Machine learning approach for materials technologies

Abstract A substantial amount of the energy produced globally is utilized for household utilities, for example to maintain air-conditioning in buildings for personal comfort and essential weathering necessities, in tropical or cold climate geographic regions. The development of innovative functional materials in combination with cutting edge technology is vital for sustainable urban solutions. The progress and scaling-up of new technology for urban solution is necessary to addresses key concerns like improved energy efficacies, zero energy building (ZEB), recyclability, waste management, reduce carbon footprints, de-carbonization, etc. The building energy consumption can be controlled by adopting specialized cloaking technologies using materials or nanoadditives to create high reflective coatings/surfaces. However, large number of possible configurations and physical experiments that includes complexity of nanoadditives to achieve optimized materials performance and optical properties are time consuming as well as very expensive. In remedies, physical experiments and computational modeling methods have been utilized to develop optimized functional properties of the materials. Progression in materials research and innovation is critical for the requirement of futuristic sustainable solution, for example, green electricity and energy saving needs. Experimental techniques and computational modeling are time consuming; hence, it is much desirable to develop new methods to accelerate the materials development technologies, design optimization and implementation. This chapter aims to introduce the basics of machine learning for material technologies and list out major work carried out in this domain recently.