I-Corps: Digital soil and yield mapping with an optimized sampling design to provide accurate, rapid, and inexpensive maps for farm managers

这个i-Corps项目的更广泛的影响/商业潜力是了解廉价和高质量的土壤肥力和产量地图的好处。土壤测试帮助农民确定种植所需的化肥数量。2017年，爱荷华州农业用地总量为3050万英亩，平均农场规模为351英亩。如果所有农场经理都根据常用的抽样设计进行抽样，他们将花费超过2.91亿美元。有了新的抽样设计，爱荷华州的农民可以节省近1.29亿美元(44%)。在参与ISU i-Corps站点计划期间，一个关键的客户发现发现，与现有地图相比，农民需要这些更准确、更便宜的地图，以便有效地为他们的作物施肥，而不是浪费。这个i-Corps项目将有助于确定农民是否对替代抽样设计感兴趣，这种抽样设计可以提供对田地变化的低成本分析。这项技术将有能力根据准确的土壤地图提供精确的管理区。这项技术将创建分辨率相对较高的土壤地图(9平方英尺)。米)，而现有地图(2.5英亩)。初步结果表明，克立格法可以生成9平方英尺的土壤图。然而，小样本量克立格图(R2=0.1)的精度明显低于所提出的克立格图(R2=0.53-0.61)。因此，营养建议将保持有效，同时与目前的方法(块和克里格法)相比成本降低。这一奖项反映了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 potential of this I-Corps project is to understand the benefits of inexpensive and high-quality soil fertility and yield maps. Soil testing helps farmers to determine the amount of fertilizer needed for plants. In 2017, total agricultural land in Iowa was 30.5 million acres, and the average farm size was 351 acres. If all farm managers took samples based on the commonly used sampling design, they would spend over $291 million. With the new sampling design, farmers in Iowa may save close to $129 million (44%). During participation in the ISU I-Corps Site program, a key customer discovery finding was that farmers need these more accurate and less expensive maps compared to existing ones in order to fertilize their crops effectively, but without waste. This I-Corps project will help to determine if farmers are interested in an alternative sampling design, which can provide low cost analysis of field variations. The technology will have the ability to supply precise management zones from accurate soil maps. The technology will create soil maps with relatively fine resolution (9 sq. meters) compared to the existing maps (2.5 acres). Preliminary results show that kriging can produce a soil map with 9 sq. meters; however, the accuracy of kriging maps (R2 = 0.1) with small sample sizes is remarkably smaller than the proposed maps (R2 = 0.53-0.61). Thus, the nutrient recommendations will remain effective while the costs decrease compared to the current methods (block and kriging).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.