This paper defines the concept of "Drilling in Incompatible Conditions" and how its identification can help in the inclusion of unconventional drilling fluids and technologies, in the planning phase or as a contingency plan. These technologies include casing and liner drilling, MPD, UBD, HPWBM, and their combination (ex: MPCD). This paper also presents a method to point out whether a given drilled section is compatible with overbalanced conventional rotary drilling – referred to as conventional drilling on this paper. Identification of drilling incompatibility starts from a basic definition and widens based on field case histories of drilling using unconventional drilling methods (which means fields that have parameters incompatible with conventional drilling) or from cases in which an unplanned contingency casing was used. The parameters influencing the usage of these methods are used as inputs in machine learning. While the technological complexity level of the techniques in use can be divided into as many as four categories based on logistical and cost considerations. Only level 1 - conventional drilling - is in the scope of this work. Machine learning classification algorithms are used to predict if the conventional drilling method is incompatible with parameters designated as input values, such as heterogeneity of lithologies in a drilled section, the presence of problematic drilling formations (mobile/reactive), presence of weak formations, formation temperature (high, moderate or low), formation pressure (over/under-pressurized), formation permeability and presence of natural fractures, and the ERD value. The outputs will present themselves as a binary value (Compatible/Incompatible). The inputs can be classified into continuous, binary, and ordinal data. This model provides insights on whether geological and operational parameters are too complex for conventional drilling, thereby avoiding drilling based on trial and error. This work will fill the gap in terms of quantifying the complexity of a drilled section, both operationally and geologically, and deals with it from a relativity point of view with respect to the level of technology implemented through the usage of machine learning. This new concept will help drilling engineers be more efficient by answering complexity issues before the commencement of drilling. This will lead to cost savings and enhanced profitability by designing a wellbore with the least sections possible. Besides, this terminology reflects the definition of sustainability which is of utmost importance not just from the technical point of view.