Farm Operations Research Articles

Multi-Etiological Abortion due to Campylobacter spp. and Chlamydia abortus in a Sheep

In this case, multi-etiologic abortion due to Campylobacter spp. and Chlamydia abortus was determined in an aborted sheep fetus sent to Konya Veterinary Control Institute (KVKE) from a sheep farm operating in Aksaray province in 2020. The presence of Campylobacter spp. was determined by the bacterial isolation method. C.abortus was identified by qPCR and immunohistochemistry (IHC) methods. This study should be published in order to emphasize that in the fight against sheep abortions, multi-etiologic abortions involving multiple agents should be taken into consideration in addition to a single etiologic agent, and a multidisciplinary approach should be used in the diagnosis to identify the abortion agents.

Supplementing Monosodium Glutamate in Sow Diets Enhances Reproductive Performance in Lactating Sows and Improves the Growth of Suckling Piglets.

In most current farm operations, lactating sows need to overcome reproductive and environmental stresses that have resulted in poor sow production performance and piglet growth. Therefore, this study aimed to investigate the effects of in-feed supplementation of monosodium glutamate (MSG) in sows during late gestation lactation in regard to litter performance. The study subjects were 12 multi-parity sows (Landrace × Large White), farrowing sows with an average parity of four (three with three parities, seven with four parities, and two with five parities). They were randomly divided into the following two diet groups: the basal diet as a control (CON) group based on corn and soybean meal; and the basal diet + 2% MSG group. The experimental time ranged from 109 days before delivery to 21 days after delivery. There were six sows in each group, and each sow served as the experimental unit. There were no significant differences (p > 0.05) in body weight (BW), back fat (BF) thickness and estrus interval between sows supplemented with 2% MSG in their diets before and after farrowing and during weaning (p > 0.05). However, MSG-treated sows tended to increase BW loss at farrowing more than the CON group (p = 0.093) but lost less weight during lactation than the CON group (p = 0.019). There were no significant differences in the body condition scores (BCSs) and BF loss of the two groups of sows before and after farrowing and at weaning (p > 0.05). There was no significant difference in the weight of newborn piglets between the two groups of sows (p > 0.05). The weaning weight (p = 0.020) and average daily gain (ADG) (p = 0.045) of suckling piglets were higher in the MSG treated group compared to the CON group. The daily milk production of sows in the MSG treatment group was higher compared to the CON group (p = 0.045). The protein concentration of milk at week 3 (p = 0.060) and fat concentration of milk at week 5 (p = 0.095) of the MSG-supplemented sows tended to increase more than the CON group. In summary, the dietary inclusion of MSG supplementation had a beneficial effect on the late gestating sows and their piglet's growth and milk production. Our research has shown that the addition of 2% MSG in late gestation and lactation diet would be beneficial for both sow and piglet production.

A novel hybrid model based on multiple influencing factors and temporal convolutional network coupling ReOSELM for wind power prediction

Highly accurate wind power prediction is important for the operation and management of wind farms, energy utilization and power supply. In recent years, in order to further improve prediction accuracy, some researchers have considered utilizing factors such as wind speed and wind direction to establish prediction models. However, this often results in input redundancy due to a lack of technical means. In this paper, a multivariate prediction model for wind power based on variational mode decomposition (VMD), fuzzy entropy (FE), partial auto-correlation function and cross-correlation function (PACF&CCF, abbreviated as PC), improved artificial hummingbird algorithm (IAHA), temporal convolutional network (TCN), and regularized online sequential extreme learning machine (ReOSELM) is proposed. To address the nonlinearity and non-stationarity of the original wind power time series and decrease computational costs, the VMD combined with FE data preprocessing technique is employed. Considering the information redundancy in the multivariate data, the PC technique is utilized to conduct correlation analysis on the input data and select highly correlated features as inputs. When the input is multivariate and high-dimensional, the ReOSELM model struggles to achieve satisfactory prediction performance. Therefore, a new model based on TCN-ReOSELM is constructed. Additionally, to overcome the drawbacks of manual parameter adjustment, an IAHA algorithm is proposed, which integrates Latin hypercube sampling and chaotic local search strategies, to optimize the crucial parameters of TCN-ReOSELM. The experimental results demonstrate that the multivariate method proposed in this paper reduces the RMSE by 31% compared to the univariate method. Specifically, the proposed VMD-FE-PC-TCN-ReOSELM model reduces the RMSE, MAE, and SMAPE by 60–64%, 55–58%, and 10–36%, respectively, compared to the PC-TCN-ReOSELM model.

Convolutional neural networks to classify human stress that occurs during in‐field sugarcane harvesting: A case study

AbstractAssessing human stress in agriculture proves to be a complex and time‐intensive endeavor within the field of ergonomics, particularly for the development of agricultural systems. This methodology involves the utilization of instrumentation and the establishment of a dedicated laboratory setup. The complexity arises from the need to capture and analyze various physiological and psychological indicators, such as heart rate (HR), muscle activity, and subjective feedback to comprehensively assess the impact of farm operations on subjects. The instrumentation typically includes wearable devices, sensors, and monitoring equipment to gather real‐time data of subject during the performance of farm operations. Deep learning (DL) models currently achieve human performance levels on real‐world face recognition tasks. In this study, we went beyond face recognition and experimented with the recognition of human stress based on facial features during the drudgery‐prone agricultural operation of sugarcane harvesting. This is the first research study for deploying artificial intelligence‐driven DL techniques to identify human stress in agriculture instead of monitoring several ergonomic characteristics. A total of 20 (10 each for male and female) subjects comprising 4300 augmented RGB images (215 per subject) were acquired during sugarcane harvesting seasons and then these images were deployed for training (80%) and validation (20%). Human stress and nonstress states were determined based on four ergonomic physiological parameters: heart rate (ΔHR), oxygen consumption rate (OCR), energy expenditure rate (EER), and acceptable workload (AWL). Stress was defined when ΔHR, OCR, EER, and AWL reached or exceeded certain standard threshold values. Four convolutional neural network‐based DL models (1) DarkNet53, (2) InceptionV3, (3) MobileNetV2 and (4) ResNet50 were selected due to their remarkable feature extraction abilities, simple and effective implementation to edge computation devices. In all four DL models, training performance results delivered training accuracy ranging from 73.8% to 99.1% at combinations of two mini‐batch sizes and four levels of epochs. The maximum training accuracies were 99.1%, 99.0%, 97.7%, and 95.4% at the combination of mini‐batch size 16 and 25 epochs for DarkNet53, InceptionV3, ResNet50, and MobileNetV2, respectively. Due to the best performance, DarkNet53 was tested further on an independent data set of 100 images and found 89.8%–93.3% confident to classify stressed images for female subjects while 92.2%–94.5% for male subjects, though it was trained on the integrated data set. The comparative classification of the developed model and ergonomic measurements for stress classification was carried out with a net accuracy of 88% where there were few instances of wrong classifications.

Forecasting China's agricultural carbon emissions: A comparative study based on deep learning models

Given the critical urgency to combat the escalating climate crisis and the continuous rise in agricultural carbon emissions (ACE) in China, accurately forecasting their future trends is crucial. This research employs the emission factor method to assess ACE throughout mainland China from 1993 to 2021. To refine our forecasting approach, both statistical and neural network methodologies were utilized to pinpoint key factors influencing ACE. We crafted forecasting models incorporating both deep learning techniques and traditional methods. Notably, the Tree-structured Parzen Estimator Bayesian Optimization (TPEBO) algorithm was applied to optimize Long Short-Term Memory (LSTM) neural networks, culminating in the creation of a superior integrated TPEBO-LSTM model that demonstrated strong performance across various datasets. The forecasting outcomes suggest that ACE in 24 provinces are expected to reach their zenith before 2030, primarily driven by farm operations, as well as livestock and poultry manure management. The result provides a significant forecasting tool for assessing agricultural carbon emissions in different regions, offering insights crucial for targeted mitigation strategies.

Wind turbine main shaft crack detection with SCADA generator speed measurement

Preventing failure of structural components is a necessity for safe and economic operation of wind farms. This paper presents a novel detection method of wind turbine main shaft fractures based on data from the turbine SCADA system thus not needing retrofit sensors. The authors developed the crack detection method in the wake of a catastrophic failure on an offshore 3.6 MW wind turbine and applied it across multiple wind farms totalling more than a thousand turbines of the same type, minimising any further risk of failure. The novel method consists of tracking the amplitude of the 2P rotor harmonic in the generator speed and is found to outperform the most common metrics proposed in shaft crack detection literature: Rotor harmonics measured in fore-aft and side-side accelerations and estimates of the drivetrain torsional eigenfrequencies. The generator speed 2P amplitude of the cracked shaft turbine was significantly elevated 16 months before failure while all other benchmark metrics failed to detect the crack. The analysis showed that no other turbine in the fleet were exhibiting similar indications of main shaft cracks and indicated that any such failure would have a long lead time.

Refocusing aquatic noise: Shifting from single to combined anthropogenic pressures

Aquatic animals (invertebrates, fishes, and marine mammals) are encountering an increasing array of underwater anthropogenic noises that can disrupt and even harm ecosystems as well as the lives of individuals and populations. Sources of anthropogenic noise include, but are not limited to, shipping, offshore exploration and production for fossil fuels, and the construction and operation of wind farms. Because of the continuing increase in anthropogenic noise, research on its potential effects on aquatic animals has intensified over the past two decades. However, a major under-explored issue is that noise is only one type of anthropogenic pressure acting (often simultaneously) on animals. Indeed, multiple simultaneous anthropogenic pressures are likely to affect how aquatic animals respond to each of the individual stimuli. Moreover, animal responses may be very different in the presence of multiple pressures as compared to when there is only a single anthropogenic source. We suggest refocusing of aquatic noise so that research prioritizes studies that deal with the interaction of noise with other anthropogenic pressures on aquatic life. At the same time, we call for an acceleration of studies providing baseline data for cumulative risk studies, such as monitoring of ambient noise around the globe.

Reconstruction of dynamic wind turbine wake flow fields from virtual Lidar measurements via physics-informed neural networks

Accurate characterisation of wind turbine wakes is important for the optimal design and operation of wind farms. However, current techniques for full-scale wind measurements are still limited to point characterisation. To address the research challenge in obtaining field characterisation of real-world wind turbine wakes, this work investigates the reconstruction of the dynamic wake flow fields based on a virtual turbine-mounted Lidar and physics-informed neural networks. Specifically, the wake flow field is reconstructed by fusing the sparse measurements with the two-dimensional Navier-Stokes equations without imposing any models for the unsteady wake. Different from supervised machine learning approaches which need the measured values for the quantities of interest in the first place, the proposed method can achieve the prediction of the wind velocity at new locations where there is no measurement available. The reconstruction performance is evaluated via high-fidelity numerical experiments and it is shown that the dynamic wind turbine wake flow fields are predicted accurately, where the main wake features, including the downwind development and crosswind meandering of the wake, are both captured. This work thus paves the way for investigating full-scale in situ wake flow dynamics in real-world wind energy sites.

Experimental campaign for the characterization of precipitation in a complex terrain site using high resolution observations

Precipitation has an effect on wind power at several levels. It affects the wind current, blade status, wake development and power production. Power production is affected by the harmful effect of precipitation on the blades eroding its surface and altering their aerodynamic performance. In the past decades, wind has been characterized using different techniques, but less effort has been devoted to precipitation measurement. In this work, the results of an experimental campaign performed at a high altitude complex terrain site to characterize precipitation using high resolution observations are presented. The campaign, carried out at CENER’s experimental wind farm (Alaiz) during 2023 within the framework of the Horizon Europe AIRE project, lasted nine months and different precipitation types (rain, snow, graupel) were recorded using a Micro Rain Radar (MRR), a Parsivel disdrometer and a rain gauge co-located with an instrumented wind mast with anemometers and wind vanes at different heights. Two case studies are selected to illustrate the wide range of variability found in precipitation conditions, particularly during the cool season. Precipitation characterization is very challenging at high temporal resolution, making necessary measurement campaigns with different precipitation equipment to optimize their performance and optimise its calibration. The study of precipitation profiles with MRR will support the study of precipitation impingement on wind turbine blades responsible of blade erosion. Moreover, these measurements will contribute to create the link between in-field wind farm data, laboratory experiments in rain erosion test rig and blade damage models necessary to improve wind turbine and wind farm design and operation.

Investigating North Sea Precipitation Variability: Implications for Offshore Wind Energy Siting and Condition Assessments

Rain-driven wind turbine blade erosion, particularly in offshore locations, has been observed as early as within 5 to 7 years of turbine operation, which is below the lifetime expectancy design age of 20 to 25 year. Due to the harsh atmospheric conditions offshore, the preservation of wind turbine blade integrity has become a fundamental necessity. To address this challenge, we compare precipitation maps from two distinct sources (satellite data and a reanalysis product) over 12 years in the region of the North Sea, and we pursue insights into local weather patterns through temporal analysis. This integrated approach enhances the understanding of offshore conditions by focusing on precipitation and wind speed data analysis in time and space. This enables more efficient wind farm planning, operation and maintenance, as well as wind farm siting via informed decisions that account for the risk of rain-driven blade erosion and allow for mitigation measures.

Extension Experts‘ Intentions to use Precision Agricultural Technologies, a Test with the Technology Acceptance Model

Abstract Precision agriculture (PA) is a farm management strategy that relies on various technologies to improve the productivity and sustainability of farming operations. The adoption of PA entails on-farm and off-farm benefits; however, the adoption rates remain low in Iran. Using the socio-psychological framework of the technology acceptance model (TAM), this study examined agricultural extension experts‘ intentions to use precision agricultural technologies (PATs) in Ardabil province, Iran. Structural equation modelling (SEM-PLS) was used to map the components of the TAM (perceived usefulness, perceived ease of use, and attitudes toward PATs). All the components of the TAM showed a significant effect on experts‘ intentions, confirming the importance of socio-psychological variables in predicting agricultural experts‘ decision to apply PATs. Experts perceived PATs as helpful and relatively easy to use. In addition, they had positive attitudes toward PATs and intended to use most PA technologies. The TAM posits that two attitudinal components of perceived usefulness (PU) and perceived ease of use (PEU) determine acceptance and use. PU is the degree to which one believes using technology would enhance job performance, while PEU is the degree to which using technology is free of effort. The results showed that PEU and PU had a positive impact on attitudes. The three constructs positively affected behavioural intention toward the application of PATs and explained 68.8% of the variance of this construct. Due to the novelty of PA in the country, PEU was the most critical determinant of intention.

Optimization of curtailment intervals of wind turbines through assessment of measured loads during start-up and shutdown events

There is an increasing amount of curtailment of wind parks due to grid overload or negative market prices. Operators need to also account for the effect of curtailment on component loads, wear, and lifetime. This paper investigates curtailment leading to turbine shutdown. A novel methodology to optimize the length of curtailment intervals based on load neutrality is introduced. Measurement data from the structural health monitoring system of an onshore and an offshore wind turbine are used to quantify effects of curtailment on loads and wear of tower, blade, and pitch system. Shutdown and start-up events increase loads on the tower and pitch system. Blades benefit from lower edgewise loads and reduced erosion. Results show that load neutrality for the tower is reached on average after 63 min of idling for the onshore and after 200 min for the offshore wind turbine evaluated (not generalizable). An optimal curtailment strategy shall use flexible time intervals but ensure load neutrality on yearly average. This can serve as a simple and valuable guideline for wind farm operators to evaluate the criticality of curtailment times in terms of asset fatigue life. Future research shall investigate curtailment strategies that also include deration of power output.

Development of an unmanned ground vehicle for seed planting

As global population growth intensifies the demand for sustainable food production, the application of robotics to agriculture emerges as a promising solution. This research focuses on the design, development, and deployment of an unmanned ground vehicle for seed planting, also known as a robotic seed planter. The robotic seed planter automates seed planting processes, offering advantages such as increased accuracy, reduced labour requirements, and optimal resource usage. Parametric Technology Corporation (PTC) Creo was used for the structural design, Proteus 8.14 for the circuitry design, and Arduino IDE 2.0 with Visual Studio Code for the programming. The design incorporates seed metering and drilling mechanisms guided by intelligent systems. Results show exceptional accuracy in seed placement (94%), operational efficiency, and adaptability to diverse conditions, with energy consumption relatively low. The planter is equipped with a web application for remote monitoring and control. The application is hosted on one of the microcontrollers and WebSockets protocol is utilized for inter-microcontroller communication. It offers an auto mode for automated planting and Manual mode for easier manoeuvrability. The findings of this study demonstrate the robotic seed planter’s transformative impact on precision agriculture, providing a glimpse into the future of efficient and sustainable farming operations.

Opensource machine learning metamodels for assessing blade performance impairment due to general leading edge degradation

Blades leading edge erosion can significantly reduce annual energy production of wind turbines. Accurate estimates of the resulting blade performance impairment are paramount to predict the resulting energy losses and enable cost-informed decisions on optimal maintenance and operational strategies, maximizing energy production and reducing maintenance costs. Computational Fluid Dynamics (CFD) is a robust approach for predicting the performance losses due to LEE. However, the impact of the damage on blade aerodynamics varies depending on damage pattern, extent and location. Therefore, direct CFD simulation of a sufficiently general set of damaged blades is computationally not viable in industrial applications, since the energy loss assessment needs to be performed for hundreds of turbines at many times of the wind farm operation. To address this issue, previous studies showed how CFD can be used to train machine learning metamodels of the perfomance of damaged blade sections, enabling the definition of multi-fidelity energy loss prediction systems. This study presents improved metamodels, using validated CFD to generate training datasets that cover a more general and wider range of erosion patterns, from low-amplitude roughness to severe grooves. In order to provide the industry with additional erosion geometry-linked tools for estimating energy yield losses, and foster further research and development in this area, the developed meta-models have been made available online with unrestricted access.

Enhanced Wind Farm Maintenance Scheduling Including Wake Effects

With the expansion and dissemination of offshore wind farms, the costs associated with asset maintenance and operation become ever more relevant. Among maintenance activities, preventive interventions represent a significant share of the costs and, as opposed to corrective interventions, may be calendarized according to the farm operator’s strategy. In an offshore wind farm there is often aerodynamic interaction between different machines, namely as a given upstream turbine extracts energy from the wind, it will necessarily reduce the energy available for a turbine that is downstream in the farm. This is broadly referred to as wake effects. The relative proximity of turbines within a farm means such an interaction results in lower energy yield for downstream turbines. Maintenance activities require the shutdown of the turbine, hence the turbine under maintenance effectively produces no wake effect. It follows that, depending on weather conditions, the sequence of wind turbines to be deactivated for large preventive maintenance campaigns may impact the total energy production of an offshore wind farm, especially when the wind direction is considered. The present study investigates the potential of incorporating wake effects in the scheduling of offshore wind farm maintenance activities, considering a reference farm layout and using historical climate data for a real offshore site. Different maintenance scenarios are considered, including distinct maintenance vessels and different intervention criteria. Results show there is a small but relevant potential gain in energy yield when the maintenance scheduling is determined including wake effects, with annual energy production increase of up to 0.18% for the parametric values considered.

Integrating Technology and Agriculture with Advanced Machinery

Abstract: Agricultural technologies are rapidly evolving towards a new paradigm – Integrating Technology. Within this paradigm, digitalization, automation and artificial intelligence play a major role in crop production, including weeding and pest control. This evolution presents both challenges and opportunities, such as leapfrogging from manual and animal-driven technologies to automated and mechanized equipment in developing countries and closing the digital divide. Traditional agricultural mechanization, characterized by the use of tractors and engine power, will be matched and even surpassed by automated equipment and robotics and the precision they can provide in farm operations. Conservation agriculture (CA) is an approach that involves crop diversification, permanent soil cover and minimal soil disturbance (e.g. limited tillage). CA increases soil structure and soil organic matter, promotes rich microbial diversity, retains water and nutrients, and better manages pests and diseases, making agricultural soils more productive and resilient to changes in climate. However, it requires specialized equipment – for example, for direct drilling of crop seed into the soil at the right depth and sowing density. Agricultural robotics can support these environmentally sustainable practices, by allowing spot weeding and precision management of nutrients, pests, diseases and weeds through mechanical removal or spot application of chemicals. Agricultural robots will also be able to substitute arduous labour, especially when there is limited availability, thus increasing social sustainability. The development of Integrating Technology will create new opportunities that can attract youth and entrepreneurs into the sector, tackling some of the causes for rural–urban migration and contributing to the economic component of sustainability.

Navigating the Agricultural Landscape

Abstract: In today’s world agricultural landscape, technological progress has become essential for improving productivity, sustainability, and profitability. This paper investigates Farm Tech Central, an innovative platform that sits at the intersection of agricultural technology and information sharing. Through a thorough examination, this paper clarifies the crucial role played by Farm Tech Central in enabling access to state-of-the-art agricultural technologies, research findings, and best practices. Acting as a central hub for farmers, agronomists, researchers, and industry stakeholders, Farm Tech Central provides users with valuable resources and tools to enhance farm operations, manage risks, and take advantage of emerging opportunities. Utilizing case studies, data analysis, and expert opinions, this paper delves into how Farm Tech Central is transforming agriculture by promoting modernization, encouraging sustainable practices, and fostering innovation. As the agricultural sector continues its journey towards digitalization and technological integration, Farm Tech Central emerges as a leading platform for collaboration, knowledge sharing, and technological progress, poised to usher in a new era of agricultural excellence

EquipFarm: Farmer's Apartment Internet Site

Abstract: A farmer-focused rental software called Equip Farm was created to make agricultural machinery and equipment more accessible. By linking farmers and equipment owners, the platform facilitates the effective use of resources and raises farming operations' output. Farmers may browse a variety of machinery options, compare rental costs, and conveniently reserve the equipment they require for particular chores like planting, harvesting, or plowing with Equip Farm. The Equip Farm abstract emphasizes the organization's commitment to helping smallholder farmers overcome the obstacles of equipment affordability and accessibility, which will ultimately lead to the development of sustainable agricultural methods.

Design, Fabrication and Monitoring of Automated Polyhouse

The agriculture sector faces the challenge of feeding a growing population while dealing with the effects of climate change. With the limited expansion of cropland, agriculture automation has become necessary. Internet of Things (IoT) and Artificial Intelligence (AI) have made significant strides in various industries, including agriculture. These digital technologies offer smart systems that can monitor, control, and visualize farm operations in realtime, approaching human expertise. The potential applications of IoT and AI in agriculture include smart machinery, irrigation systems, pest control, crop monitoring, and more. Automated polyhouses equipped with IoT and AI components can optimize crop conditions, enhancing yield and quality while minimizing climate impacts. Over the past decade, research in this field has matured, transitioning from conceptual stages to implementation. The integration of AI and IoT into agriculture practices poses technical challenges, but understanding these technologies will facilitate their adoption and the development of IoT and AI-based solutions in farming.

CHANGES IN THE MACROENVIRONMENT AND NEW THREATS TO FARMS

In the context of agriculture, numerous significant long-term trends are emerging. Some of these pose threats to farm operations. They can be categorized as threats related to pressure to achieve climate and environmental targets under emission reduction, animal welfare and biodiversity policy, climate changes, structural changes in the farm environment, increasing technological pressure, changes in consumption patterns and unequal conditions of competition in international markets. This study aimed to identify phenomena perceived as threats to agricultural activities and the general mechanisms of their impact on agricultural farms. It is prepared based on a literature review. It was found that the effect of some threats can be mitigated through proper farming practices and increasing production scale. Other threats, including those arising from enforced climate and agricultural policies, have consequences that necessitate economic support for farms or compensation for losses, for example, through subsidies. Insurance may be useful only for protection against well-known threats of measurable risk. One can state that currently published research results still insufficiently recognize how emerging threats alter the outcomes of agricultural farms, what strategies farmers adopt, and which of these are effective for particular production types and given production scales.