Machine Learning and Artificial Intelligence for Agricultural Economics: Prognostic Data Analytics to Serve Small Scale Farmers Worldwide ... Research & Management Science, 314)

Preface
Acknowledgment
Abbreviations
Contents
Section I: Artificial Intelligence
	Chapter 1: Introduction
		What Is AI?
		Machine Learning
		Types of Analytics
			Descriptive Analytics
			Predictive Analytics
			Prescriptive Analytics
			Prognostics Analytics
		Types of Learning
		Supervised Learning
			Decision Tree Classification Models
			Decision Tree Classification Models Metrics
		Use Case: Binary Decision Trees—Managing Temperature Effects in Edge IoT Deployments with ML-Enabled Adaptive Coefficients
			Temperature Variations and Sensor Data Errors
			Machine Learning Model Design of Adaptive System to Autocorrect
			Binary Base Decision Tree: Adaptive Edge Thermal Calibration Coefficient
			Regression Models
			Metrics for Regression Models
		Unsupervised Learning
			Metrics for Clustering Models
				Reinforcement Learning
		Deep Learning
		Agricultural Datasets and Ensemble Learning
		Multiclass Classification: Classifying Wines and Ensemble Model
			Data Source
			Model Construction: Base Decision Tree
			Model Construction: Ensemble Gradient Boosting Classifier
		Tope 15 Destinations for Italian Exports, 2019
		Choosing the Right Estimator
		Mapping AI Technique to Classical ML
		AI Economics
		Artificial Intelligence and Income Equality and Inclusive Growth
			AI Readiness
			Group 1: Active Global Leaders
			Group 2: Economies with Strong Comparative Strength
			Group 3 Countries: Economies with Moderate Foundations
			Group 4: Economies that Need to Strengthen Foundations
		AI-Driven Agricultural Economics
			United States of America
			China
		Call for Policy Makers and Government Agencies!
		References
	Chapter 2: Data Engineering and Exploratory Data Analysis Techniques
		Knowledge Discovery in Databases (KDD)
		Architecture of a Data Mining System
		Agricultural Time Series Data
			Wheat Exporters22
		Agricultural Data Frequencies
			Hourly
			Daily
			Weekly
			Monthly
			Quarterly
			Yearly/Annual
		Agricultural Data Types
			Structured Data
			Unstructured Data
			Semi-Structured Data
		Agricultural Dataset Structure
			Tabular
			Relational Data
		Exploratory Data Analysis (EDA)
		Colombia Rural Agricultural Contribution to GDP!
			Data Sources
			Descriptive Statistics and Data Distribution
				Measures of Central Tendency
				Box-and-Whiskers Plot
				Density Function
				Comparing Numeric and Categorical Variables
				Correlation
			Feature Selection
			Feature Reduction Techniques
			Hyperparameter Tuning
		Model Interpretability
			The Explainable AI (XAI)60 [14]
			Global and Local Feature Importance
			Interpretability Techniques
		Imbalanced Datasets
			Synthetic Minority Oversampling Technique (SMOTE)
			Adaptive Synthetic Sampling (ADASYN)
		Feature Engineering
			Numeric Data
				Binning
				Adaptive Binning
				Statistical Transformations
				Log Transform
				Box-Cox Transform
		Missing Data
			Imputation Using (Mean/Median) Values
			Imputation Using (Most Frequent) or (Zero/Constant) Values
			Imputation Using K-NN
			Imputation Using Multivariate Imputation by Chained Equation (MICE)
		References
Section II: GDP and Commodity Markets
	Chapter 3: Agricultural Economy and ML Models
		Global Agriculture Landscape
			The Unites States of America
			European Union
			Asia
			Africa
			The Latin America and Caribbean
		Agriculture Farm Sizes: Scale Classification
			North America
			Europe
			Asia
		Agricultural Economics
			Advanced Analytics
			Data Units and Frequencies
				Machine Learning Modeling
					Moving Averages
					Stationary
					How to Test if a Process Is Stationary
			Commodity Pricing Signals
			Information Services and ICT
			Government Ordinances
			Data
			Macroeconomy and GDP
				GDP Method: As the Sum of Goods and Services Sold to Final Users
					New Motor Vehicles100
					Net Purchase of Used Motor Vehicles
					Purchased Meals and Beverages
				Econometric Models
				Machine Learning
				Predicting Real GDP Growth
					Data
					Feature Engineering
					Target
				Machine Learning Models (ML)
					Coincident Indicators
		Challenges
			Decline in Agriculture Output and Increase in Rural Poverty
			Farmers’ Suicides in Different Cultures
			Food Security
		References
	Chapter 4: Commodity Markets: Machine Learning Techniques
		Commodities
		Machine Learning and Commodity Prices
			Demand and Supply
			Stocks to Use Ratio
		Predicting Commodity Prices: Gold Price Predictability
			Machine Learning Techniques
			Data Sources
			Exploratory Data Analysis
			Data Model Diagram
			Model Development
		Fertilizers, Crude Oil, and Agricultural Commodity Model
			Top Fertilizers in Agricultural Use Case
			Data Fields
			Top 10 Countries: Urea Agricultural Use Case
			US Commodity Prices: Producer Price Index
			Data Sources
		Model Development
		Fertilizer Price Prediction Using Commodity (RICE, SORGHUM, MAIZE, and WHEAT) and Oil Prices
			Data Sources
		What if Analysis
			Demand Spike for CRUDE Oil
			Demand Goes Down
		References
Section III: Employment and Weather
	Chapter 5: Weather Patterns and Machine Learning
		Rice Production
			Rice Crop Calendar
			Rice Farm Consolidation
			Water Use
			Weather Events
				Storm Rainfall Depth and Distribution40
			Rice Data Sources
			Data Variables: Temperature, Precipitation, and PDSI
			NOAA: National Centers for Environmental Information—Storm Data
				Heavy Rains
				Heat and Excessive Heat
			Model Development
			Step 1: Load Required Libraries
			Step 2: Load Rice Harvested, Rice Yields, Rice Price, PDSI Values, PCP, and Rice Consumer Prices
			Step 3: Feature Engineer and Validate Each Data Frames
			Step 4a: Load Rice Agricultural Data
			Step 4b: Max and Min Temperature Data
			Step 5: Load Weather Events Data
			Step 6: Construct Model
				Model: Linear Regression
			Step 7: Construct Model with Optimized Features Based on Rice Crop Calendar
				Crop Calendar92 [4]
				Ensemble Model: Extra Trees Regressor
			Step 8: Model Interpretability
		Milk Production
		Relationship Between Milk Production and Price Variations
			Price Elasticity of Supply
		Milk Prices Received
		Basic Commodity Prices and Milk Production
			Step 1: Load Dataset
			Step 2: Missing Values
			Step 3: Compute Basic Statistics of Data Frame
			Step 4: Statistical Plots
			Step 5: Plot Histogram of Each Numerical Feature—Corn Price, Soybean Price, HW Wheat Price, and Sorghum Price
			Step 6: Scatter Plot
			Step 7: Check for Normal Distribution
			Step 8a: Kurtosis and Skewness
			Step 8b: Boxplots
			Step 9: Train a Regression Model
				Linear Regression
				Evaluate Trained Model
			Step 10: Train Model Pipeline
				Linear Model: Lasso
				Prediction:
				Random Forrest Regressor
			Step 11: Model Explainability
		References
	Chapter 6: Agriculture Employment and the Role of AI in Improving Productivity
		Factors Influencing to Agriculture’s Contribution to GDP
			Population Growth
			Rural Population (% of the Total Population)
			Life Expectancy at Birth (LEB): Total (Years)
			External Debt Stocks (% of GNI)
			Foreign Direct Investment and Net (BoP, Current US$)
			Inflation, Consumer Prices (Annual %) (ICP)
			Ratio of Export to Import Agricultural Products (EXIM)
			Employment in Agriculture (% of Total Employment) (Modeled ILO Estimate)
			Agriculture, Forestry, and Fishing: Value Added (% of GDP)
		Brazil’s Machine Learning Model: Agriculture’s Contribution to Economy and GDP and the Role of AI Readiness
			Data
			Model Development
			Explainability of Model
		India’s Machine Learning Model: Agriculture’s Contribution to Economy and GDP and the Role of AI Readiness
			Data
			Model Development
			Explainability of Model
		References
	Chapter 7: The Role of the Government and the AI Readiness
		Agricultural Data
		AI Technology Policy and Enablement at the Gross Root Levels
		AI Readiness and Lower Productivity
			World: Agriculture, Forestry, and Fishing, Value Added (Annual % Growth)10
			Employment in Agriculture (% of Total Employment) (Modeled ILO Estimate)11
			Brazil
			Pakistan
			Indonesia
			Uruguay
			Peru
			Government as Enabler of Digital Infrastructure
		Credit to Agriculture
			The United States
			China
			India
			France
		History of Credit to Agriculture
			2010
			2000
			1991
		The World Bank: Accessing Finance
		Government: A Major Risk Bearer
			Technology Policies
				Season-Average Price Forecasts45
			Title I: Crop Commodity Program Provisions After Enactment of the Agriculture Improvement Act of 2018
			Major Commodity Programs
		Agriculture Credit Policy: India
		Special Thrust Programs
		Poverty Headcount Ratio at $1.90 a Day (2011 PPP) (% of Population): World
			Development Relevance
		Import Duties
		Use Case: The Role of Government Spending in Milk Production
			Data Sources
			Milk Production Data
			Livestock Data
			Macro Indicators Data
			Consumer Price Indices Data
			Total Population Data
			Credit to Agriculture
				Impact of Farm Loan Waivers on Agricultural Credit
			Model Development
			Step 1: Load Required Libraries
			Step 2: Import Data from the NDDB and FAO Data Sources
			Step 3: Combine All Data Frames (CPI, Food Inflation, Government Expenditure, Credit, Annual Population, and Temperature)
			Step 4: Feature Distribution
			Step 5: Feature Density Function
			Step 6: Train and Test Data
			Step 7: Regression model
			Step 8: Explainability of the Model
			Step 9: Explainability of the Model—Azure
			Step 10: Model Deployment
		What If Analysis
			Consumer Price Increase
			Consumer Price Decrease
			Credit to Agriculture Increases
			Credit to Agriculture Decreases
		References
Section IV: Future
	Chapter 8: Future
Appendixes
	Appendix A: Data and Agricultural Statistics Services – Mission Statements
		Service to the Nation and the Humanity
			USDA NASS
			The World Bank
	Appendix B: Department of Commerce
		Bureau of Economic Analysis – The United States Department of Commerce
	Appendix C: Family Agricultural Farms
		The United States of America
		Agricultural Data Surveys
			USDA Nass
	Appendix D: Data Sources
		UN Data Marts
		IHS Global Economy Data
		US Commodities Futures Data
		IMF Data Access to Macroeconomic and Financial Data
		IMF Country Index Weights
		The World Bank Data
		The World Bank Development Indicators
		Food and Agriculture Organization of the United Nations
	Appendix E: Conversion Factors
	Appendix F: USDA Datasets
		DATA.GOV
		Wheat Data Disappearance and End Stocks
			Hard Red Wheat Contracts
		Brazil Coffee16 Annual
		Dollars/Bushel: Dollars/Ton Converter
	Appendix G: NOAA – Storm Events Database
		Storm Events Database
		Storm Data Event Table
	Appendix H: National Dairy Development Board (NDDB) India
	Appendix I: Worldwide – Artificial Intelligence (AI) Readiness
	Appendix J: Food Aids
		PL-480 or Food for Peace
		The U.S. Bureau of Labor Statistics
	Appendix K: The United Nations – 17 Sustainable Development Goals (SDGs)
	Appendix L: The Statistical Distributions of Commodity Prices in Both Real and Nominal Terms
	Appendix M: Poverty Thresholds for 2019 by Size of Family and Number of Related Children Under 18 Years
	Appendix N: Crop Calendar
		US CROP Calendar
		Canada Crop Calendar
		Brazil Crop Calendar
		Global Coffee Harvest Calendar
		World Specialty Coffee Harvest Chart
		The India Meteorological – Crop Calendar
	Appendix O: G20 – The Agricultural Market Information System (AMIS)
		Wheat Crops
		Rice
	Appendix P: National Feed Security Mission (NFSM) – Ministry of Agriculture and Farmers’ Welfare
		Indian Crop Calendar 1956 – Third Edition
	Appendix Q: Rice Production Manual
Index