Large-scale Farms Research Articles

Considering Urbanism at Mound Key (Caalus), the capital of the Calusa in the 16th Century, Southwest Florida, USA

In 1566, Pedro Menéndez de Avilés arrived at Mound Key, the capital of the Calusa polity. What he saw there was unlike anything else he would encounter in La Florida, a capital teaming with people and complex architecture that was essentially a terraformed anthropogenic island constructed mostly of mollusk shells situated in the middle of Estero Bay. The Calusa literally raised this landscape—51 ha in area—from the sea and built a complex canal system to the capital’s interior. The capital and its outlying towns did not practice large-scale agriculture, but rather relied upon harvesting and management of aquatic resources. Here, I outline the nature of urban processes at the settlement. From this evaluation, I argue that there are many similarities between the settlement and other urban areas of research, particularly in other parts of the Americas. I explore how the occupants of Mound Key worked through some of the experiences of urban processes present via collective action, specifically regarding waste management, transparent governance, and sustainability.

CAT-CBAM-Net: An Automatic Scoring Method for Sow Body Condition Based on CNN and Transformer.

Sow body condition scoring has been confirmed as a vital procedure in sow management. A timely and accurate assessment of the body condition of a sow is conducive to determining nutritional supply, and it takes on critical significance in enhancing sow reproductive performance. Manual sow body condition scoring methods have been extensively employed in large-scale sow farms, which are time-consuming and labor-intensive. To address the above-mentioned problem, a dual neural network-based automatic scoring method was developed in this study for sow body condition. The developed method aims to enhance the ability to capture local features and global information in sow images by combining CNN and transformer networks. Moreover, it introduces a CBAM module to help the network pay more attention to crucial feature channels while suppressing attention to irrelevant channels. To tackle the problem of imbalanced categories and mislabeling of body condition data, the original loss function was substituted with the optimized focal loss function. As indicated by the model test, the sow body condition classification achieved an average precision of 91.06%, the average recall rate was 91.58%, and the average F1 score reached 91.31%. The comprehensive comparative experimental results suggested that the proposed method yielded optimal performance on this dataset. The method developed in this study is capable of achieving automatic scoring of sow body condition, and it shows broad and promising applications.

Hierarchical power control of a large-scale wind farm by using a data-driven optimization method.

With the participation in automatic generation control (AGC), a large-scale wind farm should distribute the real-time AGC signal to numerous wind turbines (WTs). This easily leads to an expensive computation for a high-quality dispatch scheme, especially considering the wake effect among WTs. To address this problem, a hierarchical power control (HPC) is constructed based on the geographical layout and electrical connection of all the WTs. Firstly, the real-time AGC signal of the whole wind farm is distributed to multiple decoupled groups in proportion of their regulation capacities. Secondly, the AGC signal of each group is distributed to multiple WTs via the data-driven surrogate-assisted optimization, which can dramatically reduce the computation time with a small number of time-consuming objective evaluations. Besides, a high-quality dispatch scheme can be acquired by the efficient local search based on the dynamic surrogate. The effectiveness of the proposed technique is thoroughly verified with different AGC signals under different wind speeds and directions.

The economic performance of mango integrated pest management practices at different scales of production.

Integrated pest management (IPM) strategies are being promoted to suppress tephritid fruit fly infestation and reduce economic damage in mango production. However, research on their economic performance across different mango production scales (measured by the number of mango trees) is limited. This study estimated the economic benefits of IPM practices (parasitoids, orchard sanitation, food bait, biopesticides, male annihilation technique, and their combinations) in Kenya's small-, medium-, and large-scale mango production systems. We used the value-cost ratio (VCR) and net present value methods to estimate the heterogeneous economic performance of IPM practices using data from two unique farm surveys. On average, all IPM practices were profitable across various production scales. However, we found that these practices were more profitable for medium-scale farmers than for small- and large-scale farmers. The results show that farmers need a minimum of 9-17 trees, depending on the practice used, to break even and that there are little to no economic benefits to using IPM practices for farmers with more than 320 mango trees. The male annihilation technique was the most profitable practice, with a VCR of 36, and consequentially, the most adopted practice across all scales of production. Overall, we found significant heterogeneity in the profitability of IPM practices across different scales of production. The reason for the lack of profitability of IPM on large-scale farms remains unclear and warrants further investigation.

Factors Limiting the Adoption of Climate-Resilient Agricultural Practices in and Around Oruchiga Settlement

This study was conducted to establish the potential factors limiting the adoption of climate-resilient agricultural practices in and around the Oruchiga settlement. It was a descriptive study employing both qualitative and quantitative approaches for data collection and analysis. Information was gathered from a sample of 322 respondents and other key informants using questionnaires and interviews. Data was analysed using Microsoft EXCEL and SPSS Version 21.0 to generate both descriptive and inferential statistics. The study identified the different climate-resilient agricultural practices used by smallholder farmers including agroforestry, the use of improved crop varieties and livestock breeds, water-smart technologies, soil fertility management, the use of compost and organic pesticides and small-scale irrigation. The study also found that age, family size (labour), size of land, gender, off-farm activities, group membership and access to credit were some of the potential factors limiting the adoption of climate-resilient agricultural practices in the camp. In conclusion, the study confirmed that different climate-resilient agricultural practices are being used by farmers in the area, and these practices have significantly supported food production systems. Despite their great role in agricultural production, the adoption is still constrained by several factors. The study therefore, recommends government to introduce policies that enable farmers to own and cultivate large-scale farms to increase output. Revisiting land policies is paramount if farmers in the area must increase production through adopted climate-resilient agricultural practices. Small-sized land was one of the reasons farmers failed to use recommended practices; therefore, increasing production per unit area through opening new arable land areas would mean that farmers have enough space to try new technologies/practices. The study also recommends that the government 1) consider the farmers’ willingness and factors impeding their practice before introducing climate-resilient agricultural practices; 2) create awareness among the farmers about the overall benefits and challenges of climate-resilient agricultural practices; 3) integrate newly introduced practices with farmer-friendly indigenous practices; and 4) follow down-top approach and include farmers in any decision-making processes

Exploring VA presence in groundwater of densely populated livestock farming watersheds: Sources, seasonal dynamics and geospatial relationships

Antibiotics are an indispensable component of the livestock industry and are released into the environment through various pathways during livestock rearing processes. Among various environmental mediums, groundwater holds significant importance as it serves as a crucial resource for potable water supply and agricultural practices. However, the persistent use of antibiotic-contaminated groundwater can lead to prolonged exposure to these agents in human and ecological systems, thereby engendering serious apprehensions, including the emergence of antibiotic-resistant bacterial strains. Therefore, in this study, the concentration of antibiotics in groundwater within densely populated livestock farming areas was analyzed using UHPLC-q-orbitrap HRMS combined with online solid-phase extraction. The measured cumulative concentrations of antibiotics in the groundwater samples collected from the surveyed areas ranged from 15.8 ng L─1 to 1530.0 ng L─1. The residual antibiotics obtained from the surveyed region exhibited significant seasonal variation, with higher concentrations observed during summer. This seasonal pattern is attributed to the combined effects of agricultural activities and climatic factors. The concentrations of antibiotics in the investigated area demonstrated associations between the composition of livestock species and the density of livestock farming facilities. Specifically, veterinary-specific antibiotics (sulfaquinoxaline [SQX] and clopidol [CLO]), commonly employed in poultry farming, were found to be more prominent in the area with a high concentration of poultry farming facilities. In regions characterized by a dense poultry farm presence, the highest concentrations of SQX and CLO were founded at 135.7 ng L─1 and 178.6 ng L─1, respectively. In contrast, areas without any farms exhibited lower concentrations, measuring 39.9 ng L─1 for SQX and 10.1 ng L─1 for CLO. Similarly, antibiotics primarily used in swine farming showed a strong correlation with the presence of large-scale swine farming operations. In the case of sulfamethazine, which is commonly used in pig farming, concentrations exceeding 500 ng L─1 were observed in groundwater samples collected near large-scale swine farming facilities. These observations suggest that antibiotics are introduced into groundwater through the discharge of wastewater and excreta from livestock farming facilities. Consequently, this study establishes that regional variations in antibiotic concentrations within groundwater are influenced by factors such as local usage patterns, the scale and types of livestock farming, and the prevailing climatic conditions. In order to elucidate the precise associations between multiple sources of contamination, including livestock farming facilities, and to enhance our understanding of their spatial correlations, there appears to be a need for research focused on spatial correlation analysis.

Rhizobiome Transplantation: A Novel Strategy beyond Single-Strain/Consortium Inoculation for Crop Improvement.

The growing human population has a greater demand for food; however, the care and preservation of nature as well as its resources must be considered when fulfilling this demand. An alternative employed in recent decades is the use and application of microbial inoculants, either individually or in consortium. The transplantation of rhizospheric microbiomes (rhizobiome) recently emerged as an additional proposal to protect crops from pathogens. In this review, rhizobiome transplantation was analyzed as an ecological alternative for increasing plant protection and crop production. The differences between single-strain/species inoculation and dual or consortium application were compared. Furthermore, the feasibility of the transplantation of other associated micro-communities, including phyllosphere and endosphere microbiomes, were evaluated. The current and future challenges surrounding rhizobiome transplantation were additionally discussed. In conclusion, rhizobiome transplantation emerges as an attractive alternative that goes beyond single/group inoculation of microbial agents; however, there is still a long way ahead before it can be applied in large-scale agriculture.

Estimation of Short-Term Power of Wind Turbines Using Artificial Neural Network (ANN) and Swarm Intelligence

The integration of wind power into the electricity grid faces a significant challenge due to the unpredictable nature of wind speed fluctuations. Therefore, ensuring precise short-term predictions of power output from wind turbines is vital for effectively incorporating wind energy into the grid and proficiently managing power systems. In this paper, an Artificial Neural Network (ANN)-based approach for the short-term power forecasting of wind turbines based on a swarm intelligence algorithm is proposed. Also, a simulation study of the wind power real system at different wind speeds is presented by using MATLAB/Simulink. The swarm intelligence algorithm is employed to optimize the forecasting model parameters. The performance of the proposed algorithm is evaluated using real data from a wind farm in Turkey. Three distinct methodologies are utilized to process the data efficiently: ANN, ANN with Firefly Algorithm (ANN-FA), and ANN with Particle Swarm Optimization (ANN-PSO). The results demonstrate that the swarm intelligence algorithm outperforms traditional forecasting methods, such as statistical approaches and machine learning techniques, in terms of accuracy and reliability. Furthermore, the computational efficiency of the algorithm is examined, and it is shown that the swarm intelligence-based approach offers a practical solution for real-time forecasting applications. The algorithm’s scalability and adaptability make it suitable for large-scale wind farms with multiple turbines, as it can handle the inherent variability and uncertainties associated with wind power generation. The proposed method offers an accurate and reliable forecasting tool that can assist power system operators and energy market participants in making informed decisions for the efficient utilization of wind energy resources.

The Impact of Farmland Management Scale on Carbon Emissions

In rural China, the conversion between fine-grained farmland and large-scale farmland is a widespread phenomenon, changes in the size of farmland can have an impact on agricultural carbon emissions. Based on the agricultural panel data of Gansu Province for 2000–2020, taking the scale of agricultural land management as the breakthrough point and the consumption intensity of agricultural materials as the intermediary factor, this paper discusses the driving mechanism of agricultural carbon emissions by the scale of agricultural land management. The results including: (1) From the perspective of the intermediary effect, large-scale farmers pay more attention to input efficiency of chemicals such as fertilizers than small-scale farmers, which can effectively promote the development of low-carbon agriculture. (2) A “U-shaped” relationship existed between agricultural land management scale and agricultural carbon emissions. The agricultural carbon emissions were the lowest when agricultural land management scale in Gansu was 0.608 hm2/person. (3) The carbon emission intensity reached its peak when the scale of farmland management in the Hexi region was 0.143 hm2/person. The optimal scale of farmland management in the Longdong and Longnan regions was 0.143 and 0.348 hm2/person, respectively, Longzhong and Gannan regions was all showed complete intermediary effects.

Life Cycle Assessment of a large commercial kelp farm in Shandong, China

The environmental benefits of seaweed cultivation have gained a lot of attention, both in policy strategies and by private companies. Sustainability evaluations of seaweed farming have however focused on a very small part of global production of seaweed - on European cultivations at research and pilot-scales although Asia stands for 99 % of global production with China alone producing 60 %. In this study, we use Life Cycle Assessment (LCA) to evaluate the environmental performance of a 400-hectare Chinese kelp farm with a yearly harvest of 60,000 tons. Primary data from the farm was used to assess impacts up until harvest for the functional unit of 1 ton of fresh-weight kelp. Included in the LCA were impact on climate change, acidification terrestrial and marine eutrophication, and use of land water and energy. In addition, we calculated nutrient uptake. Further, we extracted inventory data of four published LCA studies of farmed kelp and recalculated environmental impacts, applying the same background data and method choices with the aim to compare the effects of scale and cultivation system. The results of the hotspot analysis showed that the plastic ropes and buoys dominated impacts on climate change, freshwater and marine eutrophication, and energy consumption. Consequently, the most effective improvement action was recycling after use. The yearly harvest of the Chinese farm was 1000–4000 times larger than previously evaluated farms compared. Results suggest that streamlined and mature production in the large-scale Chinese kelp farm led to lower electricity and fuel consumption compared to small-scale production, thus placing the Chinese farm with a climate impact of 57.5 kg CO2 eq. per ton fresh-weight kelp on the lower end when comparing the carbon footprint. There was a large variation in carbon footprints, which implies that the kelp cultivation sector has considerable room for optimization.

Adaptive economic predictive control for offshore wind farm active yaw considering generation uncertainty

Inevitable model uncertainty could render active yaw control (AYC) to make suboptimal or even irrational decisions. To this end, this paper quantitatively analyzes the influential mechanisms of uncertainty on optimal yaw policy in terms of the wake model and power model. In order to address power model uncertainty that has received little attention in the AYC field, this paper proposes an efficient adaptive economic predictive control. This framework begins with the construction of a neural network-based compensator to provide online adaptive estimation of parameter uncertainty. On this basis, an adaptive economic predictive control with the economic objective of maximizing the total power is designed to increase the confidence of yaw policy in the presence of generation uncertainty, and a parallel heuristic solver is developed to allow real-time control of large-scale wind farms. Finally, extensive results based on three wind farm cases demonstrate the effectiveness and advantages of the proposed control strategy.

Bio-geophysical feedback to climate caused by the conversion of Amazon Forest to soybean plantations

Over the past two decades, soybean cultivation has become one of the principal replacements for forests in the Brazilian Amazon. Previous studies showed that the conversion of forests into large-scale soybean farms has different effects on local and regional climate than other forms of land use, e.g., conversion to pasture. The bio-geophysical feedbacks that lead to changes in temperature and rainfall caused by the expansion of commodity crops is not fully understood, and this has implications for both modelling potential future climatic change and understanding its impact. Here we performed model simulations to characterize the feedback to climate caused by the replacement of Amazonian forests with soybean and pastures. Our results show that: when compared to deforestation caused by pastures, the conversion of forests into soybean plantations results in more pronounced changes in the atmospheric boundary layer. Because they are characterized by a period of the year with bare soil, soybean fields transmit more long-wave radiation to the atmosphere than pastures, leading to an increase in boundary layer average temperature by 2.4 K. Although soybean plantations tend to strengthen convective lifting, the decrease in boundary layer water vapor content plays a decisive role in reducing rainfall. Finally, we demonstrate that the climatic impacts associated with the replacement of forests by soybean is likely to be magnified with agricultural expansion along new frontiers in the northern and western regions of the Amazon basin due to a more pronounced reduction in water vapor content.

Comparative study of power production using a generic empirical model in a tidal farm

This study presents a generic model for estimating the velocity deficit and turbulence intensity ina tidal turbine farm. The proposed model considers a range of ambient turbulence intensity, the rotor diameter-to-depth ratio, and the rotor thrust coefficient in realistic applications. We evaluate the power generation of a large-scale tidal farm composed of 16 turbines in an in-line and staggered configuration in an ideal channel similar to the Alderney Race in the English Channel. The added turbulence effect is taken into account when assessing the velocity deficit in the farm. As supported by previous studies, the results show that the staggered array produces more power than the rectilinear array. The staggered arrangement benefits from flow acceleration and wide turbine spacing, which improves wake recovery. According to the results, the farm can be resized by decreasing the lateral spacing in the rectilinear array and decreasing the longitudinal spacing in the staggered array without affecting the farm’s efficiency. The reduction in farm size will reduce cable costs and provide an opportunity for future expansion. For the tidal turbines in shallow water regions, the ratio of rotor diameter to depth is shown to affect the power generated by the turbines. The power produced in the farm decreases with an increase in the rotor diameter-to-depth ratio due to the limited wake expansion along the vertical plane. This low-computational model can be useful in studying the wake interaction of tidal turbine parks in different configurations.

Evaluation of dynamic effects of dietary medium-chain monoglycerides on performance, intestinal development and gut microbiota of broilers in large-scale production.

Medium-chain monoglycerides (MG) have been reported to affect the productive performance, gut microbiota and health of broiler chickens reared in ideal experimental conditions at home and abroad. However, the effects of MG on performance, intestinal development and gut microbiota of chickens in large-scale farms during different feed stages remain unknown. The present study was conducted on a modern farm with a total of 12,000 yellow feathered broiler chicks that were randomly allotted to 2 groups (1000 chicks/replicate, 6 replicates/group) for a 70-day trial. The control group (CON group) received a basal diet, and the treated group (MG group) was fed a basal diet containing 300mg/kg mixed MG. The results revealed that dietary MG significantly (P<0.05) increased the body weight and average feed intake, but notably reduced the feed conversion and mortality of chickens in large-scale production during the starter phase. The villus height of the duodenum in the MG group at 1, 2 and 7wk of age increased notably, and the villus height to crypt depth ratio at 1, 2, 5 and 10wk of age was improved. Dietary MG decreased the serum insulin content of chickens at 5, 7 and 10wk of age, and decreased the serum lipopolysaccharide at 3 and 7wk of age. The triglyceride level of chickens at 3, 5 and 10wk of age and the low-density lipoprotein cholesterol level of chickens at 7 and 10wk of age in the MG group decreased notably, while the high-density lipoprotein cholesterol increased significantly. Moreover, MG supplementation selectively increased the relative abundance of genus Bacteroides (family Bacteroidaceae) and Lachnospiraceae_NK4A136_group, but decreased the content of genus Rikenellaceae_RC9_gut_group, Collinsella and family Barnesiellaceae in the cecum of chickens at 3, 7 and 10wk of age. Conclusively, these findings showed that dietary MG notably enhanced chicken performance, health and feed nutrient utilization at early ages by regulating gut microbiota, intestinal development and serum biochemical indices.

Drivers of antimicrobial resistance in layer poultry farming: Evidence from high prevalence of multidrug-resistant Escherichia coli and enterococci in Zambia.

Inappropriate use of antimicrobials exacerbates antimicrobial resistance (AMR) in the poultry sector. Information on factors driving AMR in the layer poultry sector is scarce in Zambia. This study examined the drivers of AMR in the layer poultry sector in the Lusaka and Copperbelt Provinces of Zambia. This cross-sectional study employed a structured questionnaire in 77 layer poultry farms in the provinces of Lusaka and Copperbelt, Zambia, from September 2020 to April 2021. Data analysis was conducted using Stata version 16.1. Antimicrobial resistance was defined as the presence of multidrug resistance (MDR) isolates. Multivariable regression analysis was used to identify drivers of AMR. In total, 365 samples were collected, from which 339 (92.9%) Escherichia coli and 308 (84.4%) Enterococcus spp. were isolated. Multidrug resistance was identified in 39% of the E. coli and 86% of the Enterococcus spp. The overall prevalence of AMR in layer poultry farms was 51.7% (95% confidence interval [CI]: 40.3%-63.5%). Large-scale farmers (Adjusted odds ratio [AOR] = 0.20, 95% CI: 0.04%-0.99%) than small-scale and farmers who were aware of AMR than those who were unaware (AOR = 0.26, 95% CI: 0.08%-0.86%) were less likely to experience AMR problems. This study found a high prevalence of AMR in layer poultry farming linked to the type of farm management practices and lack of AMR awareness. Evidence of high MDR in our study is of public health concern and requires urgent attention. Educational interventions must increase AMR awareness, especially among small- and medium-scale poultry farmers.

Study on a Boat-Assisted Drone Inspection Scheme for the Modern Large-Scale Offshore Wind Farm

This study proposes a novel and comprehensive boat-assisted drone inspection scheme for offshore wind farms. Specifically, we develop a unique wireless communication model, a detailed wind turbine blade detection model, and a route planning scheme for the drone and boat to formulate the minimum energy consumption problem for drone inspection. Then, we demonstrate that this problem is a combinatorial optimization mixed-integer nonlinear programming problem, which we solve by decomposing the optimization problem into four subproblems. Moreover, an improved heuristic algorithm is constructed to solve the optimum energy consumption problem, exploiting these subproblems. The simulation results indicate that the proposed scheme achieves optimal energy consumption for boat-assisted drone inspection. Furthermore, compared with the existing methods, the proposed algorithm obtains the lowest total energy consumption and provides a higher route planning performance for the unmanned aerial vehicle and boat when utilized for offshore wind farm inspection.

The technical efficiency of large-scale agricultural investment in Northwest Ethiopia: A stochastic frontier approach

This study endeavoured to measure the technical efficiency of large-scale agricultural investment in Northwest Ethiopia. Besides, it strives to fathom the socioeconomic attributes and farm management techniques that influence technical inefficiency. This study uses the stochastic frontier approach to estimate the technical efficiency based on the cross-section data of 200 investors selected through a multiple-stage random sampling technique. The study established that better utilization of capital, labour, land, and seed inputs was reflected positively (albeit proportionally less) in grain output; however, the influence of agrochemical inputs was negative. The study highlighted the positive role of gender and level of education in improving technical efficiency, whereas on the other hand, age, occupation, district, and subsidies contributed to technical inefficiency. The study found that the overall mean technical efficiency for the study area was 71.7%, meaning that producers produce grain at a loss of around 28.3% due to technical inefficiency. As a result, it might be said that producers use their technology and resources somewhat inefficiently. The outcome of the study calls for more education for adults, and female producers should be encouraged and given the opportunity to manage the large-scale grain farming segment. In addition, the government is compelled to provide strategies about proper input appliances and set up a pilot research institution in the study area.

Determination of Structural Characteristics of Large-Scale Dairy Farms: Example of Yozgat Province

This research was carried out to determine the status of dairy cattle farms in Yozgat province, which has significant potential in animal husbandry, to evaluate the positive and negative aspects of the existing barns, and to put forward suggestions for solving the problems. The research was completed by conducting observation and physical measurement studies in 28 dairy cattle farms with more than 50 milking animals, which we classified as large-scale, with the data obtained through questionnaires. Most dairy farms were established in the last ten years and received investment and grant support from various public institutions. It has been observed that the criteria suitable for animal welfare, especially in ventilation and building materials, are not followed by avoiding investment costs in farms established with equity capital. In the dairy farms established by receiving grants and investment support, it was observed that the stables were built in conditions suitable for animal welfare. Still, the herd management system was not established, and the records were not kept healthy because the farm owners and employees of the farms were insufficient in dairy cattle breeding knowledge, which would increase the costs. Although the majority of the examined enterprises did not have structural and technical problems, the absence of a birth partition in 21.43%, an individual calf pen in 25%, a ventilation shaft in 3.57%, and a manure pit slope in 28.57% was seen as an obstacle for these dairy farms to be modern enterprises. It is recommended that the economic sustainability of dairy cattle farms, which is a long-term investment branch, does not only depend on having sufficient equipment in terms of structural features but also on farm owners and employees should have sufficient knowledge and infrastructure on dairy cattle breeding and training should be provided to the relevant people.

Wind Power Group Prediction Model Based on Multi-Task Learning

Large-scale wind power grid connection increases the uncertainty of the power system, which reduces the economy and security of power system operations. Wind power prediction technology provides the wind power sequence for a period of time in the future, which provides key technical support for the reasonable development of the power generation plan and the arrangement of spare capacity. For large-scale wind farm groups, we propose a cluster model of wind power prediction based on multi-task learning, which can directly output the power prediction results of multiple wind farms. Firstly, the spatial and temporal feature matrix is constructed based on the meteorological forecast data provided by eight wind farms, and the dimensionality of each attribute is reduced by the principal component analysis algorithm to form the spatial fusion feature set. Then, a network structure with bidirectional gated cycle units is constructed, and a multi-output network structure is designed based on the Multi-gate Mixture-of-Experts (MMoE) framework to design the wind power group prediction model. Finally, the data provided by eight wind farms in Jilin, China, was used for experimental analysis, and the predicted average normalized root mean square error is 0.1754, meaning the prediction precision meets the scheduling requirement, which verifies the validity of the wind power prediction model.

Body weight estimation of beef cattle with 3D deep learning model: PointNet++

It is necessary to measure the live body weight (BW) of beef cattle to assess their health and nutritional degree. Instead of continual manual measuring in holding frames or crates currently used in the breeding industry, this paper has proposed a novel non-contact BW prediction with 3D deep learning model PointNet++. The three-dimensional (3D) point cloud data (PCD) of the whole contour surface of a beef cattle is proximally obtained by a light detection and ranging (LiDAR) sensor. To preserve the quality of the silhouette, the fusion of classical PCD preprocessing is employed. To better the accuracy of manual selection to the position of body conformation, the data extension of PCD and dataset annotations expressed by the feature regions are employed. The PCD part segmentation of deep learning models is validated and redefined with datasets of beef cattle, where the PointNet++ model with the highest accuracy of 95.1% is finally redesigned. With the advantages of being suitable for most beef breeds for the classical Johnson’s live BW prediction, the Gaussian curvature and principal curvature of contour points of feature regions are calculated to extract the body measurement points of body size, and the body length (BL) and chest girth (CG) are calculated and fit-calibrated. With the experimentation of 100 cattle in breeding farms, the results of live BW prediction have shown that the mean absolute percentage error (MAPE) is 3.2%, the root mean square error (RMSE) is 10.2 kg. The effective and practical resolution of BW estimation can improve the weighing process and animal welfare in large-scale breeding farms, and the real silhouette dataset of large animals can help the automated recognition and classification of body conformation.