TAICHI
Member
First name (team leader)
Yu
Last name
Wang
Organisation name
Nanjing University
Organisation type
Academic (Student)
Organisation location
China
Models
Please note that the model information below reflects the latest details provided by the team and does not show previous versions. Only the model summary questionnaires retain a submission history.
Model name
TAICHIAI
Model type
Hybrid
Number of individuals supporting model development:
1-5
Maximum number of Central Processing Units (CPUs) supporting model development or forecast production:
8-48
Maximum number of Graphics Processing Units (GPUs) supporting model development or forecast production:
< 4
How would you best classify the IT system used for model development or forecast production:
Single node system
Model summary questionnaire for model TAICHIAI
The list below shows all model summary questionnaires submitted for this model. Participants may submit an updated questionnaire whenever their methodology changes.
Questionnaires are displayed from the most recent to the earliest, with the latest version opened by default.
Which of the following descriptions best represent the overarching design of your forecasting model?
- Machine learning-based weather prediction.
- Hybrid model that integrates physical simulations with machine learning or statistical techniques.
What techniques did you use to initialise your model? (For example: data sources and processing of initial conditions)
Based on climate dynamics and climate predictability, I have designed a hybrid physical-statistical and AI prediction model. For this prediction, my target is weekly averages or weekly accumulations. That is, I first process the data into weekly averages, then transform them into anomalous relative tendencies using online time-scale separation. Next, I use various large-scale circulation patterns as predictors to extract the large-scale climate modes that influence the anomalous relative tendencies of regional climate elements. By leveraging historical data, I establish relationships between these climate modes and the regional climate elements. Finally, I generate AI-based ensemble forecast results through multi-parameter perturbation.
If any, what data does your model rely on for real-time forecasting purposes?
NCEP Reanalysis CPC daily precipitation/ tempretature and ERA5
What types of datasets were used for model training? (For example: observational datasets, reanalysis data, NWP outputs or satellite data)
Observational datasets and reanalysis data
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)
Using seasonal modes as predictors, and based on the LSTM model, I generate ensemble forecast results by perturbing initial weights, recurrent weights, and other parameters. Since the model employs a sliding window approach for modeling, each prediction is trained independently.
Have you published or presented any work related to this forecasting model? If yes, could you share references or links?
This model is based on my phd thesis.
Before submitting your forecasts to the AI Weather Quest, did you validate your model against observational or independent datasets? If so, how?
Yes, I competed my result with obs in China, it worked well.
Did you face any challenges during model development, and how did you address them?
How to decide the predictors is the biggest challenge for me.
Are there any limitations to your current model that you aim to address in future iterations?
This model is total based on the obs, then I try to use some NWP data.
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.
The model is built by myself.
Which of the following descriptions best represent the overarching design of your forecasting model?
- Machine learning-based weather prediction.
- Hybrid model that integrates physical simulations with machine learning or statistical techniques.
What techniques did you use to initialise your model? (For example: data sources and processing of initial conditions)
Based on climate dynamics and climate predictability, I have designed a hybrid physical-statistical and AI prediction model. For this prediction, my target is weekly averages or weekly accumulations. That is, I first process the data into weekly averages, then transform them into anomalous relative tendencies using online time-scale separation. Next, I use various large-scale circulation patterns as predictors to extract the large-scale climate modes that influence the anomalous relative tendencies of regional climate elements. By leveraging historical data, I establish relationships between these climate modes and the regional climate elements. Finally, I generate AI-based ensemble forecast results through multi-parameter perturbation.
If any, what data does your model rely on for real-time forecasting purposes?
NCEP Reanalysis CPC daily precipitation/ tempretature and ERA5
What types of datasets were used for model training? (For example: observational datasets, reanalysis data, NWP outputs or satellite data)
Observational datasets and reanalysis data
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)
Using seasonal modes as predictors, and based on the LSTM model, I generate ensemble forecast results by perturbing initial weights, recurrent weights, and other parameters. Since the model employs a sliding window approach for modeling, each prediction is trained independently.
Have you published or presented any work related to this forecasting model? If yes, could you share references or links?
This model is based on my phd thesis.
Before submitting your forecasts to the AI Weather Quest, did you validate your model against observational or independent datasets? If so, how?
Yes, I competed my result with obs in China, it worked well.
Did you face any challenges during model development, and how did you address them?
How to decide the predictors is the biggest challenge for me.
Are there any limitations to your current model that you aim to address in future iterations?
This model is total based on the obs, then I try to use some NWP data.
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.
The model is built by myself.
Which of the following descriptions best represent the overarching design of your forecasting model?
- Machine learning-based weather prediction.
- Hybrid model that integrates physical simulations with machine learning or statistical techniques.
What techniques did you use to initialise your model? (For example: data sources and processing of initial conditions)
Based on climate dynamics and climate predictability, I have designed a hybrid physical-statistical and AI prediction model. For this prediction, my target is weekly averages or weekly accumulations. That is, I first process the data into weekly averages, then transform them into anomalous relative tendencies using online time-scale separation. Next, I use various large-scale circulation patterns as predictors to extract the large-scale climate modes that influence the anomalous relative tendencies of regional climate elements. By leveraging historical data, I establish relationships between these climate modes and the regional climate elements. Finally, I generate AI-based ensemble forecast results through multi-parameter perturbation.
If any, what data does your model rely on for real-time forecasting purposes?
NCEP Reanalysis CPC daily precipitation/ tempretature and ERA5
What types of datasets were used for model training? (For example: observational datasets, reanalysis data, NWP outputs or satellite data)
Observational datasets and reanalysis data
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)
Using seasonal modes as predictors, and based on the LSTM model, I generate ensemble forecast results by perturbing initial weights, recurrent weights, and other parameters. Since the model employs a sliding window approach for modeling, each prediction is trained independently.
Have you published or presented any work related to this forecasting model? If yes, could you share references or links?
This model is based on my phd thesis.
Before submitting your forecasts to the AI Weather Quest, did you validate your model against observational or independent datasets? If so, how?
Yes, I competed my result with obs in China, it worked well.
Did you face any challenges during model development, and how did you address them?
How to decide the predictors is the biggest challenge for me.
Are there any limitations to your current model that you aim to address in future iterations?
This model is total based on the obs, then I try to use some NWP data.
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.
The model is built by myself.
Model name
TAICHIML
Model type
Number of individuals supporting model development:
1-5
Maximum number of Central Processing Units (CPUs) supporting model development or forecast production:
< 8
Maximum number of Graphics Processing Units (GPUs) supporting model development or forecast production:
< 4
How would you best classify the IT system used for model development or forecast production:
Single node system
Submitted forecast data in previous period(s)
Please note: Submitted forecast data is only publicly available once the evaluation of a full competitive period has been completed. See the competition's full detailed schedule with submitted data publication dates for each period here.
Access forecasts data