+ +
+ +
+

Final Integrated Project in Machine Learning in Geoscience#

+

Objective: Integrate the learning of the entire class into a single, group project that demonstrates understanding and skill to manipulate data and develop machine learning approaches to a scientific problem. Evaluate the integration of AI-ready data preparation, classical machine learning (CML), and deep learning (DL) components into a cohesive project, with a focus on scientific discussion, interpretation, reproducibility, and team contributions.

+
+
+
+

1. Report (5 Pages) - 40%#

+
+

Integration and Cohesion (10%)#

+
    +

  • Clearly integrates AI-ready data preparation, CML, and DL components into a single narrative.

    • +

  • Demonstrates the logical progression of methods and their relevance to the geoscientific problem.

    • +
+
+
+

Scientific Discussion and Interpretation (15%)#

+
    +

  • Provides insightful analysis of results, including comparisons between CML and DL methods.

    • +

  • Discusses trade-offs, advantages, and limitations of the approaches used.

    • +

  • Includes domain-specific interpretations and implications of findings.

    • +
+
+
+

Clarity and Organization (10%)#

+
    +

  • The report is well-structured, concise, and within the 5-page limit (excluding references and appendices).

    • +

  • Includes high-quality figures, tables, and diagrams to support the narrative.

    • +
+
+
+

Team Contributions (5%)#

+
    +

  • Clearly documents individual contributions from each team member to the report writing and analysis.

    • +
+
+
+
+
+

2. GitHub Repository - 35%#

+
+

Comprehensiveness (10%)#

+
    +

  • Repository includes all three components: AI-ready data, CML, and DL.

    • +

  • Each component is complete and well-documented with code, results, and explanations.

    • +
+
+
+

Reproducibility and Code Quality (10%)#

+
    +

  • Code is modular, organized, and follows standard practices for AI/ML projects (e.g., using PyTorch for DL).

    • +

  • Instructions for reproducing results are clear (e.g., README with dependencies, instructions, and commands).

    • +
+
+
+

Integration and Documentation (10%)#

+
    +

  • Demonstrates integration across components with shared preprocessing steps, consistent evaluation metrics, and unified outputs.

    • +

  • Includes high-quality documentation that explains the project, methods, and findings holistically.

    • +
+
+
+

Team Contributions (5%)#

+
    +

  • Repository reflects contributions from all team members (e.g., clear commit history, attribution in code/comments).

    • +
+
+
+
+
+

3. Presentation (10 Minutes) - 25%#

+
+

Content and Delivery (10%)#

+
    +

  • Presentation provides a clear and engaging summary of the project, including objectives, methods, results, and key insights.

    • +

  • Demonstrates understanding of the methods and their relevance to the geoscientific problem.

    • +
+
+
+

Integration and Interpretation (10%)#

+
    +

  • Focuses on the integration of all three components and the scientific conclusions derived from them.

    • +

  • Highlights key comparisons, domain-specific implications, and future directions.

    • +
+
+
+

Team Contributions (5%)#

+
    +

  • All team members participate in the presentation, demonstrating their understanding and contributions.

    • +
+
+
+
+
+

4. Overall Team Contributions - 10%#

+
    +

  • Evaluates how well the team worked together to deliver a cohesive project.

    • +

  • Assessed through peer evaluations, clear documentation of roles, and balance of contributions across all deliverables.

    • +
+
+
+
+

Summary of Weightage:#

+
    +

  1. Report: 40%

    2. +

  2. GitHub Repository: 35%

    3. +

  3. Presentation: 25%

    4. +

  4. Overall Team Contributions: 10%

    5. +
+
+ + + + +
+ +