An explainable deep machine vision framework for plant stress phenotyping.
An explainable deep machine vision framework for plant stress phenotyping.
复制标题
DOI：
10.1073/pnas.1716999115
复制
发表时间：
2018-05-01
影响因子：
11.1
通讯作者：
Sarkar S
中科院分区：
文献类型：
--
作者：
Ghosal S;Blystone D;Singh AK;Ganapathysubramanian B;Singh A;Sarkar S
基于视觉症状的植物胁迫鉴定主要仍然是由受过训练的病理学家进行的手工练习，主要是由于混淆症状的发生。然而，手动评级过程是繁琐的，是耗时的，并遭受内部和内部的变异性。我们的工作通过可解释的深度机器学习的概念来解决这些问题，以自动化植物胁迫识别，分类和量化的过程。我们构建了一个非常准确的模型，不仅可以提供训练有素的病理学家水平的性能，而且还可以解释哪些视觉症状用于进行预测。我们证明，我们的方法是适用于各种各样的生物和非生物应力，并可转移到其他成像条件和植物。目前在作物研究和生产中准确识别、分类和量化生物和非生物胁迫的方法主要是视觉的，需要专门的培训。然而，这种技术受到主观性的阻碍，主观性来自于个体间和个体内的认知差异。这意味着错误的决定和大量的资源浪费。在这里，我们展示了机器学习框架识别和分类大豆[Glycine max（L.）梅尔。]非常准确我们还提出了一种解释机制，使用前K高分辨率特征图，隔离用于进行预测的视觉症状。这种视觉症状的无监督识别提供了胁迫严重程度的定量测量，允许在单个框架中进行识别（叶胁迫的类型）、分类（低、中或高胁迫）和量化（胁迫严重程度），而无需专家进行详细的症状注释。通过从超过25，000张图像中学习，我们可靠地识别和分类了几种生物（细菌和真菌疾病）和非生物（化学损伤和营养缺乏）胁迫。学习模型对输入图像扰动具有鲁棒性，证明了高通量部署的可行性。我们还注意到，学习模型似乎对物种是不可知的，似乎展示了迁移学习的能力。一个可解释的模型，可以持续，快速，准确地识别和量化叶面压力的可用性将在科学研究，植物育种和作物生产具有重要意义。经训练的模型可以部署在移动的平台中（例如，无人驾驶飞行器和自动地面侦察机）进行快速、大规模侦察，或作为农民和研究人员实时检测压力的移动的应用。
Plant stress identification based on visual symptoms has predominately remained a manual exercise performed by trained pathologists, primarily due to the occurrence of confounding symptoms. However, the manual rating process is tedious, is time-consuming, and suffers from inter- and intrarater variabilities. Our work resolves such issues via the concept of explainable deep machine learning to automate the process of plant stress identification, classification, and quantification. We construct a very accurate model that can not only deliver trained pathologist-level performance but can also explain which visual symptoms are used to make predictions. We demonstrate that our method is applicable to a large variety of biotic and abiotic stresses and is transferable to other imaging conditions and plants. Current approaches for accurate identification, classification, and quantification of biotic and abiotic stresses in crop research and production are predominantly visual and require specialized training. However, such techniques are hindered by subjectivity resulting from inter- and intrarater cognitive variability. This translates to erroneous decisions and a significant waste of resources. Here, we demonstrate a machine learning framework’s ability to identify and classify a diverse set of foliar stresses in soybean [Glycine max (L.) Merr.] with remarkable accuracy. We also present an explanation mechanism, using the top-K high-resolution feature maps that isolate the visual symptoms used to make predictions. This unsupervised identification of visual symptoms provides a quantitative measure of stress severity, allowing for identification (type of foliar stress), classification (low, medium, or high stress), and quantification (stress severity) in a single framework without detailed symptom annotation by experts. We reliably identified and classified several biotic (bacterial and fungal diseases) and abiotic (chemical injury and nutrient deficiency) stresses by learning from over 25,000 images. The learned model is robust to input image perturbations, demonstrating viability for high-throughput deployment. We also noticed that the learned model appears to be agnostic to species, seemingly demonstrating an ability of transfer learning. The availability of an explainable model that can consistently, rapidly, and accurately identify and quantify foliar stresses would have significant implications in scientific research, plant breeding, and crop production. The trained model could be deployed in mobile platforms (e.g., unmanned air vehicles and automated ground scouts) for rapid, large-scale scouting or as a mobile application for real-time detection of stress by farmers and researchers.
登录
查看更多内容
影响因子：
5.6
作者：
Ubbens JR;Stavness I
通讯作者：
Stavness I
影响因子：
25
作者：
Yamins, Daniel L. K.;DiCarlo, James J.
通讯作者：
DiCarlo, James J.
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
4.6
作者：
Stoecklein D;Lore KG;Davies M;Sarkar S;Ganapathysubramanian B
通讯作者：
Ganapathysubramanian B
影响因子：
64.8
作者：
Mnih, Volodymyr;Kavukcuoglu, Koray;Hassabis, Demis
通讯作者：
Hassabis, Demis