In recent years, deep learning methods have played a great role in the plant sciences and achieved a series of remarkable achievements in many fields, such as yield prediction and estimation, crop pest identification, plant disease detection, physiological trait indication, seedling development monitoring, plant irrigation strategy, cultivar recognition, leaf counting, etc. However, the applications based on typical deep learning rely heavily on big-scale datasets requiring substantial manual annotation of training data, which is a serious shortcoming. After all, large-scale real-world agricultural datasets are time-consuming and expensive to collect and label by experts for every potential application. In order to alleviate this problem, few-shot learning is emerging, also called learning from few data. Few-shot learning is a new branch of deep learning, which aims to develop an intelligent model with good generalization from only few data, towards the combination of machine intelligence with flexibility and extensibility. Both deep learning and few-shot learning are technological explorations in the field of plant sciences that have the potential to greatly accelerate their applications. Therefore, we encourage you to share your research and opinions in this area and submit your paper to this thematic series.
To facilitate community development and use of these methods, deposition of novel data and image sets in publicly accessible repositories is highly encouraged, as is new use of such publicly available data.
Topics of this article collection include, but are not limited to:
• Survey of deep learning and few-shot learning in the plant sciences and agriculture
• Advanced techniques and methods of deep learning and few-shot learning
• Root segmentation from complex backgrounds
• Path planning in the smart farms
• Plant diseases recognition
• Leaf area index estimation
• Plant status assessment
• Plant pests classification
• Plant yield prediction
• Plant irrigation strategy
• Special hardware architectures, software packages
Manuscript submission deadline: 31 December 2021
Yang Li is an Associate Editor for the journal Plant Methods and also a Lecturer at Shihezi University, Xinjiang, China. He received the MSc degree in Electrical Engineering from Dalian University of Technology, Dalian, China, in 2016. From 2016 to 2019, he taught several main courses for undergraduates at Shihezi University. Since 2019, he is pursuing a PhD degree at Tianjin University while teaching at Shihezi University. His current research interests include image processing, artificial intelligence, precision agriculture, few-shot learning, and nondestructive testing. In these areas, he has published more than 10 technical articles as the first author or the corresponding author in some flagship journals, such as Computers and Electronics in Agriculture, Nondestructive Testing and Evaluation, Agriculture-Basel, etc. He is also an active peer reviewer for many influential scientific journals in the agricultural research field, e.g., Computers and Electronics in Agriculture, Plant Methods, Precision Agriculture, Biosystems Engineering, Remote Sensing, etc.
Jiachen Yang received his BSc, MSc and PhD degrees in communication and information engineering from Tianjin University, Tianjin, China, in 2002, 2005 and 2009, respectively. He is currently a professor at School of Electronical and Information Engineering, Tianjin University. From 2014 to 2015, he was a visiting scholar with the Department of Computer Science, School of Science, Loughborough University, U.K. In 2019, He was a visiting scholar with Embry-Riddle Aeronautical University. He is the leader of the Lab of Stereo Visual Information Processing at Tianjin University. His research interests include image processing, artificial intelligence and information security. In these areas, he has published more than 100 technical articles in refereed journals and proceedings. He is on the editorial board of IEEE Access, Sensors, and Multimedia Tools and Applications, and has edited a number of special issues in journals by IEEE and Springer.
Francesco Marinello is an Associate Professor at the University of Padova (Department of Land, Environment, Agriculture and Forestry, Padova, Italy) and adjunct professor at the University of Georgia (Department of Crop and Soil Sciences, Athens, USA). He holds an MSc from the University of Padova in Mechanical Engineering and in 2006, achieved a PhD in Industrial Production Engineering from the University of Padova, in joint supervision with the Technical University of Denmark. He has more than 10 years’ experience in measurement and sensing technologies applied for the monitoring and enhancement of agricultural operations. He is author of four patents and more than 140 papers indexed by Scopus, published in the field of proximal and remote sensing and in precision agriculture. His teaching activity includes courses on Applied Statistics, Agricultural Engineering, Precision Farming, and Unmanned Aerial Vehicles for Agriculture. He is participating as proposer or as scientific partner for several projects funded in the framework of the European rural development program and of the European Regional Development Fund, focused on vineyard sustainability, greenhouses sensing, and agricultural machinery improvement. He is also participating in two other H2020 funded projects.