Precision agriculture can be defined as applying real-time, reliable information to optimize the use of resources and the management of farming practices, minimizing environmental impacts. With the evolution of remote sensing technologies, big data that must be converted to information is being generated in the agricultural sector. When analysed with machine and deep learning approaches applied to remote sensing products, this data has been used successfully. The computational power using cloud-based systems and recent advances in farm machinery equipment providing data collection, processing, and analysis opens several opportunities to develop and adopt new technologies. Large-scale farm precision experimentation conducted in partnership with commercial farms and the appearance of new sensors on board UAVs, crop duster airplanes, and satellites such as radar technologies that allow daily remote data collection under cloudy skies are exciting and require more investigation. In addition, new equipment and sensors are enabling improved crop monitoring and land use mapping on a regional scale. Recent advances in imaging and information technology have led to the massive production of digital images of plant specimens and living plants worldwide. Computer vision and machine learning approaches are up-and-coming technologies to investigate and interpret digitized images of wild and domesticated taxa. Deep learning technologies have been recently shown to achieve impressive performance on a variety of predictive tasks such as automated species identification, trait detection, and organ counting, measurement, and recognition.
The objective of this Research Topic is to explore how big data, machine, and deep learning algorithms are being applied to precision agriculture and plant health. This topic will investigate how these tools could be used and improved in the future to aid food security, mainly involving the integration of state-of-the-art technologies. We hope to increase the recognition and accessibility of AI/ML tools in agricultural and plant research. This Research Topic will bring together researchers from diverse fields and specializations, such as plant bioinformatics, computer engineering, computer science, agricultural engineering, environmental engineering, food engineering, information technology, and mathematics.
This Research Topic welcomes diverse types of articles including original research, reviews, and perspective papers. Potential topics include, but are not limited to:
• Big data, machine, and deep learning for plant and fruit disease classification
• Features optimization for plant disease classification
• Classification of plant types using big data, machine, and deep learning
• Recognition of plant and fruit diseases using big data, machine, and deep learning
• On-farm precision experimentation
• Monitoring and surveillance using hyperspectral images
• Monitoring crop areas
• Convolutional Neural Network-based fruit and crop disease detection
• Fusion of fully connected layers for classification of plant disease
• Selection of optimal features for plant disease
Precision agriculture can be defined as applying real-time, reliable information to optimize the use of resources and the management of farming practices, minimizing environmental impacts. With the evolution of remote sensing technologies, big data that must be converted to information is being generated in the agricultural sector. When analysed with machine and deep learning approaches applied to remote sensing products, this data has been used successfully. The computational power using cloud-based systems and recent advances in farm machinery equipment providing data collection, processing, and analysis opens several opportunities to develop and adopt new technologies. Large-scale farm precision experimentation conducted in partnership with commercial farms and the appearance of new sensors on board UAVs, crop duster airplanes, and satellites such as radar technologies that allow daily remote data collection under cloudy skies are exciting and require more investigation. In addition, new equipment and sensors are enabling improved crop monitoring and land use mapping on a regional scale. Recent advances in imaging and information technology have led to the massive production of digital images of plant specimens and living plants worldwide. Computer vision and machine learning approaches are up-and-coming technologies to investigate and interpret digitized images of wild and domesticated taxa. Deep learning technologies have been recently shown to achieve impressive performance on a variety of predictive tasks such as automated species identification, trait detection, and organ counting, measurement, and recognition.
The objective of this Research Topic is to explore how big data, machine, and deep learning algorithms are being applied to precision agriculture and plant health. This topic will investigate how these tools could be used and improved in the future to aid food security, mainly involving the integration of state-of-the-art technologies. We hope to increase the recognition and accessibility of AI/ML tools in agricultural and plant research. This Research Topic will bring together researchers from diverse fields and specializations, such as plant bioinformatics, computer engineering, computer science, agricultural engineering, environmental engineering, food engineering, information technology, and mathematics.
This Research Topic welcomes diverse types of articles including original research, reviews, and perspective papers. Potential topics include, but are not limited to:
• Big data, machine, and deep learning for plant and fruit disease classification
• Features optimization for plant disease classification
• Classification of plant types using big data, machine, and deep learning
• Recognition of plant and fruit diseases using big data, machine, and deep learning
• On-farm precision experimentation
• Monitoring and surveillance using hyperspectral images
• Monitoring crop areas
• Convolutional Neural Network-based fruit and crop disease detection
• Fusion of fully connected layers for classification of plant disease
• Selection of optimal features for plant disease
