N2Vision+: A robot-enabled, data-driven machine vision tool for nitrogen diagnosis of arable soils

N2Vision：一种由机器人驱动、数据驱动的机器视觉工具，用于耕地土壤的氮诊断

• 批准号: 10091423
• 金额: $ 30.18万
• 依托单位: AUTODISCOVERY LTD.
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2024
• 资助国家: 英国
• 起止时间: 2024 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=10091423
• 关键词: N2Vision+; robot; enabled; data; driven

Increasing crop productivity while minimising resource use and environmental impact is a global challenge for food production. Among all farmer-controlled input factors, Nitrogen (N) has the second-largest impact on crop growth after water, and arable soils are a predominant source of N in many cropping systems. Optimal N fertilisation can increase crop production and enhance soil fertility. On the other hand, high N inputs are costly for farmers and result in reductions in plant biodiversity, pollution of natural ecosystems and increases in emissions of the potent greenhouse gas, nitrous oxide. UK farmers currently spend £1.345 billion on fertilisers, often applying excessive N due to the lack of precise information about soil N levels.Driven by the needs of the growers, our previous feasibility project (N2Vision), addressed this challenge by developing a non-destructive robot-enabled AI vision system for automated N diagnosis in plants and soil (TRL 5). This system automatically collected data using a mobile robot with image cameras and intelligently diagnosed crop and soil N levels using AI algorithms. Initial assessments showed potential cost reductions of 27%, increased farm profitability by 17%, and emission savings of 65% compared to current practices. To make this technology practical for farmers and further advance its adoption, we aim to raise its TRL and move closer to commercialization.Building upon our N2Vision innovations, our follow-on project, N2Vision+, aims to develop a commercial product for automated soil nitrogen monitoring at a higher TRL. We will enhance our existing innovations by adding optional modular sensors like 3D mapping (360-degree) and soil probes, enabling cost-effective data collection and scalable N monitoring. Additionally, we will conduct field trials to simulate robotic foliar nitrogen application, potentially reducing N usage and costs.This precision agriculture solution will revolutionise food production by optimising N use, increasing farm profitability, and contributing to net-zero emissions. It offers early detection of crop and soil N levels, precise information on N use efficiency, and soil quality assessment, positioning UK precision agriculture technologies at the forefront of new industries and driving economic growth in the UK.

提高作物产量，同时最大限度地减少资源使用和环境影响，是粮食生产面临的全球性挑战。在所有农民控制的输入因素中，氮（N）对作物生长的影响仅次于水，而耕地土壤是许多种植系统中氮的主要来源。最佳的氮肥施用可以增加作物产量和提高土壤肥力。另一方面，高氮投入对农民来说是昂贵的，并导致植物生物多样性的减少，自然生态系统的污染和强效温室气体一氧化二氮排放的增加。英国农民目前在化肥上花费了13.45亿英镑，由于缺乏土壤氮素水平的精确信息，他们经常过量施用氮肥。在种植者需求的驱动下，我们之前的可行性项目（N2Vision）通过开发一种非破坏性的机器人人工智能视觉系统来解决这一挑战，该系统用于自动诊断植物和土壤中的氮素（TRL 5）。该系统使用带有图像摄像头的移动的机器人自动收集数据，并使用AI算法智能诊断作物和土壤氮水平。初步评估显示，与目前的做法相比，潜在的成本降低了27%，农场盈利能力提高了17%，排放量减少了65%。为了使这项技术对农民实用并进一步推动其采用，我们的目标是提高其TRL并向商业化迈进。在我们的N2Vision创新的基础上，我们的后续项目N2Vision+旨在开发一种商业化产品，用于以更高的TRL自动监测土壤氮。我们将通过增加可选的模块化传感器（如3D绘图（360度）和土壤探头）来增强我们现有的创新，从而实现具有成本效益的数据收集和可扩展的N监测。此外，我们还将进行田间试验，模拟机器人叶面施氮，从而有可能降低氮肥使用量和成本。这种精准农业解决方案将通过优化氮肥使用、提高农场盈利能力和实现净零排放来彻底改变粮食生产。它提供作物和土壤氮素水平的早期检测，氮素利用效率的精确信息和土壤质量评估，使英国精准农业技术处于新产业的前沿，并推动英国的经济增长。