Exploring Kolmogorov–Arnold networks for hyperspectral crop classification – an evaluative study

Key Points

• Hyperspectral imaging significantly improves crop classification accuracy using Kolmogorov–Arnold networks.
• Classification accuracy increases by 15% compared to traditional methods, highlighting method efficacy.
• Evaluation conducted through feature extraction techniques using machine learning algorithms on diverse agricultural data.
• Findings suggest potential for enhanced agricultural monitoring and precision farming practices.