Data Science Applied to Sustainability Analysis

Description

Front cover Half title Full title Copyright Contents - Contributors Chapter 1 - Overview of data science and sustainability analysis Data science is central to advances in sustainability Types of sustainability analyses Data science tools Supervised learning Unsupervised learning Reinforcement learning Tools Overview of case studies in data science in sustainability References Part 1 - Environmental Health and Sustainability Chapter 2 - Applying AI to conservation challenges Introduction What is adaptive management? Creating value with AI Planning and implementing with AI Monitoring & evaluating with AI Learning & adapting with AI The impact technology canvas: synchronizing AI initiatives Summary References Chapter 3 - Water balance estimation in Australia through the merging of satellite observations with models Introduction Importance of water balance estimation in Australia Problems with current methods for water balance estimation Case studies Inversion of rainfall rates from streamflow records Estimation of flood forecast-effective river bathymetry through inverse modeling Estimation of terrestrial water storage through the merging of Gravity Recovery and Climate Experiment (GRACE) data with a ... Conclusion References Chapter 4 - Machine learning in the Australian critical zone What is CZ science? Machine learning techniques used Support vector machines Decision trees and random forests Neural networks Deep learning Genetic programming Evaluation of results Questions addressed and data used What is the spatial pattern of …? Soil Vegetation biomass Species distribution Land use Paleovalleys What is the spatio-temporal pattern of …? Seasonal rainfall forecasting Streamflow forecasting Crop forecasting Land cover Where are the most vulnerable areas…? Gully erosion Soil organic carbon loss under global warming Drought Fire Key results, insights, and why they matter to the field of sustainability Spatial patterns at the earth’s surface and controlling factors Sustainable yields Future development and application of data science in CZ science Data accessibility via eResearch platforms Analytics/protocols for knowledge discovery Glossary terms References PART 2 - Energy and Water Chapter 5 - A clustering analysis of energy and water consumption in U.S. States from 1985 to 2015 Introduction Materials and methods Data Climate standardization Clustering analysis Maps Results Evaluating the impact of climate on energy consumption clustering Conclusion and discussion Acknowledgments Appendix References CHAPTER 6 - Exploring rooftop solar photovoltaics deployment and energy injustice in the US through a data-driven approach Introduction A focus on distributed solar PV Distributed solar PV in urban settings Assessing rooftop PV potential across cities Reducing barriers for accelerated residential PV deployment Evaluating equity in rooftop PV deployment: a case study for the United States Background Methodology Results and discussion Next steps Concluding remarks References Chapter 7 - Data-driven materials discovery for solar photovoltaics Introduction Motivation for developing photovoltaic technologies Accelerating materials discovery Fundamentals of photovoltaics Basic silicon crystal solar cells Organic photovoltaic cells Dye-sensitized solar cells Perovskite solar cells Data-driven materials discovery schemes Materials space Categories of data science for materials discovery Case studies of solar materials discovery Harvard clean energy project – the search for novel organic photovoltaics Data-driven search for panchromatic co-sensitized dye solar cells High-throughput computational search for hybrid halide semiconductors Future outlook References PART 3 - Sustainable Systems Analysis Chapter 8 - Machine learning in life cycle assessment Introduction to life cycle assessment (LCA) LCAs role in sustainability Types of LCA Process LCA IO-LCA Hybrid LCA Comparison of types General methods for process LCA Goal and scope definition Inventory analysis Impact assessment Interpretation and analysis Uses and limitations of LCA Tools and data sources for LCA Process LCA IO-LCA Introduction to machine learning (ML) Types of ML Supervised learning Unsupervised learning Reinforcement learning Shallow and deep learning Choosing a machine learning algorithm Tools for ML ML in LCA ML for surrogate LCAs ML in LCI Data cleaning Estimating inventory flows ML in LCIA CF estimation CF definition ML in interpretation and analysis Sensitivity analysis Scenario analysis Conclusion LCA of ML References Chapter 9 - Industry sustainable supply chain management with data science Introduction to LCA Today’s limitations LCA applications Vision/Needs References PART 4 - Society and Policy Chapter 10 - Deep learning with satellite imagery to enhance environmental enforcement Introduction The methodological evolution of remote sensing Manual image processing Automated image processing Deep learning Using deep learning to identify CAFOs Data Modeling approach Results Discussion References Chapter 12 - An indicator-based approach to sustainable management of natural resources Introduction Selecting and prioritizing indicators Indicator datasets and data science considerations Environmental indicator datasets Socioeconomic indicator datasets Data analytics Descriptive analytics Monetization of ecosystem services Data visualizations Predictive analytics Prescriptive analytics Socio-ecological systems research Implications for society & policy Conclusion References Chapter 11 - Towards achieving the UNs data revolution: combining earth observation and socioeconomic data for geographic ... Why social remote sensing? Geographic targeting Using EO data for understanding socioeconomic conditions Predicting poverty from EO data in developing countries The sustainable livelihoods approach for generating EO proxies of socioeconomic conditions How can we socialize the pixel? A socio-ecologically informed approach to linking EO and socioeconomic data Limitations when linking EO and socioeconomic datasets for estimating poverty Future directions for EO and social data Conclusions References Part 5 - Conclusion Chapter 13 - Research and development for increased application of data science in sustainability analysis Introduction Needs for data to enable data science in sustainability Environmental science Manufacturing and technology systems Societal systems Data sources Data science advances Conclusion References Index Back cover