EUVIMEDFaigh amach EUVIMED
Crossref

Enhancing practicality of deep learning for crop disease identification under field conditions: insights from model evaluation and crop‐specific approaches

Qi Tian, Gang Zhao, Changqing Yan, Linjia Yao, Junjie Qu, Ling Yin, Hao Feng, Ning Yao, Qiang Yu iD

Pest Management Science · 2024-11 · 80 (11) · 5864-5875

DOI: 10.1002/ps.8317 ↗

At a glance

Journal article in Pest Management Science, published online on 2024-07-19. Written by Qi Tian and 8 co-authors. Institution: College of Natural Resources and Environment, Northwest A&F University, Xianyang, China. Major MEDLINE topics: Deep Learning, Solanum lycopersicum, Crops, Agricultural, Solanum tuberosum. Cited 10 times so far (Crossref); 58 references. Funded by: Guangxi Key Research and Development Program Project, Key Research and Development Program of Shaanxi, Key Research and Development Projects of Shaanxi Province.

AchoimreSubjectsSonraí leabharliostaCiteRelated studies

Abstract (original language)

BACKGROUND Crop diseases can lead to significant yield losses and food shortages if not promptly identified and managed by farmers. With the advancements in convolutional neural networks (CNN) and the widespread availability of smartphones, automated and accurate identification of crop diseases has become feasible. However, although previous studies have achieved high accuracy (>95%) under laboratory conditions (Lab) using mixed data sets of multiple crops, these models often falter when deployed under field conditions (Field). In this study, we aimed to evaluate disease identification accuracy under Lab, Field, and Mixed (Lab and Field) conditions using an assembled data set encompassing 14 diseases of apple ( Malus × domestica Borkh.), potato ( Solanum tuberosum L.), and tomato ( Solanum lycopersicum L.). In addition, we investigated the impact of model architectures, parameter sizes, and crop‐specific models (CSMs) on accuracy, using DenseNets, ResNets, MobileNetV3, EfficientNet, and VGG Nets. RESULTS Our results revealed a decrease in accuracy across all models from Lab (98.22%) to Mixed (91.76%) to Field (71.55%) conditions. Interestingly, disease classification accuracy showed minimal variation across model architectures and parameter sizes: Lab (97.61–98.76%), Mixed (90.76–92.31%), and Field (68.56–73.81%). Although CSMs were found to reduce inter‐crop disease misclassifications, they also led to a slight increase in intra‐crop misclassifications. CONCLUSION Our findings underscore the importance of enriching data representation and volumes over employing new model architectures. Furthermore, the need for more field‐specific images was highlighted. Ultimately, these insights contribute to the advancement of crop disease identification applications, facilitating their practical implementation in farmer's fields. © 2024 Society of Chemical Industry.

Subjects

MeSH terms (MEDLINE)

Deep LearningSolanum lycopersicumCrops, AgriculturalSolanum tuberosumPlant DiseasesMalus

Author keywords

agricultural applicationcrop diseasesdeep learningdisease identification

Authors and institutions

  • College of Natural Resources and Environment, Northwest A&F University, Xianyang, China.
  • State Key Laboratory of Soil Erosion and Dryland Farming on the Loess Plateau, Northwest A&F University, Xianyang, China.
  • BASF Digital Farming GmbH, Köln, Germany.
  • College of Intelligent Equipment, Shandong University of Science and Technology, Taian, China.
  • Guangxi Crop Genetic Improvement and Biotechnology Key Lab, Guangxi Academy of Agricultural Sciences, Nanning, China.
  • Institute of Water-Saving Agriculture in Arid Areas of China, Northwest A&F University, Xianyang, China.

ORCID profiles: Qiang Yu

Funding

  • Guangxi Key Research and Development Program Project
  • Key Research and Development Program of Shaanxi
  • Key Research and Development Projects of Shaanxi Province

Cite

APA

Tian, Q., Zhao, G., Yan, C., Yao, L., Qu, J., Yin, L., Feng, H., Yao, N., & Yu, Q. (2024). Enhancing practicality of deep learning for crop disease identification under field conditions: insights from model evaluation and crop‐specific approaches. Pest Management Science, 80(11), 5864-5875. https://doi.org/10.1002/ps.8317

Vancouver

Tian Q, Zhao G, Yan C, Yao L, Qu J, Yin L, et al. Enhancing practicality of deep learning for crop disease identification under field conditions: insights from model evaluation and crop‐specific approaches. Pest Management Science. 2024;80(11):5864-5875. doi:10.1002/ps.8317

BibTeX
@article{Tian2024,
  author = {Tian, Qi and Zhao, Gang and Yan, Changqing and Yao, Linjia and Qu, Junjie and Yin, Ling and Feng, Hao and Yao, Ning and Yu, Qiang},
  title = {Enhancing practicality of deep learning for crop disease identification under field conditions: insights from model evaluation and crop‐specific approaches},
  journal = {Pest Management Science},
  year = {2024},
  volume = {80},
  number = {11},
  pages = {5864--5875},
  doi = {10.1002/ps.8317}
}
Start for free →