Photovoltaic (PV) power generation has become a key area for investment worldwide. Solar PV panels are the core components of PV power generation systems, and the accumulation of soiling on their surfaces has numerous adverse effects on power generation. This paper provides an overview of the soiling accumulation on PV panels and the existing soiling removal methods. Firstly, the sources of soiling particles and the mechanism of soiling fall are analyzed, based on which the accumulation of soiling on the surface of the PV panels is described in detail, and then the effect of the surface soiling on the PV panels is investigated in the order of optics‐thermology‐electrical, with the necessary semiempirical formulas provided to assist in more in‐depth analyses. In addition, the principles, status quo, effects, costs, advantages, and disadvantages of existing soiling removal methods are specifically described, thus providing a reference for the selection of soiling removal methods in different regions. The paper also analyses the soiling accumulation and removal challenges of PV panels in different regions of China. The results of the study are important for the improvement of the effectiveness of soiling removal and the rational optimization of the soiling removal scheme.

Waste from used solar panels will be a worldwide problem in the near future mainly due to the strong uptake in solar energy and the necessity of disposing solar panel systems at the end–of–life stage, as these materials are hazardous. While new techniques and strategies are often investigated to manage the end–of–life of solar panels effectively, there is huge potential in recycling and reusing solar panel waste as components for alternate products. Numerous studies have been conducted on using alternate materials instead of conventional materials in pavement construction. The current study presents a detailed review and a discussion on using solar panel waste materials in pavement construction. The findings present opportunities to use different solar panel waste materials such as glass, aluminium (Al), silicon (Si), and polymer waste as potential replacement materials in various types of pavement construction. The study also presents the current progress and future focus on experimental developments in pavements with solar panel waste to benchmark short–term and long–term characteristics. Finally, the review discusses the impediments that restrict and the drivers that can facilitate the implementation of solar panel waste in pavement construction. The main findings from this review can be used as a quantitative foundation to facilitate decisions on using different solar panel waste materials in pavement construction applications. Furthermore, such findings will also be beneficial for policymakers and industry stakeholders to implement effective supply chain strategies for promoting solar panel waste as a potential pavement construction material.

Low-carbon concrete mixes that incorporate high volumes of fly ash and slag as cement replacements are becoming increasingly more common as part of efforts to decarbonise the construction industry. Though environmental benefits are offered, concretes containing supplementary cementitious materials exhibit different creep behaviour when compared to conventional concrete. Creep can significantly impact long-term structural behaviour and influence the overall serviceability and durability of concrete structures. This paper develops a creep compliance prediction model using supervised machine learning techniques for concretes containing fly ash and slag as cement substitutes. Gaussian process regression (GPR), artificial neural networks (ANN), random forest regression (RFR) and decision tree regression (DTR) models were all considered. The dataset for model training was developed by mining relevant data from the Infrastructure Technology Institute of Northwestern University’s comprehensive creep dataset in addition to extracting data from the literature. Holdout validation was adopted with the data partitioned into training (70%) and validation (30%) sets. Based on statistical indicators, all machine learning models can accurately model creep compliance with the RFR and GPR found to be the best-performing models. The sensitivity of the GPR model’s performance to training repetitions, input variable selection and validation methodology was assessed, with the results indicating small variability. The importance of the selected input variables was analysed using the Shapley additive explanation. It was found that time was the most significant parameter, with loading age, compressive strength, elastic modulus, volume-to-surface ratio and relative humidity also showing high importance. Fly ash and silica fume content featured the least influence on creep prediction. Furthermore, the predictions of the trained models were compared to experimental data, which showed that the GPR, RFR and ANN models can accurately reflect creep behaviour and that the DTR model does not give accurate predictions.