Source: UNIVERSITY OF GEORGIA submitted to NRP
PRECISION FARMING PRACTICES FOR SUSTAINABLE EGG PRODUCTIONS
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
ACTIVE
Funding Source
AFRI COMPETITIVE GRANT
Reporting Frequency
Annual
Accession No.
1030188
Grant No.
2023-68008-39853
Cumulative Award Amt.
$299,000.00
Proposal No.
2022-10066
Multistate No.
(N/A)
Project Start Date
May 1, 2023
Project End Date
Apr 30, 2026
Grant Year
2023
Program Code
[A1701]- Critical Agricultural Research and Extension: CARE
Recipient Organization
UNIVERSITY OF GEORGIA
200 D.W. BROOKS DR
ATHENS,GA 30602-5016
Performing Department
(N/A)
Non Technical Summary
A number of US food chains and state governments have announced transition for sourcing cage-free (CF) eggs by 2025 or earlier due to concerns of animal welfare. According to the pledges to date, it would take more than 70% of the current US layer stock to meet the demand by 2025. While CF housing allows hens to better perform their natural behaviors when compared to conventional cage housing systems, an inherent challenge with CF housing is the poor indoor air quality and the incidence of floor eggs. The high level of air pollutants may cause infection or trigger respiratory diseases in animals and their caretakers and can also contaminate eggs. Floor eggs are collected manually by farm workers many times a day, which increases labor costs and farm workers' health risk due to longer exposure in a poor air quality environment. The goal of this research/Extension program is to improve CF house air quality, thereby improving the health and welfare of animals and their caretakers, and food safety. Our specific aims are to: 1)Integrate advanced methods for enhancing air and litter quality in CF layer houses; 2)Explore precision farming strategies for improving egg quality and safety in CF houses; and 3) Develop Extension programs for training egg producers to improve air quality and egg safety on commercial CF farms. This proposed study reflects four priority areas: (1) animal health and production; (2) food safety, nutrition, and health; (3) bioenergy, natural resources, and environment; and (4) agriculture systems and technology.
Animal Health Component
70%
Research Effort Categories
Basic
10%
Applied
70%
Developmental
20%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
3073210202060%
1330410202040%
Knowledge Area
133 - Pollution Prevention and Mitigation; 307 - Animal Management Systems;

Subject Of Investigation
3210 - Egg-type chicken, live animal; 0410 - Air;

Field Of Science
2020 - Engineering;
Goals / Objectives
The overall goal for this project is to promote the cage-free (CF) egg production by providing solutions for issues related to air quality and egg safety related to egg production. To achieve this goal, we have put together a multi-disciplinary team that is well versed in the areas of agricultural engineering, poultry and animal science, and food safety, and product quality, dedicated to developing a research and Extension program for the poultry and egg industry. Specific objectives are as follows:Integrate advanced methods for enhancing air and litter quality in CF layer houses.Test the effect of litter/bedding management and electrostatic air space charging (EASC) system on reduction efficiency of particulate matter, ammonia, and airborne bacteria (AB) in four research CF houses;Identify the best combination of bedding management and use of EASC on different air pollutants;Verify the research findings in commercial CF houses.Explore precision farming strategies for improving egg quality and safety in CF houses.Test the effect of air quality management on egg shell quality and safety in the CF houses;Test the effect of bedding management on the daily generation of floor eggs in the research CF houses;Innovate machine vision systems for detecting floor eggs and hens' behaviors for reducing mislaid eggs;Conduct socioeconomic analysis on aforementioned farming strategies.Develop Extension programs for training egg producers to improve air quality and egg safety on commercial CF farms.Translate research findings into applied knowledge for CF farms;Prepare training materials for egg producers and growers;Provide trainings through UGA Extension programs that PDs are coordinating (e.g., Georgia Layer Conference, the Layer Session of Georgia International Poultry Trainings, Georgia Precision Poultry Farming Conference, and Deep South Poultry Conference);Evaluate the newly developed Extension/education programs by surveying training attendees on willingness in investment or adaptation of different farming practices.Analyze the feedbacks from growers for assessing the project impact on CF production.
Project Methods
A multi-disciplinary team has been assembled that is well versed in the areas of poultry or animal science, poultry production, agricultural and biosystems engineering, and egg quality/safety dedicated to promoting the poultry and egg industry. The use of animals (pullets and layers) in this study will follow the guidelines of the University of Georgia (UGA) Institutional Animal Care and Use Committee and Commercial Egg Production Standards. All participants will follow the Chemical and Laboratory Safety guidelines implemented by the Environmental Health & Safety Management System (EHSMS) at UGA.1.Development of individual methods for improving litter and air qualityFour experimental CF houses (200 ft2 or 18.6 m2 floor per house) with identical set-up on the poultry research farm at the University of Georgia (UGA) will be used for this study. The house temperature will be controlled (with a heater) at 70-75oF in winter to mimic the majority of CF houses in the US. About 800 laying hens (200 hens/room or one hen per ft2) will be raised from day old until 75 weeks of age. The flock management (e.g., hens/nest box, size of nest boxes, hens/nipple water, feeder spacing/hen, perch spacing/hen, and lighting program) will follow Egg Production Standards.For bedding management: PD Chai observed that pine shavings are most popular bedding materials used in CF facilities in the US. Fresh shavings are dust-free and can absorb as twice their weight of water or moisture in the air. However, fresh shavings are always mixed with wet chicken manure on the floor to form litter gradually in layer houses, where chickens perform their natural behaviors of dustbathing, foraging, flying, and fighting/sparing, which favor the generation of dust or particulate matter. PDs observed in broiler breeder houses that large size/flake shavings and wood chips are better at lowering the dust levels. Therefore, we will explore the best bedding management strategy by replacing 50% of fine shavings with large size shavings, woods chips, or mixture of both to estimate their potential impacts on indoor air quality and bedding quality. We will keep 50% of fine shavings because it is critical for aborting moisture from air or fresh manure on floor in winter.For electrostatic space charge system (ESCS), four ion generators (-25 kVdc, current limited to < 2 mA) and conductive tubes with electrodes at 1-inch spacing will be arranged for each of the four pens. ESCS generates negative electric charge to particles that pass through the system. The particles pick up a negative charge and will be attracted to the positively charged surfaces within the room (e.g., floor, walls, and ceiling). Thus, a commercial dust collector (a filter connected to positive electrode, Active Air purifier, Dust Free®, Royse City, TX) will be modified and installed to recycle airborne dust in the CF house. Co-PD Ritz tested the wire length of 1,000 ft for an area of 20,000 ft2 (i.e., 50 ft wire/1000 ft2) and reduced dust by 40-50% in broiler houses. This study will test 0 (control), 25, 50, and 100 ft per 1000 ft2. The treatment of 100 ft wire per 1000 ft is equal to the installation of a full-length wire along four aisles of a commercial CF henhouse.Verification of mitigation methods on a commercial cage-free egg farm:Verification test and application of newly developed strategies will be conducted on a commercial farm. Commercial size cage-free houses (e.g., same hen density, age, and management operation) will be used for verifying the best finding of lab test about bedding management, electrostatic space charging, or litter additives (litter acidifiers will be used if ammonia level is higher than 20 ppm).Two houses will be control (100% shaving bedding without mitigation systems) and the other two houses will serve as treatment houses with best integration/combinations of mitigation method identified on UGA research farm. Field studies will last for 1-1.5 years to include seasonal variations in environmental control and impact on indoor air quality. According to indoor NH3 variation, the litter additive will be applied if the indoor NH3 level is close to 20 ppm to maintain the house NH3 level below 25 ppm (i.e., threshold suggested by National Institute for Occupational Safety and Health) year-round. The application amount will be determined based on results of our tests on UGA research farm.2. Smart sensing of air quality, animals' wellbeing, and floor eggsConcentrations of NH3 in poultry houses will be measured continuously with Drager NH3 sensors and a remote IoT sensing system. A total of 12 DOL-53 sensors will be installed. Newly calibrated TSI optical sensors will be used to monitor PM concentrations.Night vision 2D cameras will be installed on the ceiling at 6.6 ft or 2 m above the litter floor to monitor hens' behaviors such as feeding, drinking, floor egg laying, and locomotion on floor of each pen for evaluating potential effect of mitigation strategies on hens' welfare. In the beginning and the end of each trial, 20 hens in each pen will be randomly selected for evaluating specific welfare indicators (e.g., gait score, footpad lesion, keel bone deformation, plumage damage, and cleanliness) in treatments and control. PD Chai's lab has developed machine vision-based methods for analyzing poultry feeding and drinking behaviors and floor distribution, pecking behaviors and floor eggs. It's impossible to reduce floor eggs by 100% in commercial cage-free hen houses, so a lost-cost machine vision system will be developed for tracking and reporting floor eggs. Timely removing floor eggs are important as floor eggs could affect egg laying behaviors of other birds. Hens may mistakenly consider the spots where have floor eggs as nesting areas.3.Extension Trainings on the Sustainable Egg ProductionAn environmental management handbook/guideline will be developed as the training materials for the program. The training topics will include but are not limited to: CF egg production, manure nutrient cycling, waste and mortality composting, emissions mitigation, and leaching and runoff control. Principles and basic knowledge regarding farm waste (e.g., manure, bedding, and dead birds) generation, environmental quality (e.g., ammonia, CO2, CH4, and N2O, particulate matter, and airborne bacteria and bedding quality of moisture, total bacteria, Salmonella, and E.coli), nutrient cycling (e.g., nitrogen, phosphorus, and metals flows and losses), environmental impacts (e.g., emissions of ammonia, dust, pathogens/diseases, and odor), and mitigation strategies (e.g., floor bedding management and electrostatic space charging).Our Extension education program is expected to be developed for poultry producers, workers, and UGA graduate and undergraduate students. The trainings will be delivered to relevant stakeholders (e.g., policy makers, poultry and egg producers, university students, scientists, and extension personnel) 4-5 times a year as on-farm environmental management. In addition, we will include the new technoloiges in k-12 youth education such as Georgia 4-H poultry and egg projects.

Progress 05/01/24 to 04/30/25

Outputs
Target Audience:Poultry and egg producers, allied poultry service companies, researchers, students, and other stakeholders interested in egg production, and animal welfare and health. Changes/Problems:Due to the continue outbreak of avian influenzas, some research plans such as verifying the new methods for air quality management in commercial cage-free houses are delayed as the collaboration farms are restricting all non-farm staff fromaccessingthe farm. We will create similar situation on our research poultry farm at the University of Georgia to verify the new methods for air quality management, animal welfare monitoring, and floor egg management. What opportunities for training and professional development has the project provided?(1) The 4th Georgia-based Extension training: 2024 Georgia Precision Poultry Conference was developed and hosted virtually on May 1, 2024. The conference was initiated by Chai with 385 participants. (2) The 2024 Georgia Layer Conference (September 23, 2024), which had 230 attendees. How have the results been disseminated to communities of interest?PIs and lab studentshave presented research findings at 2024 ASABE meeting (six papers), 2024 International Poultry Scientific Forum (four papers), 2024 Poultry Science Association (four papers), 2024 Midwest Poultry (PEAK; invited talk), 2024 US Breeder Roundtable (Invitedtalk), 2024 GA International Poultry Short Course (extension), and 2024 International Egg Forum (Invited talk). What do you plan to do during the next reporting period to accomplish the goals?1) Continue to innovate themethod for enhancing air quality in cage-free laying hen houses; 2) Innovate new methods for monitoring laying hen behaviorsand welfare; 3) Test new strategies for floor egg management.

Impacts
What was accomplished under these goals? (1) Activity index detection: Chickens' behaviors and activities are important information for managing animal health and welfare in commercial poultry houses. In this study, convolutional neural networks (CNNs) models were developed to monitor the chicken activity index. A dataset consisting of 1,500 top-view images was utilized to construct tracking models, with 900 images allocated for training, 300 for validation, and 300 for testing. Six different CNN models were developed, based on YOLOv5, YOLOv8, ByteTrack, DeepSORT, and StrongSORT. The final results demonstrated that the combination of YOLOv8 and DeepSORT exhibited the highest performance, achieving a Multi-Object Tracking Accuracy (MOTA) of 94%. Further application of the optimal model could facilitate the detection of abnormal behaviors such as smothering and piling, and enabled the quantification of flock activity into three levels (low, medium, and high) to evaluate footpad health states in the flock. This research underscores the application of deep learning in monitoring poultry activity index for assessing animal health and welfare. (2) Footpad dermatitis monitoring: Footpad dermatitis (FPD) is a common poultry condition that can negatively influence chickens' production, welfare, and health. However, no automated tool for monitoring FPD in live chickens is currently available. The objective of this study was to develop and optimize deep learning models to monitor hens' FPD scores (i.e., 0-2 scale with higher scores indicating poorer footpad conditions). A total of 700 Hy-Line W-36 hens were raised in four cage-free housing systems integrated with Electrostatic Particle Ionization and various bedding materials. A GoPro camera with an upward lens was placed inside a transparent box. Individual laying hens were placed on the top surface of the box to acquire RGB images. In addition, a thermal camera was used to record RGB and thermal images of footpads, and the images were manually scored to assess their footpad conditions. Preprocessing techniques (e.g., filtration, separation, and augmentation) were deployed to enhance dataset quality and size. Moreover, YOLOv8 models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x) and YOLOv7 models (YOLOv7 and YOLOv7x) were comparatively evaluated for predicting FPD scores. The results show that the YOLOv8l outperformed other models, with higher recall (96.6%), mAP@0.50 (97.0%), and F1-score (95.0%). Additionally, the YOLOv8l-FPD model exhibited a high mAP@0.50 for score 0 (98.0%), score 1 (95.0%), and score 2 (97.9%) and F1-score (95.0%) for all FPD scores. Notably, using thermal images could result in faster convergence of model training and slightly better FPD score prediction performance than RGB images. The proposed technique can be useful for non-invasive automatic FPD scoring and further improve automation levels and animal welfare in the egg industry.

Publications

  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2025 Citation: Subedi, S., Bist, R. B., Yang, X., Li, G., & Chai, L. (2025). Advanced Deep Learning Methods for Multiple Behavior Classification of Cage-Free Laying Hens. AgriEngineering, 7(2),24. https://doi.org/10.3390/agriengineering7020024
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Bist, R. B., Yang, X., Subedi, S., Bist, K., Paneru, B., Li, G., & Chai, L. (2024). An automatic method for scoring poultry footpad dermatitis with deep learning and thermal imaging. Computers and Electronics in Agriculture, 226, 109481.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Saeidifar, M., Li, G., Chai, L., Bist, R., Rasheed, K. M., Lu, J., ... & Yang, X. (2024). Zero-shot image segmentation for monitoring thermal conditions of individual cage-free laying hens. Computers and Electronics in Agriculture, 226, 109436.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Bist, R.B., Bist, K., Poudel, S., Subedi, D., Yang, X., Paneru, B., Mani, S., Wang, D. and Chai, L., 2024. Sustainable poultry farming practices: A critical review of current strategies and future prospects. Poultry Science, 104295.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Paneru, B., Bist, R., Yang, X. and Chai, L., 2024. Tracking dustbathing behavior of cage-free laying hens with machine vision technologies. Poultry Science, 103(12), 104289.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Yang, X., Bist, R.B., Paneru, B., Liu, T., Applegate, T., Ritz, C., Kim, W., Regmi, P. and Chai, L., 2024. Computer vision-based cybernetics systems for promoting modern poultry farming: a critical review. Computers and Electronics in Agriculture, 225, 109339.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Yang, X., Bist, R., Paneru, B., & Chai, L. (2024). Monitoring activity index and behaviors of cage-free hens with advanced deep learning technologies. Poultry Science, 103(11), 104193.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Paneru, B., Bist, R., Yang, X., & Chai, L. (2024). Tracking perching behavior of cage-free laying hens with deep learning technologies. Poultry Science, 103(12), 104281.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Bist, R. B., Yang, X., Subedi, S., Paneru, B., & Chai, L. (2024). An Integrated Engineering Method for Improving Air Quality of Cage-Free Hen Housing. AgriEngineering, 6(3), 2795-2810.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Yang, X., Dai, H., Wu, Z., Bist, R. B., Subedi, S., Sun, J., ... & Chai, L. (2024). An innovative segment anything model for precision poultry monitoring. Computers and Electronics in Agriculture, 222, 109045.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Bist, R. B., Yang, X., Subedi, S., & Chai, L. (2024). Automatic detection of bumblefoot in cage-free hens using computer vision technologies. Poultry Science, 103(7), 103780.
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Bist, R. B., Yang, X., Subedi, S., Paneru, B., & Chai, L. (2024). Enhancing dust control for cage-free hens with electrostatic particle charging systems at varying installation heights and operation durations. AgriEngineering, 6(2), 1747-1759.


Progress 05/01/23 to 04/30/24

Outputs
Target Audience:Researchers and extension personnel in academia, egg producers, allied companies, and other stakeholders interested in egg production, and animal welfare and health. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?The project has been providing training opportunities to graduate students, undergraduates, and visiting scholars. Training provided included system construction, programing, instrument calibration and challenge, environmental monitoring, operation of the state-of-the-art measurement and data acquisition systems, and data analysis techniques. It has also allowed for sponsoring students to attend professional conferences such as the 2023 Poultry Science Association Conference in Philadelphia, 2023 Precision Livestock Farming Conference in Tennessee, and 2023 Integrative Precision Agriculture Conference in Athens, GA. Three Ph.D./MS students in the lab delivered 10 presentations. How have the results been disseminated to communities of interest?In this project, we provided training for 500+ attendees at 2023 Georgia Precision Poultry Farming Conference & 2023 Georgia Layer Conference, two extension training events organized by PI Chai. The 2023 Precision Poultry Farming Conference (May 2023) had 450 attendees & 2023 Georgia Layer Conference (September 2023) had 170 attendees. Besides UGA Extension training, project related materials and findings were delivered in other national Extension trainings hosted by US Poultry and Egg Association, Poultry Science Association, and the American Society of Agricultural and Biological Engineers. What do you plan to do during the next reporting period to accomplish the goals?In the coming year, the team plan to investigate further on the optimization of EPI system in wire length, operation time, and energy use for air quality management. For laying hen welfare, the team will investigate dustbathing, perching, and nesting behaviors with machine vision system for promoting the management.

Impacts
What was accomplished under these goals? Concerns over animal welfare have led to pledges of sourcing only CF eggs by a large number of U.S. food retailers and restaurants such as Walmart and McDonald's by 2025. Based on the current number of pledges, it would take more than 70% of the current US layer inventory to meet the pledged demand. California mandated that all eggs and egg products produced or utilized in the state must come from CF hens by January 2022; Nevada legislation was signed by the governor in June 2021 with the same requirements by January 2024. The state of Washington and Oregon passed a law that requires all egg production in their state to be from CF hens by January 2024. Additional states are discussing or debating a timeline for requiring CF eggs/hens. While CF housing allows the birds to perform some natural behaviors, an inherent challenge with these type of housing systems is the poor indoor air quality (i.e., high ammonia, particulate matter, and AB levels), especially during cold weather. The poor air quality primarily arises from the accumulation of manure/litter on the floor. Bedding/litter management is the key for air quality management in CF houses. Four identical research CF houses (200 Hy-Line W-36 hens per house) were prepared for this project on research farm at the University of Georgia in Athens, GA. In research houses, where perches and litter floor were provided to mimic commercial tiered aviary system. Birds were raised from day 1 to day 350 (75 weeks) in each room, measuring 7.3 m L × 6.1 m W × 3 m H (Figure 1). Each room was equipped with feeders, drinkers, lights, perch, and nest boxes. Pine shaving (5 cm depth) was spread on the floor as bedding. The indoor temperature, relative humidity, light duration (16 hours) and intensity (12-15 lux), and ventilation rates were controlled automatically with Chore-Tronics Model 8 controller (Chore-Time Equipment, Milford, Indiana, USA). The Institutional Animal Care and Use Committee (IACUC) at the University of Georgia (UGA) approved animal use and management of this study. For monitoring animal welfare and performance, this study used a night-vision network camera (PRO-1080MSB, Swann Communications USA Inc., Santa Fe Springs, LA, USA) to record hens' behaviors image dataset for the main data acquisition tool. Each room was equipped with 6 cameras mounted ~3m above the litter floor and two cameras above the ground floor placed at 0.5m from the ground. The camera records data for 24 hours, but this study took the FELB data acquisition time between 5:00 -21:00 every day because FELB was mostly observed during light periods. The captured videos were stored in a digital video recorder (DVR-4580, Swann Communications USA Inc., Santa Fe Springs, LA, USA) from 25-50 weeks of age (WOA). The video files were stored in .avi format with a 1920 × 1080 pixels resolution with a sampling rate of 15 frames per second (FPS). The five YOLOv5 models were obtained from the GitHub repository developed by ultralytics. The five YOLOv5 models were pretrained with Common Objects in Context (COCO) datasets and can be readily modified into required object detection models through target object training datasets. Before developing the FELB model detector, the experimental configurations were prepared for the model evaluation (Table 2). Training datasets were analyzed using Oracle Cloud with different experimental configurations. For air quality management, the electrostatic particle ionization (EPI) system was built in our four research CF houses for dust control. The Latin Square Design (LSD) method was employed due to the limited availability of rooms, specifically four experimental CF rooms, to conduct the four treatments across four trials (Table 1). Each Trial lasted one week, after which the EPI systems (EPI Air, LLC, Columbia, MO, USA) were thoroughly cleaned. The EPI systems operated continuously for 24 hours during each Trial. The varying lengths used in the study provide valuable insights into the specific spacing approaches utilized in previous research. The EPI systems were positioned at 8 feet instead of the standard 9-foot height in our experimental CF rooms. This adjustment was necessary to accommodate room equipment, such as heaters, circulating fans, and water supply pipes. Bird-repellent spikes (Bird-X, Inc., Elmhurst, IL, USA) were attached above the corona pipe using adhesive glue to prevent hens from perching on the corona pipes. Maintaining a minimum distance of 1 foot between the EPI system and the ceiling and walls is important to avoid any electric field effects on nearby objects. The corona pipes were positioned 1 foot (0.3 m) away from the side walls and 8 feet (2.4 m) away from the front and back walls, with a gap between the corona pipes. For behavior monitoring, this study trained and tested five deep-learning models based on YOLOv5 structure and then compared them for detecting floor egg-laying behaviors in four cage-free floor-raised rooms present within the research barn. The following conclusions were drawn from this study: The YOLOv5m-FELB and YOLOv5x-FELB model detectors yielded the highest precision, recall, mAP@0.50, and F1-score in detecting floor egg-laying behaviors. However, the YOLOv5s model had a higher speed of data processing. A lower camera height (e.g., 0.5 m above the floor) increased the performance of the FELB detection model compared to the ceiling camera (e.g., 3 m above the floor). A dusty environment and dusty camera affect the detection accuracy; therefore, cleaning a camera is periodically recommended. For air quality control, this study found that the EPI system with longer wires reduced PM2.5 concentrations (p≤0.01). Treatment T2, T3, and T4 led to reductions in PM2.5 by 12.1%, 19.3%, and 31.7%, respectively, and in small particle concentrations (particle size >0.5mm) by 18.0%, 21.1%, and 32.4%, respectively. However, no significant differences were observed for PM10 and large particles (particle size >2.5 mm) (p<0.10), though the data suggests potential reductions in PM10 (32.7%) and large particles (33.3%) by the T4 treatment. Similarly, there was no significant impact of treatment on NH3 reduction (p= 0.712), possibly due to low NH3 concentration (<2 ppm) and low LMC (<13%) among treatment rooms. Electricity consumption was significantly related to the length of the EPI system (p≤0.01), with longer lengths leading to higher consumption rates. Overall, a longer-length EPI corona pipe is recommended for better air pollutant reduction in CF housing. Further research should focus on enhancing EPI technology, assessing cost-effectiveness, and exploring combinations with other PM reduction strategies.

Publications

  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Bist, R. B., Yang, X., Subedi, S., & L. Chai. (2023). Mislaying behavior detection in cage-free hens with deep learning technologies. Poultry Science, 102(7), 102729.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Bist, R.B., S. Subedi, L. Chai, Xiao Yang (2023). Ammonia Emissions, Impacts, and Mitigation Strategies for Poultry Production: A Critical Review. Journal of Environmental Management, 328, 116919.
  • Type: Journal Articles Status: Published Year Published: 2024 Citation: Bist, R. B., Yang, X., Subedi, S., Ritz, C. W., Kim, W. K., & L. Chai*. (2024). Electrostatic particle ionization for suppressing air pollutants in cage-free layer facilities. Poultry Science, 103494.
  • Type: Journal Articles Status: Published Year Published: 2024 Citation: Yang, X., Bist, R. B., Paneru, B., & Chai, L. (2024). Deep Learning Methods for Tracking the Locomotion of Individual Chickens. Animals, 14(6), 911.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Bist, R.B., X. Yang, S. Subedi, L. Chai (2023). Automatic Detection of Cage-Free Dead Hens with Deep Learning Methods. AgriEngineering, 5(2), 1020-1038
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Bist, R. B., Subedi, S., Yang, X., & L. Chai*. (2023). Effective Strategies for Mitigating Feather Pecking and Cannibalism in Cage-Free W-36 Pullets. Poultry, 2(2), 281-291.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Bist, R. B., Yang, X., Subedi, S., Sharma, M. K., Singh, A. K., Ritz, C. W., Kim, W. K & L. Chai. (2023). Temporal variations of air quality in cage-free experimental pullet houses. Poultry, 2(2), 320-333.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Bist, R. B., Regmi, P., Karcher, D., Guo, Y., Singh, A. K., Ritz, C. W., ... & Chai, L. (2023). Bedding management for suppressing particulate matter in cage-free hen houses. AgriEngineering, 5(4), 1663-1676.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Guo, Y., Regmi, P., Ding, Y., Bist, R. B., & L. Chai. (2023). Automatic detection of brown hens in cage-free houses with deep learning methods. Poultry Science, 102(8), 102784.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Subedi, S., Bist, R. B, X.Yang, L. Chai. (2023). Tracking Pecking Behaviors and Damages of Cage-free Laying hens with Machine Vision Technologies. Computers and Electronics in Agriculture, 204 (1), 107545.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Subedi, S., Bist, R. B, X.Yang, L. Chai (2023). Tracking Floor Eggs with Machine Vision in Cage-free Hen Houses. Poultry Science, 102637.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Yang, X., R. Bist, S. Subedi, Z.Wu, T. Liu, L. Chai. (2023) An automatic classifier for monitoring applied behaviors of cagefree laying hens with deep learning. Engineering Applications of Artificial Intelligence, 123, 106377.
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Yang, X., R. Bist, S. Subedi, L. Chai. (2023) A computer vision based automatic system for egg grading and defect detection. Animals, 13(14), 2354.