Current Trends and Advances in Computer-Aided Intelligent Environmental Data Engineering

Current Trends and Advances in Computer-Aided Intelligent Environmental Data Engineering merges computer engineering and environmental engineering. The book presents the latest finding on how data science and AI-based tools are being applied in environmental engineering research. This application involves multiple domains such as data science and artificial intelligence to transform the data collected by intelligent sensors into relevant and reliable information to support decision-making. These tools include fuzzy logic, knowledge-based systems, particle swarm optimization, genetic algorithms, Monte Carlo simulation, artificial neural networks, support vector machine, boosted regression tree, simulated annealing, ant colony algorithm, decision tree, immune algorithm, and imperialist competitive algorithm.

This book is a fundamental information source because it is the first book to present the foundational reference material in this new research field. Furthermore, it gives a critical overview of the latest cross-domain research findings and technological developments on the recent advances in computer-aided intelligent environmental data engineering.

Cover image
Title page
Table of Contents
Copyright
List of contributors
Chapter 1. An introduction to Current Trends and Advances in Computer-Aided Intelligent Environmental Data Engineering
Abstract
Introduction
Book structure and relevant audience
Intelligent systems in environmental engineering research
Looking to the future
References
Section 1: Data-centric and intelligent systems in air quality monitoring, assessment and mitigation
Chapter 2. Application of deep learning and machine learning in air quality modeling
Abstract
Introduction
Data profiling
Learning from data
Conclusions and further thoughts
Acknowledgments
References
Chapter 3. Advances in data-centric intelligent systems for air quality monitoring, assessment, and control
Abstract
Introduction
Overview of AI-based technologies and data-centric systems for pollution control
References
Chapter 4. Intelligent systems in air pollution research: a review
Abstract
Introduction
The definition of atmosphere
The structure of the atmosphere
Different contaminants in the air
Tropospheric ozone (O3)
Nitrogen dioxide (NO2)
Particulate matter
Carbon monoxide and carbon dioxide
Sulfur dioxide
Review of the literature
A new studied case
Research methodology
The investigated city
Input and output parameters
Error-related criteria
Results and discussion
Uncertainty of different models
Analyzing error for smaller ranges of the input parameters
Conclusions
References
Chapter 5. ESTABLISH—a decision support system for monitoring the quality of air for human health
Abstract
Introduction
Related work
ESTABLISH pilot study: user requirements
ESTABLISH decision support system
Deployment, data acquisition, and integration
Preliminary testing of sensors
Data acquisition and integration from wearable devices
Data acquisition and integration from environmental monitoring devices
Visualization of the air quality index
ESTABLISH platform presentation
User guide for patients
User guide for therapists
Conclusions
Acknowledgments
References
Chapter 6. Indoor air pollution: a comprehensive review of public health challenges and prevention policies
Abstract
Introduction
Indoor air quality and public health
Enhanced indoor air quality and prevention strategies
Technologies and control policies for enhanced indoor air quality
Discussion
Conclusion
References
Section 2: Data-centric and intelligent systems in water quality monitoring, assessment and mitigation
Chapter 7. Data-centric intelligent systems for water quality monitoring, assessment, and control
Abstract
Introduction
Problems associated with numerical modeling in hydraulic transport and water quality prediction
Why artificial intelligence?
Conclusion
References
Further reading
Chapter 8. ANN prognostication and GA optimization of municipal solid waste leachate treatment using aluminum electrodes via electrocoagulation-flocculation method
Abstract
Introduction
Methodology
Artificial neural network modeling
Genetic algorithm optimization of the ECF process
Statistical analysis of the data
Calculation of electrode and electrical consumption
Results and discussion
Genetic algorithm optimization results
Statistical analysis results
Electrode and electrical power consumption during the ECF process
Conclusion
Acknowledgment
References
Chapter 9. Application of deep learning and machine learning methods in water quality modeling and prediction: a review
Abstract
Introduction
Deep learning and machine learning in WQ modeling and prediction
Overview of learning methods
Supervised learning
Unsupervised learning
Reinforcement learning
Semisupervised learning
Machine learning architectures used in water quality modeling and prediction
Artificial neural network
Neural networks models
Support vector machines
Decision trees
Deep learning architectures used in water quality modeling and prediction
Convolutional neural network
Recurrent neural network
Generative unsupervised models
Application of ML and DL models in WQ prediction of different water systems
Modeling and prediction of different water systems
Data collection
Input data selection
Data splitting
Data preprocessing
Model structure determination
Model training
Performance evaluation measures
Challenges facing DL and ML predictions
Conclusions and future prospects
References
Chapter 10. Intelligent systems in water pollution research: a review
Abstract
Introduction
Water standards
Water desalination technologies
Review of the literature
Selected case study from the literature
Conclusions
References
Chapter 11. A long short-term memory deep learning approach for river water temperature prediction
Abstract
Introduction
Materials and methods
Methodology
Results and discussion
Conclusions and future recommendations
References
Section 3: Data-centric and intelligent systems in land pollution research
Chapter 12. Machine learning and artifical intelligence application in land pollution research
Abstract
Introduction
Application of deep learning and machine learning methods in flow modeling of landfill leachate
Application of deep learning and machine learning methods in soil quality assessment and remediation
Establishing a nexus between nonbiodegradable waste and data-centric systems
Case studies of evaluations and analysis of solid waste management techniques by deep learning and machine learning methods
Conclusions
References
Chapter 13. Application of artificial intelligence in the mapping and measurement of soil pollution
Abstract
Introduction
Methodology
Search and selection criteria
Quality check and data extraction
Theoretical backgrounds to the different AI models
Artificial neural network
Support vector machines
Adaptive neurofuzzy inference system
Random forest
Gradient boosted machine
Bayesian machine learning
Hybrid models
Application domain of the different AI models
AI models in soil pollutant measurement
Conclusions
References
Further reading
Chapter 14. Artificial intelligence in the reduction and management of land pollution
Abstract
Introduction
The use of artificial intelligence and robotics in system modification for effective on-the-spot minimization of wastes in process industries
Convolutional neural network model system of waste classification
Support vector machine
Artificial intelligence-robotics pickup system
Artificial intelligence and robotics in waste recycling
Robotic recycle sorting system
Artificial intelligence-robotic quality assessment system
Reforestation for land pollution management: impact of drones and neural network
Land pollution management via sustainable green agriculture: use of machine learning and robotics
Conclusion
References
Further reading
Section 4: Data-centric and intelligent systems in noise pollution research and other environmental engineering issues
Chapter 15. Advanced soft computing techniques in modeling noise pollution health impacts
Abstract
Introduction
Effect of noise pollution on human health
Noise pollution health-impact modeling
Stage 1: Defining individual constructs
Stage 2: Developing and specifying the measurement model
Stage 3: Designing a study to produce empirical results
Stage 4: Assessing measurement model validity
Stage 5: Specifying the structural model
Stage 6: Assessing the structural model validity
SEM and ANFIS case studies
Conclusion
References
Chapter 16. Intelligent and knowledge-based waste management: smart decision-support system
Abstract
Introduction
Trends in exploration and production wastes in the oil and gas industry
Oil and gas waste management
Conventional waste management approach in the oil and gas industry
Environmental impact of oil and gas generated wastes
Challenges of conventional waste management systems
Expert system for the oil and gas waste management system
Gaps in a waste management expert system
Effective utilization of expert systems in oil and gas industry waste management
Conclusion
References
Chapter 17. Computer-aided modeling of solid waste conversion: case study of maize (Zea mays) residues air gasification
Abstract
Introduction
Methodology
Results and discussion
Conclusion
References
Chapter 18. Neural network model for biological waste management systems
Abstract
Introduction
Materials and methods
Data-driven modeling approaches
Artificial neural network-based predictive modeling
Choosing the activation function
Choosing the appropriate training algorithm
Data preprocessing and randomization
Data division
Internal parameters of the network and performance evaluation
Sensitivity analysis
Statistical analysis
Results and discussions
Artificial neural modeling of the different biological reactors
Predictive capability of the model for modified RBC
Sensitivity analysis of inputs
Removal of DCM in the biotrickling filter
Predictive capability and sensitivity of the ANN model
Conclusion
References
Chapter 19. The role of artificial neural networks in bioproduct development: a case of modeling and optimization studies
Abstract
Introduction
Bioproduct development
Product formulation
Product deformulation
Selected optimization tools used in bioprocess development as computational intelligence
Genetic algorithms
Fuzzy logic
Application of optimization tools in bioprocessing operations
Bioremediation
Biofuel production
Biopharmacy
Future developments or trends
Conclusion
References
Chapter 20. Modeling of grains sun drying: from theoretical methods to intelligent systems
Abstract
Introduction
An account of early theoretical modeling efforts
Intelligent systems in the modeling of grain sun drying
Conclusion
References
Index

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Current Trends and Advances in Computer-Aided Intelligent Environmental Data Engineering

Purchase options

Institutional subscription on ScienceDirect

Goncalo Marques

Joshua O. Ighalo