I-Corps: Geospatial Analytics

这个I-Corps项目的更广泛的影响/商业潜力将跨越多个行业，这些行业可以从对地球表面变化的定期监测中受益。干旱、洪水、森林砍伐、城市化和粮食供应（种植面积和产量）波动等变化对企业和环境都有相当大的影响。例如，据估计，美国在2012年因干旱损失了大约230亿美元。该I-Corps项目将利用大量的卫星数据，为商品交易、农作物保险、精准农业、牧场管理等各个行业的客户提供有关这些变化的准确、及时和可操作的见解。我们在全球范围内跟踪这些变化的能力也将提高我们对气候和人类引起的变化对各种生态系统的影响的理解。这个I-Corps项目使用机器学习算法来分析大量的卫星图像数据集，以提供关于地球表面各种变化的近真实的时间和历史信息。这些算法是通过各种联邦研究赠款开发的，其中包括三个NSF赠款。使用这些算法创建的数据产品已被验证，以提高国家的最先进的几个地球科学应用，如森林火灾测绘，地表水动力学，棕榈油种植园测绘和作物测绘。分析技术更普遍地适用于具有类似底层数据特征的其他领域。商业用途的原型将与商品贸易商一起开发，他们将提供最有意义的用例的专家反馈。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值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 will be across multiple industries that can benefit from regular monitoring of changes on the Earth's surface. Changes such as droughts, floods, deforestation, urbanization, and grain supply (acreage and yields) fluctuations have considerable impact on businesses as well as the environment. For example, it is estimated that US lost approximately 23 billion dollars due to drought in 2012. This I-Corps project will make use of vast amounts of satellite data to provide accurate, timely and actionable insights about these changes to customers in various industries such as commodity trading, crop insurance, and precision agriculture, pasture management. Our ability to track these changes at a global scale will also improve our understanding of the impact of climate and human induced changes on various ecosystems. This I-Corps project uses machine learning algorithms that analyze vast amounts of satellite imagery datasets to provide near real time as well as historical information about various changes on the Earth's surface. These algorithms were developed through various federal research grants which includes three NSF grants. Data products created using these algorithms have been validated to improve the state-of-the-art in several earth science applications such as forest fire mapping, surface water dynamics, palm oil plantation mapping, and crop mapping. The analytics technology is more generally applicable to other domains with similar underlying data characteristics. The commercial-use prototype will be developed with commodity traders providing expert feedback on their most meaningful use-cases.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.