{"product_id":"machine-learning-in-chemical-safety-and-health-9781119817482","title":"Machine Learning in Chemical Safety and Health","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003e\u003cp\u003e\u003cb\u003eIntroduces Machine Learning Techniques and Tools and Provides Guidance on How to Implement Machine Learning Into Chemical Safety and Health-related Model Development\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eThere is a growing interest in the application of machine learning algorithms in chemical safety and health-related model development, with applications in areas including property and toxicity prediction, consequence prediction, and fault detection. This book is the first to review the current status of machine learning implementation in chemical safety and health research and to provide guidance for implementing machine learning techniques and algorithms into chemical safety and health research. \u003c\/p\u003e\u003cp\u003eWritten by an international team of authors and edited by renowned experts in the areas of process safety and occupational and environmental health, sample topics covered within the work include: \u003c\/p\u003e\u003cul\u003e\u003cli\u003eAn introduction to the fundamentals of machine learning, including regression, classification and cross-validat\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003cp\u003eList of Contributors xiii\u003c\/p\u003e \u003cp\u003ePreface xvii\u003c\/p\u003e \u003cp\u003e1 Introduction 1\u003c\/p\u003e \u003cp\u003ePingfan Hu and Qingsheng Wang\u003c\/p\u003e \u003cp\u003e1.1 Background 2\u003c\/p\u003e \u003cp\u003e1.2 Current State 5\u003c\/p\u003e \u003cp\u003e1.2.1 Flammability Characteristics Prediction Using Quantitative Structure–Property\u003c\/p\u003e \u003cp\u003eRelationship 5\u003c\/p\u003e \u003cp\u003e1.2.2 Consequence Prediction Using Quantitative Property–Consequence\u003c\/p\u003e \u003cp\u003eRelationship 6\u003c\/p\u003e \u003cp\u003e1.2.3 Machine Learning in Process Safety and Asset Integrity Management 6\u003c\/p\u003e \u003cp\u003e1.2.4 Machine Learning for Process Fault Detection and Diagnosis 7\u003c\/p\u003e \u003cp\u003e1.2.5 Intelligent Method for Chemical Emission Source Identification 7\u003c\/p\u003e \u003cp\u003e1.2.6 Machine Learning and Deep Learning Applications in Medical Image Analysis 7\u003c\/p\u003e \u003cp\u003e1.2.7 Predictive Nanotoxicology: Nanoinformatics Approach to Toxicity Analysis of\u003c\/p\u003e \u003cp\u003eNanomaterials 8\u003c\/p\u003e \u003cp\u003e1.2.8 Machine Learning in Environmental Exposure Assessment 8\u003c\/p\u003e \u003cp\u003e1.2.9 Air Quality Prediction Using Machine Learning 8\u003c\/p\u003e \u003cp\u003e1.3 Software and Tools 9\u003c\/p\u003e \u003cp\u003e1.3.1 R 9\u003c\/p\u003e \u003cp\u003e1.3.2 Python 12\u003c\/p\u003e \u003cp\u003eReferences 13\u003c\/p\u003e \u003cp\u003e2 Machine Learning Fundamentals 19\u003c\/p\u003e \u003cp\u003eYan Yan\u003c\/p\u003e \u003cp\u003e2.1 What Is Learning? 19\u003c\/p\u003e \u003cp\u003e2.1.1 Machine Learning Applications and Examples 20\u003c\/p\u003e \u003cp\u003e2.1.2 Machine Learning Tasks 21\u003c\/p\u003e \u003cp\u003e2.2 Concepts of Machine Learning 22\u003c\/p\u003e \u003cp\u003e2.3 Machine Learning Paradigms 24\u003c\/p\u003e \u003cp\u003e2.4 Probably Approximately Correct Learning 25\u003c\/p\u003e \u003cp\u003e2.4.1 Deterministic Setting 26\u003c\/p\u003e \u003cp\u003e2.4.2 Stochastic Setting 29\u003c\/p\u003e \u003cp\u003ev\u003c\/p\u003e \u003cp\u003e0005453285.3D 5 30\/8\/2022 8:51:33 PM\u003c\/p\u003e \u003cp\u003e2.5 Estimation and Approximation 31\u003c\/p\u003e \u003cp\u003e2.6 Empirical Risk Minimization 32\u003c\/p\u003e \u003cp\u003e2.6.1 Empirical Risk Minimizer 32\u003c\/p\u003e \u003cp\u003e2.6.2 VC-dimension Generalization Bound 33\u003c\/p\u003e \u003cp\u003e2.6.3 General Loss Functions 34\u003c\/p\u003e \u003cp\u003e2.7 Regularization 35\u003c\/p\u003e \u003cp\u003e2.7.1 Regularized Loss Minimization 35\u003c\/p\u003e \u003cp\u003e2.7.2 Constrained and Regularized Problem 36\u003c\/p\u003e \u003cp\u003e2.7.3 Trade-off Between Estimation and Approximation Error 37\u003c\/p\u003e \u003cp\u003e2.8 Maximum Likelihood Principle 38\u003c\/p\u003e \u003cp\u003e2.8.1 Maximum Likelihood Estimation 39\u003c\/p\u003e \u003cp\u003e2.8.2 Cross Entropy Minimization 40\u003c\/p\u003e \u003cp\u003e2.9 Optimization 41\u003c\/p\u003e \u003cp\u003e2.9.1 Linear Regression: An Example 42\u003c\/p\u003e \u003cp\u003e2.9.2 Closed-form Solution 42\u003c\/p\u003e \u003cp\u003e2.9.3 Gradient Descent 43\u003c\/p\u003e \u003cp\u003e2.9.4 Stochastic Gradient Descent 45\u003c\/p\u003e \u003cp\u003eReferences 46\u003c\/p\u003e \u003cp\u003e3 Flammability Characteristics Prediction Using QSPR Modeling 47\u003c\/p\u003e \u003cp\u003eYong Pan and Juncheng Jiang\u003c\/p\u003e \u003cp\u003e3.1 Introduction 47\u003c\/p\u003e \u003cp\u003e3.1.1 Flammability Characteristics 47\u003c\/p\u003e \u003cp\u003e3.1.2 QSPR Application 48\u003c\/p\u003e \u003cp\u003e3.1.2.1 Concept of QSPR 48\u003c\/p\u003e \u003cp\u003e3.1.2.2 Trends and Characteristics of QSPR 48\u003c\/p\u003e \u003cp\u003e3.2 Flowchart for Flammability Characteristics Prediction 49\u003c\/p\u003e \u003cp\u003e3.2.1 Dataset Preparation 51\u003c\/p\u003e \u003cp\u003e3.2.2 Structure Input and Molecular Simulation 52\u003c\/p\u003e \u003cp\u003e3.2.3 Calculation of Molecular Descriptors 53\u003c\/p\u003e \u003cp\u003e3.2.4 Preliminary Screening of Molecular Descriptors 54\u003c\/p\u003e \u003cp\u003e3.2.5 Descriptor Selection and Modeling 55\u003c\/p\u003e \u003cp\u003e3.2.6 Model Validation 57\u003c\/p\u003e \u003cp\u003e3.2.6.1 Model Fitting Ability Evaluation 57\u003c\/p\u003e \u003cp\u003e3.2.6.2 Model Stability Analysis 59\u003c\/p\u003e \u003cp\u003e3.2.6.3 Model Predictivity Evaluation 60\u003c\/p\u003e \u003cp\u003e3.2.7 Model Mechanism Explanation 61\u003c\/p\u003e \u003cp\u003e3.2.8 Summary of QSPR Process 61\u003c\/p\u003e \u003cp\u003e3.3 QSPR Review for Flammability Characteristics 62\u003c\/p\u003e \u003cp\u003e3.3.1 Flammability Limits 62\u003c\/p\u003e \u003cp\u003e3.3.1.1 LFLT and LFL 62\u003c\/p\u003e \u003cp\u003e3.3.1.2 UFLT and UFL 64\u003c\/p\u003e \u003cp\u003e3.3.2 Flash Point 65\u003c\/p\u003e \u003cp\u003e3.3.3 Auto-ignition Temperature 68\u003c\/p\u003e \u003cp\u003e3.3.4 Heat of Combustion 69\u003c\/p\u003e \u003cp\u003evi Contents\u003c\/p\u003e \u003cp\u003e0005453285.3D 6 30\/8\/2022 8:51:33 PM\u003c\/p\u003e \u003cp\u003e3.3.5 Minimum Ignition Energy 70\u003c\/p\u003e \u003cp\u003e3.3.6 Gas-liquid Critical Temperature 70\u003c\/p\u003e \u003cp\u003e3.3.7 Other Properties 72\u003c\/p\u003e \u003cp\u003e3.4 Limitations 72\u003c\/p\u003e \u003cp\u003e3.5 Conclusions and Future Prospects 73\u003c\/p\u003e \u003cp\u003eReferences 73\u003c\/p\u003e \u003cp\u003e4 Consequence Prediction and Quantitative Property–Consequence Relationship\u003c\/p\u003e \u003cp\u003eModels 81\u003c\/p\u003e \u003cp\u003eZeren Jiao and Qingsheng Wang\u003c\/p\u003e \u003cp\u003e4.1 Introduction 81\u003c\/p\u003e \u003cp\u003e4.2 Conventional Consequence Prediction Methods 82\u003c\/p\u003e \u003cp\u003e4.2.1 Empirical Method 82\u003c\/p\u003e \u003cp\u003e4.2.2 Computational Fluid Dynamics (CFD) Method 83\u003c\/p\u003e \u003cp\u003e4.2.3 Integral Method 84\u003c\/p\u003e \u003cp\u003e4.3 Machine Learning and Deep Learning-Based Consequence Prediction Models 84\u003c\/p\u003e \u003cp\u003e4.4 Quantitative Property–Consequence Relationship Models 86\u003c\/p\u003e \u003cp\u003e4.4.1 Consequence Database 88\u003c\/p\u003e \u003cp\u003e4.4.2 Property Descriptors 89\u003c\/p\u003e \u003cp\u003e4.4.3 Machine Learning and Deep Learning Algorithms 89\u003c\/p\u003e \u003cp\u003e4.5 Challenges and Future Directions 90\u003c\/p\u003e \u003cp\u003eReferences 91\u003c\/p\u003e \u003cp\u003e5 Machine Learning in Process Safety and Asset Integrity Management 93\u003c\/p\u003e \u003cp\u003eMing Yang ,Hao Sun and Rustam Abubarkirov\u003c\/p\u003e \u003cp\u003e5.1 Opportunities and Threats 93\u003c\/p\u003e \u003cp\u003e5.2 State-of-the-Art Reviews 95\u003c\/p\u003e \u003cp\u003e5.2.1 Artificial Neural Networks (ANNs) 95\u003c\/p\u003e \u003cp\u003e5.2.2 Principal Component Analysis (PCA) 97\u003c\/p\u003e \u003cp\u003e5.2.3 Genetic Algorithm (GA) 97\u003c\/p\u003e \u003cp\u003e5.3 Case Study of Asset Integrity Assessment 98\u003c\/p\u003e \u003cp\u003e5.4 Data-Driven Model of Asset Integrity Assessment 105\u003c\/p\u003e \u003cp\u003e5.4.1 Condition Monitoring Data Collection 106\u003c\/p\u003e \u003cp\u003e5.4.2 Data Processing and Storage 106\u003c\/p\u003e \u003cp\u003e5.4.3 Data Mining for Risk Quantification and Monitoring Control 107\u003c\/p\u003e \u003cp\u003e5.4.4 AIM Application 107\u003c\/p\u003e \u003cp\u003e5.4.5 The Application of the Framework 108\u003c\/p\u003e \u003cp\u003e5.5 Conclusion 109\u003c\/p\u003e \u003cp\u003eReferences 109\u003c\/p\u003e \u003cp\u003e6 Machine Learning for Process Fault Detection and Diagnosis 113\u003c\/p\u003e \u003cp\u003eRajeevan Arunthavanathan, Salim Ahmed, Faisal Khan and Syed Imtiaz\u003c\/p\u003e \u003cp\u003e6.1 Background 113\u003c\/p\u003e \u003cp\u003e6.2 Machine Learning Approaches in Fault Detection and Diagnosis 114\u003c\/p\u003e \u003cp\u003e6.3 Supervised Methods for Fault Detection and Diagnosis 115\u003c\/p\u003e \u003cp\u003eContents vii\u003c\/p\u003e \u003cp\u003e0005453285.3D 7 30\/8\/2022 8:51:33 PM\u003c\/p\u003e \u003cp\u003e6.3.1 Neural Network 115\u003c\/p\u003e \u003cp\u003e6.3.1.1 Neural Network Theory and Algorithm 115\u003c\/p\u003e \u003cp\u003e6.3.1.2 Neural Network Learning for Fault Classification 117\u003c\/p\u003e \u003cp\u003e6.3.1.3 Algorithm for Fault Classification Using Neural Network 118\u003c\/p\u003e \u003cp\u003e6.3.2 Support Vector Machine 118\u003c\/p\u003e \u003cp\u003e6.3.2.1 Support Vector Machine Theory and Algorithm 118\u003c\/p\u003e \u003cp\u003e6.3.3 Support Vector Machine Model Selection and Algorithm 120\u003c\/p\u003e \u003cp\u003e6.3.4 Support Vector Machine Multiclass Classification 121\u003c\/p\u003e \u003cp\u003e6.4 Unsupervised Learning Models for Fault Detection and Diagnosis 122\u003c\/p\u003e \u003cp\u003e6.4.1 K-Nearest Neighbors 122\u003c\/p\u003e \u003cp\u003e6.4.2 One-Class Support Vector Machine 123\u003c\/p\u003e \u003cp\u003e6.4.3 One-Class Neural Network 124\u003c\/p\u003e \u003cp\u003e6.4.4 Comparison Between Deep Learning with Machine Learning in Fault Detection\u003c\/p\u003e \u003cp\u003eand Diagnosis 126\u003c\/p\u003e \u003cp\u003e6.5 Intelligent FDD Using Machine Learning 127\u003c\/p\u003e \u003cp\u003e6.5.1 Model Development 127\u003c\/p\u003e \u003cp\u003e6.5.2 Data Collection 129\u003c\/p\u003e \u003cp\u003e6.5.2.1 Model Development Steps 129\u003c\/p\u003e \u003cp\u003e6.5.2.2 Result Comparison 130\u003c\/p\u003e \u003cp\u003e6.6 Concluding Remarks 134\u003c\/p\u003e \u003cp\u003eReferences 134\u003c\/p\u003e \u003cp\u003e7 Intelligent Method for Chemical Emission Source Identification 139\u003c\/p\u003e \u003cp\u003eDenglong Ma\u003c\/p\u003e \u003cp\u003e7.1 Introduction 139\u003c\/p\u003e \u003cp\u003e7.1.1 Development of Detecting Gas Emission 139\u003c\/p\u003e \u003cp\u003e7.1.2 Development of Source Term Identification 140\u003c\/p\u003e \u003cp\u003e7.2 Intelligent Methods for Recognizing Gas Emission 141\u003c\/p\u003e \u003cp\u003e7.2.1 Leakage Recognition of Sequestrated CO2 in the Atmosphere 141\u003c\/p\u003e \u003cp\u003e7.2.1.1 Gas Leakage Recognition for CO2 Geological Sequestration 142\u003c\/p\u003e \u003cp\u003e7.2.1.2 Case Studies for CO2 Recognition 144\u003c\/p\u003e \u003cp\u003e7.2.2 Emission Gas Identification with Artificial Olfactory 149\u003c\/p\u003e \u003cp\u003e7.2.2.1 Features of Responses in AOS 150\u003c\/p\u003e \u003cp\u003e7.2.2.2 Support Vector Machine Models for Gas Identification 150\u003c\/p\u003e \u003cp\u003e7.2.2.3 Deep Learning Models for Gas Identification 155\u003c\/p\u003e \u003cp\u003e7.3 Intelligent Methods for Identifying Emission Sources 158\u003c\/p\u003e \u003cp\u003e7.3.1 Source Estimation with Intelligent Optimization Method 158\u003c\/p\u003e \u003cp\u003e7.3.1.1 Principle of Source Estimation with Optimization Method 158\u003c\/p\u003e \u003cp\u003e7.3.1.2 Case Studies of Source Estimation with Optimization Method 159\u003c\/p\u003e \u003cp\u003e7.3.2 Source Estimation with MRE-PSO Method 159\u003c\/p\u003e \u003cp\u003e7.3.2.1 Principle of PSO-MRE for Source Estimation 161\u003c\/p\u003e \u003cp\u003e7.3.2.2 Case Studies 163\u003c\/p\u003e \u003cp\u003e7.3.3 Source Estimation with PSO-Tikhonov Regulation Method 164\u003c\/p\u003e \u003cp\u003e7.3.3.1 Principle of PSO-Tikhonov Regularization Hybrid Method 164\u003c\/p\u003e \u003cp\u003e7.3.3.2 Case Study 167\u003c\/p\u003e \u003cp\u003eviii Contents\u003c\/p\u003e \u003cp\u003e0005453285.3D 8 30\/8\/2022 8:51:33 PM\u003c\/p\u003e \u003cp\u003e7.3.4 Source Estimation with MCMC-MLA Method 168\u003c\/p\u003e \u003cp\u003e7.3.4.1 Forward Gas Dispersion Model Based on MLA 168\u003c\/p\u003e \u003cp\u003e7.3.4.2 Source Estimation with MCMC-MLA Method 169\u003c\/p\u003e \u003cp\u003e7.3.4.3 Case Study 172\u003c\/p\u003e \u003cp\u003e7.4 Conclusions and Future Work 173\u003c\/p\u003e \u003cp\u003e7.4.1 Conclusions 173\u003c\/p\u003e \u003cp\u003e7.4.2 Limitations and Future Work 177\u003c\/p\u003e \u003cp\u003eReferences 178\u003c\/p\u003e \u003cp\u003e8 Machine Learning and Deep Learning Applications in Medical Image\u003c\/p\u003e \u003cp\u003eAnalysis 183\u003c\/p\u003e \u003cp\u003ePingfan Hu, Changjie Cai, Yu Feng and Qingsheng Wang\u003c\/p\u003e \u003cp\u003e8.1 Introduction 183\u003c\/p\u003e \u003cp\u003e8.1.1 Machine Learning in Medical Imaging 183\u003c\/p\u003e \u003cp\u003e8.1.2 Deep Learning in Medical Imaging 183\u003c\/p\u003e \u003cp\u003e8.2 CNN-Based Models for Classification 184\u003c\/p\u003e \u003cp\u003e8.2.1 ResNet50 184\u003c\/p\u003e \u003cp\u003e8.2.2 YOLOv4 (Darknet53) 185\u003c\/p\u003e \u003cp\u003e8.2.3 Grad-CAM 186\u003c\/p\u003e \u003cp\u003e8.3 Case Study 186\u003c\/p\u003e \u003cp\u003e8.3.1 Background 186\u003c\/p\u003e \u003cp\u003e8.3.2 Study Design 187\u003c\/p\u003e \u003cp\u003e8.3.3 Training and Testing Database Preparation 187\u003c\/p\u003e \u003cp\u003e8.3.4 Results 190\u003c\/p\u003e \u003cp\u003e8.3.4.1 Classification Performance of the Modified ResNet50 Model 190\u003c\/p\u003e \u003cp\u003e8.3.4.2 Classification Performance of the YOLOv4 Model 190\u003c\/p\u003e \u003cp\u003e8.3.4.3 Post-Processing Via Grad-CAM Model and HSV 193\u003c\/p\u003e \u003cp\u003e8.3.5 Conclusion 194\u003c\/p\u003e \u003cp\u003e8.4 Limitations and Future Work 194\u003c\/p\u003e \u003cp\u003eReferences 195\u003c\/p\u003e \u003cp\u003e9 Predictive Nanotoxicology: Nanoinformatics Approach to Toxicity Analysis of\u003c\/p\u003e \u003cp\u003eNanomaterials 199\u003c\/p\u003e \u003cp\u003eBilal M. Khan and Yoram Cohen\u003c\/p\u003e \u003cp\u003e9.1 Predictive Nanotoxicology 199\u003c\/p\u003e \u003cp\u003e9.1.1 Introduction 199\u003c\/p\u003e \u003cp\u003e9.1.2 Nano Quantitative Structure–Activity Relationship (QSAR) 200\u003c\/p\u003e \u003cp\u003e9.1.3 Importance of Data for Nanotoxicology 204\u003c\/p\u003e \u003cp\u003e9.2 Machine Learning Modeling for Predictive Nanotoxicology 205\u003c\/p\u003e \u003cp\u003e9.2.1 Overview 205\u003c\/p\u003e \u003cp\u003e9.2.2 Unsupervised Learning 211\u003c\/p\u003e \u003cp\u003e9.2.2.1 Data Exploration Via Self-Organizing Maps (SOMs) 211\u003c\/p\u003e \u003cp\u003e9.2.2.2 Evaluating Associations among Sublethal Toxicity Responses 214\u003c\/p\u003e \u003cp\u003e9.2.3 Supervised Learning 215\u003c\/p\u003e \u003cp\u003e9.2.3.1 Random Forest Models 216\u003c\/p\u003e \u003cp\u003eContents ix\u003c\/p\u003e \u003cp\u003e0005453285.3D 9 30\/8\/2022 8:51:33 PM\u003c\/p\u003e \u003cp\u003e9.2.3.2 Support Vector Machines 216\u003c\/p\u003e \u003cp\u003e9.2.3.3 Bayesian Networks 216\u003c\/p\u003e \u003cp\u003e9.2.3.4 Supervised Classification and Regression-Based Models for Nano-(Q)SARs 218\u003c\/p\u003e \u003cp\u003e9.2.4 Predictive Nano-(Q)SARs for the Assessment of Causal Relationships 220\u003c\/p\u003e \u003cp\u003e9.3 Development of Machine Learning Based Models for Nano-(Q)SARs 224\u003c\/p\u003e \u003cp\u003e9.3.1 Overview 224\u003c\/p\u003e \u003cp\u003e9.3.1.1 Data-Driven Models 224\u003c\/p\u003e \u003cp\u003e9.3.1.2 Mechanistic\/Theoretical Models 225\u003c\/p\u003e \u003cp\u003e9.3.2 Data Generation, Collection, and Preprocessing 225\u003c\/p\u003e \u003cp\u003e9.3.3 Descriptor Selection 226\u003c\/p\u003e \u003cp\u003e9.3.4 Model Selection and Training 229\u003c\/p\u003e \u003cp\u003e9.3.5 Model Validation 230\u003c\/p\u003e \u003cp\u003e9.3.5.1 Descriptor Importance 231\u003c\/p\u003e \u003cp\u003e9.3.5.2 Applicability Domain 231\u003c\/p\u003e \u003cp\u003e9.3.6 Model Diagnosis and Debugging 231\u003c\/p\u003e \u003cp\u003e9.4 Nanoinformatics Approaches to Predictive Nanotoxicology 234\u003c\/p\u003e \u003cp\u003e9.5 Summary 235\u003c\/p\u003e \u003cp\u003eReferences 238\u003c\/p\u003e \u003cp\u003e10 Machine Learning in Environmental Exposure Assessment 251\u003c\/p\u003e \u003cp\u003eGregory L. Watson\u003c\/p\u003e \u003cp\u003e10.1 Introduction 251\u003c\/p\u003e \u003cp\u003e10.2 Environmental Exposure Modeling 252\u003c\/p\u003e \u003cp\u003e10.3 Machine Learning Exposure Models 254\u003c\/p\u003e \u003cp\u003e10.4 Model Evaluation 257\u003c\/p\u003e \u003cp\u003e10.5 Case Study 258\u003c\/p\u003e \u003cp\u003e10.6 Other Topics 260\u003c\/p\u003e \u003cp\u003e10.6.1 Bias and Fairness 260\u003c\/p\u003e \u003cp\u003e10.6.2 Wearable Sensors 260\u003c\/p\u003e \u003cp\u003e10.6.3 Interpretability 260\u003c\/p\u003e \u003cp\u003e10.6.4 Extreme Events 260\u003c\/p\u003e \u003cp\u003e10.7 Conclusion 261\u003c\/p\u003e \u003cp\u003eReferences 261\u003c\/p\u003e \u003cp\u003e11 Air Quality Prediction Using Machine Learning 267\u003c\/p\u003e \u003cp\u003eLan Gao, Changjie Cai and Xiao-Ming Hu\u003c\/p\u003e \u003cp\u003e11.1 Introduction 267\u003c\/p\u003e \u003cp\u003e11.2 Air Quality and Climate Data Acquisition 269\u003c\/p\u003e \u003cp\u003e11.2.1 Earth Satellite Observation Datasets 269\u003c\/p\u003e \u003cp\u003e11.2.1.1 Basics of Earth Satellite Observations 269\u003c\/p\u003e \u003cp\u003e11.2.1.2 Earth Satellite Products 270\u003c\/p\u003e \u003cp\u003e11.2.2 Ground-Based In Situ Observation Datasets 276\u003c\/p\u003e \u003cp\u003e11.2.2.1 Basics of the Ground-Based In Situ Observations 276\u003c\/p\u003e \u003cp\u003e11.2.2.2 Ground-Based In Situ Products 277\u003c\/p\u003e \u003cp\u003e11.3 Applications of Machine Learning in Air Quality Study 279\u003c\/p\u003e \u003cp\u003ex Contents\u003c\/p\u003e \u003cp\u003e0005453285.3D 10 30\/8\/2022 8:51:34 PM\u003c\/p\u003e \u003cp\u003e11.3.1 Shallow Learning 280\u003c\/p\u003e \u003cp\u003e11.3.2 Deep Learning 280\u003c\/p\u003e \u003cp\u003e11.4 An Application Practice Example 281\u003c\/p\u003e \u003cp\u003e11.4.1 Satellite Data Acquisition and Variable Selections 282\u003c\/p\u003e \u003cp\u003e11.4.2 Machine Learning and Deep Learning Algorithms 282\u003c\/p\u003e \u003cp\u003eReferences 283\u003c\/p\u003e \u003cp\u003e12 Current Challenges and Perspectives 289\u003c\/p\u003e \u003cp\u003eChangjie Cai and Qingsheng Wang\u003c\/p\u003e \u003cp\u003e12.1 Current Challenges 289\u003c\/p\u003e \u003cp\u003e12.1.1 Data Development and Cleaning 289\u003c\/p\u003e \u003cp\u003e12.1.2 Hardware Issues 290\u003c\/p\u003e \u003cp\u003e12.1.3 Data Confidentiality 290\u003c\/p\u003e \u003cp\u003e12.1.4 Other Challenges 291\u003c\/p\u003e \u003cp\u003e12.2 Perspectives 291\u003c\/p\u003e \u003cp\u003e12.2.1 Real-Time Monitoring and Forecast of Chemical Hazards 291\u003c\/p\u003e \u003cp\u003e12.2.2 Toolkits for Dummies 292\u003c\/p\u003e \u003cp\u003e12.2.3 Physics-Informed Machine Learning 292\u003c\/p\u003e \u003cp\u003eReferences 293\u003c\/p\u003e \u003cp\u003eIndex 000\u003c\/p\u003e\n\u003c\/li\u003e\u003c\/ul\u003e","brand":"John Wiley \u0026 Sons Inc","offers":[{"title":"Default Title","offer_id":49407161532759,"sku":"9781119817482","price":104.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9781119817482.jpg?v=1730498386","url":"https:\/\/bookcurl.com\/products\/machine-learning-in-chemical-safety-and-health-9781119817482","provider":"Book Curl","version":"1.0","type":"link"}