The availability of an ever‐expanding portfolio of 2D materials with rich internal degrees of freedom (spin, excitonic, valley, sublattice, and layer pseudospin) together with the unique ability to tailor heterostructures made layer by layer in a precisely chosen stacking sequence and relative crystallographic alignments, offers an unprecedented platform for realizing materials by design. However, the breadth of multi‐dimensional parameter space and massive data sets involved is emblematic of complex, resource‐intensive experimentation, which not only challenges the current state of the art but also renders exhaustive sampling untenable. To this end, machine learning, a very powerful data‐driven approach and subset of artificial intelligence, is a potential game‐changer, enabling a cheaper – yet more efficient – alternative to traditional computational strategies. It is also a new paradigm for autonomous experimentation for accelerated discovery and machine‐assisted design of functional 2D materials and heterostructures. Here, the study reviews the recent progress and challenges of such endeavors, and highlight various emerging opportunities in this frontier research area.

A new method is proposed to produce even finite transmission zeros without any cross-coupling between the resonators of filter, by loading the second-order extracted-pole unit (EPU) composed of two mutual coupled resonators at the input or output port of the filter. An arbitrary distribution of finite transmission zeros on the imaginary axis can be achieved by adjusting the resonant frequencies of resonators in the EPUs and the coupling strength between them. The finite transmission zeros can be symmetrically or asymmetrically distributed about the center frequency of the filter, even all on the same side outside the passband of the filter. And the topological structures of these filters are given in this paper. Besides, Cauchy method is adopted to analyze the proposed EPU configuration filter as well. This paper not only discusses how to implement a pair and two pairs of finite transmission zeros, and how to control the distribution of finite transmission zeros, but also gives multiple sets of computer-aided synthesized normalized coupling matrices. Based on this, an eighth-order quasi-elliptic function high-temperature superconducting filter with two pairs of finite transmission zeros was designed on a double-sided YBCO/LaAlO3/YBCO films to verify the feasibility of this new structure.

This paper proposes a miniature 3D SIP (system in package) design of the four-channel RF transceiver. The Key advancement is the demonstration of 3D stacking of silicon carriers and ALN (aluminium nitride) HTCC carrier based on 70 um Au micro-bumps. The influences of the carrier on the performance of GaAs (gallium arsenide) MMICs are analyzed in detail. A new silicon carrier with hollow annular TSV and non-metalized cavity is proposed, which is characterized by less impact on MMIC performance, more compact stacking size and lower fabrication cost. The GaAs MMICs, silicon and ALN carriers are heterogeneous integrated and stacked vertically to form a 3D SIP. The proposed hermetic 3D SIP is highly integrated in a volume of 12.7 mm × 13.9 mm × 3.6 mm with 7 × 8 BGA (ball grid array) input and output ports, and capable of working with four different types of passbands for anti-jamming. Measured results indicate that the SIP has the advantages of high reliability, high performance and mass manufacture.

A multi-order dual-band high temperature superconducting (HTS) bandpass filter (BPF) with multiple transmission zeros (TZs) is designed in this paper. The theoretical characteristics of the introduction of TZs by the electric and magnetic mixed coupling, and the cascade quadruplet (CQ) cross-coupling structures are analyzed, respectively. These two methods can be applied to the design of the multi-mode compact dual-band HTS BPF with controllable central frequency, bandwidth and TZs. For demonstration, a Y-shape tunable resonator structure which can simultaneously implement the internal electric and magnetic mixed coupling, and the external cross coupling is constructed to achieve the proposed dual-band BPF. The external quality factors required by the two passbands and the feasibility of independently adjusting the coupling strength between adjacent resonators are analyzed. Finally, a 6-order dual-band HTS BPF with the center frequencies of 1490MHz (bandwidth of 40 MHz) and 2340MHz (bandwidth of 80 MHz) is designed and fabricated on the double-sided YBCO/MgO/YBCO HTS thin films with the size of 17.2mm × 14.7mm (0.20μg × 0.17μg), and there are multiple of TZs located outside the two passbands, respectively. The out-of-band rejections are greatly improved to 70dB and 80dB due to these TZs, which fully exhibits the advantages of the proposed dual-band BPF. The measured results are in good agreement with the simulated ones.

This paper presents the compact hybrid choke rings for the dual-band circularly polarized GPS antenna, in order to suppress the surface wave propagation and reduce the back lobe levels. The designed dual-band circularly polarized antenna is center fed and composed of two radiation patches. The novel compact hybrid choke rings are introduced to reduce the radiation back lobes and improve the front to back ratio effectively. The measured results show that the return loss of the antenna is greater than 10 dB and the bandwidth covers GPS L2 from 1.168 GHz to 1.238 GHz and GPS L1 from 1.543 GHz to 1.599 GHz. In the working bands, the front to back ratio of the proposed antenna is greater than 30 dB.

In this paper, an effective high order superconducting filter design technique is proposed. The key advancement is the demonstration of neural network HTS (high temperature superconducting) high order filter design for the first time. An artificial neural network (ANN) combined with the coupling matrix is used as a fast model of the high order superconducting filters. The initial filter layout is established and characterized by a set of geometric variables. The coupling matrix is extracted from the simulated response of the filter layout, and the ANN is trained to learn the relationship between the coupling matrix and the filter geometric variables. The well-trained neural network model can provide an accurate and fast prediction of filter performance with different input geometric variables in less than one second, which greatly improve the design effectiveness. The experiments show that there is an excellent match between the responses of the simulated data and those from the neural network. Compared with the conventional electromagnetic simulation method, this model is time saving especially in high-order filters design with complex undesired stray couplings.