Water and wastewater quality prediction: current trends and challenges in the implementation of artificial neural network

Carbon Emission Prediction and Emission Reduction Analysis of Wastewater Treatment Plant Based on Machine Learning and Deep Learning

“…𝑀 𝑐 is the emission equivalent of the consumption, 𝑘𝑔𝐶𝑂 2 /𝑘𝑔 ; 𝑓 𝑐,𝑔 is the emission factor for chemical g, 𝑘𝑔𝐶𝑂 2 /𝑘𝑔; 𝑀 𝑐𝑔 is the amount of chemical g used, kg. (6) The formula for calculating the total carbon emissions from a wastewater treatment plant is as follows:…”

“…Both types of predictive models have been widely used in the fields of wastewater treatment and carbon emission prediction. Specific methods including regression analysis, random forests, and neural networks have been widely used in real-world scenarios such as wastewater quality prediction, carbon emission estimation, and greenhouse gas emission impact assessment [3][4][5][6]. For example, Azeez et al developed a support vector regression (SVR) model to predict carbon emissions from automobiles [7], Zhu et al investigated and predicted the peak carbon emissions from the transportation sector in China using an SVR model and a scenario analysis model [8] ; furthermore, Chu and Zhao used an enhanced PSO-SVR model to predict carbon emissions from buildings [9].…”

Computational Chemistry as Applied in Environmental Research: Opportunities and Challenges

“…ML is a subset of statistics and AI, and it is focused on creating algorithms that allow computer systems to learn, extract, cluster, and analyze data to make predictions or decisions without specific coding to perform the given tasks . ML models perform well when dealing with large amounts of data (training sets), and they have been used in environmental applications including the management and disposal of waste, modeling environmental and ecological systems, − advancing and predicting water treatment processes, , assessing the physicochemical parameters of environmental quality, and in pollution monitoring and forecasting . By 2030, the investment in AI in the water industry is expected to reach 6.3 billion USD, and it is predicted to save around 20%–30% of operational costs by optimizing processes and raw materials for water treatment …”

“…46 AI models, including machine learning, are expected to pave the way to improve the understanding and modeling of complex environmental processes and replace operating models (e.g., WWTP) with the help of proper historical data sets, higher computer capacities, and proper domain knowledge. 305 The unique capacity of AI and ML to learn and adapt its models based on input data (either computational or experimental) holds the promise to advance the discovery of novel chemical systems for solving our current concerns even further and faster. 24 The inclusion of ML in QM and MD simulations has already been explored to study interfacial processes, radical chemical reactions, extended systems (e.g., biomolecules and nanomaterials), and photochemical transformations.…”

“…Other significant drawbacks of AI models include validation, which can be time demanding and computationally expensive when dealing with large data sets, and, in some cases, the difficulty of explaining the correlations between input and output variables . AI models, including machine learning, are expected to pave the way to improve the understanding and modeling of complex environmental processes and replace operating models (e.g., WWTP) with the help of proper historical data sets, higher computer capacities, and proper domain knowledge . The unique capacity of AI and ML to learn and adapt its models based on input data (either computational or experimental) holds the promise to advance the discovery of novel chemical systems for solving our current concerns even further and faster .…”