Which of the following descriptions best represent the overarching design of your forecasting model?
- Machine learning-based weather prediction.
What techniques did you use to initialise your model? (For example: data sources and processing of initial conditions)
1- Data used: The three inputs (pressure, precipitation, and temperature), that are readily available for downloading as provided by ECMWF.
2- The initial condition is made by running the LSTM with the three inputs for the previous 28 days from the time of prediction.
If any, what data does your model rely on for real-time forecasting purposes?
pressure, precipitation, and temperature
What types of datasets were used for model training? (For example: observational datasets, reanalysis data, NWP outputs or satellite data)
only observational datasets
Please provide an overview of your final ML/AI model architecture (For example: key design features, specific algorithms or frameworks used, and any pre- or post-processing steps)
for each grid-cell, three lstms crunch the time-series of the inputs (pressure, precipitation, and temperature) and the output of all the lstms are passed to a feed-forward network, with hope to capture teleconnection effects. The output layer has dimensions (3 x #grid-cells) .
Have you published or presented any work related to this forecasting model? If yes, could you share references or links?
No
Before submitting your forecasts to the AI Weather Quest, did you validate your model against observational or independent datasets? If so, how?
No
Did you face any challenges during model development, and how did you address them?
No
Are there any limitations to your current model that you aim to address in future iterations?
Yes, we would like to add a new model and improve our current model to capture temperature and pressure more accurately.
Are there any other AI/ML model components or innovations that you wish to highlight?
No
Who contributed to the development of this model? Please list all individuals who contributed to this model, along with their specific roles (e.g., data preparation, model architecture, model validation, etc) to acknowledge individual contributions.
Mehrdad Mohannazadeh: model development and structuring the forecast chain
Ehsan Modiri: pre and post processing of inputs/forcing and structuring the forecast chain