This is the AI-ready benchmark dataset (OPSSAT-AD) containing the telemetry data acquired on board OPS-SAT---a CubeSat mission that has been operated by the European Space Agency.

It is accompanied by the paper with baseline results obtained using 30 supervised and unsupervised classic and deep machine learning algorithms for anomaly detection. They were trained and validated using the training-test dataset split introduced in this work, and we present a suggested set of quality metrics that should always be calculated to confront the new algorithms for anomaly detection while exploiting OPSSAT-AD. We believe that this work may become an important step toward building a fair, reproducible, and objective validation procedure that can be used to quantify the capabilities of the emerging anomaly detection techniques in an unbiased and fully transparent way.

The two included files are:

segments.csv with the acquired telemetry signals from ESA OPS-SAT aircraft,

dataset.csv with the extracted, synthetic features are computed for each manually split and labeled telemetry segment.

Please have a look at our two papers commenting on this dataset:

The benchmark paper with results of 30 supervised and unsupervised anomaly detection models for this collection:Ruszczak, B., Kotowski. K., Nalepa, J., Evans, D.: The OPS-SAT benchmark for detecting anomalies in satellite telemetry, 2024, preprint arxiv: 2407.04730,

the conference paper in which we presented some preliminary results for this dataset:Ruszczak, B., Kotowski. K., Andrzejewski, J., et al.: (2023). Machine Learning Detects Anomalies in OPS-SAT Telemetry. Computational Science – ICCS 2023. LNCS, vol 14073. Springer, Cham, DOI:10.1007/978-3-031-35995-8_21.

There has been a tremendous increase in the volume of Earth Science data over the last decade from modern satellites, in-situ sensors and different climate models. All these datasets need to be co-analyzed for finding interesting patterns or for searching for extremes or outliers. Information extraction from such rich data sources using advanced data mining methodologies is a challenging task not only due to the massive volume of data, but also because these datasets are physically stored at different geographical locations. Moving these petabytes of data over the network to a single location may waste a lot of bandwidth, and can take days to finish. To solve this problem, in this paper, we present a novel algorithm which can identify outliers in the global data without moving all the data to one location. The algorithm is highly accurate (close to 99%) and requires centralizing less than 5% of the entire dataset. We demonstrate the performance of the algorithm using data obtained from the NASA MODerate-resolution Imaging Spectroradiometer (MODIS) satellite images.

DISTRIBUTED ANOMALY DETECTION USING SATELLITE DATA FROM MULTIPLE MODALITIES KANISHKA BHADURI, KAMALIKA DAS, AND PETR VOTAVA** Abstract. There has been a tremendous increase in the volume of Earth Science data over the last decade from modern satellites, in-situ sensors and different climate models. All these datasets need to be co-analyzed for finding interesting patterns or for searching for extremes or outliers. Information extraction from such rich data sources using advanced data mining methodologies is a challenging task not only due to the massive volume of data, but also because these datasets ate physically stored at different geographical locations. Moving these petabytes of data over the network to a single location may waste a lot of bandwidth, and can take days to finish. To solve this problem, in this paper, we present a novel algorithm which can identify outliers in the global data without moving all the data to one location. The algorithm is highly accurate (close to 99%) and requires centralizing less than 5% of the entire dataset. We demonstrate the performance of the algorithm using data obtained from the NASA MODerate-resolution Imaging Spectroradiometer (MODIS) satellite images.

This dataset comes from the telemetry data of Quantum Science Experiment Satellite's Attitude Control System from 2017 to 2018. The original data was processed with Python's pandas data processing package to do wild value rejection and downsampling (from the original sampling rate of 1s to 6s). The pre-processed data contains 11250 data points with 19 dimensions and can be used for satellite telemetry data correlation anomaly detection.

Acoustic Anomaly Detection Satellite Market Outlook

According to our latest research, the global Acoustic Anomaly Detection Satellite market size reached USD 1.42 billion in 2024 and is projected to grow at a strong CAGR of 14.7% from 2025 to 2033. By the end of 2033, the market is expected to achieve a valuation of USD 4.72 billion. This robust growth trajectory is driven by escalating demand for advanced satellite-based monitoring solutions, rising investments in space technologies, and the increasing necessity for real-time anomaly detection across diverse industries. As per our latest research, the market is witnessing significant technological advancements and expanding application scope, which are accelerating its adoption globally.

One of the primary growth factors fueling the Acoustic Anomaly Detection Satellite market is the surge in global security concerns and the need for sophisticated surveillance systems. Governments and defense organizations are increasingly leveraging satellite-based acoustic anomaly detection to monitor strategic assets, detect unauthorized activities, and enhance national security. The ability of these satellites to provide real-time, high-fidelity acoustic data from remote or inaccessible locations is revolutionizing defense and intelligence operations. Furthermore, the integration of artificial intelligence and machine learning algorithms with acoustic sensors is significantly improving anomaly detection accuracy, reducing false positives, and enabling more proactive threat responses.

Another critical driver is the growing emphasis on environmental monitoring and disaster management. The capability of acoustic anomaly detection satellites to identify abnormal sound patterns such as volcanic eruptions, earthquakes, and underwater disturbances is proving invaluable for early warning systems and rapid response initiatives. Environmental agencies and research institutions are increasingly adopting these technologies to monitor climate change impacts, assess ocean health, and track wildlife activity. This expanding application spectrum is not only enhancing environmental stewardship but also opening up new commercial opportunities in the market.

The commercialization of space and the proliferation of private sector investments are also playing a pivotal role in market expansion. Commercial enterprises are deploying acoustic anomaly detection satellites for applications ranging from asset monitoring and infrastructure management to maritime security and resource exploration. The decreasing cost of satellite launches, coupled with advancements in miniaturization and sensor technologies, is making it feasible for smaller organizations to participate in this market. As a result, the competitive landscape is becoming more dynamic, fostering innovation and accelerating the development of next-generation acoustic anomaly detection solutions.

From a regional perspective, North America currently dominates the Acoustic Anomaly Detection Satellite market owing to its advanced space infrastructure, significant government funding, and a strong presence of leading technology providers. However, the Asia Pacific region is expected to witness the fastest growth over the forecast period, driven by increasing investments in space programs, rising security concerns, and growing awareness about the benefits of acoustic anomaly detection technologies. Europe is also emerging as a key market, supported by collaborative research initiatives and robust regulatory frameworks. The market’s global footprint is expanding as more countries recognize the strategic value of satellite-based acoustic anomaly detection in addressing both security and environmental challenges.

Component Analysis

The Component segment of the Acoustic Anomaly Detection Satellite market is categorized into Hardware, Software, and Services. Hardware remains the backbone of this segment, encompassing satellite platforms, acoustic sensors, signal processors, and commu

We have curated a unique dataset derived from EIRSAT-1, Ireland's inaugural domestically produced satellite, as a testing and validation resource for these ML models and the future development cycle of AI-enabled small satellites. This dataset consists of a training set developed during ground testing and containing artificial anomalies induced to train satellite operators, a validation dataset containing real anomalies encountered during the qualification campaign, and an early flight test dataset collected since the satellite was launched on December 1^st, 2023. This paper presents an in-depth analysis of the efficacy of these ML techniques when applied to the EIRSAT-1 dataset, offering insights into their potential to revolutionize the domain of satellite operations through enhanced autonomy and responsiveness. This study not only showcases the capabilities of these ML techniques in an operational environment but also sets the stage for future research and development in autonomous satellite systems.

There has been a tremendous increase in the volume of sensor data collected over the last decade for different monitoring tasks. For example, petabytes of earth science data are collected from modern satellites, in-situ sensors and different climate models. Similarly, huge amount of flight operational data is downloaded for different commercial airlines. These different types of datasets need to be analyzed for finding outliers. Information extraction from such rich data sources using advanced data mining methodologies is a challenging task not only due to the massive volume of data, but also because these datasets are physically stored at different geographical locations with only a subset of features available at any location. Moving these petabytes of data to a single location may waste a lot of bandwidth. To solve this problem, in this paper, we present a novel algorithm which can identify outliers in the entire data without moving all the data to a single location. The method we propose only centralizes a very small sample from the different data subsets at different locations. We analytically prove and experimentally verify that the algorithm offers high accuracy compared to complete centralization with only a fraction of the communication cost. We show that our algorithm is highly relevant to both earth sciences and aeronautics by describing applications in these domains. The performance of the algorithm is demonstrated on two large publicly available datasets: (1) the NASA MODIS satellite images and (2) a simulated aviation dataset generated by the ‘Commercial Modular Aero-Propulsion System Simulation’ (CMAPSS).

ESA Anomaly Dataset is the first large-scale, real-life satellite telemetry dataset with curated anomaly annotations originated from three ESA missions. We hope that this unique dataset will allow researchers and scientists from academia, research institutes, national and international space agencies, and industry to benchmark models and approaches on a common baseline as well as research and develop novel, computational-efficient approaches for anomaly detection in satellite telemetry data.

The dataset results from the work of an 18-month project carried by an industry Consortium composed of Airbus Defence and Space, KP Labs and the European Space Agency’s European Space Operations Centre. The project, funded by the European Space Agency (ESA), is part of the Artificial Intelligence for Automation (A²I) Roadmap (De Canio et al., 2023), a large endeavour started in 2021 to automate space operations by leveraging artificial intelligence.

Further details can be found on the arXiv and Github.

References
De Canio, G. et al. (2023) Development of an actionable AI roadmap for automating mission operations. In, 2023 SpaceOps Conference. American Institute of Aeronautics and Astronautics, Dubai, United Arab Emirates.

Swarm C Grid 5 Ludian, experimental results.

The Multi-Domain Outlier Detection Dataset contains datasets for conducting outlier detection experiments for four different application domains:

1. Astrophysics - detecting anomalous observations in the Dark Energy Survey (DES) catalog (data type: feature vectors)
2. Planetary science - selecting novel geologic targets for follow-up observation onboard the Mars Science Laboratory (MSL) rover (data type: grayscale images)
3. Earth science: detecting anomalous samples in satellite time series corresponding to ground-truth observations of maize crops (data type: time series/feature vectors)
4. Fashion-MNIST/MNIST: benchmark task to detect anomalous MNIST images among Fashion-MNIST images (data type: grayscale images)

Each dataset contains a "fit" dataset (used for fitting or training outlier detection models), a "score" dataset (used for scoring samples used to evaluate model performance, analogous to test set), and a label dataset (indicates whether samples in the score dataset are considered outliers or not in the domain of each dataset).

To read more about the datasets and how they are used for outlier detection, or to cite this dataset in your own work, please see the following citation:

Kerner, H. R., Rebbapragada, U., Wagstaff, K. L., Lu, S., Dubayah, B., Huff, E., Lee, J., Raman, V., and Kulshrestha, S. (2022). Domain-agnostic Outlier Ranking Algorithms (DORA)-A Configurable Pipeline for Facilitating Outlier Detection in Scientific Datasets. Under review for Frontiers in Astronomy and Space Sciences.

This layer presents detectable thermal activity from VIIRS satellites for the last 7 days. VIIRS Thermal Hotspots and Fire Activity is a product of NASA’s Land, Atmosphere Near real-time Capability for EOS (LANCE) Earth Observation Data, part of NASA's Earth Science Data.Consumption Best Practices: As a service that is subject to Viral loads (very high usage), avoid adding Filters that use a Date/Time type field. These queries are not cacheable and WILL be subject to Rate Limiting by ArcGIS Online. To accommodate filtering events by Date/Time, we encourage using the included "Age" fields that maintain the number of Days or Hours since a record was created or last modified compared to the last service update. These queries fully support the ability to cache a response, allowing common query results to be supplied to many users without adding load on the service.When ingesting this service in your applications, avoid using POST requests, these requests are not cacheable and will also be subject to Rate Limiting measures.Source: NASA LANCE - VNP14IMG_NRT active fire detection - WorldScale/Resolution: 375-meterUpdate Frequency: Hourly using the aggregated live feed methodologyArea Covered: WorldWhat can I do with this layer?This layer represents the most frequently updated and most detailed global remotely sensed wildfire information. Detection attributes include time, location, and intensity. It can be used to track the location of fires from the recent past, a few hours up to seven days behind real time. This layer also shows the location of wildfire over the past 7 days as a time-enabled service so that the progress of fires over that timeframe can be reproduced as an animation.The VIIRS thermal activity layer can be used to visualize and assess wildfires worldwide. However, it should be noted that this dataset contains many “false positives” (e.g., oil/natural gas wells or volcanoes) since the satellite will detect any large thermal signal.Fire points in this service are generally available within 3 1/4 hours after detection by a VIIRS device. LANCE estimates availability at around 3 hours after detection, and esri livefeeds updates this feature layer every 15 minutes from LANCE.Even though these data display as point features, each point in fact represents a pixel that is >= 375 m high and wide. A point feature means somewhere in this pixel at least one "hot" spot was detected which may be a fire.VIIRS is a scanning radiometer device aboard the Suomi NPP and NOAA-20 satellites that collects imagery and radiometric measurements of the land, atmosphere, cryosphere, and oceans in several visible and infrared bands. The VIIRS Thermal Hotspots and Fire Activity layer is a livefeed from a subset of the overall VIIRS imagery, in particular from NASA's VNP14IMG_NRT active fire detection product. The downloads are automatically downloaded from LANCE, NASA's near real time data and imagery site, every 15 minutes.The 375-m data complements the 1-km Moderate Resolution Imaging Spectroradiometer (MODIS) Thermal Hotspots and Fire Activity layer; they both show good agreement in hotspot detection but the improved spatial resolution of the 375 m data provides a greater response over fires of relatively small areas and provides improved mapping of large fire perimeters.Attribute informationLatitude and Longitude: The center point location of the 375 m (approximately) pixel flagged as containing one or more fires/hotspots.Satellite: Whether the detection was picked up by the Suomi NPP satellite (N) or NOAA-20 satellite (1). For best results, use the virtual field WhichSatellite, redefined by an arcade expression, that gives the complete satellite name.Confidence: The detection confidence is a quality flag of the individual hotspot/active fire pixel. This value is based on a collection of intermediate algorithm quantities used in the detection process. It is intended to help users gauge the quality of individual hotspot/fire pixels. Confidence values are set to low, nominal and high. Low confidence daytime fire pixels are typically associated with areas of sun glint and lower relative temperature anomaly (<15K) in the mid-infrared channel I4. Nominal confidence pixels are those free of potential sun glint contamination during the day and marked by strong (>15K) temperature anomaly in either day or nighttime data. High confidence fire pixels are associated with day or nighttime saturated pixels.Please note: Low confidence nighttime pixels occur only over the geographic area extending from 11 deg E to 110 deg W and 7 deg N to 55 deg S. This area describes the region of influence of the South Atlantic Magnetic Anomaly which can cause spurious brightness temperatures in the mid-infrared channel I4 leading to potential false positive alarms. These have been removed from the NRT data distributed by FIRMS.FRP: Fire Radiative Power. Depicts the pixel-integrated fire radiative power in MW (MegaWatts). FRP provides information on the measured radiant heat output of detected fires. The amount of radiant heat energy liberated per unit time (the Fire Radiative Power) is thought to be related to the rate at which fuel is being consumed (Wooster et. al. (2005)).DayNight: D = Daytime fire, N = Nighttime fireHours Old: Derived field that provides age of record in hours between Acquisition date/time and latest update date/time. 0 = less than 1 hour ago, 1 = less than 2 hours ago, 2 = less than 3 hours ago, and so on.Additional information can be found on the NASA FIRMS site FAQ.Note about near real time data:Near real time data is not checked thoroughly before it's posted on LANCE or downloaded and posted to the Living Atlas. NASA's goal is to get vital fire information to its customers within three hours of observation time. However, the data is screened by a confidence algorithm which seeks to help users gauge the quality of individual hotspot/fire points. Low confidence daytime fire pixels are typically associated with areas of sun glint and lower relative temperature anomaly (<15K) in the mid-infrared channel I4. Medium confidence pixels are those free of potential sun glint contamination during the day and marked by strong (>15K) temperature anomaly in either day or nighttime data. High confidence fire pixels are associated with day or nighttime saturated pixels.RevisionsSeptember 15, 2022: Updated to include 'Hours_Old' field. Time series has been disabled by default, but still available.July 5, 2022: Terms of Use updated to Esri Master License Agreement, no longer stating that a subscription is required!This layer is provided for informational purposes and is not monitored 24/7 for accuracy and currency.If you would like to be alerted to potential issues or simply see when this Service will update next, please visit our Live Feed Status Page!

There has been a tremendous increase in the volume of sensor data collected over the last decade for different monitoring tasks. For example, petabytes of earth science data are collected from modern satellites, in-situ sensors and different climate models. Similarly, huge amount of flight operational data is downloaded for different commercial airlines. These different types of datasets need to be analyzed for finding outliers. Information extraction from such rich data sources using advanced data mining methodologies is a challenging task not only due to the massive volume of data, but also because these datasets are physically stored at different geographical locations with only a subset of features available at any location. Moving these petabytes of data to a single location may waste a lot of bandwidth. To solve this problem, in this paper, we present a novel algorithm which can identify outliers in the entire data without moving all the data to a single location. The method we propose only centralizes a very small sample from the different data subsets at different locations. We analytically prove and experimentally verify that the algorithm offers high accuracy compared to complete centralization with only a fraction of the communication cost. We show that our algorithm is highly relevant to both earth sciences and aeronautics by describing applications in these domains. The performance of the algorithm is demonstrated on two large publicly available datasets: (1) the NASA MODIS satellite images and (2) a simulated aviation dataset generated by the ‘Commercial Modular Aero-Propulsion System Simulation’ (CMAPSS).

With advancements in aerospace technology and the widespread deployment of low Earth orbit constellations, challenges to astronomical observation and deep space exploration have intensified. The need for accurate orbital data on space targets, as well as the analysis of satellite positioning, constellation configurations, and deep space satellite behavior, has grown more critical. However, there is a significant gap in publicly available, real-world datasets to support research on space target maneuver prediction and anomaly detection. This paper addresses this gap by collecting and organizing representative maneuver data from the Starlink satellites, which includes precise star-tracking predictions and Two-Line Element (TLE) catalog orbital data. This dataset offers a more realistic and multi-dimensional scenario for modeling space target behavior. It provides valuable insights into practical deployment of maneuver detection and anomaly detection approaches.

The satellite data services market encompasses two primary product types: Image Data and Data Analytics. Image Data: Satellite imagery obtained from diverse sensors, providing valuable insights into the Earth's surface and vegetation. Data Analytics: The processing and analysis of satellite data to extract actionable insights and facilitate informed decision-making. This includes advanced techniques such as machine learning and artificial intelligence (AI) for pattern recognition, anomaly detection, and predictive modeling. Recent developments include: For instance,July 2022 Northrop Grumman has contracted Airbus U.S. Space & Defense, Inc. to provide 42 satellite platforms as well as assembly, integration, and test (AIT), launch, and space vehicle commissioning support services to fulfill the Tranche 1 Transport Layer prototype constellation (T1TL) award from the United States Space Development Agency (SDA)., For instance,February 2023 BlackSky is embedding the Inmarsat and Addvalue inter-satellite data relay technology, IDRS, into its next-generation satellite architecture. Addvalue has developed a novel Low-Earth Orbit (LEO) satellite antenna system that provides complete communications coverage when satellites are not visible to a base station. The IDRS terminal makes advantage of Inmarsat's satellite network to provide LEO satellites with continuous communications for mission tasking and data monitoring.. Key drivers for this market are: Technological advancements in satellite technology and data analytics

Government initiatives supporting satellite data utilization

Rising demand for satellite data in various industries. Potential restraints include: Regulatory restrictions on satellite operations

High cost of satellite launch and deployment. Notable trends are: Growing need for satellite imagery data is driving the market growth.

Satellite Data Services Market Outlook

As per our latest research, the global satellite data services market size reached USD 8.7 billion in 2024, driven by increasing demand for real-time geospatial intelligence and advanced analytics across multiple industries. The market is poised for robust expansion, registering a CAGR of 18.2% from 2025 to 2033. By 2033, the satellite data services market is forecasted to attain a value of USD 44.1 billion, propelled by technological advancements, the proliferation of small satellite constellations, and growing integration of satellite data into commercial applications. This growth trajectory underscores the transformative impact of satellite data on decision-making processes and operational efficiency across global sectors.

One of the principal growth factors for the satellite data services market is the surge in demand for high-resolution imagery and geospatial analytics across sectors such as agriculture, energy, defense, and environmental monitoring. The rapid digitization of industries and the need for precise, real-time data to support critical operations have fueled investments in satellite data services. Additionally, the increasing frequency of natural disasters and the growing importance of climate change monitoring have necessitated the use of satellite-based solutions for timely and accurate information. The integration of artificial intelligence and machine learning with satellite data analytics has further amplified the value proposition of these services, enabling predictive insights and automated anomaly detection for enhanced decision-making.

Another significant driver is the expansion of small satellite constellations and the decreasing cost of satellite launches, which have democratized access to satellite data. The advent of low Earth orbit (LEO) satellites has revolutionized data acquisition, offering improved revisit rates and cost-effective solutions for commercial and governmental clients. The proliferation of private players and public-private partnerships has accelerated innovation in satellite data services, resulting in enhanced data quality, faster delivery times, and a wider range of value-added services. This democratization has opened new avenues for start-ups and SMEs, fostering a competitive environment that stimulates continuous technological advancement and market expansion.

The satellite data services market is also benefiting from increased government initiatives and policy support for space-based infrastructure and data utilization. Governments worldwide are investing in satellite programs to bolster national security, disaster management, and socio-economic development. These initiatives have led to greater collaboration between governmental agencies and private enterprises, promoting the adoption of satellite data for urban planning, resource management, and infrastructure development. Moreover, international efforts to standardize satellite data formats and improve interoperability are facilitating cross-border data sharing, thereby expanding the global reach and utility of satellite data services.

Regionally, North America remains the largest market for satellite data services, accounting for over 37% of global revenue in 2024, driven by the presence of leading satellite operators, advanced technological infrastructure, and substantial government funding. Europe follows closely, supported by strong investments in space programs and a burgeoning commercial sector. The Asia Pacific region is witnessing the fastest growth, with a projected CAGR of 21.5% during the forecast period, fueled by increasing adoption of satellite technologies in emerging economies such as China and India. Latin America and the Middle East & Africa are also experiencing steady growth, albeit from a smaller base, as governments and enterprises in these regions recognize the strategic value of satellite data for development and security.

Service Type Analysis

Warning - Anomalies currently not usable

I notice there are some problems with the anomalous sequences. Please do not consider using the dataset with the firing sequence marked as anomalous. I am investigating what is the problem and work towards a new release. I recommend to not use this dataset for anomaly detection at the moment.

Context

Testing hardware to qualify it for Spaceflight is critical to model and verify performances. Hot fire tests (also known as life-tests) are typically run during the qualification campaigns of satellite thrusters, but results remain proprietary data, hence making it difficult for the machine learning community to develop suitable data-driven predictive models. This synthetic dataset was generated partially based on the real-world physics of monopropellant chemical thrusters, to foster the development and benchmarking of new data-driven analytical methods (machine learning, deep-learning, etc.).

Overview of chemical monopropellant thruster

A monopropellant thruster is an engine that provide thrust by usage a unique propellant, as opposed to bipropellant systems which uses the combustion of fuel and oxidizer. The unique propellant flow into the chamber is controlled by a valve, usually an integral part of the thruster. It is injected into a catalyst bed, where it decomposes. A monopropellant must be slightly unstable chemical, which will decompose exothermally to produce a hot gas. The resulting hot gases are expelled through a converging/diverging nozzle generating thrust. The gas temperature is high which require the usage of high-temperature alloys to manufacture the nozzle.

The most classical type of monopropellant thrusters are reaction control thrusters generating about 1 to 10 Newton of thrust using hydrazine as propellant. These reaction control thrusters are used, for instance to control the attitude of a spacecraft and/or to desaturate the reaction wheels.

The performance of a monopropellant thruster (and its degradation) is mostly driven by the valve performance and the s of the catalyst bed on which the propellant decomposes. The life of the catalyst bed is mainly affected by the degradation of catalyst granules. The catalyst is made of alumina-based Indium metal granules (about 1mm in diameter) that are carefully designed and selected to optimize its lifetime. However, catalyst granules are easily damaged by thermoelastic shocks, collisions with other granules, and so on, thus hey are broken up into fine particles which reduces their efficiency. After the long duration of firing, large voids are formed in the catalyst bed and induce unstable decomposition of hydrazine and degradation of thruster performance.

The properties of this simulated thruster fire tests are fictious and not necessarily equivalent to a real-world thruster available on the market. Nevertheless, it provides sufficient granularity and challenge to benchmark algorithm that may then be tested on real fire test sequences. This is possible because the simulator is based, partially, on real-world physics of such reaction control thrusters. The details of the simulator are not provided on purpose to avoid leakage into feature engineering methods and modelling approaches developed.

Tasks and use cases

Regression for Performance Prediction

• Performance Modelling: Prediction of the thruster performances (target can be thrust, mass flow rate, and/or the average specific impulse of over a given sequence that can be calculated using the first two). This task may also be referred to as “time seriesforecasting with exogenous inputs”, or “System Dynamics modelling with control”, where the control is the command sent to the thruster (on/off) in the column “ton”. It is very unlikely in practice to have more than a few complete SN qualification datasets, so we suggest a 50:50 split between the train and test sets.
  • Use SN01 to SN12 to build your train and validation sets. These are data assumed to be collected on-ground.
  • Use SN13 to SN24 as the final test set. Warning: given that these thrusters are expected to be mounted on a flying satellite, you cannot retrain the model progressively using SN13 to SN24 data. The data is the ground truth as if we were able to measure it on-board.
• Acceptance Test for Individualised Performance Model refinement:
  • In practice, every newly manufactured thruster is tested via acceptance tests: test_id 1 to 12. So these measurement are actually available for each thruster serial number. For this reason, it is possible to use the acceptance test data (test_id 1 to 12) of SN13 to SN24 as input to the model to predict the flight performance of these SN over test_id 13 to 112. Taking into account the acceptance test of individual thruster might be helpful to generate individualized thruster predictive model. This use case propose to investigate...

Sen12Landslides: A Spatio-Temporal Dataset for Satellite-Based Landslide and Anomaly Detection

This repository hosts Sen12Landslides, a large-scale, multi-sensor benchmark for spatio-temporal landslide and anomaly detection. It comprises 39,556 NetCDF patches (128×128 px with 10m resolution) spanning 15 time steps, derived from both Sentinel-1 (VV, VH; ascending/descending) and Sentinel-2 (10 spectral bands B02–B12). Every patch includes additionally:

A binary landslide mask
A… See the full description on the dataset page: https://huggingface.co/datasets/paulhoehn/Sen12Landslides.

Parameters used for the AD methods.

The global Satellite Monitoring and Control Services market is experiencing robust growth, driven by increasing demand for reliable satellite-based communication, navigation, and Earth observation services. The market's expansion is fueled by several key factors: the proliferation of small satellites and constellations, requiring sophisticated monitoring and control capabilities; the growing adoption of satellite-based internet services, especially in remote areas; and the increasing reliance on satellite imagery for various applications, including defense, agriculture, and disaster management. The market is segmented by type (Ground and Space Segment Monitoring and Control Services) and application (Aerospace, Communication, Military, and Others). Ground segment services are currently dominant due to their established infrastructure and critical role in mission control, while space segment services are experiencing rapid growth due to technological advancements in onboard processing and autonomous control systems. The North American market currently holds a significant share due to the presence of major satellite manufacturers and operators, coupled with substantial government investments in space technology. However, the Asia-Pacific region is projected to witness the fastest growth rate in the coming years, driven by increasing investments in satellite infrastructure and communication networks across countries like China and India. Competition is intense, with established players like Lockheed Martin, Thales Group, and Boeing competing with smaller, more specialized firms. The market’s continued expansion hinges on ongoing technological innovation, particularly in areas such as artificial intelligence (AI) for automated anomaly detection, and the development of more resilient and cost-effective satellite systems. The forecast period (2025-2033) anticipates continued market expansion, influenced by several factors including government initiatives to support space exploration, the increasing demand for high-bandwidth satellite internet, and the rising adoption of satellite-based navigation systems across various sectors. While potential restraints like regulatory hurdles and the high initial investment costs associated with satellite systems exist, the overall outlook remains positive. The market is poised for significant growth, particularly in emerging economies experiencing rapid technological advancements and a burgeoning need for advanced communication and Earth observation solutions. Strategic partnerships and mergers and acquisitions are anticipated to reshape the market landscape, driving further consolidation amongst key players. This synergistic effect will likely lead to the development of more comprehensive and integrated solutions that cater to the evolving needs of a globally interconnected world.

Investigated seismic regions and their coordinates.