Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

Abstract

Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high performance end-to-end machine learning pipelines with minimal effort from the user. AutoML with neural architecture search which searches for the best neural network architectures in deep learning has delivered state-of-the-art performance in computer vision tasks such as image classification and object detection. Using wheat lodging assessment with UAV imagery as an example, we compared the performance of an open-source AutoML framework, AutoKeras in image classification and regression tasks to transfer learning using modern convolutional neural network (CNN) architectures pretrained on the ImageNet dataset. For image classification, transfer learning with Xception and DenseNet-201 achieved best classification accuracy of 93.2%, whereas Autokeras had 92.4% accuracy. For image regression, transfer learning with DenseNet-201 had the best performance (R2=0.8303, RMSE=9.55, MAE=7.03, MAPE=12.54%), followed closely by AutoKeras (R2=0.8273, RMSE=10.65, MAE=8.24, MAPE=13.87%). Interestingly, in both tasks, AutoKeras generated compact CNN models with up to 40-fold faster inference times compared to the pretrained CNNs. The merits and drawbacks of AutoML compared to transfer learning for image-based plant phenotyping are discussed.

Automated Machine Learning for Satellite Data: Integrating Remote Sensing Pre-trained Models into AutoML Systems

“…Current remote sensing research does not fully exploit hyperparameter tuning to further improve these models; researchers have mainly considered optimizing a subset of hyperparameters using a parameter sweep approach [6,18]. The authors of [13] have considered AutoML for a specific application of high-throughput image-based plant phenotyping. They use Auto-Keras and compare its results with human-designed ImageNet pre-trained CNN architectures, finding the best performance while using the pre-trained network.…”

Artificial Intelligence Meets Marine Ecotoxicology: Applying Deep Learning to Bio-Optical Data from Marine Diatoms Exposed to Legacy and Emerging Contaminants

“…These optical biomarkers have been used from field to experimental trials using a wide array of organisms from microalgae to higher plants [9,10,14]. Conventional data analysis pipelines typically involve computer vision tasks (e.g., wheat head counting using object detection), which are addressed through the development of signal processing or machine learning (ML) algorithms [19]. When exposed to anthropogenic contaminants the typical chlorophyll a induction curves suffer alterations, not only on their intensity values but also on their shape [9].…”

Testing the Suitability of Automated Machine Learning for Weeds Identification

“…AutoML model achieved a higher overall classification accuracy of 88.15% using Sentinel-2 and 74% using Landsat 8, results that confirmed the significance of the AutoML in mapping Parthenium weed infestations using satellite imagery. In [19], authors used wheat lodging assessment with UAV images for high-throughput plant phenotyping. They compared AutoKeras in image classification and regression tasks to transfer learning techniques.…”