RG: Machine Learning - Revision history

Svalluri: /* GEM 2026 */

2026-07-12T15:15:15Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-09T04:05:40Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-09T03:51:33Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-09T03:50:49Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-07T18:27:42Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-07T18:26:31Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-07T18:24:56Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-07T17:59:31Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-07T17:56:17Z

GEM 2026

Svalluri: /* GEM 2026 */

2026-07-07T17:54:51Z

GEM 2026

@@ Line 45: / Line 45: @@
 | 11:03–11:13 || Mike Coughlan || NASA GSFC || In-person || ML-FAC: Results and Validation of a New Field Aligned Current Model
 |-
-| 11:13–11:23 || Man Hua || Wuhan University || Virtual || Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
+| 11:13–11:23 || Sheng Tian || UCLA || Virtual || Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
 |-
 | 11:23–11:33 || Xiangning Chu || LASP || Virtual || Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt

@@ Line 87: / Line 87: @@
 '''Session 3: MLGEM/MPEC/GIC/MAC Joint Session  - Discussion'''
 ''' – July 15, 2026 (Wednesday, 1:30 PM – 3:00 PM)'''
 This interactive discussion session will focus on how artificial intelligence, data analysis, and physics-based modeling interact to support and advance magnetosphere–ionosphere coupling research. We invite modelers, data scientists, and researchers to share perspectives on current challenges and future opportunities.

@@ Line 32: / Line 32: @@
 {| class="wikitable"
-|+ Session 1 (Monday, 10:30 AM – 12:00 PM) - Tentative Schedule
+|+ Session 1 (Monday, 10:30 AM – 12:00 PM)
 ! Time !! Speaker !! Affiliation !! Mode !! Title
 |-
@@ Line 63: / Line 63: @@
 {| class="wikitable"
-|+ Session 2 (Monday, 1:30 PM – 3:00 PM) - Tentative Schedule
+|+ Session 2 (Monday, 1:30 PM – 3:00 PM)
 ! Time !! Speaker !! Affiliation !! Mode !! Title
 |-

@@ Line 22: / Line 22: @@
 The Machine Learning-based Geospace Environment Modeling (MLGEM) resource group is excited to announce one standalone session for general contributions and two joint sessions exploring magnetosphere-ionosphere coupling research at the upcoming GEM 2026 Workshop, which will be held from July 12-17 in Portland, ME, at the Holiday Inn By the Bay.
-Interested speakers are invited to submit presentation titles by '''July 6, 2026''' using the following link:
+'''Presentations are finalized.'''
 The session schedule and descriptions are provided below.
@@ Line 44: / Line 43: @@
 | 10:53–11:03 || James Edmond || Air Force Research Laboratory || In-person || A Semi-Supervised, Multi-modal Plasma Region Classification of Earth’s Cislunar Magnetotail using ARTEMIS Observations
 |-
-| 11:03–11:13 || Deep || CUA/NASA GSFC || In-person || Morphology-First One-Class Detection of Current Sheets in MMS Burst Data: A Surrogate Library Anchored to a Single Reference Event
+| 11:03–11:13 || Mike Coughlan || NASA GSFC || In-person || ML-FAC: Results and Validation of a New Field Aligned Current Model
 |-
-| 11:13–11:23 || Mike Coughlan || NASA GSFC || In-person || ML-FAC: Results and Validation of a New Field Aligned Current Model
+| 11:13–11:23 || Man Hua || Wuhan University || Virtual || Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
 |-
-| 11:23–11:33 || Man Hua || Wuhan University || Virtual || Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
+| 11:23–11:33 || Xiangning Chu || LASP || Virtual || Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt
 |-
-| 11:33–11:43 || Xiangning Chu || LASP || Virtual || Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt
+| 11:33–11:43 || Jing Lao || UNH || In-person || Investigation of the Ring Current Pressure Response during CME and SIR storms using Machine Learning Model
 |-
-| 11:43–11:53 || Jing Lao || UNH || In-Person || Investigation of the Ring Current Pressure Response during CME and SIR storms using Machine Learning Model
+| 11:43–11:53 || Evan Thomas || Dartmouth College || In-person || Ensemble SuperDARN Convection Modeling
 |-
 | 11:53–12:00 || || || || Closing discussion
 |}
 '''Session 2: MLGEM/MPEC/GIC/MAC Joint Session - Presentations'''
@@ Line 68: / Line 68: @@
 | 1:30–1:33 || || || || Opening remarks / session introduction
 |-
-| 1:33–1:45 || Connor O'Brien || JHUAPL || In-person || Estimating Solar Wind Uncertainty in Coupled Geospace Models with ML-derived Solar Wind Ensembles
+| 1:33–1:44 || Connor O'Brien || JHUAPL || In-person || Estimating Solar Wind Uncertainty in Coupled Geospace Models with ML-derived Solar Wind Ensembles
 |-
-| 1:45–1:57 || Brendan Powers || University of Iowa || In-person || Bursty Bulk Flow Identification with Machine Learning
+| 1:44–1:55 || Brendan Powers || University of Iowa || In-person || Bursty Bulk Flow Identification with Machine Learning
 |-
-| 1:57–2:09 || Raman Mukundan || University of New Hampshire || In-person || Contributions from the Solar Wind and Magnetospheric Processes to Localized Geomagnetic Disturbances
+| 1:55–2:06 || Raman Mukundan || University of New Hampshire || In-person || Contributions from the Solar Wind and Magnetospheric Processes to Localized Geomagnetic Disturbances
 |-
-| 2:09–2:21 || Sai Gowtam Valluri || NASA GSFC/CUA || Virtual || Validating the Auroral Boundaries Predicted by the ML-based Electron Precipitation Model
+| 2:06–2:17 || Sai Gowtam Valluri || NASA GSFC/CUA || Virtual || Validating the Auroral Boundaries Predicted by the ML-based Electron Precipitation Model
 |-
-| 2:21–2:33 || Hyunju Connor || NASA GSFC || In-person || AIMFAHR: Integrating Data-Driven Geospace Models for Space Weather Research and Operations
+| 2:17–2:28 || Hyunju Connor || NASA GSFC || In-person || AIMFAHR: Integrating Data-Driven Geospace Models for Space Weather Research and Operations
 |-
-| 2:33–2:45 || Evan Thomas || Dartmouth College || In-person || Ensemble SuperDARN Convection Modeling
+| 2:28–2:39 || Kawther Rouabhi || University of Colorado Boulder || In-person || ML Analysis of Multi-Year DMSP Data Sets: Estimation of Auroral Electron Energy Flux Spectra from Multispectral FUV Satellite Imagery
 |-
-| 2:45–2:57 || Kawther Rouabhi || University of Colorado Boulder || In-person || ML Analysis of Multi-Year DMSP Data Sets: Estimation of Auroral Electron Energy Flux Spectra from Multispectral FUV Satellite Imagery
+| 2:39–2:50 || Dogacan Ozturk || UAF || In-person || Insights into the Electrodynamic Properties and Thermospheric Impacts of Meso-Scale Auroral Morphologies Through Self-Supervised Learning
 |-
-| 2:57–3:00 || || || || Closing discussion
+| 2:50–3:00 || Soumyajit Dey || University of South Alabama || In-person || Identification of Isolated Substorms Using WINDMI: A Physics-based Magnetosphere-Ionosphere Model
 |}

@@ Line 52: / Line 52: @@
 | 11:33–11:43 || Xiangning Chu || LASP || Virtual || Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt
 |-
-| 11:43–11:53 || Jing Lao || UNH || TBA || Investigation of the Ring Current Pressure Response during CME and SIR storms using Machine Learning Model
+| 11:43–11:53 || Jing Lao || UNH || In-Person || Investigation of the Ring Current Pressure Response during CME and SIR storms using Machine Learning Model
 |-
 | 11:53–12:00 || || || || Closing discussion

@@ Line 38: / Line 38: @@
 | 10:30–10:33 || || || || Opening remarks / session introduction
 |-
-| 10:33–10:45 || Grant Stephens || JHU/APL || In-person || From Research Model to Community Resource: Building the ARGUS Ecosystem for Empirical Geomagnetic Field Reconstruction
+| 10:33–10:43 || Grant Stephens || JHU/APL || In-person || From Research Model to Community Resource: Building the ARGUS Ecosystem for Empirical Geomagnetic Field Reconstruction
 |-
-| 10:45–10:57 || Savvas Raptis || JHU/APL || In-person || Machine Learning Modeling of Earth’s Plasma Sheet using Multi-Spacecraft Observations
+| 10:43–10:53 || Savvas Raptis || JHU/APL || In-person || Machine Learning Modeling of Earth’s Plasma Sheet using Multi-Spacecraft Observations
 |-
-| 10:57–11:09 || James Edmond || Air Force Research Laboratory || In-person || A Semi-Supervised, Multi-modal Plasma Region Classification of Earth’s Cislunar Magnetotail using ARTEMIS Observations
+| 10:53–11:03 || James Edmond || Air Force Research Laboratory || In-person || A Semi-Supervised, Multi-modal Plasma Region Classification of Earth’s Cislunar Magnetotail using ARTEMIS Observations
 |-
-| 11:09–11:21 || Deep || CUA/NASA GSFC || In-person || Morphology-First One-Class Detection of Current Sheets in MMS Burst Data: A Surrogate Library Anchored to a Single Reference Event
+| 11:03–11:13 || Deep || CUA/NASA GSFC || In-person || Morphology-First One-Class Detection of Current Sheets in MMS Burst Data: A Surrogate Library Anchored to a Single Reference Event
 |-
-| 11:21–11:33 || Mike Coughlan || NASA GSFC || In-person || ML-FAC: Results and Validation of a New Field Aligned Current Model
+| 11:13–11:23 || Mike Coughlan || NASA GSFC || In-person || ML-FAC: Results and Validation of a New Field Aligned Current Model
 |-
-| 11:33–11:45 || Man Hua || Wuhan University || Virtual || Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
+| 11:23–11:33 || Man Hua || Wuhan University || Virtual || Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
 |-
-| 11:45–11:57 || Xiangning Chu || LASP || Virtual || Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt
+| 11:33–11:43 || Xiangning Chu || LASP || Virtual || Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt
 |-
-| 11:57–12:00 || || || || Closing discussion
+| 11:43–11:53 || Jing Lao || TBA || TBA || TBA
 |}

@@ Line 33: / Line 33: @@
 {| class="wikitable"
-|+ Session 1 – General Contributions (Monday, 10:30 AM – 12:00 PM)
+|+ Session 1 – General Contributions (Monday, 10:30 AM – 12:00 PM) Tentative Schedule
 ! Time !! Speaker !! Affiliation !! Mode !! Title
 |-
@@ Line 58: / Line 58: @@
 ''' – July 13, 2026 (Monday, 1:30 PM – 3:00 PM)'''
-This joint session will highlight machine learning research relevant to the Magnetosphere-Ionosphere Coupling community. Topics may include the use of AI/ML techniques to investigate coupling processes, improve event detection and prediction, analyze large and complex datasets, enhance scientific understanding, and uncover new insights into the coupled geospace system.
+{| class="wikitable"
 '''Session 3: MLGEM/MPEC/GIC/MAC Joint Session  - Discussion'''

← Older revision		Revision as of 17:54, 7 July 2026
Line 31:		Line 31:

	This session will provide a dedicated forum for researchers to present the latest advances in machine learning applications for geospace and environmental modeling. We encourage submissions covering novel methodologies, scientific discoveries enabled by AI/ML, operational nowcast and forecast models, foundation models, uncertainty quantification, and other emerging machine learning technologies relevant to geospace science.		This session will provide a dedicated forum for researchers to present the latest advances in machine learning applications for geospace and environmental modeling. We encourage submissions covering novel methodologies, scientific discoveries enabled by AI/ML, operational nowcast and forecast models, foundation models, uncertainty quantification, and other emerging machine learning technologies relevant to geospace science.
		+
		+	{\| class="wikitable"
		+	\|+ Session 1 – General Contributions (Monday, 10:30 AM – 12:00 PM)
		+	! Time !! Speaker !! Affiliation !! Mode !! Title
		+	\|-
		+	\| 10:30–10:33 \|\| \|\| \|\| \|\| Opening remarks / session introduction
		+	\|-
		+	\| 10:33–10:45 \|\| Grant Stephens \|\| JHU/APL \|\| In-person \|\| From Research Model to Community Resource: Building the ARGUS Ecosystem for Empirical Geomagnetic Field Reconstruction
		+	\|-
		+	\| 10:45–10:57 \|\| Savvas Raptis \|\| JHU/APL \|\| In-person \|\| Machine Learning Modeling of Earth’s Plasma Sheet using Multi-Spacecraft Observations
		+	\|-
		+	\| 10:57–11:09 \|\| James Edmond \|\| Air Force Research Laboratory \|\| In-person \|\| A Semi-Supervised, Multi-modal Plasma Region Classification of Earth’s Cislunar Magnetotail using ARTEMIS Observations
		+	\|-
		+	\| 11:09–11:21 \|\| Deep \|\| CUA/NASA GSFC \|\| In-person \|\| Morphology-First One-Class Detection of Current Sheets in MMS Burst Data: A Surrogate Library Anchored to a Single Reference Event
		+	\|-
		+	\| 11:21–11:33 \|\| Mike Coughlan \|\| NASA GSFC \|\| In-person \|\| ML-FAC: Results and Validation of a New Field Aligned Current Model
		+	\|-
		+	\| 11:33–11:45 \|\| Man Hua \|\| Wuhan University \|\| Virtual \|\| Artificial Neural Network for Inner Magnetospheric Electric Fields (ANNIE) Model
		+	\|-
		+	\| 11:45–11:57 \|\| Xiangning Chu \|\| LASP \|\| Virtual \|\| Imbalanced Regressive Neural Network Model for Relativistic Electrons in the Outer Radiation Belt
		+	\|-
		+	\| 11:57–12:00 \|\| \|\| \|\| \|\| Closing discussion
		+	\|}

	'''Session 2: MLGEM/MPEC/GIC/MAC Joint Session - Presentations'''		'''Session 2: MLGEM/MPEC/GIC/MAC Joint Session - Presentations'''