Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3382425

Scalable multiplexed machine learning gas sensor chips for food classification

Bassil, Carla [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000087688976)·Lee, Kichul [University of California, Berkeley, CA (United States); Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0000000278386447)·Liao, Xun [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000185381599)·Krishnan, Divya [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)]·Zhan, Yifei [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000989744738)·Wijaya, Theodorus Jonathan [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000339470029)·Hester, Edward [University of California, Berkeley, CA (United States)]·Kim, Minhyun [Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0009000988246606)·Kim, Il-Doo [Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0000000299702218)·Park, Inkyu [Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0000000157617739)·Javey, Ali [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Kavli Energy NanoScience Institute, Berkeley, CA (United States)] (ORCID:0000000172147931)
View original source ↗Read source document ↗Export metadata ↓

Abstract

Multiplexed gas sensor arrays combined with machine learning have unlocked previously inaccessible applications for scent-based sensing. Current platforms are limited by overlapping sensing materials with similar compositions, leading to highly correlated responses, or multistep deposition processes that hinder scalability. In this work, we developed a 16-element monolithic chip with fully distinct sensing layers, enabling a truly heterogeneous array. The system consists of highly sensitive carbon nanotube field effect transistors that are functionalized through a single-step microdispensing method compatible with automated pipetting systems. The resulting chip produces characteristic signal patterns in response to object-specific scent profiles and, when combined with machine learning algorithms, can perform automated object identification. We demonstrate the classification of 16 different objects, including food spoilage and nut allergens, with a 92.6% overall prediction accuracy.

Keep this discovery

BibTeXRIS

Bassil, Carla [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000087688976), Lee, Kichul [University of California, Berkeley, CA (United States); Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0000000278386447), Liao, Xun [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000185381599), Krishnan, Divya [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Zhan, Yifei [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0009000989744738), Wijaya, Theodorus Jonathan [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000339470029), Hester, Edward [University of California, Berkeley, CA (United States)], Kim, Minhyun [Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0009000988246606), Kim, Il-Doo [Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0000000299702218), Park, Inkyu [Korea Advanced Institute Science and Technology (KAIST), Daejeon (Korea, Republic of)] (ORCID:0000000157617739), Javey, Ali [University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Kavli Energy NanoScience Institute, Berkeley, CA (United States)] (ORCID:0000000172147931). 2026-06-19. Scalable multiplexed machine learning gas sensor chips for food classification. https://doi.org/10.1126/sciadv.aec7965

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

NASA NTRSDate not supplied

Toward Large Field-of-view X-ray Spectrometers with Magnetic Microcalorimeters

A future X-ray telescope mission like Lynx, a X-ray flagship mission concept, requires a large field of view, high energy resolution, and high spatial resolution. The Magnetic Microcalorimeter (MMC) detectors we are developing for such a mission feature a 5-arcminute field of view, approximately 100,000 pixels, each spanning 0.5–1 arcsecond. These detectors require the readout of 8,000 sensors. Three different array types have been designed to meet scientific goals, two of which utilize thermal multiplexing to reduce the number of readout channels in a scheme called “Hydra.” We are currently fabricating detectors on a recently completed buried wiring wafer with connections to every sensor. The sensors are read out using a microwave multiplexer (μMUX) with flux ramp modulation. A single μMUX can read out approximately 1,000 sensors with only two feed lines. We will report on the test of the first two-dimensional μMUX chip, consisting of 78 resonators. μMUX chips that pass screening will be directly bonded to MMC array chips using indium bump bonding. In parallel, we have tested a kinetic inductance traveling wave parametric amplifier (KI-TWPA) to amplify signals at low temperatures. The KI-TWPA exhibits extremely low internal noise, approaching the standard quantum limit. Since the energy resolution of an MMC is primarily limited by the readout system, the KI-TWPA is an ideal amplifier for MMCs with μMUX readout. We recently measured the readout noise of a μMUX with a KI-TWPA, demonstrating its capability for reading out MMC arrays. We present the design and fabrication of the latest MMC detectors, along with its readout performance.

Magntic Microcalorimeters↗
DOE OSTI2026

Mode Multiplexing for Scalable Cavity-Enhanced Operations in Neutral-Atom Arrays

Neutral-atom arrays provide a versatile platform for quantum information processing. However, in large-scale arrays, efficient photon collection remains a bottleneck for key tasks such as fast, nondestructive qubit readout and remote entanglement distribution. We propose a cavity-based approach that enables fast, parallel operations over many atoms using multiple modes of a single optical cavity. By selectively shifting the relevant atomic transitions, each atom can be coupled to a distinct cavity mode, allowing independent simultaneous processing. We present practical system designs that support cavity-mode multiplexing with up to 50 modes, enabling rapid mid-circuit syndrome extraction and significantly enhancing entanglement distribution rates between remote atom arrays. This approach offers a scalable solution to core challenges in neutral-atom arrays, advancing the development of practical quantum technologies.

Aqua, Ziv [Massachusetts Institute of Technology (↗
NASA NTRSDate not supplied

Autonomous Detection and Classification of Lunar Minerals Using a Convolutional Neural Network Based Framework for the SUCR DALI Project

NASA’s long-term goal is to deploy humans to the Moon and, from there, advance human exploration to Mars, with Artemis missions as pivotal milestones. Raman spectroscopy can uniquely identify minerals, compounds, water states, and other materials, providing distinctive fingerprints for classification. A Raman instrument has been successfully deployed and utilized on the Mars surface via the Perseverance rover, but has not yet been utilized at the lunar surface The SUCR DALI project is working towards developing a Raman spectroscopy instrument to be applied in various lunar mission concepts, including within the Artemis program. The objective of my research is to assist in the maturation of the proposed SUCR DALI lunar Raman instrument through the development of an autonomous detection and classification model capable of identifying minerals and water states on the Moon’s surface.

Convolutional Neural Networks↗