Drilling operations conducted under high-pressure and high-temperature conditions present significant challenges for modern drilling advancements. Downhole temperatures can significantly impact the stability of water-based mud (WBM) properties, leading to costly issues and non-productive time resulting from drilling instabilities. To mitigate these issues, it is crucial to employ high-temperature-resistant additives in such operations. This study aimed to examine the influence of temperature on the stability of commonly used polymer types in water-based mud drilling operations. A series of laboratory experiments were conducted to investigate changes in normal mud properties following exposure to temperatures ranging from 79 to 350 °F. Two different mud polymers were used, including two viscosifier polymers (Flowzan - type A and Xanthan gum - type B), with varying concentrations of potassium chloride (KCl). Rheological analysis revealed that Polymer A exhibited superior performance as most mud properties, including viscosity, yield point, and gel strength, were significantly affected at different temperatures. However, plastic viscosities fell below the minimum recommended range of 8 cP for both polymers. At 250 °F, Polymer A's apparent viscosity of WBM was enhanced by 87%, 100%, and 120% with 3%, 5%, and 7% concentrations of KCl, respectively. For Polymer B, at 200 °F, it was improved by 118%, 112%, and 106%. The addition of KCl to the viscosifier polymers enhanced the thermal stability of the drilling fluid within the operating temperature range of 250–350 °F. Gel Point (10-min) remained below the recommended 35 lb/100 ft2 for all KCl concentrations of both polymers, while Gel Point (10-s) remained below the recommended 15 lb/100 ft2 for temperatures above 200 °F. Three other polymers were studied for filtration control without any KCl concentration, namely Bio Pac (type C), Mil Pac Xlo (type D), and Perma Loss (type E). Although API fluid loss remained below the recommended 15 cm3 for all the polymers, filtration control, and cake analysis demonstrated that Polymer C exhibited superior performance compared to the others. It also displayed thermal stability and cake thickness below the recommended 0.1 in up to temperatures below 250 °F. A novel sinusoidal correlation function is fit to experimental data, which can be used for training machine learning approaches.