counterparts. [2] Therefore, 2D materials are ideal for flexible optoelectronics and have the potential to be used in the next-generation ultrathin electronic and optoelectronic devices. [1] The concept of 2D materials was first realized when graphene was found in 2004. [4] Graphene has attracted extensive attention for its excellent electrical, optical, and mechanical properties. [4][5][6] They have been investigated for various technological applications, including spintronics, sensors, optoelectronics, supercapacitors, and solar cells, etc. [5,7] Besides graphene, other 2D materials, such as h-BN, phosphorene, silicene, germanene, and transition metal dichalcogenides (molybdenum disulfide (MoS 2 ), molybdenum diselenide (MoSe 2 ), tungsten disulfide (WS 2 ), and tungsten diselenide (WSe 2 ), etc.), have been studied extensively in recent years. [1,[8][9][10][11] The thickness of single-layer 2D materials is usually on the order or less than 1 nm. At the same time, their lateral sizes could reach much larger size (from microns to even inches), and 2D materials can be transferred to different substrates before subsequent processing or follow-up measurements for characterizations or device applications.Strain engineering is a promising way to tune the electrical, electrochemical, magnetic, and optical properties of 2D materials, with the potential to achieve high-performance 2D-material-based devices ultimately. This review discusses the experimental and theoretical results from recent advances in the strain engineering of 2D materials. Some novel methods to induce strain are summarized and then the tunable electrical and optical/optoelectronic properties of 2D materials via strain engineering are highlighted, including particularly the previously less-discussed strain tuning of superconducting, magnetic, and electrochemical properties. Also, future perspectives of strain engineering are given for its potential applications in functional devices. The state of the survey presents the ever-increasing advantages and popularity of strain engineering for tuning properties of 2D materials. Suggestions and insights for further research and applications in optical, electronic, and spintronic devices are provided.

With the development of Raman spectroscopy and the expansion of its application domains, conventional methods for spectral data analysis have manifested many limitations. Exploring new approaches to facilitate Raman spectroscopy and analysis has become an area of intensifying focus for research. It has been demonstrated that machine learning techniques can more efficiently extract valuable information from spectral data, creating unprecedented opportunities for analytical science. This paper outlines traditional and more recently developed statistical methods that are commonly used in machine learning (ML) and ML‐algorithms for different Raman spectroscopy‐based classification and recognition applications. The methods include Principal Component Analysis, K‐Nearest Neighbor, Random Forest, and Support Vector Machine, as well as neural network‐based deep learning algorithms such as Artificial Neural Networks, Convolutional Neural Networks, etc. The bulk of the review is dedicated to the research advances in machine learning applied to Raman spectroscopy from several fields, including material science, biomedical applications, food science, and others, which reached impressive levels of analytical accuracy. The combination of Raman spectroscopy and machine learning offers unprecedented opportunities to achieve high throughput and fast identification in many of these application fields. The limitations of current studies are also discussed and perspectives on future research are provided.