Digital Ecosystem for Innovation in Agriculture

Foreword
Preface
Contents
Editors and Contributors
Frameworks, Tools, and Technologies for Transforming Agriculture
A Brief Review of Tools to Promote Transdisciplinary Collaboration for Addressing Climate Change Challenges in Agriculture by Model Coupling
1 Introduction
2 How Does Agriculture Contribute to Climate Change?
3 How Does Climate Change Threaten Agriculture?
4 Ongoing Approaches for a Future-Proof Agriculture
5 Why Will a Unidimensional Approach Not Work? An Example of Disconnect Between Hydrologists and Crop Modelling Communities
5.1 Crop Models and Agriculture
5.2 Hydrology and Agriculture
6 A Summary of Currently Available Tools for Coupling Models from Various Disciplines to Address Climate Change Challenges in Agriculture
6.1 Coupled Models for Agricultural and Eco-Hydrological Simulations
6.2 Coupled Models for Agricultural and Plant Biological Applications
6.3 Coupling Challenges
6.4 An Introduction to yggdrasil
7 Conclusion
8 Future Direction
9 Open Challenges
References
Machine Learning and Deep Learning in Crop Management—A Review
1 Introduction
2 Literature Review
2.1 Crop Yield Prediction
2.2 Crop Diseases and Pests’ Detection
2.3 Weed Detection
3 Discussion and Conclusions
Appendix: Literature Review Papers
References
Need for an Orchestration Platform to Unlock the Potential of Remote Sensing Data for Agriculture
1 Background
2 AgriTech as Emerging Sector
2.1 Remote Sensing in Agriculture
2.2 Remote Sensing Data in Agriculture
2.3 Scaling Remote Sensing Solutions
3 Need for Orchestration Platform
4 Orchestration Platform: Unlocking the Remote Sensing Data for Agriculture
5 Case Study—Paddy Crop Insurance Using a Satellite-Based Composite Index of Crop Performance
5.1 Motivation
5.2 Problem Statement
5.3 Study Area
5.4 Field Data Collection
5.5 Results
5.6 Analysis
6 Conclusion
References
An Algorithmic Framework for Fusing Images from Satellites, Unmanned Aerial Vehicles (UAV), and Farm Internet of Things (IoT) Sensors
1 Introduction
2 Overview of Data Fusion
3 Farm Data Acquisition and Their Characteristics
4 Our Generic Algorithm for Data Cube Construction
5 Data Fusion in the Context of Crop Monitoring
6 Conclusions and Future Work
References
Globally Scalable and Locally Adaptable Solutions for Agriculture
1 Introduction
2 Open Source Satellite Data
2.1 MODIS
2.2 Landsat
2.3 Sentinel Missions
2.4 Planet Scope
2.5 Ecostress
3 Open Source Cloud Computing Platforms
3.1 Google Earth Engine (GEE)
3.2 Python
3.3 Google Colab
3.4 Sentinel Hub
3.5 Open EO
4 Big Data Analytics
5 Case Study: Developing a Globally Scalable and Locally Adaptable Crop Monitoring System for Wheat Crop
5.1 Visualizing Time Series Vegetation Indices Derived from Open Source Satellite Data
5.2 Developing Time Series of Biophysical Parameters like LAI, CCC, CWC Derived from Open Source Satellite Data
5.3 Predicting Crop Yields Using Sentinel-1 and Sentinel-2 Derived Indices
6 Challenges in Monitoring Crops Using Open-Source Satellite Data
7 Conclusion
References
A Theoretical Framework of Agricultural Knowledge Management Process in the Indian Agriculture Context
1 Introduction
1.1 Agricultural Knowledge Management (AKM)
2 Methodology
2.1 Profile Case A: Mulukanoor Women's Cooperative Dairy (MWCD)
2.2 Profile of Case B: Mehsana District Cooperative Milk Producer's Union Ltd. (Dudhsagar Dairy)
2.3 Findings
3 The Theoretical Framework of Agricultural Knowledge Management Process
3.1 Knowledge Acquisition and Creation (KAC)
3.2 Knowledge Organization and Storage (KOS)
3.3 Knowledge Sharing and Dissemination (KSD)
3.4 Knowledge Application (KA)
3.5 Information and Communication Technologies (ICTs)
4 Role of Digital Technologies in Theoretical Framework
5 Conclusion
6 Future Direction
References
Problems and Applications of Digital Agricultural Transformations
Simple and Innovative Methods to Estimate Gross Primary Production and Transpiration of Crops: A Review
1 Introduction
2 Biophysical Link Between GPP, T, and SIF
3 Main Methods and Limitations to Calculate GPP
3.1 In Situ GPP Estimates
3.2 Model-Based GPP Estimates
3.3 Current Work and Limitations (In situ, Remote Sensing, and Modeling-Based)
3.4 Innovative and Simple Approaches to Estimate GPP
4 Main Methods to Calculate ET Components (T and E)
4.1 In situ and Model-Based Approaches to Calculate T and ET
4.2 Limitations of Current Methods and Techniques
4.3 Innovative and Simple Approaches to Estimate Water Fluxes
5 Unit Conversion of Energy, Carbon, and Water Fluxes
5.1 Solar Radiation and PAR
5.2 Carbon Fluxes
5.3 Water Fluxes (Transpiration and Evapotranspiration): Conversion of Energy Units to mm of H2O
6 Summary and Conclusion
References
Role of Virtual Plants in Digital Agriculture
1 Introduction
2 Virtual Plant: The Concept
3 Crop Models and Virtual Plant Modeling
3.1 Static and Dynamic Crop Models
3.2 Static Crop Models
3.3 Dynamic Crop Models
4 Case Study on Static Architectural Model
5 Applications of Virtual Plants
6 Challenges in Agronomic Applications of Virtual Plants
7 Preliminary Results
8 Summary
References
Remote Sensing for Mango and Rubber Mapping and Characterization for Carbon Stock Estimation—Case Study of Malihabad Tehsil (UP) and West Tripura District, India
1 Introduction
2 Study Area and Data Used
2.1 Remote Sensing Data Used in the Study
3 Methodology
3.1 Estimating Area Under Mango and Rubber Plantations and LULC Using Machine Learning
3.2 Estimating Soil Organic Carbon (SOC)
3.3 Data Acquisition and Analysis
3.4 Conversion of SOC Concentration to Profile SOC Density
4 Results and Discussions
4.1 Mapping Mango and Rubber Using Machine Learning
4.2 Estimating Biomass and Carbon Densities for Mango and Rubber
4.3 Characterizing the Tree Density
4.4 Tree Canopy Height Model
4.5 Estimating Soil Organic Carbon (SOC)
5 Conclusions
References
Impact of Vegetation Indices on Wheat Yield Prediction Using Spatio-Temporal Modeling
1 Introduction
2 Related Work
2.1 Field Survey-Based Approach
2.2 Crop Growth Model-Based Approach
2.3 Statistical Techniques-Based Approach
2.4 Machine Learning and Deep Learning-Based Approach
2.5 Vegetation Indices
2.6 Normalized Difference Vegetation Index (NDVI)
2.7 Enhanced Vegetation Index
3 Study Area and Dataset Description
4 Proposed Approach
4.1 Convolutional Neural Network (CNN)
4.2 Long Short-Term Memory
5 Results and Discussion
6 Conclusion
References
Farm-Wise Estimation of Crop Water Requirement of Major Crops Using Deep Learning Architecture
1 Introduction
2 Objective
3 Study Area
4 Amnex’s Agrogate Platform
5 Methodology
5.1 Dataset
5.2 Process Flow
5.3 Farm Boundary Delineation
5.4 Classification Output
5.5 Soil Moisture
5.6 Temperature, Rainfall, Kc, ETo
5.7 CWR
6 Result and Discussion
7 Conclusion
References
Hyperspectral Remote Sensing for Agriculture Land Use and Land Cover Classification
1 Introduction
2 Pre-processing—Radiometric and Atmospheric Corrections
2.1 Radiometric Corrections
2.2 Atmospheric Corrections
2.3 Dimensionality Reduction Techniques
3 Field Spectra Collection and Post-processing of Field Spectra
3.1 Splice Correction
3.2 Removal of Noisy and Water Vapor Regions
3.3 Spectral Smoothening
3.4 Building the Spectral Library
4 Classification Methods of Hyperspectral Data
5 Some Results from Hyperion Spaceborne Datasets
5.1 Radiometric Correction of Hyperion Data
5.2 Atmospheric Correction of Hyperion Data
5.3 Dimensionality Reduction (DR)
5.4 Post-processing of Field Spectra
5.5 Classification
6 Conclusions
References
Computer Vision Approaches for Plant Phenotypic Parameter Determination
1 Introduction
2 Recognizing and Counting of Spikes in Visual Images of a Wheat Plant
2.1 Image Acquisition
2.2 Architecture of the Deep Learning Approach
2.3 Training of the Deep Learning Model
2.4 Result
3 Machine Learning-Based Plant Senescence Quantification
4 Conclusion
References