Exponential growth of generative pre-trained transformers (GPT) belies some shortcomings of Artificial Intelligence. Specifically, heavy reliance on human-curated data for training, validation, and calibration often lead to biases in model outputs and the requirement for massive training datasets. These issues are especially prominent in data-intensive fields like computer vision and natural language processing. In contrast, classical algorithms ensure independent replicability crucial for testing hypotheses, enhance algorithmic transparency for research users, and eliminate the need for large training datasets. However, classical algorithms reliant on rule-based analytical or mathematical principles may not scale as readily as AI-based counterparts or be as adaptable. Consequently, we encourage submissions on the synthesis of AI and classical algorithms to strengthen transdisciplinary applications as diverse as planetary geoscience, plant genomics, and geo-archaeology. Meanwhile, scenarios from numerical modeling of spectra to classifying objects in planetary imagery are welcomed, especially targeting complementarity between AI-Machine Learning and classical algorithms.