ABSTRACT Background and Aim Environmental pollutants, including contaminated air, harmful chemicals, and excessive noise, are increasingly prevalent in modern society. These contaminants can significantly affect mental well‐being, a fundamental determinant of cognitive functioning, emotional regulation, interpersonal relationships, life satisfaction, and overall physical health. Methods This systematic review examines the effects of various types of pollution, such as air pollution, noise pollution, and chemical contaminants, as well as their interactions, on mental health outcomes across diverse populations. Results Our search identified 61 high‐quality studies that met our inclusion criteria. Among quantitative studies, 81% (n = 49) reported a significant association between pollution and mental health outcomes. Air pollution was the most frequently studied factor, with 50% confirming an association. In contrast, chemical pollution showed the lowest positive associations, with only 10% reporting an association. Our analysis reveals critical limitations in current research, particularly regarding data availability and quality, with most mental health data sets being limited in temporal scope and geographical coverage. While we discuss Artificial Intelligence as a prospective methodological framework to improve the precision and efficiency of future studies, we emphasize that its effective implementation fundamentally depends on addressing underlying data limitations. Specifically, spatiotemporal models can address exposure misclassification, attention mechanisms can handle confounding complexity, and deep learning can manage temporal variability, but all require systematic improvements in data collection infrastructure. Conclusion This review highlights the urgent need for standardized mental health monitoring systems, interdisciplinary collaboration, and the development of comprehensive data collection frameworks as essential prerequisites for leveraging advanced analytical methods in understanding pollution–mental health relationships.

Communication systems continue to embrace the potential of Artificial Intelligence (AI) in error correction codes (ECC) with coded modulation schemes (CMS). Despite this, there remains a substantial performance gap in AI methods in terrestrial and satellite communication systems. Additionally, AI and power efficiency for Low Earth Orbit (LEO) satellites have shown a critical gap. To the best of the author's knowledge, this is the first Systematic literature review attempting to bridge this vital gap to boost efficiency and add fault tolerance. From 389 articles published between 1993 and 2023, the construction and performance of 33 AI algorithms have been comprehensively reviewed for 16 ECC, seven higher-order CMS, and LEO satellites. Based on four key parameters: error correction, modulation, power, and energy efficiency, the PRISMA strategy with a 27-item checklist was adopted and 63 studies were selected to investigate the AI-based performance of terrestrial (40-studies) and LEO satellites (23-studies). Analysing nine performance metrics, Convolutional Neural Network was the most popular choice (20.6%) with an accuracy of 99% and SNR from 6-20dB, followed by Deep Neural Network (19.04%). The least used algorithm was Reinforcement learning (9.52%). Modified Reed Solomon codes showed the best measurement of power consumption and error rate. Adaptive LDPC codes provided a 45% increase in energy efficiency with an 11% computation decrease. Considering appropriate merits and challenges, the review identifies, discusses, and synthesises AI results to create a summary of current evidence for terrestrial and LEO satellites contributing to evidence-based practice for future researchers.

Wave energy resulting from interactions of Earth’s gravitational field with the Sun and Moon is considered a significant resource of distributed variable renewable energy to contribute to the supply of consumer electricity. In this study, we developed an artificial intelligent model based on extreme learning machine (ELM) and hourly seawater level (Ht) data collected between February 02-January 2001 and 31-December 2005 at wave energy sites in Broome, Darwin, Cape Ferguson, and Milner Bay in Northern Australia to predict Ht over near real-time hourly scales. The proposed ELM model is benchmarked against the emotional neural network (EmNN) and extreme gradient boosting (XGBoost) models. The proposed ELM is shown to outperform the EmNN and XGBoost models concerning training, validation, and testing data. For all four study sites, the proposed ELM model achieved a correlation coefficient of 0.998–0.999 vs. 0.975–0.993 (for the EmNN) and 0.975–0.998 (for the XGBoost). Correspondingly, the Legates McCabe’s Index were 0.936–0.973 vs. 0.775–0.879 and 0.775–0.953 for the ELM and EmNN models and the XGBoost model's testing phase (0.775–0.879), resulted in a significant reduction in root mean square (0.092, 0.069, 0.042 and 0.027 for the sites Broome, Darwin, Cape Ferguson and Milner Bay, respectively) and mean absolute error (0.044, 0.054, 0.033 and 0.021 for the sites Broome, Darwin, Cape Ferguson and Milner Bay, respectively), while Willmott’s Index (1.00 for all sites) and Nash–Sutcliffe’s coefficient (0.998 for Broome and Darwin, 0.996 for Cape Ferguson, and 0.995 for Milner Bay) comparing the predicted and observed Ht registered the highest values compared to all benchmark models. The ELM model also produced the greatest frequency of errors in the smallest error bracket, thus demonstrating its efficacy in predicting hourly seawater levels. In addition, the study also extracted results by developing a multiple linear regression (MLR) model, one of the well-known forecasting technique, and compared it with the machine learning models used in this study. According to the experiment, the study finding that the MLR model has slightly better accuracy in some cases when it was compared with the EmNN and XGBoost models. However, the study objective model (ELM) has relatively better performance in all study sites comparing with the MLR model. We, therefore, conclude that the proposed ELM model may be a useful stratagem for monitoring seawater levels in near-real-time and adopted for forecasting wave energy potentials in tidal energy belt regions.

Core mathematics courses are fundamental to the academic success of engineering students in higher education. These courses equip students with skills and knowledge applicable to their specialized fields. However, first-year engineering students often face significant challenges in mathematics due to a range of factors, including insufficient preparation, mathematics anxiety, and difficulty connecting theoretical concepts to real-life applications. The transition from secondary to tertiary mathematics remains a key area of educational research, with ongoing discussions about effective pedagogical approaches for teaching engineering mathematics. This study utilized a belief survey to gain general insights into the attitudes of first-year mathematics students towards the subject. In addition, it employed the activity theory framework to conduct a deeper exploration of the experiences of first-year engineering students, aiming to identify contradictions, or “tensions,” encountered within a flipped-classroom learning environment. Quantitative data were collected using surveys that assessed students’ self-reported confidence, competence, and knowledge development. Results from Friedman’s and Wilcoxon’s Signed-Rank Tests, conducted with a sample of 20 participants in 10 flipped-classroom sessions, statistically showed significant improvements in all three areas. All of Friedman’s test statistics were above 50, with p-values below 0.05, indicating meaningful progress. Similarly, Wilcoxon’s Signed-Rank Test results supported these findings, with p values under 0.05, leading to the rejection of the null hypothesis. The qualitative data, derived from student questionnaire comments and one-to-one interviews, elucidated critical aspects of flipped-classroom delivery. The analysis revealed emerging contradictions (“tensions”) that trigger “expansive learning”. These tensions encompassed the following: student expectation–curriculum structure; traditional versus novel delivery systems; self-regulation and accountability; group learning pace versus interactive learning; and the interplay between motivation and anxiety. These tensions are vital for academic staff and stakeholders to consider when designing and delivering a first-year mathematics course. Understanding these dynamics can lead to more effective, responsive teaching practices and support student success during this crucial transition phase.

This systematic review examines AI-powered assistive technologies for children with neurodevelopmental disorders, with a focus on dyslexia (DYS), attention-deficit hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Our analysis of 84 studies from 2018 to 2024 provides the first thorough cross-disorder comparison of AI implementation patterns. According to our data, each condition has different success rates and technological preferences. AI applications are expanding quickly, especially in research on ASD (56 % of studies), followed by ADHD (36 %), and DYS (8 %). In almost half of the reviewed studies, computer-assisted technologies, which have demonstrated encouraging results in terms of treatment support and diagnostic accuracy, became the main mode of intervention. Despite high accuracy in controlled settings, the implementation of these technologies in clinical practice faces significant challenges. While human oversight remains essential in clinical applications, future advancements should prioritize privacy protection and the ability to assess tools longitudinally. Notably, multimodal approaches that integrate various data types have improved diagnostic accuracy; recent research has shown that they can detect ASD with up to 99.8 % accuracy and ADHD with up to 97.4 % accuracy. A promising trend is the combination of mobile applications and wearable technology, especially for real-time monitoring and intervention. This review highlights the potential and current limitations of AI-driven tools in supporting children with neurodevelopmental disorders. Future development should focus not on replacing clinical expertise, but on augmenting it. Research efforts should aim at creating tools that enhance professional judgment while preserving the essential human components of assessment and intervention.

Artificial Intelligence (AI) and Software Defined Radio (SDR) are transforming the field of signal intelligence. However, the full extent of the capabilities is unknown. This poster presents a paper in development that introduces a cloud-based platform leveraging artificial intelligence to detect and apply 11 modulation schemes (8 digital and 3 analog) to complex or quadrature radio signals. The SNR values analysed range from 0.0 to 40.0, with moderate drift, slight fading, and labelled increments. A comprehensive synthetic database developed by DeepSig is used to train four AI models. These will be integrated with the Google Cloud AI platform to enhance flexibility and processing power. The system will undergo testing with an SDR platform in GNU Radio, showcasing its potential for real-world signal processing applications. Cloud-based platforms offer the adaptability and computational power needed to replace traditional computers for AI-driven signal processing. Initial results indicate successful identification and accurate modulation type detection, with convenient access to the system through internet-connected devices.

Low-Earth-orbit (LEO) satellites are widely acknowledged as a promising infrastructure solution for global Internet of Things (IoT) services. However, the Doppler effect presents a significant challenge in the context of long-range (LoRa) modulation uplink connectivity. This study comprehensively examines the operational efficiency of LEO satellites concerning the Doppler weather effect, with state-of-the-art artificial intelligence techniques. Two LEO satellite constellations—Globalstar and the International Space Station (ISS)—were detected and tracked using ground radars in Perth and Brisbane, Australia, for 24 h starting 1 January 2024. The study involves modelling the constellation, calculating latency, and frequency offset and designing a hybrid Iterative Input Selection–Long Short-Term Memory Network (IIS-LSTM) integrated model to predict the Doppler weather profile for LEO satellites. The IIS algorithm selects relevant input variables for the model, while the LSTM algorithm learns and predicts patterns. This model is compared with Convolutional Neural Network and Extreme Gradient Boosting (XGBoost) models. The results show that the packet delivery rate is above 91% for the sensitive spread factor 12 with a bandwidth of 11.5 MHz for Globalstar and 145.8 MHz for ISS NAUKA. The carrier frequency for ISS orbiting at 402.3 km is 631 MHz and 500 MHz for Globalstar at 1414 km altitude, aiding in combating packet losses. The ISS-LSTM model achieved an accuracy of 97.51% and a loss of 1.17% with signal-to-noise ratios (SNRs) ranging from 0–30 dB. The XGB model has the fastest testing time, attaining ≈0.0997 s for higher SNRs and an accuracy of 87%. However, in lower SNR, it proves to be computationally expensive. IIS-LSTM attains a better computation time for lower SNRs at ≈0.4651 s, followed by XGB at ≈0.5990 and CNN at ≈0.6120 s. The study calls for further research on LoRa Doppler analysis, considering atmospheric attenuation, and relevant space parameters for future work.

Digital technologies with predictive modelling capabilities are revolutionizing electricity markets, especially in demand-side management. Accurate electricity price prediction is essential in deregulated markets; however, developing effective models is challenging due to high-frequency fluctuations and price volatility. This study introduces a hybrid prediction system that addresses these challenges through a comprehensive data processing and modelling framework for half-hourly electricity price predictions. The preprocessing stage employs the Maximum Overlap Discrete Wavelet Transform (MoDWT) to enhance input quality by reducing overlap and revealing underlying price patterns. The prediction model integrates Convolutional Neural Networks with Random Vector Functional Link (CRVFL) in a deep learning hybrid approach. Bayesian Optimization fine-tunes the MoDWT-CRVFL model for optimal performance. Validation of the model is conducted using half-hourly electricity prices from New South Wales. The results highlight the efficacy of the MoDWT-CRVFL model, achieving high accuracy with superior Global Performance Indicator (GPI) values of approximately 1.61, 1.33, 1.85, 1.30, and 0.78 for Summer, Autumn, Winter, Spring, and Annual (Year 2022), respectively, outperforming alternative models. Similarly, the Kling–Gupta Efficiency (KGE) metrics for the proposed model consistently surpassed those of both decomposition-based and standalone models. For instance, the KGE value for MoDWT-CRVFL was approximately 0.972, significantly higher than values of approximately 0.958, 0.899, 0.963, 0.943, 0.930, 0.661, 0.708, 0.696, 0.739, and 0.738 for MoDWT-LSTM, MoDWT-DNN, MoDWT-XGB, MoDWT-RF, MoDWT-MLP, Bi-LSTM, LSTM, DNN, RF, XGB, and MLP, respectively. The methodologies proposed in this study optimize energy resource allocation, market prices, and network management, empowering market operators to make informed decisions for a resilient and efficient electricity market.

Accurate and trust are crucial for ChatGPT and other artificial intelligence (AI) markets. One of the challenges is data leakage, which is frequently overlooked but possesses highly consequential implications. Federated learning (FL) is recognised as a new era of secure AI systems. The market for FL is estimated to reach USD 266.77 million by 2030 according to Polaris Market Research (1). This paper focuses on FL-based approaches for improving AI safety and examines the significance of Deep learning (DL) and its privacy implications. This has been achieved through six models: Federated Convolutional Neural Network (F-CNN), Federated averaging CNN (FA-CNN), Federated Adam (FA), Malicious Generative adversarial network (MGAN), Federated M-GAN (FMGAN) and Conditional GAN (CGAN). The authors analysed MNIST and CIFAR-10 datasets and conducted extensive numerical evaluations to confirm improved user privacy in federated learning for AI models. A case study with fast convergence speed and excellent asymptotic test accuracy was designed to outline White-box attacks on MGAN, FMGAN, and CGAN models. The study also implemented active inference attacks on deep neural networks without sharing raw data through FL. We created 256 synthetic images specifically to test the effectiveness of the original classifier. These counterfeit visuals effectively deceived the classifier, appearing as legitimate representations of true class labels. Trimming shared parameters was ineffective in preventing the attack, revealing limitations in collaborative learning. The generator shows the least loss of 0.0104 encountered of all models in the study. Our Generator is also the fastest after the FMGAN model. FMGAN performs best with maximum accuracy (0.9613) followed by CGAN (0.9208), MGAN (0.9163), FA (0.5148), FCNN (0.4376) and FACNN (0.4285). It also demonstrated high efficiency by successfully attacking in a short timeframe of 0.7459 milliseconds. The Federated approach led by Adam exhibited the longest processing time, at approximately 10.52 minutes. The case study illustrates the risks of surveillance and manipulation by attackers, who pressured participants to disclose confidential information. It also aimed to increase flexibility and robustness. Our work is accessible to diverse audiences, facilitating the adoption and practical applications of deep learning methods for privacy protection by major corporations.

Atmospheric visibility and cloud ceiling forecasts are essential for the safety and efficiency of flight operations and the aviation industry. Routine hourly aviation meteorological observations are recorded at every airport. However, forecasts of these two meteorological parameters using artificial intelligence techniques are limited. This research utilizes data from two study sites in Fiji, Nadi, and Nausori International Airport, and proposes a hybrid Iterative Input Selection – Long Short-Term Memory (IIS-LSTM) integrated model to forecast the consecutive hour’s visibility and ceiling parameters. The IIS algorithm acts as a feature selector from the global predictor matrix of predictor variables with its significant lagged inputs and the significant lagged inputs of the target variable, while the LSTM algorithm acts as the learning model and makes forecasts. The performance of the proposed hybrid IIS-LSTM model is evaluated using seven statistical score metrics and compared with four competing benchmark models. The evaluated results illustrate the superiority of the proposed hybrid IIS-LSTM integrated model and its advanced capability to generate accurate atmospheric visibility and cloud ceiling forecasts for the next consecutive hour compared to the benchmark models. The most important features selected were the second lagged input of visibility and first lagged input of rainfall to improve visibility forecasts while the first and the fifth lagged inputs of the total low cloud cover were paramount for accurate cloud ceiling forecasts. Considering the geography of the study sites, the overall efficacy of the IIS method is strongly advocated to screen most suitable model predictors and the subsequent integration of this input selection method with the LSTM predictive algorithm to attain enhanced performance of the hybrid IIS-LSTM forecast model. This objective model is therefore proposed to be an efficient and cost-effective predictive tool for atmospheric visibility and cloud ceiling forecasts, especially its applications in the aviation industry for aeronautical purposes.

Adaptive modulation and coding schemes play a crucial role in ensuring robust data transfer in wireless communications, especially when faced with changes or interference in the transmission channel. These schemes involve the use of variable coding rates, which can be achieved normally through code puncturing or shortening, and have been adopted in 4G and 5G communication standards. In recent works, auto-encoders for wireless communications have demonstrated the ability to learn short code representations that achieve gains over conventional codes. Such a methodology is attractive as it can learn optimal representations under a variety of channel conditions. However, due to its structure the auto-encoder does not currently support multiple code rates with a single model. This article draws upon the discipline of multi-task learning, as it applies to deep learning and therefore devises a branching architecture for the auto-encoder and custom training algorithm in training transmitter and receiver for adaptive modulation and coding. In this article we aim to demonstrate improvements in Block Error Rate over conventional methods in the Additive White Gaussian Noise channel, and to analyse the performance of the model under Rayleigh fading channels without retraining the auto-encoder on the new channel. This article demonstrates a novel approach towards training auto-encoder models to jointly learn adaptive modulation and coding schemes framed as a multi-task learning problem. The research outcomes extend end-to-end learning approaches to the design of adaptive wireless communications systems.

The objective of this study is to develop a novel multi-level pre-processing framework and apply it for multi-step (one and seven days ahead) daily forecasting of Surface soil moisture (SSM) based on the NASA’s Soil Moisture Active Passive (SMAP)-satellite datasets in arid and semi-arid regions of Iran. The framework consists of the Boruta gradient boosting decision tree (Boruta-GBDT) feature selection integrated with the multivariate variational mode decomposition (MVMD) and advanced machine learning (ML) models including bidirectional gated recurrent unit (Bi-GRU), cascaded forward neural network (CFNN), adaptive boosting (AdaBoost), genetic programming (GP), and classical multilayer perceptron neural network (MLP). For this purpose, effective geophysical soil moisture predictors for two arid stations of Khosrowshah and Neyshabur were first filtered among 21 daily input signals from 2015 to 2020 by using the Boruta-GBDT feature selection. The selected signals were then decomposed using the MVMD scheme. In the last pre-processing stage, the most relevant sub-sequences from a large pool in previous process were filtered using the Boruta-GBDT scheme aiming to reduce the computation and enhance the accuracy, before feeding the ML approaches. The comparison of the results from the five hybrid and standalone counterpart models in term of standardized RMSE improvement (SRMSEI) revealed that MV MD-BG-CFNN for SSM(T+1)| 27.13% and SSM (T+7)| 43.55% at Khosrowshah station and SSM(T+1)| 21.16% and SSM (T+7)| 30.10% at Neyshabur station outperformed the other hybrid frameworks, followed by MV MD-BG-Bi−GRU, MV MD-BG-Adaboost, MV MD-BG-GP, and MV MD-BG-MLP. The accurately forecasted SSM data help improve irrigation scheduling, which is of significant importance in water use efficiency and food security.

The development of computationally-efficient algorithms is crucial to support the extremely-low latency and ultra-high reliability requirements of the next-generation radio communication systems. Error-correction codes (ECC) are used in communication systems to maintain the reliability of data transmissions. In this paper, several commonly used artificial intelligence (AI) methods are used to design algorithms for bitwise decoding of (ECC). The AI-based decoding algorithms are analysed and compared using their error-correction performance, training time and computational intensity. The efficacy is assessed using the benchmark codes: extended binary Golay and the Hamming code for varying Signal-to-Noise Ratios (SNR) over the Additive White Gaussian Noise (AWGN) channel and the decoding performance is evaluated using the block error rate (BLER). It is envisaged that the results from this comparative study would help to identify AI models most suitable for developing computationally efficient and practically-implementable algorithms for decoding longer ECC.

The current management of microalgae cultivation requires manual microscopic examination in order to identify desired and competing species, as well as predators. In this study, we trained and tested a transfer learning model modified from EfficientNetV2 B3 model on 434 and 161 prospectively acquired images of the preferred Nanno-chloropsis sp microalgae and competitor Spirulina, respectively, and achieved >98

Forecasting the air quality index (AQI) is a critical and pressing challenge for developing nations worldwide. With air pollution emerging as a significant threat to the environment, this study considers seven study sites of the sub-tropical region in Bangladesh and introduces a novel hybrid deep-learning model. The proposed model, expressed as CLSTM-BiGRU, integrates a convolutional neural network (CNN), a long-short term memory (LSTM), and a bi-directional gated recurrent unit (BiGRU) network. Leveraging nineteen remotely sensed predictor variables and harnessing the grey wolf optimization (GWO) algorithm, the CLSTM-BiGRU model showcases its superiority in air quality forecasting. It consistently outperforms the benchmark models, yielding lower forecasting errors and higher efficiency (i.e., correlation coefficient ~1) values. Hence, this study underscores the feasibility and substantial potential of the hybrid deep learning model, which can provide precise forecasts of air quality index, and will be highly useful for relevant stakeholders and decision-makers. Furthermore, the adaptability and potential utility of this innovative model may be ascertained for air quality monitoring and effective public health risk mitigation in urban environments.

Particulate matter (PM) or particle pollution include the tiny particles of dust and fly ash particles are expelled from coal-burning power plants. Coal combustion is an extremely prevalent source of air pollution, and resulting PM has substantial impacts on human health, especially in industrial zones. This paper aims to design a novel hybrid deep learning framework based on long short-term memory (LSTM) integrated with a two-stage data filtering technique to accurately predict the air quality indices (i.e., PM2.5 and PM10) in a chosen study region ‘Miles Airport, Queensland,’ that meets the needs of the coal seam gas industry in Australia. The data used to construct the novel hybrid two-stage data filtering technique based on LSTM comprising of six meteorological parameters (i.e., wind direction, wind speed, air temperature, relative humidity, solar radiation, and rainfall) and two environmental factors (i.e., ozone and total suspended particulate). In the first stage, two robust feature selection methods, namely, extreme gradient boosting (XGBoost) and the classification and regression tree (CART) approach, were adopted to explore the most significant predictors. Then in the second stage, the best subset regression (BSR) technique is utilized to determine the best subsets input combinations i.e., C1, C2, and C3 based on several particular metrics. The three BSR-based input combinations were employed in the LSTM model to estimate the PM2.5 and PM10. Furthermore, to validate the main hybrid framework, two advanced machine learning (ML) methods (i.e., LightGBM and ridge kernel regression (KRR)) and two traditional ML methods (i.e., Adaptive neuro-fuzzy inference system (ANFIS) and multilayer perceptron neural network (MLP)) were hybridized with the multi-level data filtering strategy by examining the optimal input combinations. Several statistical metrics, graphical tools, and diagnostic analyses evaluated the hybrid models. The outcomes of the PM2.5 simulation based on 2375 data samples showed that the LSTM-C3 containing all the selected predictors yielded the most promising accuracy, followed by the LightGBM-C3 and MLP-C3 models. On the other hand, the simulation of PM10 distribution demonstrated that the LSTM-C3 was superior to other models, followed by the KRR-C3 and LightGBM-C3 models.

Wheat dominates the Australian grain production market and accounts for 10–15% of the world’s 100 million tonnes annual global wheat trade. Accurate wheat yield prediction is critical to satisfying local consumption and increasing exports regionally and globally to meet human food security. This paper incorporates remote satellite-based information in a wheat-growing region in South Australia to estimate the yield by integrating the kernel ridge regression (KRR) method coupled with complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and the grey wolf optimisation (GWO). The hybrid model, ‘GWO-CEEMDAN-KRR,’ employing an initial pool of 23 different satellite-based predictors, is seen to outperform all the benchmark models and all the feature selection (ant colony, atom search, and particle swarm optimisation) methods that are implemented using a set of carefully screened satellite variables and a feature decomposition or CEEMDAN approach. A suite of statistical metrics and infographics comparing the predicted and measured yield shows a model prediction error that can be reduced by ~20% by employing the proposed GWO-CEEMDAN-KRR model. With the metrics verifying the accuracy of simulations, we also show that it is possible to optimise the wheat yield to achieve agricultural profits by quantifying and including the effects of satellite variables on potential yield. With further improvements in the proposed methodology, the GWO-CEEMDAN-KRR model can be adopted in agricultural yield simulation that requires remote sensing data to establish the relationships between crop health, yield, and other productivity features to support precision agriculture.

In this reflection, three faculty members (Associate Professor Linda Galligan, Associate Professor Rachel King, and Dr. Trevor Langlands), a student partner (Ekta Sharma), and the peer learning coordinator (Leigh Pickstone) from the University of Southern Queensland (USQ), a regional university in Australia, consider the partnership experience undertaken in the ongoing development and management of an online mathematics and statistics discipline learning management system site. From the perspective of academic members, an important outcome of this Students-as-Partners (SaP) project was to bring student voice and engagement to the site. This was invaluable to a resource seeking to provide a point of connection, communication, and encouragement for students and staff teaching and learning within the discipline. From the student perspective, the partnership led to increased learning about research, industry, and career opportunities and the chance to share areas of knowledge and interest. From the perspective of the peer learning coordinator, this project was an opportunity to nurture and encourage partnership work at the university.

Global solar radiation (GSR) prediction plays an essential role in planning, controlling and monitoring solar power systems. However, its stochastic behaviour is a significant challenge in achieving satisfactory prediction results. This study aims to design an innovative hybrid prediction model that integrates a feature selection mechanism using a Slime-Mould algorithm, a Convolutional-Neural-Network (CNN), a Long–Short-Term-Memory Neural Network (LSTM) and a final CNN with Multilayer-Perceptron output (SCLC algorithm hereafter). The proposed model was applied to six solar farms in Queensland (Australia) at daily temporal horizons in six different time steps. The comprehensive benchmarking of the obtained results with those from two Deep-Learning (CNN-LSTM, Deep-Neural-Network) and three Machine-Learning (Artificial-Neural-Network, Random-Forest, Self-Adaptive Differential-Evolutionary Extreme-Learning-Machines) models highlighted a higher performance of the proposed prediction model in all the six selected solar farms. From the results obtained, this work establishes that the designed SCLC algorithm could have a practical utility for applications in renewable and sustainable energy resource management.

Crop yield forecasting is critical for enhancing food security and ensuring an appropriate food supply. It is critical to complete this activity with high precision at the regional and national levels to facilitate speedy decision-making. Tea is a big cash crop that contributes significantly to economic development, with a market of USD 200 billion in 2020 that is expected to reach over USD 318 billion by 2025. As a developing country, Bangladesh can be a greater part of this industry and increase its exports through its tea yield and production with favorable climatic features and land quality. Regrettably, the tea yield in Bangladesh has not increased significantly since 2008 like many other countries, despite having suitable climatic and land conditions, which is why quantifying the yield is imperative. This study developed a novel spatiotemporal hybrid DRS–RF model with a dragonfly optimization (DR) algorithm and support vector regression (S) as a feature selection approach. This study used satellite-derived hydro-meteorological variables between 1981 and 2020 from twenty stations across Bangladesh to address the spatiotemporal dependency of the predictor variables for the tea yield (Y). The results illustrated that the proposed DRS–RF hybrid model improved tea yield forecasting over other standalone machine learning approaches, with the least relative error value (11%). This study indicates that integrating the random forest model with the dragonfly algorithm and SVR-based feature selection improves prediction performance. This hybrid approach can help combat food risk and management for other countries.