(Press-News.org)
Cultivating seed mixtures for local pastures is an age-old method to produce cost-effective and balanced animal feed, enhancing agricultural autonomy and environmental friendliness in line with evolving European regulations and organic consumer demands. Despite its benefits, farmers face adoption challenges due to the asynchronous ripening of cereals and legumes and the difficulty in assessing the nutritional value of heterogeneous seeds. Current practices rely on informal, empirical methods, and a proposed solution is to develop a mobile app or online service, similar to Pl@ntNet, for automated nutritional evaluation of seed mixtures, encouraging farmer participation and database enrichment. However, this requires overcoming agricultural and computer vision challenges. Overcoming these, along with optimizing deep neural network models and loss functions, remains a critical research focus to make this sustainable agricultural practice more accessible and efficient.
In November 2023, Plant Phenomics published a research article entitled by “Estimating Compositions and Nutritional Values of Seed Mixes Based on Vision Transformers ”.
This research presents a novel approach using Artificial Intelligence to estimate the nutritional value of harvested seed mixes, aiming to assist farmers in managing crop yields and promoting sustainable cultivation. A dataset of 4,749 images covering 11 seed varieties was created to train two deep learning models: Convolutional Neural Networks (CNN) and Vision Transformers (ViT). The results significantly favored the ViT-based BeiT model, which outperformed the CNN in all metrics, including a Mean Absolute Error (MAE) of only 0.0383 and a coefficient of determination (R2) of 0.91. Data augmentation techniques and model size variations further refined performance. Although larger models offering some improvements, the base version of BeiT proved most efficient in terms of balance between performance and computational resources. The study also explored loss functions, finding that the classical KLDiv loss outperformed the Sparsemax variant. Detailed analysis by seed type revealed distinct performance across categories, with models generally excelling in recognizing barley, lupine, rye, spelt, and wheat, while facing challenges with vetch and oats. Aggregating predictions from multiple images of the same mix significantly improved robustness and accuracy. The research culminated in the development of "ESTI'METEIL" (https://c4c.inria.fr/carpeso/), an open-access web component that allows users to estimate seed composition and nutritional value from images. This tool demonstrates the practical application and potential of the research for real-world farming scenarios.
In conclusion, the study effectively applied advanced deep learning techniques, particularly the self-supervised BeiT model, to the agricultural challenge of estimating the composition of seed mixtures and their nutritional values. The research not only showed promising results with a high R2 score but also provided a practical tool for farmers, marking a significant step towards more sustainable and informed agricultural practices. Future work will aim to improve data balance and explore synthetic image generation to further improve model performance and practical applicability.
###
References
Authors
Shamprikta Mehreen1*, Hervé Goëau2, Pierre Bonnet2, Sophie Chau3, Julien Champ1, and Alexis Joly1
Affiliations
1Inria, LIRMM, University Montpellier, CNRS, Montpellier, France.
2CIRAD, UMR AMAP, Montpellier, Occitanie, France.
3Chambre d’Agriculture - Haute Vienne, Limoges, Nouvelle-Aquitaine, France.
END
The 3-dimensional point cloud technology revolutionizes non-invasive measurement of plant phenotypic parameters, offering vital data for agriculture and research. Current research focuses on overcoming the limitations of 2.5D imaging and occlusions. Methods such as structure from motion, multi-view stereo, and advanced active 3D reconstruction techniques are being explored for this purpose. However, issues persist with incomplete data acquisition and the inaccuracy of phenotypic parameter extraction due ...
To improve grape yield predictions, automated berry counting has emerged as a crucial yet challenging task due to the dense distribution and occlusion of berries. While grape cultivation is a significant global economic activity, traditional manual counting methods are inaccurate and inefficient. Recent research has shifted towards deep learning and computer vision, employing detection and density estimation techniques for more precise counts. However, these methods grapple with the variability of farmland and high occlusion rates, leading to significant counting errors. Additionally, creating high-performance ...
Advancements in whole-genome sequencing have revolutionized plant species characterization, providing a wealth of genotypic data for analysis. The combination of genomic selection and neural networks, especially deep learning and autoencoders, has emerged as a promising method for predicting complex traits from this data. Despite the success in applications like plant phenotyping, challenges remain in accurately translating visual information from images into measurable data for genomic studies.
In November 2023, Plant ...
Erin Overstreet has been selected as the new executive director of the USC Stevens Center for Innovation where she will oversee the university’s commercialization of USC-driven intellectual property.
Overstreet’s expertise and experience embody technology transfer and innovation across the academic, educational, and venture capital sectors; such experience is critical for bridging USC research to a broadened, national technology transfer ecosystem, said Ishwar Puri, senior vice president of the Office of Research and Innovation.
“The university has the utmost confidence in Dr. Overstreet’s ability to ...
In the field of Landscape Architecture, Topography aims to study the complex and ongoing changing relationship between humans and the land through continuously updated and iterative tools and media. It maintains a balance between abstract concepts and concrete perceptions, which can both drive the development of science and technology in this field and hold on to openness to artistic expression. Thus, topographical design may be an effective way to help facilitate refining landscape design methods.
The work entitled “Can Topography ...
Associate Professor Andrew Baker from QUT School of Biology and Environmental Science said antechinuses are carnivorous marsupials well-known for suicidal sex sessions where all males die after the 1 to 3 week breeding period.
“During the breeding season, male and females mate promiscuously in frenzied bouts lasting as long as 14 hours. Certain stress-induced death follows for all males as surging testosterone causes cortisol to flood uncontrolled through the body, reaching pathological levels,” Professor Baker said.
“The males drop dead, which provides an opportunity ...
Protecting the world’s oceans against accelerating damage from human activities could be cheaper and take up less space than previously thought, new research has found.
The University of Queensland’s Professor Anthony Richardson collaborated on the study, which looks to halt the rapid decline of marine biodiversity from expanding industrial activities in marine areas beyond national jurisdictions (ABNJ).
“This ‘blue acceleration’ as we call it, has seen a greater diversity of stakeholders interested in ABNJs, such as the high seas and the international seabed beyond exclusive economic zones,” ...
Frequently using more than three strategies to stay alert while driving could be a sign of excessive sleepiness due to obstructive sleep apnoea (OSA), according to a study published today (Thursday) in ERJ Open Research [1].
People with OSA often snore loudly, their breathing starts and stops during the night, and they may wake up several times. Around one in five people are estimated to have OSA but the majority of sufferers do not realise they have a problem. OSA causes excessive sleepiness and people with untreated OSA are at higher risk of collisions on the road.
Researchers say that asking people ...
Globally, non-point source pollution is an important source of water quality deterioration in rivers and lakes. A ditch-pond system, consisting of ditches and ponds, is considered to be similar to free-surface wetlands, linking pollution sources to the receiving water bodies. The ditch-pond system includes vegetation, microorganisms and sediment, which can slow down the flow velocity and promote the precipitation of particulate matter carried by running water. At the same time, ditch and pond systems reduces nitrogen and phosphorus concentrations, and those of other nutrients entering the downstream water by means of plant absorption, sediment adsorption and microbial degradation, ...
The Lancet Child & Adolescent Health: Paediatric care for non-White children is universally worse across the USA; policy reform urgently needed to address disparities
Two-paper Series identifies pervasive racial inequities in paediatric care in the USA, and outlines policies to address structural racism embedded in wider sectors of society that shape children’s health.
A review of recent evidence reveals widespread patterns of inequitable care across paediatric specialties, including neonatal care, emergency medicine, surgery, developmental disabilities, mental ...
