AI Model Prediction - OtagoPolytechnic/Cloudy-with-a-Chance-of-LoRa GitHub Wiki

AI Model Design

Untitled Diagram

  1. Data Collection Sensor Data: Collect data from various sensors that measure weather-related parameters such as temperature, pressure, wind speed, and date/time.
  1. Data Cleaning Data Cleanup: Remove any noisy or irrelevant data, handle missing values, and ensure consistency in the data format.
  1. Data Normalization Normalize: Scale the data to a standard range to ensure that all features contribute equally to the model's performance.
  1. Feature Engineering Feature Engineering: Create new features from the existing data that might help improve the model's performance. For example, calculating wind components from wind speed and direction.
  1. Feature Selection Feature Selection: Select the most relevant features from the dataset to reduce complexity and improve the model's performance.
  1. Data Splitting Split Data: Divide the dataset into training, validation, and test sets. This helps in training the model, tuning hyperparameters, and evaluating its performance on unseen data.
  1. Model Selection and Hyperparameter Tuning Model Selection: Choose appropriate machine learning models based on the problem type (regression or classification). Hyperparameter Tuning: Optimize the model's hyperparameters using techniques like Grid Search or Random Search to achieve the best performance.
  1. Model Training and Evaluation Model Training: Train the selected model using the training dataset. Model Evaluation: Evaluate the model's performance on the validation and test datasets using appropriate metrics (e.g., Mean Squared Error, R-squared).
  1. Model Deployment Model Deployment: Deploy the trained model to a production environment where it can make predictions on new data.
  1. Prediction and Monitoring Prediction: Use the deployed model to make predictions on new incoming data. Monitoring and Maintenance: Continuously monitor the model's performance in production and retrain it periodically with new data to maintain accuracy and relevance.