报告详情
Agri Orchard: A Multi-Agent Intelligent System for Precision Fruit Crop Selection and Orchard Monitoring
编号：186
访问权限：仅限参会人
更新：2026-11-10 17:05:19 浏览：9次
Online
报告开始：2026年11月20日 13:45（Asia/Kolkata）
报告时间：15min
所在会场：[S4] Artificial Intelligence and Intelligent Computing [S4-3] Artificial Intelligence and Intelligent Computing
暂无文件
摘要
Declining crop yields in Indian fruit orchards are frequently attributed to reliance on traditional cultivation practices that disregard site-specific soil chemistry, microclimate conditions, and prevailing market dynamics. This proposed work presents the Agri Orchard, an end-to-end intelligent platform for precision fruit crop selection and continuous orchard monitoring. The system integrates a low-cost IoT sensing layer — streaming soil, microclimate, and canopy telemetry over MQTT into a time-series database — with a five-agent decision pipeline that jointly evaluates location–climate suitability, soil–water compatibility, projected yield and revenue, disease and pest risk, and seasonality to produce ranked, human-readable crop recommendations. A supervised classification pipeline comprising Random Forest, XGBoost, and Histogram Gradient Boosting (HistGB) classifiers, trained on a 100,000-record agro-telemetry dataset, identifies the most probable optimal crop, while an ARIMA-based forecaster predicts near-term sensor trends for irrigation and frost-risk management. The best-performing classifier, HistGB, achieves 91.47% test accuracy and a macro-F1 score of 0.9182. The deployed recommendation API responds with a p95 end-to-end latency of 585.6 ms. Results indicate that combining statistical forecasting, multi-agent expert reasoning, and IoT telemetry produces practical, economically sound agronomic recommendations. Future work includes a GIS-based satellite mapping interface enabling growers to delineate plot boundaries and receive section-specific alerts and recommendations.
关键词
Explainable AI.,machine learning,, crop recommendation,precision agriculture,multi-agent systems
报告人
JABIL JOSHUA.S
Student Karunya Institute of Technology and Sciences稿件作者
全部评论
重要日期
-
会议日期
11月20日
2026
至11月22日
2026
-
10月31日 2026
初稿截稿日期
-
11月07日 2026
提前注册日期
-
11月22日 2026
注册截止日期
主办单位
United Societies of Science
承办单位
Pondicherry University
协办单位
IEEE Section
IEEE Madras Section
IEEE Madras Section
联系方式
- ICon INDIA 2026
- ic******@usssociety.org
发表评论