By Chris Erasmus, Country General Manager, AWS United Arab Emirates & RoMENA 

For years, Earth observation workflows required building specialized models for every task — a labor-intensive process that presented significant scaling challenges. Transformer-based vision models are rewriting the rules of planetary monitoring.

Geospatial foundation models (GeoFMs) — including Clay, Prithvi-100M, SatMAE, AlphaEarth, OlmoEarth and SatVision-Base — transform this paradigm through self-supervised learning, pre-training on massive unlabeled datasets to master the fundamental patterns, textures, and spatial relationships embedded in geospatial data. The result? Models that understand what “Earth” looks like can be fine-tuned for specific applications using a fraction of the data and time previously required.

Amazon Web Services (AWS) provides the specialized infrastructure necessary to handle the unique demands of GeoFMs. These transformer-based vision models offer a new way to map the earth’s surface at continental scale.

The Shift to Foundation Models

Historically, analyzing satellite imagery required supervised learning, where experts manually labeled thousands of images to teach a model to identify specific features. This approach is often brittle, as models trained on one geographic area frequently fail when applied to another.

GeoFMs leverage masked autoencoders (MAE) to pre-train on unlabeled geospatial data sampled globally. This self-supervised approach ensures diverse ecosystems and surface types are represented, creating general-purpose models that understand Earth’s fundamental patterns without requiring extensive labeled datasets for every new application.

Scaling Earth Observation with AWS

AWS is designed to provide specialized infrastructure to handle the unique demands of GeoFMs, which involve massive file sizes and complex coordinate systems. Data at Scale: Through the Registry of Open Data on AWS, users access petabytes of imagery (like Sentinel-2) without moving it. This “data-gravity” approach minimizes latency and egress costs. Purpose-Built Tooling: Amazon SageMaker offers integrated environments to build, train, and deploy these models. SageMaker AI Pipelines supports the automated “chipping” of raw imagery into manageable 256×256 pixel segments for analysis. Compute Power: Training GeoFMs requires intense GPU resources. AWS GPU instances are designed to provide distributed computing capabilities to process global-scale datasets efficiently.

Core Use Cases for Planetary Intelligence

The integration of GeoFMs on AWS supports three core capabilities:

• Geospatial Similarity Search: GeoFMs convert imagery into high-dimensional vector embeddings. This allows for “image-to-image” searching where a user can select a reference area—such as a specific crop type or an area of urban sprawl—and instantly find similar patterns across vast territories.
• Embedding-Based Change Detection: By analyzing a time series of embeddings for a specific region, analysts can pinpoint exactly when and where surface disruptions occur, such as identifying early signs of forest degradation before they expand into large-scale clearing.
• Custom Machine Learning: Organizations can fine-tune a lightweight “head” on top of the GeoFMs. This allows for high-accuracy tasks like semantic segmentation (classifying every pixel in an image) with significantly less training data than traditional models.

Real-World Impact

The practical application of these models is already driving innovation. In the Amazon rainforest, researchers are using the Clay foundation model on AWS to detect subtle signatures of selective logging and new access roads. This early detection allows environmental protection agencies to deploy resources precisely to prevent major forest loss.

The solution is highly adaptable; while current examples focus on the Amazon, the same pipeline architecture works seamlessly with various satellite providers and resolutions to address challenges across industries like agriculture, insurance, energy and utilities, disaster response, and urban planning.

The Future of Earth Observation

While geospatial data pipelines remain essential, GeoFMs on AWS dramatically reduce the burden through shorter training cycles with fine-tuning or zero-training approaches like embedding-based similarity search. This enables organizations to focus on solving pressing environmental and economic challenges. The technology is ready. The question now is how quickly organizations will adopt these tools to address these challenges that demand immediate action.

Dr Fadi Alhaddadin, Director of MSc Information Technology (Business), School of Mathematical and Computer Sciences, Heriot-Watt University Dubai

Urbanisation is accelerating at an unprecedented pace, placing immense pressure on cities to become more efficient, sustainable, and resilient. Today, urban areas account for most of the global energy consumption and greenhouse gas emissions, making them central to addressing climate and resource challenges. In response, cities around the world are transitioning from traditional infrastructure systems to advanced, technology-driven models. The evolution from smart grids to fully integrated smart cities marks a new phase of urban innovation.

At the core of this transformation lies the smart grid. Unlike standard energy systems, smart grids use digital communication technologies to enable real-time interaction between energy providers and consumers. This two-way communication allows for more efficient electricity distribution, improved demand management, and the seamless integration of renewable energy sources such as solar and wind. As a result, smart grids not only reduce energy waste but also enhance reliability and support decentralised energy systems. They form the foundational layer upon which broader smart city systems are built.

However, the true power of smart cities emerges from the convergence of multiple technologies. The Internet of Things (IoT), artificial intelligence (AI), and big data analytics work together to create highly interconnected urban environments. IoT devices ranging, from sensors and smart meters to connected infrastructure continuously collect data on various aspects of city life, including energy usage, traffic flow, air quality, and public services. This data is then analysed by AI systems, which generate insights and enable real-time decision-making.

Through AI-driven analytics, cities can predict energy demand, optimise transportation networks, and detect infrastructure issues before they escalate. For example, intelligent traffic management systems can reduce congestion and emissions by dynamically adjusting traffic signals based on real-time conditions. Similarly, predictive maintenance systems can identify potential failures in utilities or transportation networks, minimising disruptions and reducing operational costs.

One of the most significant benefits of smart city technologies is their contribution to sustainability. Energy-efficient buildings equipped with smart systems can automatically regulate lighting, heating, and cooling based on occupancy and environmental conditions. Smart transportation solutions, including connected public transit and electric mobility systems, help reduce carbon emissions and improve urban mobility. Furthermore, integrated resource management systems enable cities to optimise the use of energy, water, and other essential services, supporting a more sustainable urban ecosystem. A notable example in the Middle East is Masdar City, which has been designed as a sustainable urban development powered by renewable energy and smart technologies. The city integrates energy-efficient buildings, smart grids, and intelligent transportation systems, demonstrating how digital innovation can support low-carbon urban living.

The Middle East is increasingly positioning itself as a global leader in smart city development through ambitious national strategies and large-scale projects. In Dubai, smart city initiatives focus on digital governance, artificial intelligence, and integrated urban services to enhance efficiency and citizen experience. Similarly, Saudi Arabia’s NEOM project represents a transformative vision of a fully automated and sustainable urban environment powered by advanced technologies. These initiatives highlight the region’s commitment to leveraging innovation to address urban challenges and drive future economic growth.

Beyond environmental benefits, smart cities are designed to enhance the quality of life for their residents. Digital platforms enable more accessible and efficient public services, from healthcare to administrative processes. Smart health systems can improve patient care through remote monitoring and data-driven diagnostics, while intelligent safety systems enhance security through real-time surveillance and rapid emergency response. These advancements contribute to more convenient, inclusive, and liveable urban environments.

Resilience is another critical dimension of smart cities. As urban areas face increasing risks from climate change, natural disasters, and infrastructure strain, the ability to adapt and respond effectively becomes essential. Smart grids play a key role in enhancing energy resilience by supporting decentralised power generation and rapid recovery from outages. Meanwhile, data-driven systems allow city authorities to anticipate and prepare for potential disruptions, improving overall crisis management and response capabilities.

Despite their many advantages, the development of smart cities is not without challenges. The integration of interconnected systems raises concerns about cybersecurity and data privacy, as large volumes of sensitive information are collected and processed. Additionally, the high cost of implementing advanced infrastructure and the need for standardised systems can pose significant barriers. Addressing these issues requires strong governance, clear regulatory frameworks, and collaboration between governments, private sector stakeholders, and technology providers.

In conclusion, the transition from smart grids to smart cities represents a fundamental shift in how urban environments are designed and managed. By leveraging the combined capabilities of IoT, AI, and data-driven infrastructure, cities are becoming more efficient, sustainable, and resilient. This transformation is not only redefining urban systems but also shaping the future of how people live, work, and interact within cities. As this evolution continues, smart cities will play a crucial role in addressing global challenges and improving the overall quality of urban life.

By Alfred Manasseh, Co-Founder and COO of Shaffra

For much of the past two years, AI has been discussed mainly in terms of pilots, productivity, and experimentation. But in moments of uncertainty, the conversation changes. This is when AI needs to move beyond pilots and into execution. When pressure rises, what matters most is speed, consistency, and coordination. The real question is whether institutions have the operational capacity to respond clearly, maintain continuity, and support decision-making under pressure.

In the UAE, that question carries particular weight because resilience, proactiveness, and digital by design have already been established as national priorities. This is no longer a futuristic idea. It is already being implemented across institutions.

This is why the conversation is moving beyond AI as a surface-level capability and closer to the operating core of institutions. In 2024, UAE federal government entities processed 173.7 million digital transactions and delivered 1,419 digital services, with user satisfaction reaching 91%. Once millions of people are interacting with digital systems, resilience depends not only on keeping platforms online, but on making sure information flows remain clear, response times hold steady, and service quality stays consistent under pressure.

Filtering signal from noise

In high-pressure environments, the first challenge is information overload. Fake information, true information, public questions, updates, and warnings all arrive at once, and institutions have to respond without adding confusion. Human teams remain essential because judgment and accountability must stay with people. But people alone cannot process that volume of information at the speed now required.

This is where Autonomous AI Teams become operationally valuable. AI is effective at dealing with large amounts of data, identifying patterns, and helping institutions filter signal from noise. Used properly, that gives leadership a stronger basis for communicating clearly, responding faster, and addressing confusion before it spreads.

Why governed systems hold up

Good governance is what makes AI dependable in sensitive moments. It is not only about speed. It is about consistency in messaging, consistency in how citizens and residents are served, and making sure people are well-informed. In uncertain situations, the public does not only need information. It needs information that is clear, timely, and trusted. Governed AI helps institutions provide that support without losing control or passing ambiguous situations with false confidence.

This is particularly relevant as research has found that six in 10 UAE employees use AI in their daily jobs, while IBM reported that 65% of MENA CEOs are accelerating generative AI adoption, above the global average of 61%.

The UAE can lead this shift because it is building around digital capacity at every layer, from infrastructure to service delivery to workforce readiness. The Digital Economy Strategy aims to raise the digital economy’s contribution significantly by 2031, while broader trade guidance has also framed the ambition as growing from 12% of non-oil GDP to 20% by 2030.

Working model in practice

This is also where Shaffra offers a practical example of how the model is changing. Through its AI Workforce Platform, Shaffra’s Autonomous AI Teams are already saving more than two million manual work hours per month and reducing operational costs by up to 80%. These systems can monitor inbound activity, classify issues, support fraud reviews, prepare draft responses for approval, and help institutions listen at scale to recurring public concerns.

In Shaffra deployments more broadly, this model has also delivered significant time and cost efficiencies across enterprise operations.

That does not replace leadership or human judgment. AI and humans play different roles, and the real value comes when they work together. It gives institutions stronger operational support, with greater speed, consistency, and control when pressure is highest. In the years ahead, the strongest organisations will be the ones that move beyond AI as a productivity tool and build it as a governed resilience layer that stays reliable when uncertainty tests every process around them.