This study presents a transmitarray antenna design operating at a center frequency of 9 GHz, addressing the need for high-gain and broad bandwidth antennas in modern data communication. The proposed design is structured as a quad-layer configuration using FR-4 dielectric substrates. The transmitarray’s phase profile is tailored to deliver a wideband flat response with low Side Lobe Level (SLL) and stable aperture efficiency across the operating band. It achieves a 1-dB gain bandwidth of 12.12% (from 8.56 GHz to 9.67 GHz) and a 3-dB gain bandwidth of 49.43% (from 8.45 GHz to 13.46 GHz) with an aperture efficiency of 21.3%. A prototype of the proposed design with 11 × 11 elements was fabricated and measured, and its measurement results closely aligned with simulation results, validating its performance. The proposed simple design realizes reduced complexity and fabrication costs while expanding operational gain bandwidth, thereby demonstrating substantial promise for next-generation X-band communication systems.

Repeated inverse design of terahertz metasurfaces requires accurate, reusable predictions of complex scattering responses under physical constraints. We develop an angle-conditioned extreme learning machine (ELM) coupled with coordinate search for fixed-incidence geometry optimization. The ELM learns four complex scattering channels over 401 frequency samples from 7,776 CST-generated unit-cell configurations. Cross-channel equality is imposed by output parameterization, while radial spectral-norm scaling controls the adopted passivity bound. In the unseen incidence-angle test, mean MSE decreases from 0.0975 to 0.0169 relative to the data-driven ELM. Ablation identifies spectral scaling as the source of the accuracy gain; equality wiring supplies the structural constraint. With 2% and 5% labeled target-angle data, mean MSE is \(1.2783\times 10^{-3}\) and \(5.6210\times 10^{-4}\), respectively. Independent full-wave validation on 50 off-grid targets gives mean complex MSEs of \(9.6272\times 10^{-4}\) for the proposed pipeline and \(9.5264\times 10^{-4}\) for the data-driven ELM plus genetic algorithm. Four new PCR-specific designs reuse the same trained model; three satisfy both polarization-conversion and reflected-power specifications at every prescribed band sample. The framework combines inexpensive repeated prediction and geometry search with reusable complex-response objectives and full-wave candidate verification.

The depletion of conventional supplementary cementitious materials (SCMs), such as fly ash and ground granulated blast furnace slag, necessitates alternative binders for sustainable cement production. Limestone Calcined Clay Cement (LC3) is a promising option, yet optimizing calcination for heterogeneous low-grade clays remains difficult because of mineralogical variability. This study proposes an integrated experimental–computational framework combining pozzolanic activity tests, explainable artificial intelligence (XAI), and multi-criteria decision analysis to determine optimal calcination conditions for four low-grade clays (Vez, Lim, WG, and WO) from the Bilecik region of Türkiye. Clays were calcined at 600–900 °C for 30–120 min, and performance was assessed using the Strength Activity Index (SAI, ASTM C311) and Frattini tests (TS EN 196-5). Material-specific ensemble models incorporating polynomial and interaction features achieved test R² values of 0.86–0.95 and mean absolute errors of 1.0–1.5 MPa. SHAP analysis identified calcination temperature and the temperature–curing interaction as dominant predictors, together accounting for 60–75% of total feature importance. To address instabilities in time modeling, a unified voting ensemble was developed, achieving a cross-validation R² of 0.82 ± 0.08. TOPSIS-based ranking, balancing compressive strength, energy consumption, CO2 emissions, and cost, identified Lim clay calcined at 800 °C for 30 min as the optimal scenario (TOPSIS score = 0.928). SEM observations supported the SAI results, showing improved gel continuity and pore refinement in high-performing samples. This workflow offers a scalable, transparent, and reproducible method for selecting low-carbon calcination regimes and supports broader adoption of LC3 using locally available clays.