AgriMAPO: A multimodal automatic prompt optimization approach for crop disease classification using large language models

计算机科学 人工智能 机器学习 鉴定(生物学) 自然语言处理 数据挖掘 语言模型 模式识别(心理学) 特征(语言学) 数据建模
作者
Luyu Shuai,Linchao Zhu,Yi Yang,Tao Lin
出处
期刊:Artificial intelligence in agriculture [Elsevier BV]
卷期号:16 (2): 911-925 被引量:5
标识
DOI:10.1016/j.aiia.2026.04.002
摘要

Accurate identification of crop diseases is a core challenge in promoting precision agriculture and reducing yield losses. Current deep learning-based recognition methods heavily rely on large-scale annotated data, which limits their scalability across diverse crop scenarios. While large language models (LLMs) show potential for zero-shot classification, their performance on fine-grained disease recognition tasks is often inadequate due to a lack of domain-specific expertise and cross-modal alignment capabilities. To address these issues, this paper proposes a multimodal, automatic prompt-optimization-based method for crop disease classification (AgriMAPO) that enhances the discriminative power of LLMs through automated prompt engineering, enabling high-accuracy, few-shot disease recognition. The AgriMAPO framework integrates three core components: a deep learning-based, dual-stage screening strategy to construct a high-quality few-shot image-label example library; an Automatic Prompt Optimization (APO) agent that uses an evolutionary algorithm to generate a library of fine-grained disease symptom descriptions; and a GPT-4o-based classification agent guided by chain-of-thought (CoT) reasoning. Experimental results on an eight-class soybean disease dataset demonstrate that the proposed method achieves an overall classification accuracy of 90.3%, significantly outperforming the native GPT-4o model, which scored 40.3%. Further analysis showed that the optimized multimodal prompts exhibit excellent generalization, transferring effectively across different datasets and models. This study provides a training-free, highly generalizable solution for few-shot, fine-grained disease recognition in agriculture, significantly reducing reliance on annotated data and expert knowledge. • AgriMAPO: a multimodal auto prompt optimizer for training-free crop disease classification. • Dual-stage strategy screens high-quality few-shot examples with diversity. • APO agent auto-generates fine-grained symptom descriptions via evolution. • Achieves 90.3% overall accuracy on soybean diseases, 50% higher than GPT-4o. • Optimized prompts show strong cross-dataset and cross-model transfer.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Az驳回了yyds的应助
刚刚
科研通AI6.3的应助被FionaZhang采纳,获得10
刚刚
1秒前
1秒前
yyy完成签到 ,获得积分10
1秒前
YAM完成签到 ,获得积分10
2秒前
luoshiwen发布了新的文献求助10
2秒前
Wali完成签到,获得积分10
2秒前
埃及舞发布了新的文献求助10
2秒前
JamesPei的应助被无溪现龙采纳,获得10
2秒前
乌贼爱吃发布了新的文献求助10
3秒前
3秒前
微信研友发布了新的文献求助10
3秒前
xhj666完成签到,获得积分10
3秒前
4秒前
JJyue发布了新的文献求助50
4秒前
wy完成签到,获得积分10
5秒前
arizaki7发布了新的文献求助10
6秒前
王一硕发布了新的文献求助10
6秒前
留蓝发布了新的文献求助10
7秒前
Owen的应助被夏梓硕采纳,获得10
7秒前
周林发布了新的文献求助10
8秒前
8秒前
wl完成签到,获得积分10
9秒前
humble发布了新的文献求助10
9秒前
羊羊羊完成签到,获得积分20
9秒前
白术完成签到,获得积分10
9秒前
11秒前
11秒前
jjj完成签到,获得积分10
12秒前
wanci的应助被Rauf采纳,获得10
12秒前
CHEN完成签到,获得积分10
13秒前
GIN的应助被胡萝卜卜采纳,获得10
13秒前
科研通AI6.4的应助被WYF1996采纳,获得10
14秒前
科研通AI65的应助被科研通管家采纳,获得10
14秒前
CipherSage的应助被科研通管家采纳,获得10
14秒前
大模型的应助被科研通管家采纳,获得10
14秒前
xlxl完成签到,获得积分10
14秒前
无极微光的应助被科研通管家采纳,获得20
14秒前
AAAA完成签到,获得积分10
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8193348
求助须知:如何正确求助?哪些是违规求助? 9579548
关于积分的说明 21866040
捐赠科研通 7792906
什么是DOI,文献DOI怎么找? 3437242
关于科研通互助平台的介绍 2560702
邀请新用户注册赠送积分活动 2484066