An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction

The issue of pesticide and chemical residue in food has drawn increasing public attention, making effective control of plant pests and diseases a critical research focus in agriculture. Monitoring of pest populations is a key factor constraining the precision of pest management strategies. Low-cost...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruijun Jing, Deyan Peng, Jingtong Xu, Zhengjie Zhao, Xinyi Yang, Yihai Yu, Liu Yang, Ruiyan Ma, Zhiguo Zhao
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/11/1210
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129032570470400
author Ruijun Jing
Deyan Peng
Jingtong Xu
Zhengjie Zhao
Xinyi Yang
Yihai Yu
Liu Yang
Ruiyan Ma
Zhiguo Zhao
author_facet Ruijun Jing
Deyan Peng
Jingtong Xu
Zhengjie Zhao
Xinyi Yang
Yihai Yu
Liu Yang
Ruiyan Ma
Zhiguo Zhao
author_sort Ruijun Jing
collection DOAJ
description The issue of pesticide and chemical residue in food has drawn increasing public attention, making effective control of plant pests and diseases a critical research focus in agriculture. Monitoring of pest populations is a key factor constraining the precision of pest management strategies. Low-cost and high-efficiency monitoring devices are highly desirable. To address these challenges, we focus on <i>Cacopsylla chinensis</i> and design a portable, AI-based detection device, along with an integrated online monitoring and forecasting system. First, to enhance the model’s capability for detecting small targets, we developed a backbone network based on the RepVit block and its variants. Additionally, we introduced a Dynamic Position Encoder module to improve feature position encoding. To further enhance detection performance, we adopt a Context Guide Fusion Module, which enables context-driven information guidance and adaptive feature adjustment. Second, a framework facilitates the development of an online monitoring system centered on <i>Cacopsylla chinensis</i> detection. The system incorporates a hybrid neural network model to establish the relationship between multiple environmental parameters and the <i>Cacopsylla chinensis population</i>, enabling trend prediction. We conduct feasibility validation experiments by comparing detection results with a manual survey. The experimental results show that the detection model achieves an accuracy of 87.4% for both test samples and edge devices. Furthermore, the population dynamics model yields a mean absolute error of 1.94% for the test dataset. These performance indicators fully meet the requirements of practical agricultural applications.
format Article
id doaj-art-be218dad58f849a79b4c19ef57ce9fe2
institution OA Journals
issn 2077-0472
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-be218dad58f849a79b4c19ef57ce9fe22025-08-20T02:33:07ZengMDPI AGAgriculture2077-04722025-06-011511121010.3390/agriculture15111210An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics PredictionRuijun Jing0Deyan Peng1Jingtong Xu2Zhengjie Zhao3Xinyi Yang4Yihai Yu5Liu Yang6Ruiyan Ma7Zhiguo Zhao8School of Software, Shanxi Agricultural University, Taiyuan 030800, ChinaSchool of Software, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Plant Protection, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Plant Protection, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Resources and Environment, Shanxi Agricultural University, Taiyuan 030800, ChinaSchool of Computer Science, The University of Sydney, Sydney, NSW 2006, AustraliaCollege of Plant Protection, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Plant Protection, Shanxi Agricultural University, Taiyuan 030800, ChinaCollege of Plant Protection, Shanxi Agricultural University, Taiyuan 030800, ChinaThe issue of pesticide and chemical residue in food has drawn increasing public attention, making effective control of plant pests and diseases a critical research focus in agriculture. Monitoring of pest populations is a key factor constraining the precision of pest management strategies. Low-cost and high-efficiency monitoring devices are highly desirable. To address these challenges, we focus on <i>Cacopsylla chinensis</i> and design a portable, AI-based detection device, along with an integrated online monitoring and forecasting system. First, to enhance the model’s capability for detecting small targets, we developed a backbone network based on the RepVit block and its variants. Additionally, we introduced a Dynamic Position Encoder module to improve feature position encoding. To further enhance detection performance, we adopt a Context Guide Fusion Module, which enables context-driven information guidance and adaptive feature adjustment. Second, a framework facilitates the development of an online monitoring system centered on <i>Cacopsylla chinensis</i> detection. The system incorporates a hybrid neural network model to establish the relationship between multiple environmental parameters and the <i>Cacopsylla chinensis population</i>, enabling trend prediction. We conduct feasibility validation experiments by comparing detection results with a manual survey. The experimental results show that the detection model achieves an accuracy of 87.4% for both test samples and edge devices. Furthermore, the population dynamics model yields a mean absolute error of 1.94% for the test dataset. These performance indicators fully meet the requirements of practical agricultural applications.https://www.mdpi.com/2077-0472/15/11/1210Dynamic Position EncoderContext Guide Fusion Modulepopulation relationship model
spellingShingle Ruijun Jing
Deyan Peng
Jingtong Xu
Zhengjie Zhao
Xinyi Yang
Yihai Yu
Liu Yang
Ruiyan Ma
Zhiguo Zhao
An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction
Agriculture
Dynamic Position Encoder
Context Guide Fusion Module
population relationship model
title An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction
title_full An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction
title_fullStr An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction
title_full_unstemmed An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction
title_short An AI-Enabled Framework for <i>Cacopsylla chinensis</i> Monitoring and Population Dynamics Prediction
title_sort ai enabled framework for i cacopsylla chinensis i monitoring and population dynamics prediction
topic Dynamic Position Encoder
Context Guide Fusion Module
population relationship model
url https://www.mdpi.com/2077-0472/15/11/1210
work_keys_str_mv AT ruijunjing anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT deyanpeng anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT jingtongxu anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT zhengjiezhao anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT xinyiyang anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT yihaiyu anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT liuyang anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT ruiyanma anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT zhiguozhao anaienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT ruijunjing aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT deyanpeng aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT jingtongxu aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT zhengjiezhao aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT xinyiyang aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT yihaiyu aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT liuyang aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT ruiyanma aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction
AT zhiguozhao aienabledframeworkforicacopsyllachinensisimonitoringandpopulationdynamicsprediction