This collection features four peer-reviewed reviews on Artificial Intelligence (AI) applications in agriculture.
The first chapter reviews developments in the use of AI techniques to improve the functionality of decision support systems in agriculture. It reviews the use of techniques such as data mining, artificial neural networks, Bayesian networks, support vector machines and association rule mining.
The second chapter examines how robotic and AI can be used to improve precision irrigation in vineyards. The chapter pays particular attention to robot-assisted precision irrigation delivery (RAPID), a novel system currently being developed and tested at the University of California in the United States.
The third chapter reviews the current state of mechanized collection technology, such as the development of harvest-assist platforms, as well as the possibilities of these machines to incorporate artificial vision systems to perform an in-field pre-grading of the product.
The final chapter explores the emergence of the automated assessment of plant diseases and traits through new sensor systems, AI and robotics. The chapter then considers the application of these digital technologies in plant breeding, focussing on smart farming and plant phenotyping.
- Provides a comprehensive overview of the recent developments in the use of Artificial Intelligence (AI) throughout an array of agricultural systems
- Considers the use of AI to better understand plant-pathogen interactions and improve plant disease detection
- Provides readers with a selection of case studies which illustrate the range and utilisation of AI technologies, including GeoSense, Rice-based decision support systems and deep learning
Table of contents
- Advances in artificial intelligence (AI) for more effective decision making in agriculture: L. J. Armstrong, Edith Cowan University, Australia; N. Gandhi, University of Mumbai, India; P. Taechatanasat, Edith Cowan University, Australia; and D. A. Diepeveen, Department of Primary Industries and Regional Development, Australia
2 Agricultural DSS using AI technologies: an overview
3 Data and image acquisition
4 Core AI technologies
5 Case study 1: AgData DSS tool for Western Australian broad acre
6 Case study 2: GeoSense
7 Case study 3: Rice-based DSS
8 Summary and future trends
9 Where to look for further information
10 ReferencesChapter 2
- The use of intelligent/autonomous systems in crop irrigation: Stefano Carpin, University of California-Merced, USA; Ken Goldberg, University of California- Berkeley, USA; Stavros Vougioukas, University of California-Davis, USA; Ron Berenstein, University of California-Berkeley, USA; and Josh Viers, University of California-Merced, USA
2 Related work
3 Overview of RAPID
4 Preliminary results
5 Future trends and conclusion
7 Where to look for further information
8 ReferencesChapter 3
- Advances in automated in-field grading of harvested crops: Jose Blasco, María Gyomar González González, Patricia Chueca and Sergio Cubero, Instituto Valenciano de Investigaciones Agrarias (IVIA), Spain; and Nuria Aleixos, Universitat Politècnica de València, Spain
2 Advantages of in-field sorting
3 Harvest-assist platforms
4 Case study: in-field pre-sorting of citrus
6 Future trends in research
7 Where to look for further information
8 ReferencesChapter 4
- Automated assessment of plant diseases and traits by sensors: how can digital technologies support smart farming and plant breeding?: Anne-Katrin Mahlein, Institute of Sugar Beet Research, Germany; Jan Behmann, Bayer Crop Science, Germany; David Bohnenkamp, BASF Digital Farming GmbH, Germany; René H. J. Heim, UAV Research Centre (URC), Ghent University, Belgium; and Sebastian Streit and Stefan Paulus, Institute of Sugar Beet Research, Germany
2 Digital plant disease detection
3 Complexity of host–pathogen interactions
4 Complexity in a crop stand
5 Case study: application of deep learning to foliar plant diseases
7 Future trends in research
8 Where to look for further information