carlospachecolima/AI-Assisted-Visual-Assessment-of-Physiological-Disorders-in-Sweet-Potato-Roots: Initial release: AI-assisted visual assessment framework for sweet potato disorders

Initial Release This release presents the first stable version (v1.0.0) of the computational framework for: AI-assisted visual assessment of physiological disorders in sweet potato (Ipomoea batatas) roots under climate change scenarios, using prompt engineering and command chaining. Key Features Structured prompt engineering workflow Command chaining for reproducible analysis Python-based modular pipeline Hash-based reproducibility support Scientific documentation included Contents Core analysis pipeline (main_analise.py) Prompt engineering module (prompt_engine_batata_doce_raizes.py) Hash generation utility (gerar_hash.py) Full methodological documentation (PDF) Scientific Contribution This framework contributes to: AI-assisted phenotyping Climate-resilient agriculture Digital agriculture workflows Reproducible research in crop science Reproducibility Deterministic workflow Modular architecture Data integrity verification via hashing Zenodo Integration This release is intended for archival via Zenodo to generate a DOI, ensuring: Long-term preservation Citation standardization Scientific traceability License BSD 3-Clause License Notes Future releases will include: Machine learning integration Expansion to additional crops Integration with climate datasets (CMIP6, WorldClim) QGIS interoperability