Course Catalog & Credential Pathway — Dwg. No. PF-002C
A field branch of the Construction Track, for students aimed at neural weather and climate modeling — the same architectures behind GraphCast and AIFS, pointed at the atmosphere instead of language.
Field branch of Dwg. No. PF-002, The Construction Track — same core sequence through Phase II, concentrated here into atmospheric physics & neural forecasting from Phase II onward. See also Dwg. No. PF-001, The Verification Track.
Five core strands, plus the domain strand this branch concentrates in
No frameworks yet, and no atmospheric physics yet either. Two years of straight math and programming fundamentals, identical to the core Construction Track.
Precalculus, Accelerated
Compressed to clear room for calculus by grade 11 — the standard on-ramp for anyone headed toward a quantitative degree.
Programming I — Python
Variables, control flow, functions, data structures. Fluency, not tricks.
Discrete Mathematics & Logic
Sets, proofs, graphs, combinatorics — the math CS theory actually runs on, usually skipped until it's overdue.
Technical Writing for Research
Writing a clear methods section and an honest results section — the two paragraphs every paper lives or dies on.
The math and CS sequences converge into an actual first model, same as the core track. The atmospheric-physics layer begins concurrently — by the end of Phase II a student can both train a small model and read a primitive-equations weather model without translation help.
Calculus I & II
Through multivariable and the gradient — backpropagation is the chain rule with bookkeeping, and it should read that way.
MATH 101
Linear Algebra
Vector spaces, eigendecomposition, matrix calculus. Every tensor operation is this course wearing a framework's syntax.
MATH 101
Probability & Statistics for ML
Distributions, estimation, Bayes — framed toward loss functions and uncertainty, not toward the social-science stats track.
Data Structures & Algorithms
Complexity analysis and the standard structures, drilled to fluency — still the baseline technical-interview bar at every AI lab.
CS 100
Intro to Machine Learning
Regression through a first neural net, built from array operations before any framework is allowed to hide the mechanics.
MATH 210, STAT 220
Research Seminar — Reading Group
Weekly seminal-paper reads (perceptron through transformers), presented and defended aloud, not just summarized.
Fluid Dynamics & Atmospheric Physics
Navier-Stokes fundamentals, thermodynamics of the atmosphere, and the primitive equations that every numerical weather model — and every neural emulator of one — is standing in for.
MATH 210 (concurrent)
Numerical Weather Prediction Fundamentals
Grid discretization, data assimilation, and ensemble forecasting as traditionally done — the baseline a neural weather model has to beat, and the diagnostic a graduate needs when it doesn't.
PHYS 225
Here the domain degree takes over from the general CS/applied-math track. An atmospheric science or applied-physics-plus-CS program replaces DEG 300 — the domain training is what a national weather service or climate lab actually hires against.
Atmospheric Science / Applied Physics Degree
Formal core in an atmospheric science or applied-physics-plus-CS program — the credential a national weather service or climate lab actually hires against.
Neural Weather & Climate Emulation
Graph neural network and transformer architectures for global forecasting — GraphCast and AIFS-style systems — plus the failure modes specific to extreme events that fall outside the training distribution.
CLI 235, ML 230
Deep Learning for Earth System Modeling
Graph neural networks and transformer architectures in depth, taught directly against the systems that made them famous in this field — GraphCast, AIFS — rather than as a generic survey.
ML 230
Systems for ML
Distributed training, GPU/accelerator programming, the infrastructure that turns a notebook model into one that trains at scale — the same infrastructure a global forecasting run needs.
CS 210
Supervised Research Practicum
Placement inside an operational forecasting or climate-modeling group, with a mentor of record. Graded on a reproduction that actually reproduces, or a contribution that gets merged.
RES 240, ML 310
Capstone — Build & Ship
One model or tool — a regional forecasting fine-tune, an extreme-event detector, a forecast-visualization service — taken from idea to a deployed, load-bearing artifact with real users.
ENG 320, RES 350
No end date: the ML baseline moves every conference cycle, and the physical-verification baseline — whether the fast neural forecast still agrees with a traditional numerical run on extreme events — moves on its own slower schedule that a purely computational graduate can lose track of.