Using Artificial Intelligence for Space Challenges: A Survey

Russo, Antonia; Lax, Gianluca

doi:10.3390/app12105106

Cited by 37 publications

(11 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a growing use of algorithms, models, and machine learning tools that are being used in different areas of knowledge, such as engineering, education, administration, business, medicine, sales, space systems [4] [5], etc. Satellite telemetry data are labelled data, so we can use supervised [6] machine learning. Amazonia-1 satellite telemetry has categorial (nominal) data that can be used for classification and numerical (continuous) data that can be used for regression.…”

Section: Machine Learningmentioning

confidence: 99%

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

Barbosa

Ferreira

Júnior

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This article presents the data acquisition, exploratory data analysis, model training, evaluation, and use of hyperparameters in a machine learning model that will be used to predict telemetry data from the Amazonia-1 satellite. The Amazonia-1 satellite was launched in 2021, it uses the Multi-Mission Platform as a service module and has a Wide Field Imager imaging camera. Its power subsystem has 715 telemetries with distinct data types that will be used as dependent and independent variables. The amount of telemetry data generated daily is large, making manual analysis of this data unfeasible. The ensemble XGBoost machine learning algorithm is used to predict the values of the dependent variable D008 “Battery Module 1 Voltage” that belongs to the electric power subsystem. For the evaluation and performance Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R2 are used. The final learning model resulted in the coefficient of determination (R2) with 99.99%, MAE of 0.005749, and RMSE of 0.007727. After the cross-validation step, RMSE reached 0.006888. The execution time was 57 minutes and 32 seconds. Based on these numbers, we can consider that the machine learning model built reached a good result, especially when used with cross-validation.

show abstract

Section: Machine Learningmentioning

confidence: 99%

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

Barbosa

Ferreira

Júnior

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…which may place extra demand on the supply chain of consumable products. Some of the many current and emerging technologies to assist space travelers and colonists shown in Table 4 include the consideration of ergonomic design and how AI may play a role [66,67] based on the momentum for AI in terrestrial healthcare management (e.g., Bohr & Memarzadeh 2020 [68]). Delivery of drugs via impregnated bandages (e.g., Maver et al [69]) or nano-fluidics where a tunable supply of the beta-agonist formoterol from a nano-reservoir has been demonstrated to reduce muscle atrophy in mice [70] and may form the start of a promising modality which was recently been reviewed [71].…”

Section: Emergency Evacuation Protocol and Processes Clinical Waste M...mentioning

confidence: 99%

A Crowd-Sourcing Project to Understand, Prevent and Manage Incidences of Injury and Wounding to Astronauts and Off-Earth Colonists

Cahill¹,

Braddock²

2022

J. Hum. Earth Future

View full text Add to dashboard Cite

Recent technical successes of the unmanned Mars 2020, Tianwen-1 and Hope Mars missions have further increased our hunger for space exploration and the possible colonisation of Mars is now firmly on the mid-term horizon. Furthermore, renewed commitment to settle on the Moon is anticipated within the next three years, led by NASA’s Artemis programme utilising the pan-space agency constructed lunar Gateway or Space X’s Starship system. These programmes will necessitate a larger number of astronauts spending longer periods in space and despite rigorous risk identification and mitigation procedures, injury is an inevitable consequence and management procedures will demand efficient and effective implementation. We have employed Cognitive Work Analysis to derive an abstraction hierarchy for reducing the potential for physical injury and managing the consequence of injury in space. We have used a crowd-sourcing approach to cluster factors and themes which may emanate from within or without habitat and consider solution management in the light of current and emerging technology. In addition, we also consider mental fitness as a confounder which may emerge during missions and propose methods for both measurement and management. Doi: 10.28991/HEF-2022-03-03-04 Full Text: PDF

show abstract

“…A picture is worth a thousand words. Images are very important in information transmission, especially for special fields such as aerospace, medical treatment and criminal investigation where high-quality images can often play an important role [2,3] . In the field of image processing, the image generative model based on deep learning has been able to obtain images of different scales and different resolutions [4,5].…”

Section: Introductionmentioning

confidence: 99%

P‐2.9: A review of image generation methods based on deep learning

Wang

Song

Wang

2023

Symp Digest of Tech Papers

View full text Add to dashboard Cite

Image as a medium of visual information transmission have the advantages of vividness, intuition and easy understanding. They play an important role in information transmission and utilization. In recent years, due to the rapid development of deep learning technology in the field of image processing, image generative model based on neural network has become one of the current research hotspots. In the field of deep learning, unsupervised learning model has received more and more attentions, especially in the field of deep generative models, which has made breakthrough progress [1] . Among them, Variational Auto-Encoder (VAE), Generative Adversarial Network (GAN), and Diffusion Model are the three most representative research methods in the field of unsupervised learning. They have been applied more and more in the field of deep generative models. Especially, the high-quality image generative models based on the generative adversarial network continue to be hot. The diffusion model is a rising star, which is favored by more and more researchers. This paper first summarizes the main research work, improvement mechanism and features of image generation methods based on VAE and GAN, then introduces the principle of the rising diffusion model and its representative models. Finally, the advantages and limitations of the above methods are compared and analyzed, and prospects for future research are put forward.

show abstract

Using Artificial Intelligence for Space Challenges: A Survey

Cited by 37 publications

References 121 publications

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

A Crowd-Sourcing Project to Understand, Prevent and Manage Incidences of Injury and Wounding to Astronauts and Off-Earth Colonists

P‐2.9: A review of image generation methods based on deep learning

Contact Info

Product

Resources

About