ML Process

NASA's Asteroid Grand Challenge: Strategy, Results and Lessons Learned - Space Policy, Science Direct Journal 2018 Arxiv

Advancing Astrobiology Through Public/Private Partnerships - The FDL Model - 49th Lunar and Planetary Science Conference 2018

Best practices in sharing enhanced data products and machine learning algorithms - Learnings from NASA Frontier Development Lab - JPL Data Science & AI Workshop 2021

Space ML: Distributed Open-source Research with Citizen Scientists for the Advancement of Space Technology for NASA - COSPAR 2021 Workshop on Cloud Computing for Space Sciences

Learnings from Frontier Development Lab and SpaceML AI Accelerators for NASA and ESA - Arxiv

Technology Readiness Levels for Machine Learning Systems - Arxiv

Space ML: Distributed Open-Source Research with Citizen-Scientists for Advancing Space Technology for NASA - Nvidia GTC21 - Accepted

Beyond reproducibility at the Frontier Development Lab (FDL): Community driven continuous optimization for the SDO machine learning dataset (SDOML) - AGU 2021

Planetary Defence

CAMS

Recovery of meteorites using an autonomous drone and machine learning - Arxiv Meteoritics & Planetary Science 2021 (FDL USA 2016)

Meteorite recovery using a drone and machine learning - Lunar and Planetary Science 2017 (FDL USA 2017)

The Deflector Selector: A Machine Learning Framework for Prioritizing Hazardous Object Deflection Technology Development - Acta Astronautica, Science Direct Journal 2018 - Arxiv (FDL USA 2017)

The Deflector Selector: A Machine Learning Framework for Prioritizing Hazardous Object Deflection Technology Development - Arxiv

Artificial Intelligence Techniques applied to Automating Meteor Validation and Trajectory Quality Control to Direct the Search for Long Period Comets - International Meteor Conference 2017 (FDL USA 2017)

A survey of southern hemisphere meteor showers - Planetary and Space Science Journal 2018 (FDL USA 2017)

Using Bayesian Optimization to Find Asteroids' Pole Directions - American Astronomical Society, DPS meeting #50 2018 (FDL USA 2017)

Machine learning tools to develop 3D shape models of near Earth asteroids from radar observations - EPSC-DPS Joint Meeting 2019 (FDL USA 2017)

Heliophysics

A deep learning virtual instrument for monitoring extreme UV solar spectral irradiance - Science Advances 2019 (FDL USA 2018)

A machine learning dataset prepared for NASA’s Solar Dynamics Observatory - Astrophysical Journal 2019 (FDL USA 2018)

Using U-Nets to create high-fidelity virtual observations of the solar corona - NeurIPS Workshop 2019 (FDL USA 2019) - ArXiv

A deep-learning based approach for predicting high latitude ionospheric scintillations using geospace data and auroral imagery - JPL NASA Abstract (FDL USA 2019)

Auto-Calibration of Remote Sensing Solar Telescopes with Deep Learning - NeurIPS Workshop 2019 (FDL USA 2019) - ArXiv

Single-Frame Super-Resolution of Solar Magnetograms: Investigating Physics-Based Metrics & Losses - NeurIPS Workshop 2019 (FDL USA 2019) - ArXiv

Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder - NeurIPS Workshop 2019 (FDL USA 2019) - ArXiv

Prediction of GNSS Phase Scintillations: A Machine Learning Approach - NeurIPS Workshop 2019 (FDL USA 2019) - ArXiv

A deep learning Approach to forecast Tomorrow's Solar Wind Parameters - AGU 2019 (FDL USA 2019)

Enhancing the Predictability of GNSS Scintillations - AGU 2019 (FDL USA 2019)

Auto-calibration and reconstruction of SDO’s Atmospheric Imaging Assembly channels with Deep Learning - AGU 2019 (FDL USA 2019)

RotNet: Fast and Scalable Estimation of StellarRotation Periods Using Convolutional NeuralNetworks - NeurIPS 2020 ML4PS (Physical Sciences) Workshop (FDL USA 2020)

Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition - NeurIPS 2020 ML4PS (Physical Sciences) Workshop  (FDL USA 2020) - ArXiv

Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly instrument with Deep Learning - AGU 2020 (FDL USA 2019)

Determining new representations of “Geoeffectiveness” using deep learning - AGU 2020 (FDL USA 2020)

Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning - Astronomy & Astrophysics Journal 2021 (FDL USA 2019)

Auto-Calibration and High-Fidelity Virtual Observations of Remote Sensing Solar Telescopes with Deep Learning - JPL AI and Data Science Workshop 2021 (FDL USA 2019)

Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder - JPL AI and Data Science Workshop 2021 (FDL USA 2019)

Autonomous deep-space missions: can deep learning be used to optimize data transmission - COSPAR 2021 (FDL USA 2019)

Automating the Calibration of the Atmospheric Imaging Assembly - COSPAR 2021 (FDL USA 2019)

Modeling and forecasting ground geomagnetic perturbations using deep learning on spherical harmonics - COSPAR2021 Machine Learning for Space Sciences (YouTube Link)  (FDL USA 2020)

Forecasting Ground Magnetic Perturbation Using Deep Learning on Spherical Harmonics - American Meteorological Society 100th annual meeting 2020 (FDL USA 2020)

Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning - Astronomy & Astrophysics Journal(FDL USA 2019)

Astrobiology

Item descriptionINARA: Intelligent exoplaNet Atmospheric RetrievAl A Machine Learning Retrieval Framework with a Data Set of 3 Million Simulated Exoplanet Atmospheric Spectra - Astrobiology Science Conference 2019 (FDL USA 2018)

Using machine learning to study E.T. biospheres - NeurIPS Workshop 2019 (FDL USA 2018)

EXO-ATMOS: A Scalable Grid of Hypothetical Planetary Atmospheres - Astrobiology Science Conference 2019 (FDL USA 2018)

INARA: A Bayesian Deep Learning Framework for Exoplanet Atmospheric Retrieval - JPL AI and Data Science Workshop 2021 (FDL USA 2018)

Advancing Space Science with Machine Learning: Frontier Development Lab Projects with NASA-Nvidia GTC21 - Accepted (FDL USA 2018, FDL USA 2019, FDL USA 2020)

Exoplanets

Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning - Astrophysical Journal 2018 - Arvix (FDL USA 2018)

Bayesian Deep Learning for Exoplanet Atmospheric Retrieval - NeurIPS Workshop 2018 (FDL USA 2018) - ArXiv

An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval - Astrophysical Journal 2019 (FDL USA 2018) - Arxiv

The NASA FDL Exoplanet Challenge: Transit Classification with Convolutional Neural Networks - Astrobiology Science Conference 2019 (FDL USA 2018)

Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks - Astronomy & Astrophysics Journal 2020 (FDL USA 2018) - Arvix

Astronaut health

Prototyping CRISP: A Causal Relation and Inference Search Platform applied to Colorectal Cancer Data - IEEE LifeTech 2021 / NASA HRP IWS 2021 (FDL USA 2020) - research paper award winners for IEEE Lifetech 2021

Generative Models for Synthesizing Symptomatic ECG Astronaut Health Data for Future Deep Space Missions - JPL Data Science & AI Workshop 2021 (FDL USA 2020)

A Generative Machine Learning Framework for Synthesizing Symptomatic ECG Astronaut Health Data - NASA HRP Workshop 2021 (FDL USA 2020)

Advancing Space Science with Machine Learning: Frontier Development Lab Projects with NASA - Nvidia GTC21- Accepted (FDL USA 2019, FDL USA 2019, FDL USA 2020)

Learning Invariant Representations for non-i.i.dFederated Settings - NeurIPS 2021 (FDL USA 2021)

Federated causal inference for out-of-distribution generalization in predicting physiological effects of radiation exposure - AGU 2021 (FDL USA 2021)

Invariant Risk Minimisation for Cross-Organism Inference: Substituting Mouse Data for Human Data in Human Risk Factor Discovery - (FDL USA 2021) ArXiv

Earth Science

SAR-based landslide classification pretraining leads to better segmentation - NeurIPS 2022 (FDL 2022) - ArXiv

Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes - NeurIPS 2022 (FDL 2022) - ArXiv

Deep learning based landslide density estimation on SAR data for rapid response (FDL 2022) - ArXiv

Short-term Prediction of Severe Thunderstorm Hazards with Machine Learning and the Geostationary Lightning Mapper - American Meteorological Society Conference 2020 (FDL USA 2020)

Machine Learning for Generalizable Prediction of Flood Susceptibility - NeurIPS Workshop 2019 / DeepAI (FDL USA 2019) - ArXiv

Leveraging Lightning with Convolutional Recurrent AutoEncoder and ROCKET for Severe Weather Detection - NeurIPS 2020 - AI for Earth Science and AI for Earth Science Workshop (FDL USA 2020)

Dynamic Hydrology Maps from Satellite-LiDAR Fusion - NeurIPS 2020 - AI for Earth Science Workshop - Video (FDL USA 2020) - ArXiv

Knowledge Discovery Framework: Deep Learning Applications for Remote Sensing - AGU 2020 (FDL USA 2020)

Severe Weather Prediction Using Lightning Data - COSPAR 2021 (FDL USA 2020)

Severe Weather Prediction Using Lightning Data - NeurIPS Workshop 2020 - LatinX in AI (FDL USA 2020)

Severe Weather Prediction Using Lightning Data - NVIDIA GTC21 - Accepted (FDL USA 2020)

Where Are the Earth's Streams Flowing Right Now? Dynamic Hydrology Maps from Satellite-Lidar Fusion - NVIDIA GTC21 (FDL USA 2020)

Water monitoring with Very High Resolution satellite imagery - EGU'21 (FDL USA 2020)

Physics-informed GANs for Coastal Flood Visualization - (FDL USA 2020) - ArXiv

Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization - IEEE Transactions on Neural Networks and Learning Systems (FDL USA 2020) - ArXiv

Detecting Spatiotemporal Lightning Patterns: An Unsupervised Graph-Based Approach - ML4PS (FDL USA 2021)

Artificial Intelligence for the Advancement of Lunar and Planetary Science and Exploration - Planetary Science and Astrobiology Decadal Survey 2023-2032 (FDL USA 2021)

Coastal Digital Twin: Learning a fast and physics-informed surrogate model for coastal floods via neural operators - AGU 2021 (FDL USA 2021)

Generating informative and accurate descriptions of natural hazards and phenomena using large transformer-based models - AGU 2021 (FDL USA 2021)

Earth Observation

Multi-spectral multi-image super-resolution of Sentinel-2 with radiometric consistency losses and its effect on building delineation - ISPRS Journal of Photogrammetry and Remote Sensing (2022)

Multi3Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery - NeurIPS & AAAI (FDL Europe 2018) - ArXiv

Rapid Computer Vision-Aided Disaster Response via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery - NeurIPS (FDL Europe 2018)

UNICEF-ESA-FDL - AI to automate disaster impact assessment - Concept Note - UNICEF (FDL Europe 2018)

Mapping Informal Settlements in Developing Countries with Multi-resolution, Multi-spectral Data - NeurIPS & AAAI (FDL Europe 2018) - ArXiv

Mapping Informal Settlements in Developing Countries using Machine Learning and Low Resolution Multi-spectral Data - AAAI/ACM Conference (FDL Europe 2018)

Generating Material Maps to Map Informal Settlements - NeurIPS & AAAI arXiv (FDL Europe 2018) - ArXiv

Mapping Informal Settlements in Developing Countries with Multi-resolution, Multi-spectral Data - NeurIPS & AAAI arXiv - (FDL Europe 2018) - ArXiv

Mapping Informal Settlements in Developing Countries using Machine Learning and Low Resolution Multi-spectral Data - AIES 19 (FDL Europe 2018)

Cumulo: A Dataset for Learning Cloud Classes - JPL NASA Abstract (FDL Europe 2019)

The Link of Tropical Convection and Low Cloud Cover - NeurIPS (FDL Europe 2019)

Classifying without Supervision but with Distributional Constraints - NeurIPS - (FDL Europe 2019)

Cumulo: A Dataset for Learning Cloud Classes - NeurIPS (FDL Europe 2019) Received best paper award - Arvix

Flood Detection on low cost orbital Software - NeurIPS (FDL Europe 2019)

FDL: Mission Support Challenge - NeurIPS - (FDL Europe 2019)

Learning from History: Scoring & Automating Spacecraft Constellation Schedules - SpaceOps (FDL Europe 2019)

AI for the Developing World, Self-supervised Learning Theory & Practice - NeurIPS 2021 (FDL Europe 2021)- Submitted

Mission Operations

Spacecraft Collision Risk Assessment with Probabilistic Programming - Neurips 2020 - AI for Earth Science (FDL Europe - 2020)

Towards Automated Satellite Conjunction Management with Bayesian Deep Learning - Neurips 2020 - ML4PhysicalSciences (FDL Europe 2020)

RainBench: Towards Global Precipitation Forecasting from Satellite Imagery - AAAI 2020, top-5 conference in CS (FDL Europe 2020)

Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery - Neurips 2020 - Tackling Climate Change with Machine Learning (FDL Europe 2020)

RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale - Neurips 2020 - Tackling Climate Change with Machine Learning (FDL Europe 2020)

Tracking Marine Boundary Layer Cloud Transitions Using Machine Learning - AGU 2020 (FDL Europe 2020)

ML Onboard

Smart satellites: machine learning on-board for low-latency ‘hot-spots’ detection - AGU 2021 (FDL Europe 2021)

Smart satellites: machine learning on-board for low-latency novelty detection - AGU 2021 (FDL Europe 2021)

Unsupervised change detection of extreme events using ML on-board - HADR.ai NeurIPS (FDL Europe 2021)