Deep Learning for Sustainable Agriculture

Front Matter
Copyright
Contributors
Smart agriculture: Technological advancements on agriculture-A systematical review
	Introduction
	Methodology
	Role of image processing in agriculture
		Plant disease identification
		Fruit sorting and classification
		Plant species identification
		Precision farming
		Fruit quality analysis
		Crop and land assessment
		Weed recognition
	Role of Machine Learning in Agriculture
		Yield prediction
		Disease detection
		Weed recognition
		Crop quality
		Species recognition
		Soil management
	Role of deep learning in agriculture
		Leaf disease detection
		Plant disease detection
		Land cover classification
		Crop type classification
		Plant recognition
		Segmentation of root and soil
		Crop yield estimation
		Fruit counting
		Obstacle detection
		Identification of weeds
		Prediction of soil moisture
		Cattle race classification
	Role of IoT in agriculture
		Climate condition monitoring
		Crop yield
		Soil patter
		Pest and crop disease monitoring
		Irrigation monitoring system
		Optimum time for plant and harvesting
		Tracking and tracing
		Farm management system
		Agricultural drone
	Role of wireless sensor networks in agriculture
		Irrigation management
		Soil moisture prediction
		Precision farming
		Climate condition monitoring
	Role of data mining in agriculture
		Irrigation management
		Prediction and detection of plant diseases
		Pest monitoring
		Optimum management of inputs (fertilizer and pesticides)
		Crop yield prediction
		Climate condition monitoring
	Conclusion
	References
A systematic review of artificial intelligence in agriculture
	Precision farming
		Introduction
		Related work using AI
		Objective and design consideration
		Challenges and future scope
	Plant disease detection
		Introduction
		Deep learning in image processing
		Review of plant disease detection using image processing and deep learning
		Performance analysis of some state-of-art techniques
		Research gaps and future scope
	Soil health monitoring using AI
		Introduction
		Brief history
		Opportunity of AI in soil health monitoring
		Current status
	Scope and challenges of AI in agriculture
	Conclusions
	References
Introduction to deep learning in precision agriculture: Farm image feature detection using unmanned aerial veh ...
	Introduction
	Deep learning overview
	CNN training
		CNN in agricultural applications
	Methodology
		Data collection and processing
		UAV specification
		Image processing and labeling
			Image processing
			Data augmentation strategy
			Software and hardware configuration
	Experiment and results
		Binary classification
		Multiclass classification
	Discussion
		Advantages of the developed model
	Conclusion
	References
Design and implementation of a crop recommendation system using nature-inspired intelligence for Rajasthan, India
	Introduction
	Literature survey
	Proposed methodology
		Preprocessing layer
			Download and tiling
		Feature extraction
			Image-based features
				Sand and clay content
			Knowledge-based features
		Optimization layer
			Plate tectonics optimization
			BBO
			Adaptive moment estimation optimization
			PBO-BBO hybrid
			PBO-Adam hybrid
		Softmax classification layer
	Results
	Conclusion and future work
	References
	Further reading
Artificial intelligent-based water and soil management
	Introduction
	Applications of artificial intelligence in water management
		Evapotranspiration estimation
		Crop water content prediction
		Water footprint modeling
		Groundwater simulation
		Pan evaporation estimation
	Applications of artificial intelligence in soil management
		Soil water content determination
		Soil temperature monitoring
		Soil fertilizer estimation
		Soil mapping
	Conclusion and recommendations for water-soil management
	References
Machine learning for soil moisture assessment
	Introduction
	Overview of machine learning
	Machine learning algorithms applied in soil moisture research
		Linear regression
		Artificial neural network/deep neural network
		Support vector machine
		Classification and regression tree
		Random forest
		Extremely randomized trees
	Applications of machine learning for soil moisture assessment
		Pedotransfer functions
		Prediction models for soil moisture estimation/forecasting
		Soil moisture retrieval through remote sensing
		Irrigation scheduling
		Downscaling of satellite-derived soil moisture products
	Conclusions
	Abbreviations
	References
Automated real-time forecasting of agriculture using chlorophyll content and its impact on climate change
	Introduction
	Current status
		National Status
		International status
	Problem statement
	Objective of the proposed work
	Research highlights
	Scientific significance of the proposed work
	Materials and methods
		Histogram of oriented gradients
		Principal component analysis
		Backpropagation algorithm
	Detailed work plan to achieve the objectives
		Methodology
	Results and discussion
	Conclusion
	References
Transformations of urban agroecology landscape in territory transition
	Introduction
	Agroecological landscapes
	Agroecological practices
	Agroecological territorial transformation and transition
	Conclusion
	References
WeedNet: A deep neural net for weed identification
	Introduction
	Related work
	WeedNet
		Model architecture
		Complexity analysis
	Evaluation strategy
		Performance metrics
			AUC
			Precision
			Recall
			Accuracy
		Data set
	Experimental setup
	Experimental evaluation
	Conclusion
	References
Sensors make sense: Functional genomics, deep learning, and agriculture
	Introduction
	Section I. Functional genomics
		The emerging applications of soil microbial metabolites
		Agricultural-based metabolites to advance nutraceutical production and drug discovery
		Marine microalgae, aquaculture, and the DL toolbox Ludwig
		Pollinators, Ludwig combiners, and the carbon-energy cycle
	Section II. DAS networks
		Agricultural factors in the plant-silicon cycle: Genomic regulation of blight, drought, and invasive species
		Helically wound DAS
	Section III. GRANITE and the agent-based GRANITE Network Discovery Tool
	Conclusions
	Acknowledgments
	References
Crop management: Wheat yield prediction and disease detection using an intelligent predictive algorithms and  ...
	Introduction
	Literature review
		Wheat yield prediction
			Genotypexenvironment interaction for wheat yield prediction
			Machine learning algorithms for wheat yield prediction
			Remote and satellite data for wheat yield prediction
			CERES-Wheat model for wheat yield prediction
			Evapotranspiration and soil moisture content for wheat yield prediction
		Wheat diseases detection
			Machine learning algorithms for wheat diseases detection
			Web-based system with multiple regression for wheat disease detection
			Image-processing techniques for wheat disease detection
	Discussion
	Conclusion and future scope
	References
Sugarcane leaf disease detection through deep learning
	Introduction
	Methodology
		Dataset
		Leaf disease detection system architecture
		Leaf disease detection model architecture
		SAFAL-FASAL android application
		Method of evaluation
	Experimentation
	Results and discussion
		Performance evaluation
		SAFAL-FASAL Android application results
	Conclusion
	References
Prediction of paddy cultivation using deep learning on land cover variation for sustainable agriculture
	Introduction
	Applications of geospatial analytics for agriculture
		Importance of remote sensing to estimate paddy area
		Related studies based on satellite imaginary
			Applications with machine learning approaches
			Applications with deep learning approaches
		Related studies based on the Internet of Things
		Related studies with integrated data
		Dataset associated with land-use land-cover data
		Comparison of related studies with satellite imagery and deep learning
	Material analysis
		Data source
		Analysis of raster data
	System model design and implementation
		Process view
		Data preprocessing and feature selection
		Transfer learning process
	System evaluation
		Model evaluation
		Ground truth measurement
		Model prediction comparison for contextual analysis
	Discussion
		Contribution of the proposed study
		Limitations of the datasets
		Future research directions
	Conclusions
	References
Artificial intelligence-based detection and counting of olive fruit flies: A comprehensive survey
	Introduction
	Literature survey of recognition systems
		Manual detection and counting
		Semiautomatic detection and counting
		Automatic detection and counting
			Artificial neural networks
			Deep learning via CNNs
			Image processing
			Optoacoustic spectral analysis
			Spectroscopy hyperspectral imaging
	Evaluation and discussions
		Semiautomatic detection
		Image-based automatic detection
			Machine and deep learning
			Image processing
		Nonimage-based automatic detection
	Conclusions
	Acknowledgments
	References
Index