{"id":352,"date":"2026-11-12T07:03:28","date_gmt":"2026-11-12T12:03:28","guid":{"rendered":"https:\/\/blogs.mathworks.com\/engineering\/?p=352"},"modified":"2026-11-12T07:03:28","modified_gmt":"2026-11-12T12:03:28","slug":"agentic-ai-for-climate-data-in-matlab","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/engineering\/2026\/11\/12\/agentic-ai-for-climate-data-in-matlab\/","title":{"rendered":"Agentic AI for Climate Data in MATLAB"},"content":{"rendered":"

<\/p>\n

\n
\"Kostas<\/div>\n
\n

Guest blogger: <\/strong>Kostas Leptokaropoulos<\/strong><\/a><\/p>\n

Kostas is the MathWorks Geoscience Academic Manager, supporting Geoscience researchers and educators. He is also a visiting lecturer at Aristotle University of Thessaloniki (AUTH).
\nIn this blog, he describes his experience working with Agentic AI for geoscience data.<\/p>\n<\/div>\n<\/div>\n

\n

I have been experimenting with coding Agents for my geoscience data <\/span><\/h2>\n
If you\u2019re not familiar with Agentic AI yet, this resource [<\/span>Guide to Agentic AI with MATLAB and Simulink<\/span><\/a>] gives some useful background.<\/span><\/div>\n
When I approach geoscience problems, I often do so by building computational tools. These tools let me interact with the data and draw scientific conclusions. They also let colleagues who are less familiar with programming do the same.<\/span><\/div>\n
If you\u2019ve ever been the \u201ccomputation person\u201d in your lab, you\u2019ll know that developing such tools can take hours, or even days! Using an Agent, I can speed up the process of creating these custom tools. That lets me (and my colleagues) spend more time thinking about the science rather than the coding. <\/span><\/div>\n

My goal is to build a climate data app <\/span><\/h2>\n
A lot of my colleagues often want to interface with data, but don’t want to directly interact with the code. So for my work, building apps like this is common practice. <\/span><\/div>\n
Before I even start building it, I already have a clear idea in my mind what the end state looks like and I am accelerating the development process with Agentic tools.<\/span><\/div>\n
What I want to get is a visual interface where I can import and visualize climate data and export my selections at the end.<\/span><\/div>\n
I downloaded climate data from <\/span>Copernicus<\/span> in NetCDF (.nc) format and saved the folder into my working directory as “<\/span>Copernicus_Data”<\/span>: <\/span>ORAS5 global ocean reanalysis monthly data from 1958 to present<\/span><\/a>. This data contains information on global ocean and sea-ice reanalysis. If you want to learn more about NetCDF, <\/span>this is a useful resource<\/span><\/a>. <\/span><\/div>\n
\"\"<\/img><\/div>\n
Normally, I would first inspect the NetCDF structure, identify the relevant variables and dimensions, write the code to read and visualize them, add controls for interactive exploration, and then refine the figures and export workflow. None of these steps is particularly unusual, but putting them together into a useful tool takes time. For me, MATLAB is a natural environment for this work because I can explore the data, analyze it, visualize it and build an interactive workflow all in the same place. These are some of the functions I normally use for working with netCDF [<\/span>netCDF – Functions<\/span><\/a>].<\/span><\/div>\n
In this experiment, I wanted to see how much of that implementation work I could automate using a coding Agent (I am using Codex, but other Agentic tools can work too) while keeping control of the scientific choices myself. Because the Agent is working directly with MATLAB, I can build upon the tools and functions I already use, while still ending up with MATLAB code that I can inspect, modify and rerun. For this functionality I am using <\/span>MATLAB Agentic Toolkit<\/span><\/a>. <\/span><\/div>\n
<\/span><\/div>\n

Teaching my Agent how to do Geoscience in MATLAB<\/span> <\/span><\/h2>\n
I created a markdown file (init.md) in which I outlined:<\/span><\/div>\n
1) General approach 2) MATLAB execution 3) netCDF conventions 4) what the deliverable should be<\/span><\/div>\n
I highlighted key MATLAB functions that I know will be useful, what type of projection to use, as well as naming conventions. <\/span><\/div>\n