Plant science in the age of simulation intelligence

Historically, plant and crop sciences have been quantitative fields that intensively use measurements and modeling. Traditionally, researchers choose between two dominant modeling approaches: mechanistic plant growth models or data-driven, statistical methodologies. At the intersection of both paradigms, a novel approach referred to as "simulation intelligence", has emerged as a powerful tool for comprehending and controlling complex systems, including plants and crops. This work explores the transformative potential for the plant science community of the nine simulation intelligence motifs, from understanding molecular plant processes to optimizing greenhouse control. Many of these concepts, such as surrogate models and agent-based modeling, have gained prominence in plant and crop sciences. In contrast, some motifs, such as open-ended optimization or program synthesis, still need to be explored further. The motifs of simulation intelligence can potentially revolutionize breeding and precision farming towards more sustainable food production.

Decarbonization of Agriculture: The Greenhouse Gas Impacts and Economics of Existing and Emerging Climate-Smart Practices

The worldwide emphasis on reducing greenhouse gas (GHG) emissions has increased focus on the potential to mitigate emissions through climate-smart agricultural practices, including regenerative, digital, and controlled environment farming systems. The effectiveness of these solutions largely depends on their ability to address environmental concerns, generate economic returns, and meet supply chain needs. In this Review, we summarize the state of knowledge on the GHG impacts and profitability of these three existing and emerging farming systems. Although we find potential for CO2 mitigation in all three approaches (depending on site-specific and climatic factors), we point to the greater level of research covering the efficacy of regenerative and digital agriculture in tackling non-CO2 emissions (i.e., N2O and CH4), which account for the majority of agriculture's GHG footprint. Despite this greater research coverage, we still find significant methodological and data limitations in accounting for the major GHG fluxes of these practices, especially the lifetime CH4 footprint of more nascent climate-smart regenerative agriculture practices. Across the approaches explored, uncertainties remain about the overall efficacy and persistence of mitigation-particularly with respect to the offsetting of soil carbon sequestration gains by N2O emissions and the lifecycle emissions of controlled environment agriculture systems compared to traditional systems. We find that the economic feasibility of these practices is also system-specific, although regenerative agriculture is generally the most accessible climate-smart approach. Robust incentives (including carbon credit considerations), investments, and policy changes would make these practices more financially accessible to farmers.

CowMesh: a data-mesh architecture to unify dairy industry data for prediction and monitoring

Dairy is an economically significant industry that caters to the huge demand for food products in people's lives. To remain profitable, farmers need to manage their farms and the health of the dairy cows in their herds. There are, however, many risks to cow health that can lead to significant challenges to dairy farm management and have the potential to lead to significant losses. Such risks include cow udder infections (i.e., mastitis) and cow lameness. As automation and data recording become more common in the agricultural sector, dairy farms are generating increasing amounts of data. Recently, these data are being used to generate insights into farm and cow health, where the objective is to help farmers manage the health and welfare of dairy cows and reduce losses from cow health issues. Despite the level of data generation on dairy farms, this information is often difficult to access due to a lack of a single, central organization to collect data from individual farms. The prospect of such an organization, however, raises questions about data ownership, with some farmers reluctant to share their farm data for privacy reasons. In this study, we describe a new data mesh architecture designed for the dairy industry that focuses on facilitating access to data from farms in a decentralized fashion. This has the benefit of keeping the ownership of data with dairy farmers while bringing data together by providing a common and uniform set of protocols. Furthermore, this architecture will allow secure access to the data by research groups and product development groups, who can plug in new projects and applications built across the data. No similar framework currently exists in the dairy industry, and such a data mesh can help industry stakeholders by bringing the dairy farms of a country together in a decentralized fashion. This not only helps farmers, dairy researchers, and product builders but also facilitates an overview of all dairy farms which can help governments to decide on regulations to improve the dairy industry at a national level.

Towards deep learning based smart farming for intelligent weeds management in crops

Introduction

Deep learning (DL) is a core constituent for building an object detection system and provides a variety of algorithms to be used in a variety of applications. In agriculture, weed management is one of the major concerns, weed detection systems could be of great help to improve production. In this work, we have proposed a DL-based weed detection model that can efficiently be used for effective weed management in crops.

Methods

Our proposed model uses Convolutional Neural Network based object detection system You Only Look Once (YOLO) for training and prediction. The collected dataset contains RGB images of four different weed species named Grass, Creeping Thistle, Bindweed, and California poppy. This dataset is manipulated by applying LAB (Lightness A and B) and HSV (Hue, Saturation, Value) image transformation techniques and then trained on four YOLO models (v3, v3-tiny, v4, v4-tiny).

Results and discussion

The effects of image transformation are analyzed, and it is deduced that the model performance is not much affected by this transformation. Inferencing results obtained by making a comparison of correctly predicted weeds are quite promising, among all models implemented in this work, the YOLOv4 model has achieved the highest accuracy. It has correctly predicted 98.88% weeds with an average loss of 1.8 and 73.1% mean average precision value.

Future work

In the future, we plan to integrate this model in a variable rate sprayer for precise weed management in real time.

Inside out: transforming images of lab-grown plants for machine learning applications in agriculture

Introduction

Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a result of different growing conditions. Synthetically-augmented datasets have shown promise in improving existing models when real data is not available.

Methods

In this paper, we employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) and simple image processing techniques to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images.

Results

Furthermore, we use our synthetic multi-plant images to train several YoloV5 nano object detection models to perform the task of plant detection and measure the accuracy of the model on real field data images.

Discussion

The inclusion of training data generated by the CUT-GAN leads to better plant detection performance compared to a network trained solely on real data.

Quantifying the Income-Increasing Effect of Digital Agriculture: Take the New Agricultural Tools of Smartphone as an Example

Smartphones are increasingly used in rural areas and have become indispensable new farming tools in farmers' production and their lives. Based on data from the 2018 China Household Tracking Survey, this study uses ordinary least squares regression with two-stage least squares as a benchmark regression to investigate the impact of the extent of smartphone use on farm household income. Our findings are as follows. ① The degree of use of new smartphone farming tools has a significant income-increasing effect on farm households. ② There is variability in the impact of the use of new smartphone farming tools on the income of farmers in different regions. The highest income-generating effects on the use of smartphone tools were found in the western region, followed by the eastern region, with the smallest effects found in the central region. ③ Low-income farmers have the highest income effects from using new smartphone farming tools. We therefore recommend further improving the digital infrastructure in rural areas to give full play to the driving force of digital technology.

Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects

The ornamental crop industry is an important contributor to the economy in the United States. The industry has been facing challenges due to continuously increasing labor and agricultural input costs. Sensing and automation technologies have been introduced to reduce labor requirements and to ensure efficient management operations. This article reviews current sensing and automation technologies used for ornamental nursery crop production and highlights prospective technologies that can be applied for future applications. Applications of sensors, computer vision, artificial intelligence (AI), machine learning (ML), Internet-of-Things (IoT), and robotic technologies are reviewed. Some advanced technologies, including 3D cameras, enhanced deep learning models, edge computing, radio-frequency identification (RFID), and integrated robotics used for other cropping systems, are also discussed as potential prospects. This review concludes that advanced sensing, AI and robotic technologies are critically needed for the nursery crop industry. Adapting these current and future innovative technologies will benefit growers working towards sustainable ornamental nursery crop production.

AI-Driven Validation of Digital Agriculture Models

Digital agriculture employs artificial intelligence (AI) to transform data collected in the field into actionable crop management. Effective digital agriculture models can detect problems early, reducing costs significantly. However, ineffective models can be counterproductive. Farmers often want to validate models by spot checking their fields before expending time and effort on recommended actions. However, in large fields, farmers can spot check too few areas, leading them to wrongly believe that ineffective models are effective. Model validation is especially difficult for models that use neural networks, an AI technology that normally assesses crops health accurately but makes inexplicable recommendations. We present a new approach that trains random forests, an AI modeling approach whose recommendations are easier to explain, to mimic neural network models. Then, using the random forest as an explainable white box, we can (1) gain knowledge about the neural network, (2) assess how well a test set represents possible inputs in a given field, (3) determine when and where a farmer should spot check their field for model validation, and (4) find input data that improve the test set. We tested our approach with data used to assess soybean defoliation. Using information from the four processes above, our approach can reduce spot checks by up to 94%.

On-Device Intelligence for Malfunction Detection of Water Pump Equipment in Agricultural Premises: Feasibility and Experimentation

The digital transformation of agriculture is a promising necessity for tackling the increasing nutritional needs on Earth and the degradation of natural resources. Toward this direction, the availability of innovative electronic components and of the accompanying software programs can be exploited to detect malfunctions in typical agricultural equipment, such as water pumps, thereby preventing potential failures and water and economic losses. In this context, this article highlights the steps for adding intelligence to sensors installed on pumps in order to intercept and deliver malfunction alerts, based on cheap in situ microcontrollers, sensors, and radios and easy-to-use software tools. This involves efficient data gathering, neural network model training, generation, optimization, and execution procedures, which are further facilitated by the deployment of an experimental platform for generating diverse disturbances of the water pump operation. The best-performing variant of the malfunction detection model can achieve an accuracy rate of about 93% based on the vibration data. The system being implemented follows the on-device intelligence approach that decentralizes processing and networking tasks, thereby aiming to simplify the installation process and reduce the overall costs. In addition to highlighting the necessary implementation variants and details, a characteristic set of evaluation results is also presented, as well as directions for future exploitation.

Making sense of uses and benefits

Digital technology is being introduced to global agriculture in a wide variety of forms that are collectively known as digital agriculture. In this paper we provide opportunities and value propositions of how this is occurring in livestock production systems, with a consistent emphasis on technology relating to animal health, animal welfare, and product quality for value creation. This is achieved by organizing individual accounts of digital agriculture in livestock systems according to four broad types-commodity-based; value seeking; subsistence and nature-based. Each type presents contrasting modes of value creation in downstream processing; as well as from the perspective of One Health. The ideal result of digital technology adoption is an equitable and substantial diversification of supply chains, increased monetization of animal product quality, and more sensitive management to meet customer demands and environmental threats. Such changes have a significance beyond the immediate value generated because they indicate endogenous growth in livestock systems, and may concern externalities imposed by the pursuit of purely commercial ends.

The Impact of Environmental Regulation on Agricultural Productivity: From the Perspective of Digital Transformation

China's goal of becoming a strong agricultural country cannot be achieved without the modernization and digital transformation of the agricultural sector. Presently, China's agriculture has ushered in the era of digital economy transformation. The digital transformation of agriculture has played a huge role in improving agricultural productivity, promoting sustainable development of China's agricultural economy, and achieving sustainable development goals. The deep integration of digital economy and agricultural economy has become an important issue of The Times. This study uses a two-way fixed-effects model and an instrumental variable method to examine the impact of environmental regulation on agricultural total factor productivity. Using the method of mechanism analysis, the conduction path of improving agricultural productivity under the means of environmental regulation is discussed. Therefore, the visualization analysis results based on the panel data of Chinese agricultural enterprises from 2011 to 2019 show that the distribution of digital transformation and productivity level of enterprises is uneven and tends to be stable in space. The empirical analysis results show that there is a direct and significant positive relationship between voluntary environmental regulation and agricultural total factor productivity. The results of mechanism analysis show that, under the means of environmental regulation, digital transformation plays an indirect role in improving agricultural productivity. On the basis of enriching and deepening the theoretical extension of the "Porter Hypothesis", this study subtly incorporates environmental regulation, digital transformation, and agricultural productivity into a unified framework, expanding existing research.

Cyber-Security Threats and Side-Channel Attacks for Digital Agriculture

The invention of smart low-power devices and ubiquitous Internet connectivity have facilitated the shift of many labour-intensive jobs into the digital domain. The shortage of skilled workforce and the growing food demand have led the agriculture sector to adapt to the digital transformation. Smart sensors and systems are used to monitor crops, plants, the environment, water, soil moisture, and diseases. The transformation to digital agriculture would improve the quality and quantity of food for the ever-increasing human population. This paper discusses the security threats and vulnerabilities to digital agriculture, which are overlooked in other published articles. It also provides a comprehensive review of the side-channel attacks (SCA) specific to digital agriculture, which have not been explored previously. The paper also discusses the open research challenges and future directions.

Evaluation of different deep convolutional neural networks for detection of broadleaf weed seedlings in wheat

BACKGROUND

In-field weed detection in wheat (Triticum aestivum L.) is challenging due to the occurrence of weeds in close proximity with the crop. The objective of this research was to evaluate the feasibility of using deep convolutional neural networks for detecting broadleaf weed seedlings growing in wheat.

RESULTS

The object detection neural networks, including CenterNet, Faster R-CNN, TridenNet, VFNet, and You Only Look Once Version 3 (YOLOv3) were insufficient for weed detection in wheat because the recall never exceeded 0.58 in the testing dataset. The image classification neural networks including AlexNet, DenseNet, ResNet, and VGGNet were trained with small (5500 negative and 5500 positive images) or large training datasets (11 000 negative and 11 000 positive images) and three training image sizes (200 × 200, 300 × 300, and 400 × 400 pixels). For the small training dataset, increasing image sizes decreased the F1 scores of AlexNet and VGGNet but generally increased the F1 scores of DenseNet and ResNet. For the large training dataset, no obvious difference was detected between the training image sizes since all neural networks exhibited remarkable classification accuracies with high F1 scores (≥0.96). All image classification neural networks exhibited high F1 scores (≥0.99) when trained with the large training dataset and the training images of 200 × 200 pixels.

CONCLUSION

CenterNet, Faster R-CNN, TridentNet, VFNet, and YOLOv3 were insufficient, while AlexNet, DenseNet, ResNet, and VGGNet trained with a large training dataset were highly effective for detection of broadleaf weed seedlings in wheat. © 2021 Society of Chemical Industry.

Deep Learning Based Automatic Grape Downy Mildew Detection

Grape downy mildew (GDM) disease is a common plant leaf disease, and it causes serious damage to grape production, reducing yield and fruit quality. Traditional manual disease detection relies on farm experts and is often time-consuming. Computer vision technologies and artificial intelligence could provide automatic disease detection for real-time controlling the spread of disease on the grapevine in precision viticulture. To achieve the best trade-off between GDM detection accuracy and speed under natural environments, a deep learning based approach named YOLOv5-CA is proposed in this study. Here coordinate attention (CA) mechanism is integrated into YOLOv5, which highlights the downy mildew disease-related visual features to enhance the detection performance. A challenging GDM dataset was acquired in a vineyard under a nature scene (consisting of different illuminations, shadows, and backgrounds) to test the proposed approach. Experimental results show that the proposed YOLOv5-CA achieved a detection precision of 85.59%, a recall of 83.70%, and a mAP@0.5 of 89.55%, which is superior to the popular methods, including Faster R-CNN, YOLOv3, and YOLOv5. Furthermore, our proposed approach with inference occurring at 58.82 frames per second, could be deployed for the real-time disease control requirement. In addition, the proposed YOLOv5-CA based approach could effectively capture leaf disease related visual features resulting in higher GDE detection accuracy. Overall, this study provides a favorable deep learning based approach for the rapid and accurate diagnosis of grape leaf diseases in the field of automatic disease detection.

A Bibliometric Network Analysis of Recent Publications on Digital Agriculture to Depict Strategic Themes and Evolution Structure

The agriculture sector is one of the backbones of many countries’ economies. Its processes have been changing to enable technology adoption to increase productivity, quality, and sustainable development. In this research, we present a scientific mapping of the adoption of precision techniques and breakthrough technologies in agriculture, so-called Digital Agriculture. To do this, we used 4694 documents from the Web of Science database to perform a Bibliometric Performance and Network Analysis of the literature using SciMAT software with the support of the PICOC protocol. Our findings presented 22 strategic themes related to Digital Agriculture, such as Internet of Things (IoT), Unmanned Aerial Vehicles (UAV) and Climate-smart Agriculture (CSA), among others. The thematic network structure of the nine most important clusters (motor themes) was presented and an in-depth discussion was performed. The thematic evolution map provides a broad perspective of how the field has evolved over time from 1994 to 2020. In addition, our results discuss the main challenges and opportunities for research and practice in the field of study. Our findings provide a comprehensive overview of the main themes related to Digital Agriculture. These results show the main subjects analyzed on this topic and provide a basis for insights for future research.

High-Throughput Phenotyping and Random Regression Models Reveal Temporal Genetic Control of Soybean Biomass Production

Understanding temporal accumulation of soybean above-ground biomass (AGB) has the potential to contribute to yield gains and the development of stress-resilient cultivars. Our main objectives were to develop a high-throughput phenotyping method to predict soybean AGB over time and to reveal its temporal quantitative genomic properties. A subset of the SoyNAM population (n = 383) was grown in multi-environment trials and destructive AGB measurements were collected along with multispectral and RGB imaging from 27 to 83 days after planting (DAP). We used machine-learning methods for phenotypic prediction of AGB, genomic prediction of breeding values, and genome-wide association studies (GWAS) based on random regression models (RRM). RRM enable the study of changes in genetic variability over time and further allow selection of individuals when aiming to alter the general response shapes over time. AGB phenotypic predictions were high (R 2 = 0.92-0.94). Narrow-sense heritabilities estimated over time ranged from low to moderate (from 0.02 at 44 DAP to 0.28 at 33 DAP). AGB from adjacent DAP had highest genetic correlations compared to those DAP further apart. We observed high accuracies and low biases of prediction indicating that genomic breeding values for AGB can be predicted over specific time intervals. Genomic regions associated with AGB varied with time, and no genetic markers were significant in all time points evaluated. Thus, RRM seem a powerful tool for modeling the temporal genetic architecture of soybean AGB and can provide useful information for crop improvement. This study provides a basis for future studies to combine phenotyping and genomic analyses to understand the genetic architecture of complex longitudinal traits in plants.

Corrigendum: Passive Reflectance Sensing and Digital Image Analysis Allows for Assessing the Biomass and Nitrogen Status of Wheat in Early and Late Tillering Stages

[This corrects the article DOI: 10.3389/fpls.2018.01478.].

An Open Source Low-Cost Device Coupled with an Adaptative Time-Lag Time-Series Linear Forecasting Modeling for Apple Trentino (Italy) Precision Irrigation

Precision irrigation represents those strategies aiming to feed the plant needs following the soil’s spatial and temporal characteristics. Such a differential irrigation requires a different approach and equipment with regard to conventional irrigation to reduce the environmental impact and the resources use while maximizing the production and thus profitability. This study described the development of an open source soil moisture LoRa (long-range) device and analysis of the data collected and updated directly in the field (i.e., weather station and ground sensor). The work produced adaptive supervised predictive models to optimize the management of agricultural precision irrigation practices and for an effective calibration of other agronomic interventions. These approaches are defined as adaptive because they self-learn with the acquisition of new data, updating the on-the-go model over time. The location chosen for the experimental setup is a cultivated area in the municipality of Tenna (Trentino, Alto Adige region, Italy), and the experiment was conducted on two different apple varieties during summer 2019. The adaptative partial least squares time-lag time-series modeling, in operative field conditions, was a posteriori applied in the consortium for 78 days during the dry season, producing total savings of 255 mm of irrigated water and 44,000 kW of electricity, equal to 10.82%.

Machine Learning Applications and Optimization of Clustering Methods Improve the Selection of Descriptors in Blackberry Germplasm Banks

Machine learning (ML) and its multiple applications have comparative advantages for improving the interpretation of knowledge on different agricultural processes. However, there are challenges that impede proper usage, as can be seen in phenotypic characterizations of germplasm banks. The objective of this research was to test and optimize different analysis methods based on ML for the prioritization and selection of morphological descriptors of Rubus spp. 55 descriptors were evaluated in 26 genotypes and the weight of each one and its ability to discriminating capacity was determined. ML methods as random forest (RF), support vector machines, in the linear and radial forms, and neural networks were optimized and compared. Subsequently, the results were validated with two discriminating methods and their variants: hierarchical agglomerative clustering and K-means. The results indicated that RF presented the highest accuracy (0.768) of the methods evaluated, selecting 11 descriptors based on the purity (Gini index), importance, number of connected trees, and significance (p value < 0.05). Additionally, K-means method with optimized descriptors based on RF had greater discriminating power on Rubus spp., accessions according to evaluated statistics. This study presents one application of ML for the optimization of specific morphological variables for plant germplasm bank characterization.

Extension and Advisory Organizations on the Road to the Digitalization of Animal Farming: An Organizational Learning Perspective

Agricultural digitalization emerged as a radical innovation, punctuating the gradual evolution of the agrifood sector and having the potential to fundamentally restructure the context within which extension and advisory organizations operate. Digital technologies are expected to alter the practice and culture of animal farming in the future. To suit the changing environmental conditions, organizations can make minor adjustments or can call into question their purposes, belief systems, and operating paradigms. Each pattern of change is associated with different types of organizational learning. In this conceptual article, adopting an organizational learning perspective and building upon organizational change models, we present two potential change and learning pathways that extension and advisory organizations can follow to cope with digitalization: morphostasis and morphogenesis. Morphostatic change has a transitional nature and helps organizations survive by adapting to the new environmental conditions. Organizations that follow this pathway learn by recognizing and correcting errors. This way, they increase their competence in specific services and activities. Morphogenetic change, on the other hand, occurs when organizations acknowledge the need to move beyond existing operating paradigms, redefine their purposes, and explore new possibilities. By transforming themselves, organizations learn new ways to understand and interpret contextual cues. We conclude by presenting some factors that explain extension and advisory organizations' tendency to morphostasis.

Priorities for science to overcome hurdles thwarting the full promise of the 'digital agriculture' revolution

The world needs to produce more food, more sustainably, on a planet with scarce resources and under changing climate. The advancement of technologies, computing power and analytics offers the possibility that 'digitalisation of agriculture' can provide new solutions to these complex challenges. The role of science is to evidence and support the design and use of digital technologies to realise these beneficial outcomes and avoid unintended consequences. This requires consideration of data governance design to enable the benefits of digital agriculture to be shared equitably and how digital agriculture could change agricultural business models; that is, farm structures, the value chain and stakeholder roles, networks and power relations, and governance. We argue that this requires transdisciplinary research (at pace), including explicit consideration of the aforementioned socio-ethical issues, data governance and business models, alongside addressing technical issues, as we now have to simultaneously deal with multiple interacting outcomes in complex technical, social, economic and governance systems. The exciting prospect is that digitalisation of science can enable this new, and more effective, way of working. The question then becomes: how can we effectively accelerate this shift to a new way of working in agricultural science? As well as identifying key research areas, we suggest organisational changes will be required: new research business models, agile project management; new skills and capabilities; and collaborations with new partners to develop 'technology ecosystems'. © 2018 The Authors. © 2018 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Large-Scale Phenotyping of Livestock Welfare in Commercial Production Systems: A New Frontier in Animal Breeding

Genomic breeding programs have been paramount in improving the rates of genetic progress of productive efficiency traits in livestock. Such improvement has been accompanied by the intensification of production systems, use of a wider range of precision technologies in routine management practices, and high-throughput phenotyping. Simultaneously, a greater public awareness of animal welfare has influenced livestock producers to place more emphasis on welfare relative to production traits. Therefore, management practices and breeding technologies in livestock have been developed in recent years to enhance animal welfare. In particular, genomic selection can be used to improve livestock social behavior, resilience to disease and other stress factors, and ease habituation to production system changes. The main requirements for including novel behavioral and welfare traits in genomic breeding schemes are: (1) to identify traits that represent the biological mechanisms of the industry breeding goals; (2) the availability of individual phenotypic records measured on a large number of animals (ideally with genomic information); (3) the derived traits are heritable, biologically meaningful, repeatable, and (ideally) not highly correlated with other traits already included in the selection indexes; and (4) genomic information is available for a large number of individuals (or genetically close individuals) with phenotypic records. In this review, we (1) describe a potential route for development of novel welfare indicator traits (using ideal phenotypes) for both genetic and genomic selection schemes; (2) summarize key indicator variables of livestock behavior and welfare, including a detailed assessment of thermal stress in livestock; (3) describe the primary statistical and bioinformatic methods available for large-scale data analyses of animal welfare; and (4) identify major advancements, challenges, and opportunities to generate high-throughput and large-scale datasets to enable genetic and genomic selection for improved welfare in livestock. A wide variety of novel welfare indicator traits can be derived from information captured by modern technology such as sensors, automatic feeding systems, milking robots, activity monitors, video cameras, and indirect biomarkers at the cellular and physiological levels. The development of novel traits coupled with genomic selection schemes for improved welfare in livestock can be feasible and optimized based on recently developed (or developing) technologies. Efficient implementation of genetic and genomic selection for improved animal welfare also requires the integration of a multitude of scientific fields such as cell and molecular biology, neuroscience, immunology, stress physiology, computer science, engineering, quantitative genomics, and bioinformatics.

Instance segmentation for the fine detection of crop and weed plants by precision agricultural robots

PREMISE

Weed removal in agriculture is typically achieved using herbicides. The use of autonomous robots to reduce weeds is a promising alternative solution, although their implementation requires the precise detection and identification of crops and weeds to allow an efficient action.

METHODS

We trained and evaluated an instance segmentation convolutional neural network aimed at segmenting and identifying each plant specimen visible in images produced by agricultural robots. The resulting data set comprised field images on which the outlines of 2489 specimens from two crop species and four weed species were manually drawn. We adjusted the hyperparameters of a mask region-based convolutional neural network (R-CNN) to this specific task and evaluated the resulting trained model.

RESULTS

The probability of detection using the model was quite good but varied significantly depending on the species and size of the plants. In practice, between 10% and 60% of weeds could be removed without too high of a risk of confusion with crop plants. Furthermore, we show that the segmentation of each plant enabled the determination of precise action points such as the barycenter of the plant surface.

DISCUSSION

Instance segmentation opens many possibilities for optimized weed removal actions. Weed electrification, for instance, could benefit from the targeted adjustment of the voltage, frequency, and location of the electrode to the plant. The results of this work will enable the evaluation of this type of weeding approach in the coming months.

Integrating High-Throughput Phenotyping and Statistical Genomic Methods to Genetically Improve Longitudinal Traits in Crops

The rapid development of remote sensing in agronomic research allows the dynamic nature of longitudinal traits to be adequately described, which may enhance the genetic improvement of crop efficiency. For traits such as light interception, biomass accumulation, and responses to stressors, the data generated by the various high-throughput phenotyping (HTP) methods requires adequate statistical techniques to evaluate phenotypic records throughout time. As a consequence, information about plant functioning and activation of genes, as well as the interaction of gene networks at different stages of plant development and in response to environmental stimulus can be exploited. In this review, we outline the current analytical approaches in quantitative genetics that are applied to longitudinal traits in crops throughout development, describe the advantages and pitfalls of each approach, and indicate future research directions and opportunities.

Convolutional Neural Networks for Image-Based Corn Kernel Detection and Counting

Precise in-season corn grain yield estimates enable farmers to make real-time accurate harvest and grain marketing decisions minimizing possible losses of profitability. A well developed corn ear can have up to 800 kernels, but manually counting the kernels on an ear of corn is labor-intensive, time consuming and prone to human error. From an algorithmic perspective, the detection of the kernels from a single corn ear image is challenging due to the large number of kernels at different angles and very small distance among the kernels. In this paper, we propose a kernel detection and counting method based on a sliding window approach. The proposed method detects and counts all corn kernels in a single corn ear image taken in uncontrolled lighting conditions. The sliding window approach uses a convolutional neural network (CNN) for kernel detection. Then, a non-maximum suppression (NMS) is applied to remove overlapping detections. Finally, windows that are classified as kernel are passed to another CNN regression model for finding the ( x , y ) coordinates of the center of kernel image patches. Our experiments indicate that the proposed method can successfully detect the corn kernels with a low detection error and is also able to detect kernels on a batch of corn ears positioned at different angles.

Review: Synergy between mechanistic modelling and data-driven models for modern animal production systems in the era of big data

Mechanistic models (MMs) have served as causal pathway analysis and 'decision-support' tools within animal production systems for decades. Such models quantitatively define how a biological system works based on causal relationships and use that cumulative biological knowledge to generate predictions and recommendations (in practice) and generate/evaluate hypotheses (in research). Their limitations revolve around obtaining sufficiently accurate inputs, user training and accuracy/precision of predictions on-farm. The new wave in digitalization technologies may negate some of these challenges. New data-driven (DD) modelling methods such as machine learning (ML) and deep learning (DL) examine patterns in data to produce accurate predictions (forecasting, classification of animals, etc.). The deluge of sensor data and new self-learning modelling techniques may address some of the limitations of traditional MM approaches - access to input data (e.g. sensors) and on-farm calibration. However, most of these new methods lack transparency in the reasoning behind predictions, in contrast to MM that have historically been used to translate knowledge into wisdom. The objective of this paper is to propose means to hybridize these two seemingly divergent methodologies to advance the models we use in animal production systems and support movement towards truly knowledge-based precision agriculture. In order to identify potential niches for models in animal production of the future, a cross-species (dairy, swine and poultry) examination of the current state of the art in MM and new DD methodologies (ML, DL analytics) is undertaken. We hypothesize that there are several ways via which synergy may be achieved to advance both our predictive capabilities and system understanding, being: (1) building and utilizing data streams (e.g. intake, rumination behaviour, rumen sensors, activity sensors, environmental sensors, cameras and near IR) to apply MM in real-time and/or with new resolution and capabilities; (2) hybridization of MM and DD approaches where, for example, a ML framework is augmented by MM-generated parameters or predicted outcomes and (3) hybridization of the MM and DD approaches, where biological bounds are placed on parameters within a MM framework, and the DD system parameterizes the MM for individual animals, farms or other such clusters of data. As animal systems modellers, we should expand our toolbox to explore new DD approaches and big data to find opportunities to increase understanding of biological systems, find new patterns in data and move the field towards intelligent, knowledge-based precision agriculture systems.

Light Drone-Based Application to Assess Soil Tillage Quality Parameters

The evaluation of soil tillage quality parameters, such as cloddiness and surface roughness produced by tillage tools, is based on traditional methods ranging, respectively, from manual or mechanical sieving of ground samples to handheld rulers, non-contact devices or Precision Agriculture technics, such as laser profile meters. The aim of the study was to compare traditional methods of soil roughness and cloddiness assessment (laser profile meter and manual sieving), with light drone RGB 3D imaging techniques for the evaluation of different tillage methods (ploughed, harrowed and grassed). Light drone application was able to replicate the results obtained by the traditional methods, introducing advantages in terms of time, repeatability and analysed surface while reducing the human error during the data collection on the one hand and allowing a labour-intensive field monitoring solution for digital farming on the other. Indeed, the profilometer positioning introduces errors and may lead to false reading due to limited data collection. Future work could be done in order to streamline the data processing operation and so to produce a practical application ready to use and stimulate the adoption of new evaluation indices of soil cloddiness, such as Entropy and the Angular Second Moment (ASM), which seem more suitable than the classic ones to achieved data referred to more extended surfaces.

Passive Reflectance Sensing and Digital Image Analysis Allows for Assessing the Biomass and Nitrogen Status of Wheat in Early and Late Tillering Stages

Proximal remote sensing systems depending on spectral reflectance measurements and image analysis can acquire timely information to make real-time management decisions compared to laborious destructive measurements. There is a need to make nitrogen management decisions at early development stages of cereals when the first top-dressing is made. However, there is insufficient information available about the possibility of detecting differences in the biomass or the nitrogen status of cereals at early development stages and even less comparing its relationship to destructively obtained information. The performance of hyperspectral passive reflectance sensing and digital image analysis was tested in a 2-year study to assess the nitrogen uptake and nitrogen concentration, as well as the biomass fresh and dry weight at early and late tillering stages of wheat from BBCH 19 to 30. Wheat plants were subjected to different levels of nitrogen fertilizer applications and differences in biomass, and the nitrogen status was further created by varying the seeding rate. To analyze the spectral and digital imaging data simple linear regression and partial least squares regression (PLSR) models were used. The green pixel digital analysis, spectral reflectance indices and PLSR of spectral reflectance from 400 to 1000 nm were strongly related to the nitrogen uptake and the biomass fresh and dry weights at individual measurements and for the combined dataset at the early crop development stages. Relationships between green pixels, spectral reflectance indices and PLSR with the biomass and nitrogen status parameters reached coefficients of determination up to 0.95∗∗ through the individual measurements and the combined data set. Reflectance-based spectral sensing compared to digital image analysis allows detecting differences in the biomass and nitrogen status already at early growth stages in the tillering phase. Spectral reflectance indices are probably more robust and can more easily be applied compared to PLSR models. This might pave the way for more informed management decisions and potentially lead to improved nitrogen fertilizer management at early development stages.