大模型
www.aibase.com ·
AI大模型下田“掌舵”：四川眉山永丰村300亩试点田水稻最高亩产863.6公斤
9月14日，四川眉山东坡区永丰村千亩高标准农田完成收割，其中300亩首次使用专用AI模型进行稻田管理。该系统通过无人机巡检采集数据，在水稻种植、水肥调控和病虫害预警等方面提供精准建议。专家组对四川农业大学牵头的项目进行标准化测产，三个核心品种表现良好：华浙优210亩产826.8公斤，胜两优222亩产863.6公斤，全优169亩产858.8公斤。四川农业大学水稻栽培专家马均表示，良种配良法加AI精准管理可释放增产潜力，为规模化增产提供可复制技术路径。
AI推荐理由 提供了四川眉山永丰村300亩AI试点稻田的具体测产数据（华浙优210为826.8公斤/亩、胜两优222为863.6公斤/亩、全优169为858.8公斤/亩），以及无人机巡检、水肥调控和病虫害预警等AI应用方式，属于AI在农业落地的可验证案例。但来源为AIbase聚合媒体，非官方或研究机构首发，正文未说明AI模型的具体名称、算法细节和对照田产量，无法判断AI贡献占比，且发布时间为2026年9月，时效性存疑。
62
正文
AI Big Model Takes the Helm in the Fields: 300 Acre Pilot Field in Yongfeng Village, Sichuan Meishan, Rice Yield Reaches Up to 863.6 Kilograms per Acre
AIbase基地
Published inAI News · 4 min read · Sep 15, 2026
6
On September 14, the thousand-mu high-standard farmland in Yongfeng Village, Tahe Town, Dongpo District, Meishan City, Sichuan Province, was harvested. Unlike previous years, 300 mu of this land used a specialized AI model for rice field management for the first time. The way of farming is shifting from "judging fields by experience" to "making decisions based on data."
The embankments of Yongfeng Village were crowded with agricultural technology experts and farmers who came to observe a field test: an expert group organized by the Sichuan Provincial Science and Technology Department evaluated the "Integrated Demonstration and Application of High-quality, High-yield, and Efficient Production Technologies for Rice-Vegetable (Medicinal) Crops in the Chengdu Plain" project led by Sichuan Agricultural University. The AI system collects data through drone inspections, providing precise recommendations in aspects such as rice planting, water and fertilizer regulation, and pest and disease early warning. Local large-scale grain farmer Zhao Youyong had a direct feeling: before, farming relied on experience for field inspections, but now using drones for inspections and the AI system also sends timely information about pests and diseases, allowing targeted handling. Farming has become more convenient.
The expert group's standardized yield test provided a solid answer: all three core varieties in the 300-mu AI pilot fields performed well — the high-yield and high-quality hybrid rice "Huazheyous 210" achieved an actual yield of 826.8 kilograms per mu, the super-high-yield indica-japonica hybrid rice "Shengliangyou 222" achieved an actual yield of 863.6 kilograms per mu, and the super-high-yield hybrid indica rice "Quanyou 169" achieved an actual yield of 858.8 kilograms per mu. Ma Jun, an expert in rice cultivation at Sichuan Agricultural University, stated that the actual yield data proved that combining quality seeds with appropriate methods and AI precision management can effectively release the potential for rice yield increase, providing a replicable technical path for large-scale yield improvement. He added that the more than 240 new varieties demonstrated good performance in terms of yield, plant shape, and rice quality in Yongfeng Village this year, and the application of intelligent precision sowing technology and AI technology has already shown initial results.
This article is from AIbase Daily
Scan to view
Welcome to the [AI Daily] column! This is your daily guide to exploring the world of artificial intelligence. Every day, we present you with hot topics in the AI field, focusing on developers, helping you understand technical trends, and learning about innovative AI product applications.
—— Created by the AIbase Daily Team
© Copyright AIbase Base 2024, Click to View Source -