Photovoltaic (PV) panels experience substantial efficiency losses under thermal stress, particularly in arid climates. This work introduces a novel segmented water-cooling configuration, where the PV surface is divided into multiple independently cooled sections to enhance localized heat extraction. The segmentation concept is further optimized using artificial intelligence (AI) algorithms-Genetic Algorithm, Particle Swarm Optimization (PSO), and Artificial Bee Colony-to determine the most efficient combination of cooling parameters. Results show that increasing the number of cooling sections from one to seven raises the electrical efficiency from 14.85% to 17.44% (a 17.4% relative gain), while the average PV cell temperature decreases from 57.5 degrees C to 50.1 degrees C (-12.9%). AI optimization confirmed that the PSO algorithm achieves equivalent peak performance with only three cooling sections and a lower water flow rate (0.0843 kg/s), ensuring both thermal stability and water-use efficiency. The proposed AI-guided segmentation strategy enhances PV output and operational longevity while minimizing system complexity, offering a cost-effective, scalable solution for solar installations in hot and arid environments.