The Power of Data: Driving Climate Change with Data Science and Artificial Intelligence Innovations

Description

This book discusses the advances of artificial intelligence and data sciences in climate change and provides the power of the climate data that is used as inputs to artificial intelligence systems. It is a good resource for researchers and professionals who work in the field of data sciences, artificial intelligence, and climate change applications. Preface Contents Artificial Intelligence in Climate Change Applications Artificial Intelligence for Predicting Floods: A Climatic Change Phenomenon 1 Introduction 2 Artificial Intelligence Approaches and Flood Prediction 2.1 How Does AI-Models Work to Forecast Floods 2.2 Machine and Deep Learning for Flood Forecasting 2.3 AI Systems for Flood Forecasting 3 Proposed Machine Learning-Based Flood Prediction Model 3.1 The Pre-processing Phase 3.2 Feature Selection Based on the PIO Phase 3.3 Flood Prediction Based on Machine Learning Phase 4 Experimental Results 4.1 Flood Prediction Results Using PIO and GB Algorithms 4.2 Flood Prediction Results Validation Using Random Forest (RF) Algorithm 5 Conclusion References Prediction of Climate Change Impact Based on Air Flight CO2 Emissions Using Machine Learning: Towards Green Air Flights 1 Introduction 2 Preliminary 3 Methodology 3.1 Proposed Model 3.2 Dataset Characteristics and Pre-processing 3.3 Feature Selection 4 Results and Performance Evaluation 5 Conclusion References The Impact of Artificial Intelligence on Waste Management for Climate Change 1 Introduction 2 Waste Management and Artificial Intelligence Application 3 The Application of Artificial Intelligence to Estimate Greenhouse Gas (GHG) 4 Challenges in Waste Management and Artificial Intelligence 5 Conclusion References A Machine Learning-Based Model for Predicting Temperature Under the Effects of Climate Change 1 Introduction 2 Related Work 3 Materials and Methods 3.1 Linear Regression 3.2 Decision Tree Regressor 3.3 Random Forest Regressor 3.4 K-Nearest Neighbor Regressor 3.5 Support Vector Regressor 4 Cat Boost Regressor 5 Evaluation Results and Discussion 5.1 Dataset Description 5.2 Evaluation Results 6 Conclusion and Perspectives References Emerging Technologies in Industry and Energy Sector Prediction of COSubscript 22 Emission in Cars Using Machine Learning Algorithms 1 Introduction 1.1 Motivation 1.2 Main Contribution 2 The Proposed Carbon Dioxide Emission Prediction Model 3 Simulation Results and Discussions 3.1 Performance Evaluation Measurements 3.2 Dataset Description 3.3 Experimental Results 4 Conclusions References Climate Change: The Challenge of Tunisia and Previsions for Renewable Energy Production 1 Introduction 2 Study Area 3 The Energy Situation in Tunisia 4 Energy and Climate Change 5 Renewable Energies in Tunisia 5.1 Current Situation 5.2 Self-Production of Photovoltaic Solar Energy 6 Decision Support Framework for Photovoltaic Energy Prediction 6.1 Data Collection 6.2 The Proposed Data Warehouse 7 Conclusions and Recommendations References Clean Energy Management Based on Internet of Things and Sensor Networks for Climate Change Problems 1 Introduction 2 Greenhouse Monitoring 3 Challenges Related to Energy Use 4 The Internet of Things for Sustainable Energy 4.1 Coal-Plant Sensors 4.2 Oxygen Sensing 4.3 Carbon Monoxide Sensors 4.4 Flame Detection 4.5 Sensing Coal Flow 4.6 Sensing Airflow 4.7 Ash Carbon Sensing 4.8 Temperature-Sensing Gases 5 Sensors for the Transmission System 5.1 Methods for Sensing at Substations 5.2 Sensing of Overhead Lines 6 Meters with Internet-Enabled Functions 7 Sensing of the Solar and Wind Fields 8 Conclusion References Digital Twin Technology for Energy Management Systems to Tackle Climate Change Challenges 1 Introduction 2 Basics and Background 2.1 Digital Twins Overview 2.2 Digital Twins Origin, Concept, and Scenario 2.3 Digital Twin’s Characteristics 2.4 Internet of Things 2.5 Sensor Networks 3 Digital Twins in Energy Management Applications 4 A Proposed Framework of Digital Twins in Climate Change Adaptation 5 Collaborative Digital Twins 5.1 The Need for Collaborative Digital Twins 5.2 Use Case of Collaborative Digital Twins in Healthcare 6 Challenges and Potential Solutions 6.1 Problems and Challenges 6.2 The Potential Solutions 7 Concluding Remarks References The Role of Internet of Things in Mitigating the Effect of Climate Change: Case Study: An Ozone Prediction Model 1 Introduction 2 Preliminaries 2.1 Internet of Things 2.2 The Role of the Internet of Things on Climate Change 3 Dataset Description 4 The Proposed Internet of Things Model-Based Machine Learning Techniques for Ozone Prediction 4.1 Data Preparing and Preprocessing 4.2 Training and Testing Phase 4.3 The Evaluation Measures 5 Experiments, Results, and Discussion 5.1 Experiment I 5.2 Experiment II 6 Conclusion References Emerging Climate Change Technology in Agriculture Sector Optimized Multi-Kernel Predictive Model for the Crop Prediction with Climate Factors and Soil Properties 1 Introduction 2 Related Work 3 The Proposed Optimized Crop Prediction Model 4 Results, Discussion, and Analysis 4.1 Dataset Description 4.2 Experimental Results and Analysis 5 Conclusion and Future Work References An Intelligent Crop Recommendation Model for the Three Strategic Crops in Egypt Based on Climate Change Data 1 Introduction 1.1 Motivation 1.2 Main Contributions 2 Background and Literature Review 3 Climate Change Scenarios 3.1 The Representative Concentration Pathway 3.2 The Special Report on Emissions Scenarios 4 The Proposed Automated Crop Recommendation Model Using Deep Learning 4.1 The Optimized Conventional Neural Network Using the Grey Wolf Optimization Algorithm (GWO) 5 The Experimental Results 5.1 The Dataset Used in the Experiments 5.2 Performance Evaluation Measures 5.3 Experiment 1: The Projected Impacts on the Three Strategic Crops Using Different Climate Scenarios 5.4 Experiment 2: The Accuracy Values for the Proposed ACRM Compared to Different Models 5.5 Experiment 3: The Most Significant Climate Change Factors that Affected Crop Recommendation 6 Conclusion and Discussion References Cost Effective Decision Support System for Smart Water Management System 1 Introduction 2 Urbanization Trends 3 Smart Cities Concept 4 The Proposed DSS for the Smart Water Management System 4.1 Decision Support System 4.2 Cloud-Native Systems 4.3 The Proposed DSS for Smart Water Management System 5 Conclusion References The Role of Artificial Intelligence in Water Management in Agriculture for Climate Change Impacts 1 Impact of Artificial Intelligence on Environmental Issues 1.1 Global Warming and Artificial Intelligence 1.2 Impacts of Climate Change on Production 1.3 Effect of Climate Change on Water Management 2 Automation and Traditional Farming for Water Management 3 Artificial Intelligence and Soilless Culture for Facing Climate Change 3.1 Necessity of Hydroponics 3.2 Benefits of Hydroponics Systems 3.3 Problems of Hydroponics 3.4 Classification of Soilless Culture Systems 3.5 Coupling Between Artificial Intelligence and Soilless Culture 3.6 Interaction Between Water Management and Soilless Culture 4 Conclusion References Emerging Climate Change Technologies in Healthcare Sector The Influence of Climate Change on the Re-emergence of Malaria Using Artificial Intelligence 1 Introduction 2 Related Work 3 Basics and Background for Malaria Disease 4 Machine Learning for Medical Applications 4.1 The Importance of Machine Learning for Detecting Malaria Disease 4.2 Problems and Challenges for Malaria Detection Using Machine Learning 5 Conclusion References Index