The Earth Observation (EO) sector is rapidly evolving into Earth Action (EA), with onboard Artificial Intelligence (AI) processing emerging as a key enabler. This technology offers strategic advantages through 1) enabling autonomous and low-latency EO missions with adaptive data processing capabilities that overcome the limitations of ground-based post-processing in handling the vast data volumes produced by growing satellite constellations and 2) supporting the evolution toward AI-driven and distributed EO mission architectures. This review explores the key technological advancements, mission architectures, and emerging paradigms that are shaping the next-generation EO systems. Pioneering EO missions are presented to showcase current capabilities, while the commercial, technical, and operational implications are analyzed alongside key challenges and ongoing research efforts (January 2020 to March 2025) aimed at enabling Real-Time (RT) Earth system intelligence.

Nowadays, the use of Machine Learning (ML) onboard Earth Observation (EO) satellites has been investigated for a plethora of applications relying on multispectral and hyperspectral imaging. Traditionally, these studies have heavily relied on high-end data products, subjected to extensive pre-processing chains natively designed to be executed on the ground. However, replicating such algorithms onboard EO satellites poses significant challenges due to their computational intensity and need for additional metadata, which are typically unavailable on board. Because of that, current missions exploring onboard ML models implement simplified but still complex processing chains that imitate their on-ground counterparts. Despite these advancements, the potential of ML models to process raw satellite data directly remains largely unexplored. To fill this gap, this paper investigates the feasibility of applying ML models directly to Sentinel-2 raw data to perform thermal hotspot classification. This approach significantly limits the processing steps to simple and lightweight algorithms to achieve real-time processing of data with low power consumption. To this aim, we present an end-to-end (E2E) pipeline to create a binary classification map of Sentinel-2 raw granules, where each point suggests the absence/presence of a thermal anomaly in a square area of 2.5 km. To this aim, lightweight coarse spatial registration is applied to register three different bands, and an EfficientNet-lite0 model is used to perform the classification of the various bands. The trained models achieve an average Matthew’s correlation coefficient (MCC) score of 0.854 (on 5 seeds) and a maximum MCC of 0.90 on a geographically tripartite dataset of cropped images from the THRawS dataset. The proposed E2E pipeline is capable of processing a Sentinel-2 granule in 1.8 s and within 6.4 W peak power on a combination of Raspberry PI 4 and CogniSat-XE2 board, demonstrating real-time performance.

Satellite data transmission is a crucial bottleneck for Earth observation applications. To overcome this problem, we propose a novel solution that trains a neural network on board multiple satellites to compress raw data and only send down heavily compressed previews of the images while retaining the possibility of sending down selected losslessly compressed data. The neural network learns to encode and decode the data in an unsupervised fashion using distributed machine learning. By simulating and optimizing the learning process under realistic constraints such as thermal, power and communication limitations, we demonstrate the feasibility and effectiveness of our approach. For this, we model a constellation of three satellites in a Sun-synchronous orbit. We use real raw, multispectral data from Sentinel-2 and demonstrate the feasibility on space-proven hardware for the training. Our compression method outperforms JPEG compression on different image metrics, achieving better compression ratios and image quality. We report key performance indicators of our method, such as image quality, compression ratio and benchmark training time on a Unibap iX10-100 processor. Our method has the potential to significantly increase the amount of satellite data collected that would typically be discarded (e.g., over oceans) and can potentially be extended to other applications even outside Earth observation. All code and data of the method are available online to enable rapid application of this approach.

While novel artificial intelligence and machine learning techniques are evolving and disrupting established terrestrial technologies at an unprecedented speed, their adaptation onboard satellites is seemingly lagging. A major hindrance in this regard is the need for high-quality annotated data for training such systems, which makes the development process of machine learning solutions costly, time-consuming, and inefficient. This paper presents “the OPS-SAT case”, a novel data-centric competition that seeks to address these challenges. The powerful computational capabilities of the European Space Agency’s OPS-SAT satellite are utilized to showcase the design of machine learning systems for space by using only the small amount of available labeled data, relying on the widely adopted and freely available open-source software. The generation of a suitable dataset, design and evaluation of a public data-centric competition, and results of an onboard experimental campaign by using the competition winners’ machine learning model directly on OPS-SAT are detailed. The results indicate that adoption of open standards and deployment of advanced data augmentation techniques can retrieve meaningful onboard results comparatively quickly, simplifying and expediting an otherwise prolonged development period.

Monitoring water contaminants is of paramount importance, ensuring public health and environmental well-being. Turbidity, a key parameter, poses a significant problem, affecting water quality. Its accurate assessment is crucial for safeguarding ecosystems and human consumption, demanding meticulous attention and action. For this, our study pioneers a novel approach to monitor the Turbidity contaminant, integrating CatBoost Machine Learning (ML) with high-resolution data from Sentinel-2 Level-2A. Traditional methods are labor-intensive while CatBoost offers an efficient solution, excelling in predictive accuracy. Leveraging atmospherically corrected Sentinel-2 data through the Google Earth Engine (GEE), our study contributes to scalable and precise Turbidity monitoring. A specific tabular dataset derived from Hong Kong contaminants monitoring stations enriches our study, providing region-specific insights. Results showcase the viability of this integrated approach, laying the foundation for adopting advanced techniques in global water quality management.

Radar interferoinetry can be used to obtain sub-kilometer resolution over a swath at the expense of additional transmit power and a sufficiently long baseline to accommodate at least two antennas. This paper reports an innovative concept called AltiCube+, a low-cost long fixed-baseline interferometric radar altimeter based on CubeSats on-orbit assembly. The AltiCube+ concept consists of multiple 16U CubeSats, After an early operation and commissioning phase, these CubeSats will perform autonomous rendezvous and docking with each other via deployable booms to establish a long fixed-baseline, and then deploy antennas for an interferometric altimeter configuration. The uniqueness of AltiCube+ is on the potential scientific opportunities brought by two left and right looking interferometric altimeters with around 6 meter baseline (total system length is more than 8 m) and the sustainability due to its significantly low cost and short development lifecycle. If budget allows, multiple AltiCube+ systems with same or different altimetry capabilities can form a constellation to dramatically reduce the revisit time and, therefore, provide much better spatiotemporal coverage.

The next generation of spacecraft technology is anticipated to enable novel applications, including onboard processing, machine learning, and decentralized operational scenarios. Although several of these applications have been previously investigated, the real-world operational limitations associated with actual mission scenarios have been only superficially addressed. Here, we present an open-source Python module called PASEOS, capable of modeling operational scenarios involving one or multiple spacecraft. It considers several physical phenomena, including thermal, power, bandwidth, and communications constraints, and the impact of radiation on spacecraft. PASEOS can be run as a high-performance-oriented numerical simulation and/or in a real-time mode on edge hardware. We demonstrate these capabilities in three scenarios: one in real-time simulation on a Unibap iX-10 100 satellite processor, another in a simulation modeling an entire constellation performing tasks over several hours, and one training a machine learning model in a decentralized setting. While we demonstrate tasks in Earth orbit, PASEOS also allows deep space scenarios. Our results show that PASEOS can model the described scenarios efficiently and thus provide insight into operational considerations. We show this by measuring runtime and overhead as well as by investigating the constellation's modeled temperature, battery status, and communication windows. By running PASEOS on an actual satellite processor, we showcase how PASEOS can be directly included in hardware demonstrators for future missions. Overall, we provide the first solution to holistically model the physical constraints spacecraft encounter in space. The PASEOS module is available online with extensive documentation, enabling researchers to incorporate it into their studies quickly.

We present a novel software feature for the BrainScaleS-2 accelerated neuromorphic platform that facilitates the partitioned emulation of large-scale spiking neural networks. This approach is well suited for deep spiking neural networks and allows for sequential model emulation on undersized neuromorphic resources if the largest recurrent subnetwork and the required neuron fan-in fit on the substrate. We demonstrate the training of two deep spiking neural network models—using the MNIST and EuroSAT datasets—that exceed the physical size constraints of a single-chip BrainScaleS-2 system. The ability to emulate and train networks larger than the substrate provides a pathway for accurate performance evaluation in planned or scaled systems, ultimately advancing the development and understanding of large-scale models and neuromorphic computing architectures.

Automated Band-to-Band alignment is a crucial prerequisite for satellite mission involving image operations. Many techniques are now developed for image registration: correlation-based methods, feature-based methods, hybrid methods and Deep Learning-based methods. Due to perturbations in the spacecraft orientation and dynamic disturbances, the a priori knowledge concerning the misalignment of bands is often insufficient, therefore an appropriate sub-pixel level registration scheme must be implemented on-board the satellite. In this work three registration approaches are tested and compared using raw image data from the European Space Agency Sentinel-2 mission: the Coarse Coregistration, SuperGlue Coregistration and LightGlue Coregistration. The Coarse Coregistration is a simple approach to image registration based on the deterministic shift of the sensed image, but its performance is affected by non-systematic disturbances that are not corrected, often limiting it is accuracy to a pixel level. On the other hand, SuperGlue is a powerful but computationally expensive deep network designed for computer vision tasks. Despite its excellent accuracy, the inference time does not suit the on-board requirements of the mission. For this reason, a lighter version of SuperGlue based on an adaptive network, named LightGlue, has been tested to study its performance and inference times. The maximum number of keypoints, the adaptive depth and the number of layers of the network have been modified in order to test the architecture's response. With this analysis, it has been found that LightGlue brings the precision on the correcting shift up to a sub-pixel level, up to an order of magnitude better than the Coarse Coregistration, while running up to 1.5 times faster than SuperGlue. Sentinel-2 raw data is used here for the first time.