This study introduces a compositional autoencoder (CAE) framework designed to disentangle the complex interplay between genotypic and environmental factors in high-dimensional phenotype data to improve trait prediction in plant breeding and genetics programs. Traditional predictive methods, which use compact representations of high-dimensional data through handcrafted features or latent features like PCA or more recently autoencoders, do not separate genotype-specific and environment-specific factors. We hypothesize that disentangling these features into genotype-specific and environment-specific components can enhance predictive models. To test this, we developed a compositional autoencoder (CAE) that decomposes high-dimensional data into distinct genotype-specific and environment-specific latent features. Our CAE framework employs a hierarchical architecture within an autoencoder to effectively separate these entangled latent features. Applied to a maize diversity panel dataset, the CAE demonstrates superior modeling of environmental influences and 5-10 times improved predictive performance for key traits like Days to Pollen and Yield, compared to the traditional methods, including standard autoencoders, PCA with regression, and Partial Least Squares Regression (PLSR). By disentangling latent features, the CAE provides powerful tool for precision breeding and genetic research. This work significantly enhances trait prediction models, advancing agricultural and biological sciences.

Effective pollination is a key challenge for indoor farming, since bees struggle to navigate without the sun. While a variety of robotic system solutions have been proposed, it remains difficult to autonomously check that a flower has been sufficiently pollinated to produce high-quality fruit, which is especially critical for self-pollinating crops such as strawberries. To this end, this work proposes a novel robotic system for indoor farming. The proposed hardware combines a 7-degree-of-freedom (DOF) manipulator arm with a custom end-effector, comprised of an endoscope camera, a 2-DOF microscope subsystem, and a custom vibrating pollination tool; this is paired with algorithms to detect and estimate the pose of strawberry flowers, navigate to each flower, pollinate using the tool, and inspect with the microscope. The key novelty is vibrating the flower from below while simultaneously inspecting with a microscope from above. Each subsystem is validated via extensive experiments.

Distribution shifts are characterized by differences between the training and test data distributions. They can significantly reduce the accuracy of machine learning models deployed in real-world scenarios. This paper explores the distribution shift problem when classifying pollen grains from microscopic images collected in the wild with a low-cost camera sensor. We leverage the domain knowledge that geometric features are highly important for accurate pollen identification and introduce two novel geometric image augmentation techniques to significantly narrow the accuracy gap between the model performance on the train and test datasets. In particular, we show that Tenengrad and ImageToSketch filters are highly effective to balance the shape and texture information while leaving out unimportant details that may confuse the model. Extensive evaluations on various model architectures demonstrate a consistent improvement of the model generalization to field data of up to 14% achieved by the geometric augmentation techniques when compared to a wide range of standard image augmentations. The approach is validated through an ablation study using pollen hydration tests to recover the shape of dry pollen grains. The proposed geometric augmentations also receive the highest scores according to the affinity and diversity measures from the literature.

A sugar mixture similar to hard candy studded with tiny metal discs or rings has been used to deposit patterns onto microscopic objects. This method of creating texture on small objects could be useful for biomedical robots or flexible electronics. To give microscopic robots or small electronic circuits more functionality, researchers often embellish their surfaces with patterns of even tinier objects, such as magnets. They often make these components on a flat, clean surface and then stamp them onto the bigger object. But accurately applying them in this way becomes difficult when the receiving objects are not smooth, says Gary Zabow at the National Institute of Standards and Technology in Colorado.

Exposure to bio-aerosols such as mold spores and pollen can lead to adverse health effects. There is a need for a portable and cost-effective device for long-term monitoring and quantification of various bio-aerosols. To address this need, we present a mobile and cost-effective label-free bio-aerosol sensor that takes holographic images of flowing particulate matter concentrated by a virtual impactor, which selectively slows down and guides particles larger than ~6 microns to fly through an imaging window. The flowing particles are illuminated by a pulsed laser diode, casting their inline holograms on a CMOS image sensor in a lens-free mobile imaging device. The illumination contains three short pulses with a negligible shift of the flowing particle within one pulse, and triplicate holograms of the same particle are recorded at a single frame before it exits the imaging field-of-view, revealing different perspectives of each particle. The particles within the virtual impactor are localized through a differential detection scheme, and a deep neural network classifies the aerosol type in a label-free manner, based on the acquired holographic images. We demonstrated the success of this mobile bio-aerosol detector with a virtual impactor using different types of pollen (i.e., bermuda, elm, oak, pine, sycamore, and wheat) and achieved a blind classification accuracy of 92.91%. This mobile and cost-effective device weighs ~700 g and can be used for label-free sensing and quantification of various bio-aerosols over extended periods since it is based on a cartridge-free virtual impactor that does not capture or immobilize particulate matter.

Bee pollen is a ball or pellet of field-gathered flower pollen packed by worker honeybees, consisting of simple sugars, protein, minerals and vitamins, fatty acids, and other components in small quantities. This is the primary food source for the hive. This article aims to use deep learning to differentiate between images of honey bees carrying pollen and those that aren't. These deep learning models can prove useful in bee farming for analysis/inference generation. This image dataset has been created from videos captured at the entrance of a bee colony in June 2017 at the Bee facility of the Gurabo Agricultural Experimental Station of the University of Puerto Rico.

Soap bubbles that deliver pollen to flowers could offer an alternative way of fertilising plants as bee populations decline, while being more delicate than other methods. Eijiro Miyako at the Japan Advanced Institute of Science and Technology and his colleagues developed the technique and successfully used it to pollinate a pear orchard. "I jumped for joy," he says. Miyako and his team mixed pear pollen grains with a soap solution containing nutrients and loaded the mixture into a bubble gun. They then used the gun to release bubbles into a pear orchard, with about two to 10 bubbles hitting each flower, and later measured their success rate by counting the flowers that bore fruit.

What's happening in Japan is written all over our faces -- our blank, expressionless, masked faces. Never before, it seems safe to say, have so many people gone about masked. Thus we confront the microbes that assault us. "As self-protection, your mask is practically useless," says Shukan Gendai magazine this month. Commercial face masks, medical authorities say, can block particles measuring 3 to 5 micrometers.

The cosmetics market remains as lucrative as ever, if the latest estimates are anything to go by. It's anticipated to be worth $806 billion by 2023, driven in part by spending on AI in retail, which alone is expected to top $7.3 billion by 2022 thanks to blossoming tech like computer vision. L'Oréal has its finger on the pulse. Following on the heels of My Skin Track pH, a strip co-developed with skincare brand La Roche-Posay that can measure skin acid on the fly, it today debuted the Perso, an AI-powered system that's designed to deliver personalized skincare and cosmetic formulas. The Perso, which measures 6.5 inches tall and weighs just over a pound, features an automatic mechanism that dispenses portioned doses of product at its top.

We present the first unsupervised deep learning method for pollen analysis using bright-field microscopy. Using a modest dataset of 650 images of pollen grains collected from honey, we achieve family level identification of pollen. We embed images of pollen grains into a low-dimensional latent space and compare Euclidean and Riemannian metrics on these spaces for clustering. We propose this system for automated analysis of pollen and other microscopic biological structures which have only small or unlabelled datasets available.