STTR Phase I: A Novel Approach to Manage Nitrogen Fertilizer for Potato Production using Remote Sensing

这一小型企业技术转让研究项目的更广泛的影响/商业影响是减少农业生产对环境的影响，同时优化生产者的净收入。过量使用氮肥通过硝酸盐氮淋滤造成地下水污染，并给农村市政当局和私人井主带来巨大的经济负担，他们被要求安装和支付饮用水处理费用。据估计，全球能源消耗的1%归因于合成氮肥的生产。生产商在利润微薄的情况下运营，面临着最大化作物产量以保持盈利和维持业务的压力。拟议的技术旨在优化氮肥施用量，最大限度地减少环境损失的敏感性，同时考虑构成最大生产挑战的年复一年的天气变化。这项技术不仅确定了实现最大利润的最佳氮肥用量，而且还提供了氮素管理的透明度，并可以作为一种手段来展示对激励或监管计划的遵守。这项STTR第一阶段项目提议改进和测试一种新的算法，用于在生长季使用遥感进行实时氮肥推荐。对这项技术的需要根源于这样一个问题，即生产者对当前的季节氮素管理方法不满意，因为缺乏准确性和较低的时间和空间分辨率。该项目的研究目标是：(I)利用多光谱信息预测作物氮素浓度，(Ii)将该算法与传统方法进行比较，(Iii)校准和验证用于预测地上生物量的作物生长模型，(Iv)开发辐射利用效率的预测算法，以及(V)优化算法并开发适合生产者使用的软件应用程序。该算法需要考虑气候条件、作物品种和氮素管理措施引起的作物生长动态的年度变异性。将进行实地试验，以收集评估这些目标所需的数据。预计这项技术将以合理的准确性执行，并具有与现有N管理方法类似或更好的性能，由于其能够以可扩展的方式考虑空间和时间变化，因此它比当前的做法有了巨大的改进。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial impact of this Small Business Technology Transfer Research (STTR) project is to reduce the environmental impact of agricultural production while optimizing net income to producers. Over-application of nitrogen fertilizer contributes to groundwater contamination via nitrate-nitrogen leaching, and puts substantial financial burden on rural municipalities and private well owners who are required to install and pay for treatment of their drinking water. An estimated 1% of global energy consumption is attributed to the production of synthetic nitrogen fertilizer. Producers operate under tight margins, and face pressure to maximize crop yields to remain profitable and sustain their business. The proposed technology aims to optimize nitrogen application and minimize the susceptibility of loss to the environment, while accounting for the year to year weather variability that poses the largest production challenge. The technology not only determines the optimum nitrogen rate for achieving maximum profit, but it also provides transparency in nitrogen management and can serve as a means for demonstrating compliance with incentive or regulatory programs.This STTR Phase I project proposes to refine and test a novel algorithm for making real-time nitrogen fertilizer recommendations during the growing season using remote sensing. The need for this technology is rooted in the issue that producers are not satisfied with current methods for in-season nitrogen management because of lack of accuracy and poor temporal and spatial resolution. The research objectives of this project are to: (i) predict crop nitrogen concentration using multispectral information, (ii) compare the algorithm to conventional methods, (iii) calibrate and validate a crop growth model for prediction of above-ground biomass, (iv) develop predictive algorithms for radiation use efficiency, and (v) optimize the algorithm and develop a software application suitable for use by producers. The algorithm needs to account for yearly variability in crop growth dynamics caused by climatic conditions, crop variety, and nitrogen management practices. A field experiment will be conducted to collect data necessary to evaluate these objectives. It is anticipated that this technology will perform with reasonable accuracy and have similar or superior performance to existing N management methods, making it a vast improvement over current practices because of its ability to consider spatial and temporal variability in a scalable manner.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.