EAGER: Artificial Intelligence (AI) to accelerate plant species discovery

草本植物是压榨和干燥的植物标本的档案科学收藏品。这些收藏包含了数量巨大的未命名标本，其中一些可能是科学上的新标本。已知的维管束植物约有40万种，估计仍有8万种有待发现--其中许多可能已经保存在植物标本馆中。随着气候变化的紧迫威胁，我们需要新的工具来加快这些收藏中物种发现的步伐，以便在物种灭绝之前更好地保护它们。联合国的一份报告指出，超过100万种物种面临灭绝的危险，而在这一可怕的预测中，最近的一项估计表明，植物的消失速度比动物更快。全世界大约有3000种草本植物，它们是大量植物多样性数据的储存库：这些收藏不仅代表了大量的植物多样性，而且由于植物标本收藏包括数百年前的标本，它们提供了一段时间以来植物多样性的快照。标本馆标本不仅保持了它们的形态特征，而且还包括采集日期和地点。这些信息乘以数百万的植物收集，为大规模了解植物多样性和了解它如何随着时间的推移而变化提供了框架。人工智能(AI)是一个强大的工具，可以极大地加速草本植物的物种发现。该项目将为博士后研究人员提供培训和专业发展机会。该项目将开发一个使用人工智能快速管理和鉴定草药标本的工具：这个简单易用的在线工具iCurate将供世界各地的草药机构使用，通过输入它们自己的标本图像来自动识别和鉴定植物标本。这一工具将根据GBIF和iDigBio数据库中存在的各种数字化维管植物标本建立，大大减少鉴定标本的时间，并使草药机构能够管理它们缺乏专业知识的植物组。ICurate工具将通过一个循序渐进的过程进行优化和扩展，该过程使用提交给一系列在线比赛的众包人工智能模型。比赛将使用越来越多的物种和图像进行模型训练，最终包括GBIF和iDigBio中的所有公共维管植物标本图像。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。

Herbaria are archival scientific collections of pressed and dried plant specimens. These collections contain an overwhelming number of un-named specimens, some of which may be new to science. There are approximately 400,000 known vascular plant species with an estimated 80,000 still to be discovered—many of which are likely already in herbarium collections. With the urgent threats of climate change we need new tools to quicken the pace of species discovery within these collections to better conserve species before they go extinct. A United Nations report indicates that more than one million species are at risk of extinction, and amid this dire prediction a recent estimate suggests plants are disappearing more quickly than animals. There are approximately 3,000 herbaria worldwide and they are massive repositories of plant diversity data: these collections not only represent a vast amount of plant diversity, but since herbarium collections include specimens dating back hundreds of years, they provide snapshots of plant diversity through time. Herbarium specimens not only maintain their morphological features but also include collection dates and locations. This information, multiplied by millions of plant collections, provides the framework for understanding plant diversity on a massive scale and learning how it has changed over time. Artificial Intelligence (AI) is a powerful tool that can vastly accelerate species discovery in herbaria. This project will provide training and professional development opportunities for a post-doctoral researcher.This project will develop a tool for rapid curation and identification of plant specimens from herbaria collections using AI: this easy-to-use online tool, iCurate, will be readily used by herbaria world-wide to automatically identify and curate herbarium specimens by inputting their own specimen images. This tool will be built from the wide range of digitized vascular plant specimens present in the GBIF and iDigBio databases, significantly reducing the time to identify specimens and allowing herbaria to curate plant groups for which they lack expertise. The iCurate tool will be optimized and expanded through a stepwise process that uses crowd-sourced AI models submitted to a series of online competitions. The competitions will use an ever- increasing number of species and images for model training eventually including all public vascular plant specimen images in GBIF and iDigBio.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.