Personal build, open source2024
A recurrent sequence model for climate time series — the problem shape behind any forecast that has to respect what came before it.
1
The problem
Time-series data punishes models that treat each row as independent. Order carries the signal, and a forecast is only useful if it respects it.
2
How it works
Climate observations are windowed into sequences and fed to an LSTM, which carries state across steps and predicts the next value from the pattern of the ones before it.
3
What it proves
Comfort with sequence modelling — the same instinct that decides whether a business problem is a lookup, a classification, or genuinely a forecast.
Built with
Modelling
TensorFlow / KerasLSTMNumPypandas
Losing hours to work an AI system could handle?
Tell me about the process. I'll tell you straight whether it's worth automating — no pitch, no obligation.
Book a call