Explore the vast range of titles available.

This research describes the use of high-performance computing (HPC) and deep learning to create prediction models that could be deployed on edge AI devices equipped with camera and installed in poultry farms. The main idea is to leverage an existing IoT farming platform and use HPC offline to run deep learning to train the models for object detection and object segmentation, where the objects are chickens in images taken on farm. The models can be ported from HPC to edge AI devices to create a new type of computer vision kit to enhance the existing digital poultry farm platform. Such new sensors enable implementing functions such as counting chickens, detection of dead chickens, and even assessing their weight or detecting uneven growth. These functions combined with the monitoring of environmental parameters, could enable early disease detection and improve the decision-making process. The experiment focused on Faster R-CNN architectures and AutoML was used to identify the most suitable architecture for chicken detection and segmentation for the given dataset. For the selected architectures, further hyperparameter optimization was carried out and we achieved the accuracy of AP = 85%, AP50 = 98%, and AP75 = 96% for object detection and AP = 90%, AP50 = 98%, and AP75 = 96% for instance segmentation. These models were installed on edge AI devices and evaluated in the online mode on actual poultry farms. Initial results are promising, but further development of the dataset and improvements in prediction models is needed.

This research explores the role of synthetic data in enhancing the accuracy of deep learning models for automated poultry farm management. A hybrid dataset was created by combining real images of chickens with 400 FLUX.1 [dev] generated synthetic images, aiming to reduce reliance on extensive manual data collection. The YOLOv9 model was trained on various dataset compositions to assess the impact of synthetic data on detection performance. Additionally, automated annotation techniques utilizing Grounding DINO and SAM2 streamlined dataset labeling, significantly reducing manual effort. Experimental results demonstrate that models trained on a balanced combination of real and synthetic images performed comparably to those trained on larger, augmented datasets, confirming the effectiveness of synthetic data in improving model generalization. The best-performing model trained on 300 real and 100 synthetic images achieved mAP = 0.829, while models trained on 100 real and 300 synthetic images reached mAP = 0.820, highlighting the potential of generative AI to bridge data scarcity gaps in precision poultry farming. This study demonstrates that synthetic data can enhance AI-driven poultry monitoring and reduce the importance of collecting real data.

Abstract Innovations in biological pest control and digital technologies hold great promise to reduce risks from pesticide use without compromising on agricultural productivity. These innovations are often marketed by small and emerging companies such as the Koppert Group for biological pest control or CropX for digital tools for pest prediction. However, currently these innovative technologies fail to scale effectively. In this article, we investigate whether so-called killer acquisitions contribute to this development, that is, whether emerging companies for biological pest control and digital technologies are acquired by established pesticide producers with the main goal of avoiding competition by discontinuing the activities of the acquired companies. We analyze merger and acquisition activities of the four largest pesticide producers worldwide (BASF, Bayer, Corteva, and Syngenta) in relation to criteria setting out potential killer acquisitions for the period 2000–2020. Our analysis includes 18 eligible acquisitions in the area of biological pest control and digital farm management and decision support tools for pest control, 16 of which (with a total value of nearly $5 B) have characteristics of killer acquisitions. We conclude that increased attention by policy makers and antitrust authorities is needed to enable scaling of innovations in biological pest control and digital technologies. In particular, we argue that the current criteria triggering an investigation of merger and acquisition transactions by competition authorities should be reconsidered, that is, the minimum size criterion and the criterion of market overlap between acquirer and acquisition target.

Recent research into climate shocks and what this means for the on-farm production of food revealed mixed and unanticipated results. Whilst the research was triggered by a series of catastrophic, climate related disruptions, Australian beef producers interviewed for the study downplayed the immediate and direct impacts of climate shocks. When considering the changing nature of production under shifting climatic conditions, producers offered a commentary on the digital technology and data which interconnected with climate solutions deriving from both on and off the farm. Perceptions of digital technologies were mixed. Some viewpoints outlined how data driven climate solutions supported on farm planning and decision making, helping to manage climate risks and shocks. However, alongside these narratives, concerns were raised about satellite-based sustainability surveillance and their implications for producer agency. These concerns include the data-informed actions of non-farming third parties, such as bank loan call-ins for properties perceived to be a climate risk, remote surveillance of ground cover, and the commercial re-appraisal of pastoral lands as carbon sinks. Digital solutions to climate shocks thus emerge as inherently ambivalent, a response to shocks and a potential catalyst for renewed crisis. Drawing upon the theoretical lens of relationality, we argue that digital data are increasingly entangled with other material and non-material elements that may disrupt and/or reconfigure the management of farming and with that, the future security of food production. In some instances, data-based solutions to climate risks and shocks present even greater risks to producer agency than climate risks and shocks themselves.

Digitalization has impacted agricultural and food production systems, and makes application of technologies and advanced data processing techniques in agricultural field possible. Digital farming aims to use available information from agricultural assets to solve several existing challenges for addressing food security, climate protection, and resource management. However, the agricultural sector is complex, dynamic, and requires sophisticated management systems. The digital approaches are expected to provide more optimization and further decision-making supports. Digital twin in agriculture is a virtual representation of a farm with great potential for enhancing productivity and efficiency while declining energy usage and losses. This review describes the state-of-the-art of digital twin concepts along with different digital technologies and techniques in agricultural contexts. It presents a general framework of digital twins in soil, irrigation, robotics, farm machineries, and food post-harvest processing in agricultural field. Data recording, modeling including artificial intelligence, big data, simulation, analysis, prediction, and communication aspects (e.g., Internet of Things, wireless technologies) of digital twin in agriculture are discussed. Digital twin systems can support farmers as a next generation of digitalization paradigm by continuous and real-time monitoring of physical world (farm) and updating the state of virtual world.

PurposeThis paper reviews the academic contributions that have emerged to date on the broad definition of farm-level management information systems (MISs). The purpose is twofold: (1) to identify the theories used in the literature to study the adoption of digital technologies and (2) to identify the drivers of and barriers to the adoption of such technologies.Design/methodology/approachThe literature review was based on a comprehensive review of contributions published in the 1998–2019 period. The search was both automated and manual, browsing through references of works previously found via high-quality digital libraries.FindingsDiffusion of innovations (DOIs) is the most frequently used theoretical framework in the literature reviewed, though it is often combined with other innovation adoption theories. In addition, farms’ and farmers’ traits, together with technological features, play a key role in explaining the adoption of these technologies.Research limitations/implicationsSo far, research has positioned the determinants of digital technology adoption mainly within the boundaries of the farm.Practical implicationsOn the practical level, the extensive determinants’ review has potential to serve the aim of policymakers and technology industries, to clearly and thoroughly understand adoption dynamics and elaborate specific strategies to deal with them.Originality/valueThis study’s contribution to the existing body of knowledge on the farm-level adoption of digital technologies is twofold: (1) it combines smart farming and existing technologies within the same category of farm-level MIS and (2) it extends the analysis to studies which not only focus directly on adoption but also on software architecture design and development.

The 19 papers included in this special issue examined the factors influencing the adoption of climate-smart agriculture (CSA) practices among smallholder farmers and estimated the impacts of CSA adoption on farm production, income, and well-being. Key findings from this special issue include: (1) the variables, including age, gender, education, risk perception and preferences, access to credit, farm size, production conditions, off-farm income, and labour allocation, have a mixed (either positive or negative) influence on the adoption of CSA practices; (2) the variables, including labour endowment, land tenure security, access to extension services, agricultural training, membership in farmers’ organizations, support from non-governmental organizations, climate conditions, and access to information consistently have a positive impact on CSA adoption; (3) diverse forms of capital (physical, social, human, financial, natural, and institutional), social responsibility awareness, and digital advisory services can effectively promote CSA adoption; (4) the establishment of climate-smart villages and civil-society organizations enhances CSA adoption by improving their access to credit; (5) CSA adoption contributes to improved farm resilience to climate change and mitigation of greenhouse gas emissions; (6) CSA adoption leads to higher crop yields, increased farm income, and greater economic diversification; (7) integrating CSA technologies into traditional agricultural practices not only boosts economic viability but also contributes to environmental sustainability and health benefits; and (8) there is a critical need for international collaboration in transferring technology for CSA. Overall, the findings of this special issue highlight that through targeted interventions and collaborative efforts, CSA can play a pivotal role in achieving food security, poverty alleviation, and climate resilience in farming communities worldwide and contribute to the achievements of the United Nations Sustainable Development Goals.

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords’ combinations of “machine learning” along with “crop management”, “water management”, “soil management”, and “livestock management”, and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018–2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

Effective dairy farm management requires the regular estimation and prediction of pasture biomass. This study explored the suitability of high spatio-temporal resolution Sentinel-2 imagery and the applicability of advanced machine learning techniques for estimating aboveground biomass at the paddock level in five dairy farms across northern Tasmania, Australia. A sequential neural network model was developed by integrating Sentinel-2 time-series data, weekly field biomass observations and daily climate variables from 2017 to 2018. Linear least-squares regression was employed for evaluating the results for model calibration and validation. Optimal model performance was realised with an R2 of ≈0.6, a root-mean-square error (RMSE) of ≈356 kg dry matter (DM)/ha and a mean absolute error (MAE) of 262 kg DM/ha. These performance markers indicated the results were within the variability of the pasture biomass measured in the field, and therefore represent a relatively high prediction accuracy. Sensitivity analysis further revealed what impact each farm’s in situ measurement, pasture management and grazing practices have on the model’s predictions. The study demonstrated the potential benefits and feasibility of improving biomass estimation in a cheap and rapid manner over traditional field measurement and commonly used remote-sensing methods. The proposed approach will help farmers and policymakers to estimate the amount of pasture present for optimising grazing management and improving decision-making regarding dairy farming.

Smart farming adopts advanced technology and the corresponding principles to increase the amount of production and economic returns, often also with the goal to reduce the impact on the environment. One of the key elements of smart farming is the farm management information systems (FMISs) that supports the automation of data acquisition and processing, monitoring, planning, decision making, documenting, and managing the farm operations. An increased number of FMISs now adopt internet of things (IoT) technology to further optimize the targeted business goals. Obviously IoT systems in agriculture typically have different functional and quality requirements such as choice of communication protocols, the data processing capacity, the security level, safety level, and time performance. For developing an IoT-based FMIS, it is important to design the proper architecture that meets the corresponding requirements. To guide the architect in designing the IoT based farm management information system that meets the business objectives a systematic approach is provided. To this end a design-driven research approach is adopted in which feature-driven domain analysis is used to model the various smart farming requirements. Further, based on a FMIS and IoT reference architectures the steps and the modeling approaches for designing IoT-based FMIS architectures are described. The approach is illustrated using two case studies on smart farming in Turkey, one for smart wheat production in Konya, and the other for smart green houses in Antalya.