About this Research Topic

Manuscript Submission Deadline 01 September 2022

There are many deep learning approaches that have successfully supported plant pests and disease detection. In crop pest identification, deep learning methods can achieve good feature representation from large datasets based on various linear and nonlinear transformations and then discover the relationship in ...

There are many deep learning approaches that have successfully supported plant pests and disease detection. In crop pest identification, deep learning methods can achieve good feature representation from large datasets based on various linear and nonlinear transformations and then discover the relationship in complex data based on specific supervised and unsupervised learning.

However, with the in-depth study of crop diseases and pest infestations, deep learning technology also has some limitations. The first limitation is that the current agricultural infrastructure is not yet sufficient to fully support the application of deep learning in the agricultural field. This requires a large number of computational resources and has a high time complexity caused by too many network parameters. The second reason is the lack of a large amount of labeled data and the subjectivity of manually labeled data in the agricultural domain. Moreover, it is difficult to obtain large-scale images of plant diseases and pests in real fields, and it is impossible to acquire images of multiple diseases and pests in one area. At the same time, the detection of plant diseases and pests is limited by the complex background, illumination conditions, overlapping and occlusion of leaves, and similar color of foreground and background. In addition, there are other problems in applying deep learning methods for plant pest detection, such as gradient disappearance and gradient explosion in the training process of the network, and overfitting of the network model. The most important problem is that most current deep learning networks are still considered as black-box models. Misidentification by a network, for crop pest and disease detection, can lead to disastrous results. For example, misidentification of crop damage severity can lead to the overuse of pesticides, which in turn can lead to soil contamination, environmental damage, and other vicious cycles. Therefore, we propose this research topic for the development of novel AI-based methods to solve plant disease and insect pest identification problems.

We welcome submissions of original research articles, reviews, and methods, including (but not limited to) research on the following sub-themes:
- Plant disease and insect pest databases;
- Software for plant pest detection;
- AI-based methods for trait display;
- 2D and 3D sensors for pest detection;
- Deep learning methods for plant disease and insect pest identification;
- High-throughput platforms for crop pests;
- Bigdata analysis for crop yield estimation and agricultural insurance.

Keywords: Deep Learning, BigData Analysis, Crop Diseases and Insect Pests, feature representation, Plant Sensor


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

Topic Editors

Loading..

Topic Coordinators

Loading..

Recent Articles

Loading..

articles

Sort by:

Loading..

authors

Loading..

views

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..

Share on

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.