Artificial Intelligence and Data Science in Agriculture : Specialty Crops and Climate Change Modeling.

Format:

Book

Author/Creator:

Vuppalapati, Chandrasekar.

Language:

English

Subjects (All):

Artificial intelligence.

Sustainable agriculture.

Physical Description:

1 online resource (598 pages)

Edition:

1st ed.

Place of Publication:

Berlin/Boston : Walter de Gruyter GmbH, 2026.

Summary:

Specialty crops--fruits, vegetables, nuts, horticulture, and nursery crops--are a powerful engine of agricultural growth, contributing nearly one-fifth of U.S.farm revenues and driving a 1.6 trillion global market.As demand rises and climate challenges intensify, growers need smarter tools to stay competitive.

Contents:

Intro

Also of interest

Artificial Intelligence and Data Science in Agriculture

Acknowledgments

Preface

Contents

Section I: Introduction

Chapter 1 Introduction

Brief history

Machine learning (ML)

Mother nature [16]

Deep learning (DL)

Generative AI (large language model)

Foundation models

Data pipeline

Data pipeline: average weekly regional refrigerated truck rates by distance (Florida, California, Sinaloa, Mexico, and Baja California, Mexico)

Step 1: USDA truck data

Step 2: Prepare California region truck rates

Step 3: Prepare Florida region truck rates

Supervised learning

Regression models

Metrics for regression models

ML model: field fresh tomatoes retail prices and post-harvest cost components: storage, packing, shipping, and transportation

Experiment sources

Step 1: Load libraries

Step 2: Feature: global prices (PNGASUSUSDM)

Step 3: Feature: consumer price index (CPIAUCSL)

Step 4: Feature: producer price index by commodity ethylene propylene (WPU07110224)

Step 5: Feature: US diesel sales price (GASDESM)

Step 6: Feature: industrial CO2(PCU3251203251204)

Step 6: Feature: refrigerator truck shipping rates - California and Florida regional rates

Step 7: Combined DataFrame and perform data analysis

Step 8: Apply imputation strategy to fix nulls

Step 9: Correlation analysis

Step 10: Regression models: linear regressor

Step 11: Regression models: random forest regressor

Step 12: Regression models: gradient boosting regressor

ML model: CA-FL routes: field fresh tomatoes retail prices and post-harvest cost components: Storage, packing, shipping, and transportation

Step 6: Feature: refrigerator truck shipping rates - Florida (October to June) month rates.

Step 7: Feature: refrigerator truck shipping rates - California (May to November) month rates

Step 8: Merge data frames California (May to November) and Florida (October to June) rates

Step 9: Combined DataFrame and perform data analysis

Step 10: Apply imputation strategy to fix nulls

Step 11: Correlation analysis

Step 12: Regression models: linear regressor

Step 11: Multi-tree (RF) regression model

Step 12: Regression models: gradient-boosted ensemble regression

Temporal data analysis

Single-variable temporal data

Multivariate time series

Forecasting models

Prophet forecasting

Univariate time series model: America's most beloved imported fruits: avocados imports

Step 1: Data load

Step 2: Load and plot dataset

Step 3: Avocados import with prophet

Step 4: Make an in-sample forecast

Step 5: Predict

Step 6: Model accuracies: MAE

Step 7: COVID-19 import spike

Step 8: Estimate

Summary

Multivariate time series model: America's most beloved imported fruits: avocados imports

Step 2: View temporal data

Step 4: Prepare future data

Forecasting dataset preparation: what-if modeling

Step 1: Prepare and load what-if dataset

Step 2: Setup time column

Step 3: Predict

Additional ML experiments

Commercial machinery repair and maintenance feature

US trucking industry

Chapter 2 Specialty (high-value and niche) crops

Employment opportunities

Critical industry needs

Production and marketing value chain

Field-processed crops: growers and processors

Market value chain

Data and ML - tree nuts (pistachios) market value order

Data and ML - tree nuts (tomatoes) market value order

Specialty crops pricing forecast framework.

Framework assumptions

Yield forecasting

Challenges of pests and diseases in agricultural crop production: Understanding the impact of monocropping and chemical use

Macroeconomics

Infrastructure

Machine learning mode: Maine and New Hampshire strawberries pricing model

Suggested varieties

Seasonality

Sources

Pricing model framework: variable list

Step 1: Load data

Step 2: Weather data: NOAA GSOM

Step 3: Load fertilizer data from World Bank Pink Sheet data

Step 4: Load energy costs

Step 5: Global Economic Policy Uncertainty Index: GEPUCURRENT

Step 6: Producer Price Index by Industry: Commercial Machinery Repair and Maintenance: Maintenance and Repair Services for Agricultural, Construction, and Mining Machinery (PCU8113108113105)

Step 7: How expensive things are (CPIAUCSL)

Step 8: US diesel sales price (GASDESW)

Step 9: Combine all data frames

Step 10: Check for nulls

Step 11: Perform Prophet model

Step 12: Prepare future DATAFRame: multivariate

Step 13: Overall performance of prophet model

Crop price behavior

Cobweb model

Market and weather influenced vegetable and fruit price uncertainties

Water

Evapotranspiration: Watching over water use

View gridded data

Market access and value chain

Chapter ML experiments

Transportation costs

Strawberries' prices

Chapter 3 Climate change and adaptation strategies

Climate change

Projection models

Adaptation strategies

The cost and coverage of crop insurance in the USA

Federal crop insurance: supporting traditional and specialty crops

ML model use case: almonds payment indemnity

"Parametric" and weather-based index insurance

Barriers for effective adaptation

Inventory of crop insurance model and ML feature engineering

Indemnity payments.

Role of data science in increasing adoption of crop insurance

Financial sustainability ML models: crop insurance go/no-go decision based on field-grown tomatoes price forecast model

Step 1: Load important feature engineering parameters

Understanding the chemicals PPI

Load phosphate rock, DAP, and TSP prices

Load urea prices

Analyzing the CPIAUCSL

Load consumer GDP: Normalized for US (USALORSGPNOSTSAM)

Load industrial production

Natural gas

Load PPI for machinery and equipment (WPU111)

Load refrigerated truck rates by distance

Step 2: Load tomatoes prices and feature variables DATAFRAme

Step 3: Prepare prophet data frame for tomatoes prices

Step 4: Prepare train and test data

Step 5: Check time series data for nulls

Step 6: Prepare the time series model

Step 7: Predict freshly grown tomato prices

Step 8: Tomatoes prices estimate

Step 9: Visualize forecast components

Step 10: Calculate performance metrics (MAE) and visualize the forecasted prices

Step 11: AutoML model

Step 11: KPI: crop insurance decision

Financial sustainability what-if models

Yield guarantees model

Revenue guarantees model

Re-run

Section II: Specialty crops: pistachios

Chapter 4 Specialty crops pistachio: production and yield

Top cultivating sources of pistachios

The United States

California

Türkiye

Iran

Seasonal phenology and climatic requirements

The United States of America

Turkey

Pistachios yield analysis

The United States of America (USA)

Yield and elevation

Future dataset imputation model: USA/California pistachios polynomial regression

Step 1: Setup the environment

Step 2: Load California pistachios data (1977:2023)

Step 3: Partition the data

Step 3 : Signature of the dataset

Step 4: Evaluate the model.

Step 5: Increased accuracy with polynomial regression

Step 6: Evaluate polynomial regression model metrics

Step 7: Area harvest forecast till century end: 2020:2100

Step 8: Impute future of pistachios production in California till 2100

Climate change on Fresno, San Joaquin Valley, California pistachio yield: an ML approach

Fresno pistachios production and climate data

Fresno climate and environmental readings drift

ML algorithms

Step 1: Fresno climate, pistachios production, and other data imports

Step 2: Pistachios FAO 1991:2021 data

Step 3: Alternate cropping flag

Step 4: Visualize pistachios production data (California, USA)

Step 4: Plot US CO2 1990:2020

Step 5: Visualize California historical and projected drought conditions (SPEI)

Step 6: California: Fresno county weather data 1991:2020

Step 7: Prepare Fresno climatology and pistachios combined dataset

Step 8: Fresno pistachios correlation matrix

Step 9: ML model: gradient boosting regressor

Step 10: Gradient boost explainability

Step 12: Maximizing Fresno pistachio yield: insights from random forest regressor

Step 13: Saving and loading Fresno pistachios yield ML mode

Extensive climatological Fresno pistachios: the complex relationship between climate and yield

Step 5: Fresno Yosemite International, Station 1980:2023 weather data

Step 7: Merge datasets: climatology, weather, production, and environmental

Step 8: Climatic and wind pollination pistachios yield ML regressor

Step 10: Formulate Fresno pistachios regression equation

Step 10: ML model: gradient boost explainability

Step 12: Gradient boosting regressor

Water and yield sustainability

Chapter 5 Specialty crops pistachio: climate change adaptation strategies

Historical risk management (RMA) payments.

Yield influencers.

Notes:

Description based on publisher supplied metadata and other sources.

Part of the metadata in this record was created by AI, based on the text of the resource.

ISBN:

3-11-143889-9

OCLC:

1591748918