Artificial Intelligence and Advanced Analytics for Food Security

Description

Climate change, increasing population, food-versus-fuel economics, pandemics, etc. pose a threat to food security to unprecedented levels. It has fallen upon the practitioners of agriculture and technologists of the world to innovate and become more productive to address the multi-pronged food security challenges. Agricultural innovation is key to managing food security concerns. The infusion of data science, artificial intelligence (AI), advanced analytics, satellites data, geospatial data, climatology, sensor technologies, and climate modeling with traditional agricultural practices such as soil engineering, fertilizers use, and agronomy are some of the best ways to achieve this. Data science helps farmers to unravel patterns in fertilizer pricing, equipment usage, transportation and storage costs, yield per hectare, and weather trends to better plan and spend resources. AI enables farmers to learn from fellow farmers to apply best techniques that are transferred learning from AI to improve agricultural productivity and to achieve financial sustainability. Sensor technologies play an important role in getting real-time farm field data and provide feedback loops to improve overall agricultural practices and can yield huge productivity gains. Advanced Analytics modeling is essential software technique that codifies farmers’ tacit knowledge such as better seed per soil, better feed for dairy cattle breed, or production practices to match weather pattern that was acquired over years of their hard work to share with worldwide farmers to improve overall production efficiencies, the best antidote to food security issue. In addition to the paradigm shift, economic sustainability of small farms is a major enabler of food security. The book reviews all these technological advances and proposes macroeconomic pricing models that data mines macroeconomic signals and the influence of global economic trends on small farm sustainability to provide actionable insights to farmers to avert any financial disasters due to recurrent economic crises. Cover Title Page Copyright Page Preface Table of Contents Section I: Advanced Analytics 1. Time Series and Advanced Analytics Milk Pricing Linkage & Exploratory Data Analysis (EDA) Auto Correlation Partial Autocorrelation Function (PACF) Stationarity Check: Augmented Dickey Fuller (ADF) & Kwiatkowski-Phillips-Schmidt-Shin (KPSS) Tests Non-stationary Stochastic Time Series Granger’s Causality Test Transformation & Detrending by Differencing Models VAR Linkage Model: CPI Average Milk Prices, Imported Oil Prices, and All Dairy Products (milk-fat milk-equivalent basis): Supply and Use Regressive Linkage Model: CPI Average Milk Prices, Imported Oil Prices, and All Dairy Products (milk-fat milk-equivalent basis): Supply and Use Prophet Time Series Model: CPI Average Milk Prices, Imported Oil Prices, and All Dairy Products (milk-fat milk-equivalent basis): Supply and Use References 2. Data Engineering Techniques for Artificial Intelligence and Advanced Analytics Food Security Data Data Encoding—Categorical to Numeric Data Enrichment Data Resampling Synthetic Minority Oversampling Technique (SMOTE) & Adaptive Synthetic Sampling (ADASYN) Machine Learning Model: Kansas Wheat Yield SMOTE Model Machine Learning Model: Kansas Wheat Yield with Adaptive Synthetic (ADASYN) Sampling References Section II: Food Security & Machine Learning 3. Food Security Domino Effect Food Security is National Security! Food Security Frameworks The Food Security Bell Curve—Machine Learning (FS-BCML) Framework Machine Learning Model: Who In the World is Food Insecure? Prevalence of Moderate or Severe Food Insecurity in the Population Machine Learning Model: Who In the World is Food Insecure? Prevalence of Moderate or Severe Food Insecurity in the Population—Ordinary Least Squares (OLS) Model Machine Learning Model: Who In the World is Food Insecure? Prevalence of Severe Food Insecurity in the Population (%) Machine Learning Model: Who In the World is Food Insecure? Prevalence of Severe Food Insecurity in the Population—Ordinary Least Squares (OLS) Model Guidance to Policy Makers References 4. Food Security Drivers and Key Signal Pattern Analysis Food Security Drivers & Signal Analysis Afghanistan Afghanistan Macroeconomic Key Drivers & Linkage Model - Prevalence of Undernourishment Afghanistan Macroeconomic Key Drivers, Food Security Parameters, & Linkage Model - Prevalence of Undernourishment Sri Lanka Sri Lanka Macroeconomic Key Drivers & Linkage Model - Prevalence of Undernourishment Guidance to Policy Makers References Section III: Prevalence of Undernourishment and Severe Food Insecurity in the Population Models 5. Commodity Terms of Trade and Food Security Mechanics of Food Inflation Machine Learning Model: Food Grain Producer Prices & Consumer Prices Machine Learning Model: Prophet—Food Grain Producer Prices & Consumer Prices FAO in Emergencies—CTOT & Food Inflation Trade and Food Security Food Security is National Security! References 6. Climate Change and Agricultural Yield Analytics Wheat Phenological Stages Climate Change & Wheat Yield Wheat Futures NOAA Star Global Vegetation Health (VH) Coupled Model Intercomparison Project Climate Projections (CMIP) Shared Socioeconomic Pathway (SSP) Projection Models Kansas & Wheat Production Mathematical Modeling Machine Learning Model: Drought & Wheat Yield Production Linkage in Kansas India & Wheat Production Machine Learning Model: Heat Waves & Wheat Yield Production Linkage in India Machine Learning Forecasting Model: Heat Waves & Wheat Yield Production in India Machine Learning (Mid-century 2050) Projection Model: Heat Waves with Increased Frequencies and Intensities & Wheat Yield Production in India Food Security and Climate Resilient Economy: Heatwaves and Dairy Productivity Signal Mining to create a Smart Climate Sensor for Enhanced Food Security Machine Learning Model: Drought & Heatwave Signature Mining through the Application of Sensor, Satellite Data to reduce overall Food Insecurity References 7. Energy Shocks and Macroeconomic Linkage Analytics Climate Change and Energy Shocks Linkage Unexpected Price Shocks—Gasoline, Natural Gas, and Electricity Impact of Higher Gas prices on Macroeconomic Level The Channels of Transmission & Behavioral Economy Fertilizer Use and Price The U.S. Dollar Index U.S. Dollar and Global Commodity Prices Linkage Farm Inputs & Fertilizer Linkage Model Machine Learning Model Energy Prices & Fertilizer Costs—Urea Machine Learning Model Energy Prices and Fertilizer Costs—Phosphate Machine Learning Model—Commodities Demand and Energy Shocks on the Phosphate Model Machine Learning Model—Prophet Time Series Commodities Demand and Energy Shocks on Phosphate Model References Section IV: Conclusion 8. Future Appendices Appendix A—Food Security & Nutrition The 17 Sustainable Development Goals (SDGs) Food Security Monitoring System (FSMS) NHANES 2019–2020 Questionnaire Instruments—Food Security Macroeconomic Signals that Could help Predict Economic Cycles List of World Development Indicators (WDI) Food Aids The United Nations—17 Sustainable Development Goals (SDGs) The Statistical Distributions of Commodity Prices in Both Real and Nominal Terms Poverty Thresholds for 2019 by Size of Family and Number of Related Children Under 18 Years Appendix B—Agriculture Agricultural Data Surveys USDA—The Foreign Agricultural Service (FAS) Reports and Databases USDA Data Products Data Sources Conversion Factors National Dairy Development Board (NDDB) India Worldwide—Artificial Intelligence (AI) Readiness Appendix C—Data World Global Historical Climatology Network monthly (GHCNm) Labor Force Statistics from the Current Population Survey Appendix D—Data U.S. U.S. Bureau of Labor Statistics Dollars/Bushel : Dollars/Tonne Converter NOAA - Storm Events Database Consumer Price Index, 1913 Appendix E—Economic Frameworks & Macroeconomics Macroeconomic Signals that could help Predict Economic Cycles The U.S. Recessions Labor Force Statistics from the Current Population Survey United Nations Statistics Department (UNSD) Reserve Bank of India—HANDBOOK OF STATISTICS ON INDIAN ECONOMY Department of Commerce United Nations Data Sources Poverty Thresholds for 2019 by Size of Family and Number of Related Children Under 18 Years Rice Production Manual Index