, Social and Governance) disclosure requirements, allowing them to easily find cost savings and remain competitive in a green economy. HPC enables faster time-to-market for ESG initiatives as well as improved scalability compared to traditional architectures – plus costs remain low since you pay only for what you use. In addition, this type of cloud-based solution is resilient enough to handle high demand scenarios when there are spikes in ESG data needs, such as the end of a quarter or year.

Examples of ESG Workloads

With HPC on AWS, customers can use simulation to reduce their carbon footprint. By using predictive insights from simulation and digital twins, customers can determine the best materials for their products, optimize processes and product lifecycles, and more.

Weather prediction and climate change

Weather prediction and climate change is critical to timely and more precise forecast and better understand climate change resiliency and adaptation. With HPC services and the power of the AWS Cloud, companies and countries are now able to leverage advanced analytics to understand climate change and develop better strategies for adapting to it. HPC services can provide timely and more precise weather forecasting and improved insights into potential impacts on operations. This data can be used to create early warning systems, design flood prevention for buildings’ architectures, and optimize scheduling for industries like transportation and logistics, insurance, agriculture, and energy.

Climate change is one of the most pressing issues that ESG policies need to address. In the past decade, the amount of data collected by Earth-observation satellites has been growing exponentially, making spatiotemporal data an invaluable asset for weather and climate forecasting. Spatiotemporal earth observation data includes a wide range of metrics like precipitation and surface temperature, land cover, sea surface temperature, ocean currents, and more. We can use this data can to detect regional trends in climate change, analyze the impact of human activities on the environment, and help predict future changes in weather and climate patterns. Moreover, by combining multiple datasets from various sources such as remote sensing imagery, meteorological networks, and ground-based observations, scientists can gain a comprehensive understanding of our planet’s climate system. This information can then be used to develop more accurate models for predicting future conditions and help mitigate the effects of climate change.

HPC-powered algorithms can also help identify alternative shipping routes that can reduce emissions and fuel consumption, thus contributing to a cleaner environment.

Energy and utilities

The energy sector is increasingly using HPC simulations to reduce greenhouse gas emissions and to find more efficient green energy solutions. One of the most prominent examples of this is the use of Amazon Elastic Compute Cloud (Amazon EC2) for running CFD simulations by Baker Hughes, an energy technology company. The solution went live in the fourth quarter of 2021 and is in use by 150 engineers in Italy, India, and the United States. Yogesh Kulkarni, senior director, and CTO India at Baker Hughes, commented that:

We were initially planning to migrate the equivalent compute capacity of 100 teraflops to AWS, but by giving engineers the possibility to scale, the consumption spiked by four times within 3 months of go-live“.

Amazon EC2 provides dedicated throughput of hundreds of gigabits per second per HPC job, making it a great platform for running complex simulations. Additionally, Amazon EC2 fleets of instances can be deployed in placement groups to improve performance and reduce network latency. Furthermore, AWS allows organizations to avoid the issue of hardware lock-in that is inherent to an on-premises HPC solution.

Kulkarni also said:

We now have the ability to use the best price-performance compute instances and continually onboard the latest generation processors as soon as they are available“.

Using HPC simulations on AWS can help energy companies minimize their Carbon Footprint and reduce their reliance on non-renewable energy sources. Companies like Baker Hughes demonstrate that investing in HPC simulations can significantly contribute to reducing emissions and creating a more sustainable future.

Energy and Utilities can also leverage real-time wind and solar maps for energy optimization and improved photovoltaic efficiency. HPC is playing an important role in component design of wind/tidal turbines, photovoltaic cells, heat pumps, etc. with computational fluid dynamics (CFD).

An example is GE Renewable Energy. GE engineers have built virtual versions of its wind turbines that gather data and insights from their physical counterparts. These “digital twins” consider a variety of scenarios, such as what would happen to power production from the physical turbine if the wind blew harder, longer, or not at all. This information helps engineers in the field operate the actual turbines more efficiently. HPC can also be used to identify carbon storage and sequestration sites using seismic technologies.

Drug development

Drug development can benefit from accelerated drug discovery, and with the use of digital twins, healthcare can become personalized. The cloud has enabled researchers to easily access vast amounts of data and tools to rapidly discover, develop, and deploy new drugs. HPC enables researchers to run complex simulations to study the behavior of molecules and create better materials design for drug development.

Using advanced manufacturing and digital twins, HPC allows for more efficient production of new drugs, leading to a reduction in waste and the development of more sustainable manufacturing processes and product packaging. This helps reduce the environmental impact of drug production and supports a clean environment.

AWS Cloud provides the necessary tools and resources needed to quickly develop highly effective drugs, allowing for shorter drug discovery times with improved efficacy. It also makes it possible to collect large-scale genomic data that we can use to gain insight into the genetic basis of diseases, helping to create more effective treatments.

OpenEye Scientific, is a developer of drug discovery software headquartered in Santa Fe, New Mexico. OpenEye built Orion, a software-as-a-service (SaaS) computer-aided drug-design platform, on AWS. Using Orion, chemists at pharmaceutical firms can create, share, model, calculate, visualize, analyze, and organize chemical collections of different sizes and complexities. Orion uses AWS to give companies highly scalable, maintenance-free access to up to hundreds of thousands of processors. Major pharmaceutical companies are using Orion to perform cloud-native computational chemistry for drug research and development.

“Previously, our customers needed HPC clusters for their computational chemistry capabilities. Using Orion on AWS, all they need is a browser and they can get going on their research.”

Matthew Geballe – Vice President of Product, OpenEye Scientific Software


Advanced manufacturing techniques like digital twins, enabled by HPC on AWS Cloud, helps us create a virtual representation of physical objects, a digital twin, that accurately reflect the original object, allowing manufacturers to reduce or eliminate the need for physical testing, perform predictive and prescriptive maintenance, automation of product lifecycle management, and shortened downtime cycles. This has a net positive impact on the environment as well as the supportive systems powering prototyping and testing phases. For example, Siemens Energy increased the use of renewables on the grid, which is requiring power plants to adapt their operations from the way they were originally designed.

The change resulted in increased corrosion and fatigue failures in the Heat Recovery Steam Generator (HRSG) and increased inspection efforts during planned downtimes. AWS and Siemens Energy worked together to combine physics-based models with advanced probabilistic techniques to deploy a Living Digital Twin that runs on AWS Cloud and connects data-streams from power plants to update models for reliable predictions of HRSG pipe corrosion and failure, reducing planned downtime by 60%.

“Our customers are seeking to reduce the downtime of the Heat Recovery Steam Generator to improve the availability of their power plant operations. AWS is helping us innovate in developing and deploying an L4 Living Digital Twin at-scale using hybrid models for specific failure modes. It is anticipated our HRSG service offerings will reduce planned downtime by 60%.”

Stefan Lichtenberger, Senior Key Expert Cloud and Data Services, Siemens Energy

Molecular Modelling in Chemistry and Biology

Molecular modelling is a powerful tool in the effort to develop a sustainable economy. This type of modelling uses computational techniques to simulate and analyze the behavior of molecules, and plays an important role in several industries, including clean energy solutions, advanced manufacturing, and new materials design.

New materials are used by a wide range of industries, from automotive to medical and consumer products. The development of new materials is driven by the demand for higher performance, longer life cycles, reduced emissions, better energy efficiency, and cost savings.

HPC is an important tool used to help design and test these new materials. It makes it possible to quickly identify potential new materials and predict their performance based on their physical and chemical characteristics. This helps to ensure that the materials are optimally suited for their intended applications. Automotive manufacturers, for example, use HPC to create new composite materials that they use in lightweight components that reduce emissions while still providing high performance. Medical device manufacturers also rely on HPC simulations to develop new polymers and ceramics that have unique properties ideal for use in medical devices.

HPC on AWS Cloud can also help accelerate research related to molecular modelling in chemistry and biology (using applications like GROMACS, a popular open-source software package designed for simulations of proteins, lipids, and nucleic acids).

Using quantum chemistry simulations techniques, scientists can create virtual models to gain insight into how molecules behave, leading to new discoveries and more efficient products. For example, molecular modelling helps to design drought-resistant seeds and crops that require less water and fewer energy resources to grow. Additionally, HPC helps to simulate developments in green hydrogen and synthetic fuels for transportation, further reducing our reliance on fossil fuels.

Thanks to HPC on AWS, molecular modelling is becoming a key component of the shift towards a sustainable economy.


The automotive and aerospace industries have adopted HPC to enable their own shift towards a green economy. They use it to design, develop, and analyze components like electric vehicles, micro mobility, and other innovative transit models like Maglev trains, flying taxis, driverless cars, delivery drones, underground roads, hyperloops, and autonomous vehicles.

Wisk Aero is an aviation company focused on developing eVTOL aircraft and revolutionizing mobility through quiet, fast, and clean air travel. The company has over 10 years of experience, has locations around the world, and are backed by the Boeing Company and Kitty Hawk Corporation. To study the in-flight airflow, Wisk Aero engineers perform computational fluid dynamics (CFD) simulations using in-house and NASA CFD applications on AWS HPC Clusters. Wisk Aero focuses more on using CFD than traditional aircraft builders because CFD supports rapid design iteration as the team explores different aircraft designs and architectures, especially in the early phase of the design process.

Using HPC for CFD allows for an efficient analysis of the airflow over an object. This helps engineers to test for the most efficient designs possible prior to prototyping or manufacturing, which are expensive stages for companies and the environment. With AWS, companies in these industries can simulate their products, enabling them to achieve their sustainability goals while also reducing their cost and time-to-market. These simulations are extremely useful when it comes to materials design and optimizing energy efficiency for green energy solutions. As a result, HPC on AWS is allowing the automotive and aerospace industry to contribute to a cleaner environment and drive the shift towards a green economy.

Social Systems Simulations

HPC on AWS has also been used to enable “Social Simulations” via agent-based models. In this type of modelling, researchers model complex systems using agents as the primary components. Examples include urban planning, labor economics, traffic, crowds,3 and natural resource management. These simulations can help us better understand social phenomena and lead to more effective solutions in the long term.

Scientists and researchers can model increasingly complex scenarios with greater accuracy than ever before. it’s crucial for providing clean environments for future generations. For instance, simulations of urban development or energy consumption can help identify the best strategies for reducing pollution and reducing the impact of climate change. Similarly, simulations of natural resources can help identify the most efficient use of them without harming the environment.

Simudyne, a UK based start-up, has been working with AWS on simulation-driven climate policy using Agent Based Modeling on HPC clusters. The primary goal of many agent-based modelers is to create large-scale simulations that represent the behavior of complex social and economic systems. It has become increasingly popular over the past two decades, with researchers attempting to use it to provide insights into complex phenomena such as income inequality, the impact of climate events on the economy, or the tragedy of the commons.

Meeting global climate targets will heavily depend on the interactions between government, business, and households. These interactions are highly complex and adaptive and cannot be easily predicted easily through traditional methods of regression and polling. Agent-based models provide a principled way to develop realistic forecasts for complex adaptive systems under a range of different scenarios with the goal of exploring emergent features that result from the feedback between climate-driven policy interventions and economic changes.

Using AWS SimSpace Weaver, a new compute service to run real-time spatial simulations in the cloud and at scale, developers are no longer limited by the compute and memory of their hardware. Organizations can run simulations for situations that are rare, dangerous, or very expensive to test in the real world.

City managers can’t wait for a natural disaster to hit a city to test the response systems. Event planners don’t want to wait until a large sporting event to start to understand the impact the games will have on traffic. Scenarios like these must be simulated in a safe environment in which planners can test different situations and tune each system.


HPC on AWS is playing a critical role in enabling organizations to develop sustainability-focused solutions. Through cloud-based simulation and analysis capabilities, customers can reduce their carbon footprint and increase efficiency while helping to create a better future for all.

HPC on AWS is a powerful tool for enabling the shift towards a greener future. By leveraging innovative infrastructure and technologies, organizations can take advantage of increased performance and efficiency while helping to reduce their environmental impact, paving the way for a better and cleaner environment for generations to come.

Ilan Gleiser

Ilan Gleiser

Ilan Gleiser is a Principal Global Impact Computing Specialist at AWS focusing on Circular Economy, Responsible AI and ESG. He is an Expert Advisor of Digital Technologies for Circular Economy with United Nations. Prior to AWS, he led AI Enterprise Solutions at Wells Fargo. Ilan’s background is in Quant Finance. He spent 10 years as Head of Morgan Stanley’s Algorithmic Trading Division in San Francisco.

Maria Mackey

Maria Mackey

Maria Mackey has been with AWS for six years and is currently the EMEA Principal Segment Lead for those AWS partners involved with Sustainability in HPC. This role involves the growth of sustainable practices and offerings from ISVs and G/SIs across key vertical markets and technology domains. Prior to AWS she held various systems engineering roles at SGI, Sun Microsystems, Oracle, a liquid-cooling startup and was the EMEA Energy Lead for Cray.

Raymond Chow

Raymond Chow

Dr. Raymond Chow is the Global Technical Lead for HPC in the Partner Organization at Amazon Web Services. He has over 20 years of experience designing, deploying, and using HPC clusters and workloads. He spent the first half of his career as a research engineer designing utility scale wind turbines blades and aerodynamic technologies in academia and industry using high fidelity CFD. Since moving his own HPC workloads to the AWS 8 years ago, he has been helping other users, organizations, and partners migrate to cloud.

Srinivas Tadepalli

Srinivas Tadepalli

Srinivas is the global head of HPC go-to-market at AWS with responsibility for building a comprehensive GTM strategy for a variety of HPC and Accelerated computing workloads across both commercial and public sector customers. He previously worked at Dassault systems and has a PhD in biomedical engineering.