Machine Learning and Instrument Autonomy Group

The Machine Learning and Instrument Autonomy strives to research, develop, and infuse data driven solutions built with applied Machine Learning and related technologies to support the exploration of Earth & Space and the advancement of science. MLIA is enabling data science approach for JPL’s past and future missions, such as OCO-2/3, SBG, Europa Clipper, NISR, and M2020.

Focus Areas

Instrument Autonomy Science Serving Data Science
Content-based Search Science Understanding / Insight Generation
Data Triage and Down-link Prioritization Interpretable Models
Knowledge Compression and Summarization ML Uncertainty Awareness
Change and Novelty Detection Data Exploration & Discovery

How We Work

MLIA works in tandem with instrument and mission PI’s and scientists across JPL. Typically, collaborations start with short, non-committal brain storming sessions to explore new challenges, determine whether data-driven solutions would be appropriate, and recommend approaches with the most promise . Next, we partner to draft a proposal targeting either internal (SRTD, TRTD, JNEXT) or external (ROSES, AIST, ACCESS) funding opportunities. Once funding is secured, collaborative research can begin. Together with our partners, we use data science approaches to explore and understand the data, develop simple interpretable models, and generate insight. As needed and only as much as necessary, we incorporate increasingly sophisticated technology to achieve the project goals. However, even when using cutting-edge approaches like deep learning, we strive to extract as much insight as feasible into the original data, the behavior and capability of the model, and the key drivers of uncertainty and bias.

Contact

Want to collaborate or do some quick brainstorming together?

Want to join our team? We are looking for new colleagues that know how to generate insight from complex data, have experience with UQ, or demonstrated how to merge physical and statistical models.

Please reach out to Dr. Lukas Mandrake.

Recent News

  • ▸ February 28th, 2023 by Mark Wronkiewicz

    A presentation by Mark Wronkiewicz during the Labelbox Accelerate conference was recapped in a Labelbox blog post. The post describes work by the SUDS Martian Frost team Umma Rebbapragada (co-PI), Serina Diniega (co-PI), Gary Doran, Steven Lu, and Jake Widmer to create a global, monthly map of frost on the Martian surface. The blog post specifically highlights the team’s approach to producing high-quality annotated data, which involves using consensus scores, over-labeling to capture contextual metadata, and creating a thorough labeling guide.

    Read more...

  • ▸ February 21st, 2023 by Philip Brodrick

    Phil Brodrick published a paper led by Nimrod Carmon entitled “Shape from Spectra”. The paper demonstrates the potential to retrieve structural information from the surface from imaging spectroscopy data, paving the way for more sophisticated and accurate surface reflectance retrievals.

    Read more...

  • ▸ February 21st, 2023 by Philip Brodrick

    Phil Brodrick led the design and launch of EMIT VISIONS: the VSWIR Imaging Spectroscopy Interface for Open Science. The platform is an interactive experience of EMIT data by users, and brings together MMGIS (NASA AMMOS), the LP DAAC, and the EMIT-SDS in order to allow users to explore EMIT data and to increase accessibility.

    Read more...

  • ▸ January 23rd, 2023 by Mario Damiano

    Mario Damiano as part of the JWST Transiting Exoplanet Community Early Release Science Team has published on Nature the paper “Early Release Science of the Exoplanet WASP-39b with JWST NIRCam”. Mario Damiano contributed to the data analysis described in the paper.

    Read more...