Dual-Roof Solar Greenhouse—A Novel Design for Improving the Heat Preserving Capacity in Northern China

Dual-roof solar greenhouse, a new style of solar greenhouse, was designed in this study intending to reduce heat loss in cold time and improve land use efficiency in Beijing, the Capital city of China. Designing and applying the dual-roof greenhouse in metropolitan area had dual effects of saving energy and enhancing land use efficiency. According to the monitoring study and analysis conducted in winter of 2012, the averaged night temperature of south room was about 12.1°C in December, which was satisfying for growing average leaf vegetables. Total energy saved by dual-roof in whole winter was quantified as 1.1 × 107 MJ&#46yr-1 (winter), potentially about 37.4 t coal was saved in Beijing area during whole winter-growing period. Considering the application of north room, the land use efficiency was improved by 62.5% in dual-roof solar greenhouse.

Detecting broiler chickens on litter floor with the YOLOv5-CBAM deep learning model

For commercial broiler production,about 20,000–30,000 birds are raised in each confined house,which has caused growing public concerns on animal welfare.Currently,daily evaluation of broiler wellbeing and growth is conducted manually,which is labor-intensive and subjectively subject to human error.Therefore,there is a need for an automatic tool to detect and analyze the behaviors of chickens and predict their welfare status.In this study,we developed a YOLOv5-CBAM-broiler model and tested its performance for detecting broilers on litter floor.The proposed model consisted of two parts:(1)basic YOLOv5 model for bird or broiler feature extraction and object detection;and(2)the convolutional block attention module(CBAM)to improve the feature extraction capability of the network and the problem of missed detection of occluded targets and small targets.A complex dataset of broiler chicken images at different ages,multiple pens and scenes(fresh litter versus reused litter)was constructed to evaluate the effectiveness of the new model.In addition,the model was compared to the Faster R-CNN,SSD,YOLOv3,EfficientDet and YOLOv5 models.The results demonstrate that the precision,recall,F1 score and an mAP@0.5 of the proposed method were 97.3%,92.3%,94.7%,and 96.5%,which were superior to the comparison models.In addition,comparing the detection effects in different scenes,the YOLOv5-CBAM model was still better than the comparison method.Overall,the proposed YOLOv5-CBAM-broiler model can achieve real-time accurate and fast target detection and provide technical support for the management and monitoring of birds in commercial broiler houses.

DEVELOPMENT OF AN AUTOMATIC WEIGHING PLATFORM FOR MONITORING BODYWEIGHT OF BROILER CHICKENS IN COMMERCIAL PRODUCTION

Bodyweight is a key indicator of broiler production as it measures the production efficiency and indicates the health of a flock.Currently,broiler weight(i.e.,bodyweight)is primarily weighed manually,which is timeconsuming and labor-intensive,and tends to create stress in birds.This study aimed to develop an automatic and stress-free weighing platform for monitoring the weight of floor-reared broiler chickens in commercial production.The developed system consists of a weighing platform,a real-time communication terminal,computer software and a smart phone applet userinterface.The system collected weight data of chickens on the weighing platform at intervals of 6 s,followed by filtering of outliers and repeating readings.The performance and stability of this system was systematically evaluated under commercial production conditions.With the adoption of data preprocessing protocol,the average error of the new automatic weighing system was only 10.3 g,with an average accuracy 99.5%with the standard deviation of 2.3%.Further regression analysis showed a strong agreement between estimated weight and the standard weight obtained by the established live-bird sales system.The variance(an indicator of flock uniformity)of broiler weight estimated using automatic weighing platforms was in accordance with the standard weight.The weighing system demonstrated superior stability for different growth stages,rearing seasons,growth rate types(medium-and slow-growing chickens)and sexes.The system is applicable for daily weight monitoring in floor-reared broiler houses to improve feeding management,growth monitoring and finishing day prediction.Its application in commercial farms would improve the sustainability of poultry industry.

A deep learning method for monitoring spatial distributionof cage-free hens

The spatial distribution of laying hens in cage-free houses is an indicator of flock's health and welfare.While larger space allows chickens to perform more natural behaviors such as dustbathing,foraging,and perching in cage-free houses,an inherent challenge is evaluating chickens'locomotion and spatial distribution(e.g.,realtime birds'number on perches or in nesting boxes).Manual inspection of hen's spatial distribution requires closer observation,which is labor intensive,time consuming,subject to human errors,and stress causing on birds.Therefore,an automated monitoring system is required to track the spatial distribution of hens for early detection of animal welfare and health concerns.In this study,a non–intrusive machine vision method was developed to monitor hens'spatial distribution automatically.An improved You Only Look Once version 5(YOLOv5)method was developed and trained to test hens'distribution in research cage-free facilities(e.g.,200 hens per house).The spatial distribution of hens the system monitored includes perch zone,feeding zone,drinking zone,and nesting zone.The dataset contains a whole growth period of chickens from day 1 to day 252.About 3000 images were extracted randomly from recorded videos for model training,validation,and testing.About 2400 images were used for training and 600 images for testing,respectively.Results show that the accuracy of the new model were 87–94%for tracking distribution in different zones for different ages of hens/pullets.Birds'age affected the performance of the model as younger birds had smaller body size and were hard to be detected due to blackness or occultation by equipment.The performance of the model was 0.891 and 0.942 for baby chicks(≤10 days old)and older birds(>10 days)in detecting perching behaviors;0.874 and 0.932 in detecting feeding/drinking behaviors.Miss detection happened when the flock density was high(>18 birds/m2)and chicken body was occluded by other facilities(e.g.,nest boxes,feeders,and perches).Further studies such as chicken behavior identification works in commercial housing system should be combined with the model to reach an automatic detection system.