Publications and AGU

Author: nikudarafshi

content/Blog/AGU23.md

@@ -0,0 +1,62 @@
+---
+title: "DataWave at AGU 2023"
+date: 2023-12-18
+author: "Niku Darafshi"
+featured: true
+draft: false
+weight: 20
+location: "San Francisco"
+featured_image:: '/images/wave.jpeg'
+
+---
+{{< rawhtml >}}
+<div>
+<img src="/Blog/images/Datawave_AGU.png" alt="image" style=";width:100%;height:100%">
+
+<p> Between Dec. 11th - Dec. 15th, twelve members of the DataWave group came together for the 2023 AGU conference in San Francisco.
+</p>
+</div>
+{{< /rawhtml >}}
+<!--more-->
+{{< rawhtml >}}
+<div>
+Throughout the week, affiliates of our group presented new research and chaired different sessions. Below is a list of DataWave presenters and their respective research titiles. Please feel free to reach out to a presenter if you are interested in talking more about their work.
+</p>
+ <h4> AGU DataWave Presentations: </h4> 
+</p>
+"Machine Learning Subgrid-Scale Parameterizations for Earth System Modeling," Session, Conveners: <b>Laura Mansfield</b> & <b>Minah Yang</b>.
+<p>
+"Extratropical Large-Scale Atmospheric Circulation Variability," Session, Conveners: <b>Aman Gupta</b>, <b>Pedram Hassanzadeh</b>, & <b>Aditi Sheshadri</b>.
+<p>
+"Influence of obstacle effect on convectively generated gravity wave drag in the lowermost stratosphere," Talk, <b>Martina Bramberger</b>.
+<p>
+"Can AI-based climate models learn rare, extreme weather events?," Talk, <b>Pedram Hassanzadeh</b>.
+<p>
+"Explainable Offline-Online Training of Neural Networks for Parameterization: A 1D Gravity Wave-QBO Testbed," Talk, <b>Hamid Pahlavan</b>.
+</p>
+"Balloon Borne Observation of Tropical Gravity Waves: Phase Speed and Vector Momentum Flux," Talk, <b>Milena Corcos</b>.
+<p>
+"Understanding instabilities of neural weather models: Towards seamless weather to climate prediction," Talk, <b>Ashesh Chattopadhyay</b>.
+<p>
+"A framework for stability and convergence analysis of deep neural solvers for multi-scale nonlinear PDEs," Talk, <b>Pedram Hassanzadeh</b>.
+<p>
+"Extracting Gravity Waves from a Multi-year Global High Resolution Simulation using Spectral Filters," Poster, <b>Minah Yang</b>.
+<p>
+"Inertia-Gravity Wave Energy Spectra and Propagation Directions Estimated from Loon Balloon Data," Poster, <b>Brian Green</b>.
+</p>
+"Uncertainty Quantification of a Machine Learning Gravity Wave Parameterization," Poster, <b>Laura Mansfield</b>.
+</p>
+"Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges," Poster, <b>Karan Jakhar</b>.
+<p>
+"Utilizing Bayesian History Matching for the calibration of a gravity wave parameterization," Poster, <b>Robert King</b>.
+</p>
+"Non-local Machine Learning-based Gravity Wave Parameterization Trained on a Kilometer-scale Global Climate Model," Poster, <b>Aman Gupta</b>.
+</p>
+"Using Loon to systematically observe horizontal gravity wave properties," Poster, <b>Isabella Dula</b>.
+</p>
+"Revisiting Stratospheric Eddy Diffusivity Using New Observational Capabilities," Poster, <b>Catherine Wilka</b>.
+</p>
+"Importance of Internal Gravity Waves to Global Stratospheric Variability and Climatology as Revealed by ERA5," Poster, <b>Aman Gupta</b>.
+</p>
+
+{{< /rawhtml >}}

content/Blog/images/Datawave_AGU.png

@@ -0,0 +1,18 @@
+---
+date: 2023-11-23
+description: " "
+featured_image: "/images/Data_Images/Hardiman_ML.png"
+title: "Machine Learning for Nonorographic Gravity Waves in a Climate Model"
+title2: " "
+---
+## Authors:
+***Steven Hardiman***, ***Adam Scaife***, Annelize Niekerk, Rachel Prudden, Aled Owen, Samantha Adams, Tom Dunstan, Nick Dunstone, and Sam Madge
+
+[Read the full paper here](https://doi.org/10.1175/AIES-D-22-0081.1)
+## Abstract:
+There is growing use of machine learning algorithms to replicate subgrid parameterization schemes in global climate models. Parameterizations rely on approximations; thus, there is potential for machine learning to aid improvements. In this study, a neural network is used to mimic the behavior of the nonorographic gravity wave scheme used in the Met Office climate model, important for stratospheric climate and variability.
+<!--more-->
+The neural network is found to require only two of the six inputs used by the parameterization scheme, suggesting the potential for greater efficiency in this scheme. Use of a one-dimensional mechanistic model is advocated, allowing neural network hyperparameters to be chosen based on emergent features of the coupled system with minimal computational cost, and providing a testbed prior to coupling to a climate model. A climate model simulation, using the neural network in place of the existing parameterization scheme, is found to accurately generate a quasi-biennial oscillation of the tropical stratospheric winds, and correctly simulate the nonorographic gravity wave variability associated with El Niño–Southern Oscillation and stratospheric polar vortex variability. These internal sources of variability are essential for providing seasonal forecast skill, and the gravity wave forcing associated with them is reproduced without explicit training for these patterns.
+
+## Significance Statement:
+Climate simulations are required for providing advice to government, industry, and society regarding the expected climate on time scales of months to decades. Machine learning has the potential to improve the representation of some sources of variability in climate models that are too small to be directly simulated by the model. This study demonstrates that a neural network can simulate the variability due to atmospheric gravity waves that is associated with El Niño–Southern Oscillation and with the tropical and polar regions of the stratosphere. These details are important for a model to produce more accurate predictions of regional climate.

content/Publications/Papers/ML_nonorographic_Hardiman.md

@@ -32,8 +32,8 @@ description: "Meet the Team"
       name="Claudia Stephan "
       title="Head of Task 2"
       role="High-resolution Model Simulations of Gravity Waves"
-      website="https://mpimet.mpg.de/en/staff/claudia-stephan"
-      institute="Group Leader, Max Planck Institute for Meteorology"
+      website="https://www.iap-kborn.de/home/"
+      institute="Prof., Leibniz Institute of Atmospheric Physics"
       workdesc="High-resolution model simulations with the ICON model to study the generation of gravity waves by orographic and convective sources, and their three-dimensional resolved propagation through the atmosphere." >}}
 
 <!-- name="Ulrich Achatz" -->
@@ -53,7 +53,7 @@ description: "Meet the Team"
       title="Co-Head of Task 4"
       role=" Machine Learning-based Parameterization of Gravity Waves "
       website="http://pedram.rice.edu/director/"
-      institute="Assistant Prof., Rice University"
+      institute="Assistant Prof., University of Chicago"
       workdesc="Turbulent flows using numerical, mathematical, statistical, and machine learning methods, guided by observational and experimental data." >}}
 
 <!-- name="Alberto Arribas" -->
@@ -203,15 +203,15 @@ description: "Meet the Team"
     institute="NYU"
     workdesc="Geophysical Fluid Dynamics" >}}
 
- <!--  Laura Köhler  -->
+ <!--  Yanmichel Morfa  -->
  {{< Profile_Creator  
-    imgpath="/images/team/Laura_Kohler.jpg"
-    name="Laura Köhler"
+    imgpath="/images/team/Raj_Rani.jpg"
+    name="Yanmichel Morfa-Avalos"
     title="Postdoctoral Researcher"
     role=""
-    website="https://mpimet.mpg.de/en/science/independent-research-groups/cloud-wave-coupling"
-    institute="MPI"
-    workdesc="High-resolution global ICON simulations for training and assessing ML approaches on GW, comparison of superpressure balloon data with the models." >}}
+    website="https://www.iap-kborn.de/home/"
+    institute="Leibniz Institute of Atmospheric Physics"
+    workdesc="" >}}
 
 <!--  Laura	Mansfield  -->
 {{< Profile_Creator  
@@ -355,6 +355,16 @@ description: "Meet the Team"
   institute=" NYU "
   workdesc=" " >}}
 
+ <!--  Laura Köhler  
+ {{< Profile_Creator  
+    imgpath="/images/team/Laura_Kohler.jpg"
+    name="Laura Köhler"
+    title="Postdoctoral Researcher"
+    role=""
+    website="https://mpimet.mpg.de/en/science/independent-research-groups/cloud-wave-coupling"
+    institute="MPI"
+    workdesc="High-resolution global ICON simulations for training and assessing ML approaches on GW, comparison of superpressure balloon data with the models." >}} -->
+
 <!--  Aled Owen  
 {{< Profile_Creator  
   imgpath="/images/team/Aled_Owen.jpg"