Ground Truth and Model Predictions for Regional Air Pollution Forecasts

Haochen Sun from the Hong Kong University of Science and Technology provides ground truth values and predictions from a broadcasting model and baseline models (SC and CMAQ) for regional air pollution. The dataset supports the paper 'Development of an LSTM-Broadcasting deep-learning framework for regional air pollution forecast improvement' and includes namelists for the WRF and CMAQ models.

Use Cases

• Benchmarking LSTM-based forecasting models against baseline models (SC and CMAQ) based on the provided predictions.
• Evaluating the performance of a broadcasting model for air pollution based on the ground truth values.
• Analyzing the configuration of atmospheric models based on the included WRF and CMAQ namelists.

Strengths

• Includes ground truth values for model validation.
• Provides predictions from multiple models (broadcasting, SC, CMAQ) for direct comparison.
• Contains configuration namelists for the WRF and CMAQ models, offering insight into model setup.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Haochen Sun, Hong Kong University of Science and Technology

Collection Method

Likely generated as part of the research for the associated paper on an LSTM-Broadcasting framework.

Time Range

null

Freshness

Last updated date is unknown.

Geography

null