Application of Machine Learning in Agriculture

Description

Application of Machine Learning in Smart Agriculture is the first book to present a multidisciplinary look at how technology can not only improve agricultural output, but the economic efficiency of that output as well. Through a global lens, the book approaches the subject from a technical perspective, providing important knowledge and insights for effective and efficient implementation and utilization of machine learning.

As artificial intelligence techniques are being used to increase yield through optimal planting, fertilizing, irrigation, and harvesting, these are only part of the complex picture which must also take into account the economic investment and its optimized return. The performance of machine learning models improves over time as the various mathematical and statistical models are proven. Presented in three parts, Application of Machine Learning in Smart Agriculture looks at the fundamentals of smart agriculture; the economics of the technology in the agricultural marketplace; and a diverse representation of the tools and techniques currently available, and in development.

This book is an important resource for advanced level students and professionals working with artificial intelligence, internet of things, technology and agricultural economics.

Addresses the technology of smart agriculture from a technical perspective
Reveals opportunities for technology to improve and enhance not only yield and quality, but the economic value of a food crop
Discusses physical instruments, simulations, sensors, and markets for machine learning in agriculture

Front Cover 2
Application of Machine Learning in Agriculture 5
Copyright Page 6
Contents 7
List of contributors 15
1 Fundamentals of smart agriculture 19
- 1 Machine learning-based agriculture 21
  - Introduction 21
  - Literature review 24
  - Deep learning in agriculture 26
    - Transfer learning for pest detection 27
  - Proposed method 28
    - Pest detection 28
      - Performance evaluation 30
    - Crop yield prediction 31

Front Cover 2
Application of Machine Learning in Agriculture 5
Copyright Page 6
Contents 7
List of contributors 15
1 Fundamentals of smart agriculture 19
- 1 Machine learning-based agriculture 21
  - Introduction 21
  - Literature review 24
  - Deep learning in agriculture 26
    - Transfer learning for pest detection 27
  - Proposed method 28
    - Pest detection 28
      - Performance evaluation 30
    - Crop yield prediction 31
      - Methodology 32
    - E-Mandi 33
      - Methodology 34
      - Functionalities 36
    - Results and discussions 36
      - Pest detection 36
      - Crop yield prediction 39
      - E-Mandi 41
    - Comparative study 36
      - Comparison between different pest detection techniques 36
      - Comparison between different crop yield prediction techniques 36
    - Conclusion 41
    - References 43
  - 2 Monitoring agricultural essentials 47
    - Introduction 47
    - Unsupervised machine learning algorithms for agriculture 48
    - Supervised machine learning algorithms for agriculture 51
      - Artificial neural network 51
      - Linear regression 52
      - Random forest 53
    - Proposed predictive model for agriculture 53
      - Data collection devices 54
      - Crop prediction 57
      - Data storage 57
      - Real-time monitoring 58
      - Communication technology 58
    - Results and discussion 60
    - Summary 61
    - References 62
  - 3 Machine learning-based remote monitoring and predictive analytics system for monitoring and livestock monitoring 65
    - Introduction 65
    - Motivation 67
    - Background study 68
      - Techniques used 69
        
        Artificial intelligence 69
        
        Machine learning 70
      - Benefits of the work 71
      - Research challenges 72
      - Role of artificial intelligence and machine learning for crop monitoring 74
    - Reported work 74
    - Comparative analysis 78
    - Conclusion 80
    - References 81
  - 2 Market, Technology and Products 87
    - 4 Agricultural economics 89
      - Introduction 89
      - Prediction of crop price 90
      - Impact of gross domestic product 93
        
        Share of agriculture in gross domestic product 94
        
        Government schemes 95
      - Economical changes in traditional agriculture versus machine learning agriculture 96
      - Meteorology 98
        
        Scope of agrometeorology 100
        
        Crops and animals using agrometeorology 101
        
        Crops 101
        
        Animals 102
        
        Agrometeorology’s relationship with agricultural sciences 101
        
        Difference between meteorology and agrometeorology 101
        
        Agrometeorology as an interdisciplinary science 102
      - Conclusion 102
      - References 103
    - 5 Current and prospective impacts of digital marketing on the small agricultural stakeholders in the developing countries 109
      - Introduction 109
      - Definition of and types of electronic business 111
      - Digital agricultural market before, during, and what is expected after the COVID-19 pandemic in developing countries 113
      - Digital agricultural market to mitigate the negative impacts of uncertainty 115
      - Opportunities and risks of investment in the digital agricultural market industry 116
      - Market segmentation of the digital agricultural market in developing countries 119
      - A mobile banking system 122
      - Digital agricultural value chain and its stakeholders 123
      - Impacts of digital agriculture on poverty reduction, food security rates, and food losses and waste reduction in developing... 125
      - Agricultural digitalization to achieve the sustainable development goals 2030 126
      - Conclusion 127
      - References 127
    - 6 Intelligent farming system through weather forecast support and crop production 131
      - Introduction 131
      - Technology stack used 132
        
        Internet of Things 132
      - Used algorithms 133
        
        Deep neural networks 133
        
        Random forest program 133
      - System-related architecture 134
        
        Raspberry Pi 3 135
        
        Sensor for sensing rainfall 136
        
        Sensor module based on DHT 11 136
        
        Sensor for soil moisture 136
        
        Software Raspbian (Raspberry pi) 138
        
        ThingSpeak 138
        
        Sensor BMP-180 type 138
        
        Jupyter Notebook 139
      - Weather prediction 140
        
        Predicting temperature 140
      - Results 143
      - Methodology used 143
      - References 146
      - Conclusions 146
    - 7 Deep learning-based prediction for stand age and land utilization of rubber plantation 149
      - Introduction 149
      - Background and related work 151
        
        Rubber land-use mapping and age estimation via remote sensing imagery 151
        
        Feature representation 152
        
        Supervised classification methods 153
      - Study materials 155
        
        Details of the area of study 155
        
        Dataset 155
      - Solution design and implementation 156
        
        Model design 156
        
        Data preprocessing 156
        
        Supervised learning process 159
        
        VGG-16 and FCN-8 model 159
        
        U-net model 161
        
        Model evaluation 162
        
        Experimental setup 162
        
        Classification performance analysis 162
        
        Vegetation index analysis 166
        
        Discussion 168
        
        Study contributions 168
        
        Study challenges 169
        
        Future research directions 169
        
        Conclusion 170
        
        Acknowledgment 170
        
        References 171
      - 3 Tools and Techniques 175
        
        8 Modeling techniques used in smart agriculture 177
        
        Introduction 177
        
        Expert system 178
        
        Fuzzy framework for smart agriculture 179
        
        Fuzzy system architecture 180
        
        Knowledge base 180
        
        Fuzzification 181
        
        Fuzzy framework 181
        
        Fuzzy inference engine 182
        
        Defuzzification 187
        
        Conclusion 187
        
        References 187
        
        9 Plant diseases detection using artificial intelligence 191
        
        Introduction 191
        
        Literature survey 192
        
        Recognizing plant diseases 198
        
        Image acquisition 198
        
        Image preprocessing 199
        
        Image segmentation 200
        
        Edge based 200
        
        Region based 200
        
        Threshold based 201
        
        Feature-based clustering 201
        
        Feature extraction 201
        
        Image recognition 202
        
        Performance measures for image recognition techniques 203
        
        Discussion and future work 204
        
        Conclusion 205
        
        References 206
        
        10 A deep learning-based approach for mushroom diseases classification 209
        
        Introduction 209
        
        Related works 210
        
        Dataset description 213
        
        Methods 213
        
        Image augmentation 213
        
        Noise removal from image 215
        
        Image enhancement technique 216
        
        Deep learning algorithm 218
        
        AlexNet 218
        
        ResNet15 219
        
        GoogleNet 221
        
        Result analysis and discussion 222
        
        Conclusion 227
        
        References 228
        
        11 Smart fence to protect farmland from stray animals 231
        
        Introduction 231
        
        Agricultural fences 231
        
        Natural repellents 232
        
        Smart fence to protect farmland 233
        
        Virtual fence setup using optical fiber sensor 233
        
        Optical fiber cable 234
        
        Types of optical fibers 236
        
        Optical fiber cable as sensor 237
        
        Fiber optic sensors 238
        
        Types of fiber-optic sensor systems 238
        
        Intrinsic type fiber optic sensors 238
        
        Extrinsic type fiber-optic sensors 238
        
        Classification of fiber-optic sensors on the basis of operating principles 239
        
        Intensity-based fiber-optic sensor 239
        
        Polarization-based fiber-optic sensor 239
        
        Phase-based fiber optic sensor 240
        
        Signal analysis 241
        
        Gait-based analysis to differentiate walking, running, and tapping 244
        
        Algorithm for classification 248
        
        Results 249
        
        Conclusion 251
        
        References 252
        
        12 Enhancing crop productivity through autoencoder-based disease detection and context-aware remedy recommendation system 257
        
        Introduction 257
        
        Preliminaries 259
        
        Multilayer perceptron 259
        
        Stacked denoising autoencoder 260
        
        Convolutional neural network 261
        
        Sentiment analysis 261
        
        Proposed method 262
        
        Disease detection phase 263
        
        Cascading autoencoder 263
        
        Disease classification phase 266
        
        Threshold module 266
        
        Infection region detector 266
        
        Recommendation phase 267
        
        Stacked autoencoder 269
        
        Experimental valuation 271
        
        Implementation details 271
        
        Description of the dataset 271
        
        Evaluation metric 273
        
        Performance of segmentation by cascading autoencoder 273
        
        Performance of classification by concise convolutional neural network 274
        
        Performance of remedy recommendation stacked autoencoder (SAE) 274
        
        Conclusion 275
        
        References 276
        
        13 UrbanAgro: Utilizing advanced deep learning to support Sri Lankan urban farmers to detect and control common diseases in... 281
        
        Introduction 281
        
        Literature review 282
        
        Feature extraction 282
        
        Preprocessing 282
        
        Machine learning 283
        
        Deep learning 284
        
        Classification 284
        
        Object detection 284
        
        Implementation 287
        
        Methodology 287
        
        Data collection 287
        
        Image annotation 289
        
        Data augmentation 289
        
        Deep learning model 290
        
        YOLOv3 design 290
        
        Justification for choosing an object detection model over a classification model 291
        
        Model Training 292
        
        Results and discussion 292
        
        Comparison of our results with previous works 297
        
        Conclusion 298
        
        Limitations 298
        
        Future directions 298
        
        Acknowledgments 299
        
        References 299
        
        14 Machine learning techniques for agricultural image recognition 301
        
        Introduction 301
        
        Steps for image analysis 302
        
        Machine learning strategies in agricultural image recognition 304
        
        Traditional machine learning methods 304
        
        Supervised learning algorithms 305
        
        Classification methods 305
        
        Naïve Bayes 306
        
        K-nearest neighbors 306
        
        Support vector machines 306
        
        Random forest 307
        
        Artificial neural networks 307
        
        Decision tree 307
        
        Regression methods 307
        
        Linear regression (LR) 307
        
        Multiple linear regression 307
        
        Support vector regression 308
        
        Ensemble 308
        
        Unsupervised learning algorithm 308
        
        k-Means 308
        
        Fuzzy clustering 308
        
        Gaussian 309
        
        Reinforcement learning 309
        
        Deep learning models 309
        
        Convolutional neural networks 309
        
        Restricted Boltzmann machine 309
        
        Long-term short memory 310
        
        Applications of image processing in agriculture tasks 310
        
        Leaf analysis 311
        
        Soil assessment 311
        
        Irrigation 311
        
        Weed detection 312
        
        Pest control 313
        
        Disease detection 313
        
        Monitoring plant growing 314
        
        Vegetation measurement 314
        
        Fruit/food grading 315
        
        Crop yield 315
        
        Flower and seed detection 316
        
        Plant classification 316
        
        Summary 318
        
        References 318
        
        Index 325
        
        Back Cover 333

Description

TOC

Reviews (0)