+Machine learning methodologies, particularly neural networks, are computer algorithms inspired by the structure and function of the human brain. These algorithms are capable of learning from data, identifying patterns, and making predictions or decisions without being explicitly programmed. Neural networks consist of interconnected nodes organized into layers, including input, hidden, and output layers. During training, they adjust the strength of connections between nodes, called weights, based on examples from a dataset, allowing them to learn complex patterns and relationships in the data. Neural networks are widely used in various applications, including image recognition, natural language processing, and climate modeling.
+
+
+
+
Machine learning for climate modeling
+
+Climate models often face challenges in representing complex processes of large-scale simulations. Machine learning presents innovative approaches to confront these obstacles. It provides new methodologies to learn missing model physics and model errors directly from data. Moreover, machine learning holds the potential to act as a feasible substitute for emulating the complete dynamics of models, thus offering an alternative to traditional climate modeling approaches. The next three paragraphs describe three applications of machine learning for climate modeling that are pursued within the M2LInES project.
+
+
+
+
+One of the key applications of machine learning in climate modeling is in parameterization learning. Parameterizations are used in climate models to represent subgrid-scale processes that are unresolved at the model's grid scale. Machine learning algorithms can be trained on high-resolution simulations to learn these parameterizations directly from data, enabling more accurate representation of complex physical processes such as clouds, precipitation, and turbulence.
+
+
Learning model error
+
+Machine learning algorithms can also be used to understand and correct biases that are due to the combined error of physics and numerics. One way to learn this combined error is to use analysis increments as a training dataset. Analysis increments represent the adjustments made to a model to bring it closer to observations during the data assimilation process. The information contained in analysis increments allows therefore for the development of correction schemes that improve the reliability and accuracy of model predictions.
+
+
Emulation of the full model dynamics
+
+Another important application of machine learning in climate modeling is the development of emulators. Climate model emulators are surrogate models that mimic the behavior of complex climate models. By capturing the essential features and relationships within the original models, emulators provide a computationally efficient alternative for exploring climate model outputs.
diff --git a/content/team/AlexisBarge.md b/content/team/AlexisBarge.md
index c51af169..155f55b8 100644
--- a/content/team/AlexisBarge.md
+++ b/content/team/AlexisBarge.md
@@ -2,7 +2,7 @@
title: "Alexis Barge"
draft: false
image: images/team/AlexisBarge.png
-jobtitle: "Research Engineer"
+jobtitle: "Affiliate"
promoted: true
Website:
weight: 34
diff --git a/content/team/CemGultekin.md b/content/team/CemGultekin.md
index 527e4518..e6e03280 100644
--- a/content/team/CemGultekin.md
+++ b/content/team/CemGultekin.md
@@ -2,7 +2,7 @@
title: "Cem Gultekin"
draft: false
image: "/images/team/CemGultekin.jpeg"
-jobtitle: "Graduate Student"
+jobtitle: "Affiliate"
promoted: true
weight: 20
Website:
diff --git a/content/team/AzizBhouri.md b/content/team/former/AzizBhouri.md
similarity index 100%
rename from content/team/AzizBhouri.md
rename to content/team/former/AzizBhouri.md
diff --git a/content/team/EmilyNewsom.md b/content/team/former/EmilyNewsom.md
similarity index 100%
rename from content/team/EmilyNewsom.md
rename to content/team/former/EmilyNewsom.md
diff --git a/data/tag_links.yml b/data/tag_links.yml
index 5e086bf7..aeb01c09 100644
--- a/data/tag_links.yml
+++ b/data/tag_links.yml
@@ -1,3 +1,6 @@
Ocean:
Climate:
-Machine Learning:
+Machine Learning: /blog/machinelearning
+Data Assimilation:
+Sea Ice:
+Atmosphere:
diff --git a/static/.DS_Store b/static/.DS_Store
index 973d7cad..f9317dbf 100644
Binary files a/static/.DS_Store and b/static/.DS_Store differ
diff --git a/static/images/machinelearning.md.html b/static/images/machinelearning.md.html
new file mode 100644
index 00000000..84b86d6a
--- /dev/null
+++ b/static/images/machinelearning.md.html
@@ -0,0 +1 @@
+
+