Daily scale air quality index forecasting using bidirectional recurrent neural networks: Case study of Delhi, India.

This research was established to accurately forecast daily scale air quality index (AQI) which is an essential environmental index for decision-making. Researchers have projected different types of models and methodologies for AQI forecasting, such as statistical techniques, machine learning (ML), and most recently deep learning (DL) models. The modelling development was adopted for Delhi city, India which is a major city with air pollution issues simialir to entire urban cities of India especially during winter seasons. This research was predicted AQI using different versions of DL models including Long-Short Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Bidirectional Recurrent Neural Networks (Bi-RNN) in addition to Kernel Ridge Regression (KRR). Results indicated that Bi-RNN model consistently outperformed the other models in both training and testing phases, while the KRR model consistently displayed the weakest performance. The outstanding performance of the models development displayed the requirement of adequate data to train the models. The outcomes of the models showed that LSTM, BI-LSTM, KRR had lower performance compared with Bi-RNN models. Statistically, Bi-RNN model attained maximum cofficient of determination (R2 = 0.954) and minimum root mean square error (RMSE = 25.755). The proposed model in this research revealed the robust predictable to provide a valuable base for decision-making in the expansion of combined air pollution anticipation and control policies targeted at addressing composite air pollution problems in the Delhi city.

Heavy metals prediction in coastal marine sediments using hybridized machine learning models with metaheuristic optimization algorithm.

This study proposes different standalone models viz: Elman neural network (ENN), Boosted Tree algorithm (BTA), and f relevance vector machine (RVM) for modeling arsenic (As (mg/kg)) and zinc (Zn (mg/kg)) in marine sediments owing to anthropogenic activities. A heuristic algorithm based on the potential of RVM and a flower pollination algorithm (RVM-FPA) was developed to improve the prediction performance. Several evaluation indicators and graphical methods coupled with visualized cumulative probability function (CDF) were used to evaluate the accuracy of the models. Akaike (AIC) and Schwarz (SCI) information criteria based on Dickey-Fuller (ADF) and Philip Perron (PP) tests were introduced to check the reliability and stationarity of the data. The prediction performance in the verification phase indicated that RVM-M2 (PBAIS = -o.0465, MAE = 0.0335) and ENN-M2 (PBAIS = 0.0043, MAE = 0.0322) emerged as the best model for As (mg/kg) and Zn (mg/kg), respectively. In contrast with the standalone approaches, the simulated hybrid RVM-FPA proved merit and the most reliable, with a 5 % and 18 % predictive increase for As (mg/kg) and Zn (mg/kg), respectively. The study's findings validated the potential for estimating complex HMs through intelligent data-driven models and heuristic optimization. The study also generated valuable insights that can inform the decision-makers and stockholders for environmental management strategies.

Thermohydraulic analysis of covalent and noncovalent functionalized graphene nanoplatelets in circular tube fitted with turbulators.

Covalent and non-covalent nanofluids were tested inside a circular tube fitted with twisted tape inserts with 45° and 90° helix angles. Reynolds number was 7000 ≤ Re ≤ 17,000, and thermophysical properties were assessed at 308 K. The physical model was solved numerically via a two-equation eddy-viscosity model (SST k-omega turbulence). GNPs-SDBS@DW and GNPs-COOH@DW nanofluids with concentrations (0.025 wt.%, 0.05 wt.% and 0.1 wt.%) were considered in this study. The twisted pipes' walls were heated under a constant temperature of 330 K. The current study considered six parameters: outlet temperature, heat transfer coefficient, average Nusselt number, friction factor, pressure loss, and performance evaluation criterion. In both cases (45° and 90° helix angles), GNPs-SDBS@DW nanofluids presented higher thermohydraulic performance than GNPs-COOH@DW and increased by increasing the mass fractions such as 1.17 for 0.025 wt.%, 1.19 for 0.05 wt.% and 1.26 for 0.1 wt.%. Meanwhile, in both cases (45° and 90° helix angles), the value of thermohydraulic performance using GNPs-COOH@DW was 1.02 for 0.025 wt.%, 1.05 for 0.05 wt.% and 1.02 for 0.1 wt.%.

A hybrid numerical/machine learning model development to improve the bimetal performance in the electric circuit breakers.

Bimetals are widely used as a thermal tripping mechanism inside the miniature circuit breakers (MCBs) products when an overload current passes through the circuit for a certain period. Experimental, numerical, and, recently artificial intelligence methods are widely used in designing electric components. However, developing the bimetal for MCB products somewhat differs from developing other conductor items since they are strongly related to the electrical, mechanical, and thermal performance of the MCB. The conventional experimental and numerical approaches are time-consuming processes that cannot be easily utilized in optimizing the product's performance within the development lead time. In this study, a simple, fast, robust, and accurate novel methodology has been introduced to predict the temperature rise of the bimetal and other related performance characteristics. The numerical model has been built on the time-based finite difference method to frame the theoretical thermal model of the bimetal. Then, the numerical model has been consolidated by the machine learning (ML) model to take advantage of the experiments to provide an accurate, fast and reliable model finally. The novel model agrees well with the experimental tests, where the maximum error does not exceed 8%. The model has been used to redesign the bimetal of a 32 A MCB product and significantly reduce the maximum temperature by 24 °C. The novel model is promising since it considerably reduces the required design time, provides accurate predictions, and helps to optimize the performance of the circuit breaker products.

Development of new computational machine learning models for longitudinal dispersion coefficient determination: case study of natural streams, United States.

Natural streams longitudinal dispersion coefficient (Kx) is an essential indicator for pollutants transport and its determination is very important. Kx is influenced by several parameters, including river hydraulic geometry, sediment properties, and other morphological characteristics, and thus its calculation is a highly complex engineering problem. In this research, three relatively explored machine learning (ML) models, including Random Forest (RF), Gradient Boosting Decision Tree (GTB), and XGboost-Grid, were proposed for the Kx determination. The modeling scheme on building the prediction matrix was adopted from the well-established literature. Several input combinations were tested for better predictability performance for the Kx. The modeling performance was tested based on the data division for the training and testing (70-30% and 80-20%). Based on the attained modeling results, XGboost-Grid reported the best prediction results over the training and testing phase compared to RF and GTB models. The development of the newly established machine learning model revealed an excellent computed-aided technology for the Kx simulation.

Heat Transfer and Hydrodynamic Properties Using Different Metal-Oxide Nanostructures in Horizontal Concentric Annular Tube: An Optimization Study.

Numerical studies were performed to estimate the heat transfer and hydrodynamic properties of a forced convection turbulent flow using three-dimensional horizontal concentric annuli. This paper applied the standard k-ε turbulence model for the flow range 1 × 104 ≤ Re ≥ 24 × 103. A wide range of parameters like different nanomaterials (Al2O3, CuO, SiO2 and ZnO), different particle nanoshapes (spherical, cylindrical, blades, platelets and bricks), different heat flux ratio (HFR) (0, 0.5, 1 and 2) and different aspect ratios (AR) (1.5, 2, 2.5 and 3) were examined. Also, the effect of inner cylinder rotation was discussed. An experiment was conducted out using a field-emission scanning electron microscope (FE-SEM) to characterize metallic oxides in spherical morphologies. Nano-platelet particles showed the best enhancements in heat transfer properties, followed by nano-cylinders, nano-bricks, nano-blades, and nano-spheres. The maximum heat transfer enhancement was found in SiO2, followed by ZnO, CuO, and Al2O3, in that order. Meanwhile, the effect of the HFR parameter was insignificant. At Re = 24,000, the inner wall rotation enhanced the heat transfer about 47.94%, 43.03%, 42.06% and 39.79% for SiO2, ZnO, CuO and Al2O3, respectively. Moreover, the AR of 2.5 presented the higher heat transfer improvement followed by 3, 2, and 1.5.

The influence of covalent and non-covalent functionalization of GNP based nanofluids on its thermophysical, rheological and suspension stability properties.

Covalent functionalization (CF-GNPs) and non-covalent functionalization (NCF-GNPs) approaches were applied to prepare graphene nanoplatelets (GNPs). The impact of using four surfactants (SDS, CTAB, Tween-80, and Triton X-100) was studied with four test times (15, 30, 60, and 90 min) and four weight concentrations. The stable thermal conductivity and viscosity were measured as a function of temperature. Fourier transform infrared spectroscopy (FTIR), thermo-gravimetric analysis (TGA), X-ray diffraction (XRD) and Raman spectroscopy verified the fundamental efficient and stable CF. Several techniques, such as dispersion of particle size, FESEM, FETEM, EDX, zeta potential, and UV-vis spectrophotometry, were employed to characterize both the dispersion stability and morphology of functionalized materials. At ultrasonic test time, the highest stability of nanofluids was achieved at 60 min. As a result, the thermal conductivity displayed by CF-GNPs was higher than NCF-GNPs and distilled water. In conclusion, the improvement in thermal conductivity and stability displayed by CF-GNPs was higher than those of NCF-GNPs, while the lowest viscosity was 8% higher than distilled water, and the best thermal conductivity improvement was recorded at 29.2%.