Biosystems Engineering最新文献

Improved feed-forward neural network and multidimensional motion data for accurate recognition of sheep behaviour at multiple fattening stages 改进的前馈神经网络和多维运动数据用于准确识别绵羊在多个育肥阶段的行为

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-20 DOI: 10.1016/j.biosystemseng.2025.104218

Yifan Fu , Mengjie Zhang , Dagan Mao , Daxiang Wang , Hailing Luo , Xiaoshuan Zhang

{"title":"Improved feed-forward neural network and multidimensional motion data for accurate recognition of sheep behaviour at multiple fattening stages","authors":"Yifan Fu , Mengjie Zhang , Dagan Mao , Daxiang Wang , Hailing Luo , Xiaoshuan Zhang","doi":"10.1016/j.biosystemseng.2025.104218","DOIUrl":"10.1016/j.biosystemseng.2025.104218","url":null,"abstract":"<div><div>The behavioural characteristics of Hu sheep are closely linked to their health status. This study focuses on Hu sheep at various fattening stages to explore the role of machine learning in the recognition of multidimensional motion signals and links to sheep behaviour. Multidimensional motion sensors were employed to collect movement data, such as acceleration and angular position from the necks of sheep. Independent sample <em>t</em>-tests were conducted to analyse the temporal distribution differences in sheep behaviours, whilst one-way analysis of variance (ANOVA) was utilised to compare motion data across different behaviours. Factor Analysis (FA) was employed as a dimensionality reduction method whilst retaining relevant motion data and features. An artificial neural network model based on the whale optimisation algorithm (WOA) was established using both the raw and feature dataset, and its performance was compared with other models. The <em>t</em>-test results demonstrated significant differences in the temporal distribution of sheep behaviours at different fattening stages (p < 0.05), while ANOVA revealed significant distinctions among the majority of behavioural data (p < 0.05). The motion data and feature retained through FA effectively preserved key information regarding sheep movement, reducing dimensional redundancy while ensuring the classification efficacy of the model. The integration of WOA with the feature dataset addressed the issue of overfitting and achieved an accuracy of 95.52 %, which is an improvement of 19.04 % compared to traditional models. This research provides a high-precision and high-stability behavioural recognition model for Hu sheep, offering a methodological framework for achieving precise health assessments.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104218"},"PeriodicalIF":4.4,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144329991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research progress and development in anti-blocking methods for no-till seeders in regenerative agriculture 再生农业免耕播种机防堵方法研究进展

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-19 DOI: 10.1016/j.biosystemseng.2025.104215

Xuezhen Wang, Hao Zhou, Hanmi Zhou, Jiangtao Ji

{"title":"Research progress and development in anti-blocking methods for no-till seeders in regenerative agriculture","authors":"Xuezhen Wang, Hao Zhou, Hanmi Zhou, Jiangtao Ji","doi":"10.1016/j.biosystemseng.2025.104215","DOIUrl":"10.1016/j.biosystemseng.2025.104215","url":null,"abstract":"<div><div>Regenerative agriculture (RA) is nature-based solution which has its core intention to improve soil health through elevated soil organic content and nitrogen, as well as reduced chemicals input and mechanical operations, so as to realise the sustainable development of agriculture, namely enhanced soil carbon sequestration, maximised biodiversity and improved quality of water, vegetation and land-productivity. No-till seeding and ground cover are two critical practices of RA in terms of managing soil, reducing water and wind erosion, and enhancing water infiltration characteristics. However, no-till seeders are regularly blocked by crop residue in RA systems, causing more energy inputs and less crop yield outputs. Anti-blocking methods are essential for the no-till seeding technology (NST) and have been developed over the past years. A comprehensive summary about typical furrow openers and corresponding tool characteristics and current anti-blocking methods for no-till seeding are reported. The anti-blocking methods for NST are introduced in five aspects: residue management before seeding, straw cutting, straw removing, improving straw fluidity and other methods (i.e. automatic navigation and high pressure air shooting). This review also recommends five future research directions about further improving the anti-blocking performance of no-till seeders to promote the development of NST and RA. The study discusses implications for improving the anti-blocking ability of no-till seeders and satisfying the principles of the RA by reducing energy inputs (i.e. less fuel consumption) and raising the outputs of crop yields.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104215"},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating the influence of double-channel inclined spreading blades on the effect of fertiliser granule spreading: DEM modelling and simulations 评估双通道倾斜散布叶片对肥料颗粒散布效果的影响：DEM建模与模拟

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-19 DOI: 10.1016/j.biosystemseng.2025.104211

Wenqi Zhou, Qu Lu, Yao Wang, Han Tang, Jinwu Wang, Yijia Wang, Xiaobo Sun

{"title":"Evaluating the influence of double-channel inclined spreading blades on the effect of fertiliser granule spreading: DEM modelling and simulations","authors":"Wenqi Zhou, Qu Lu, Yao Wang, Han Tang, Jinwu Wang, Yijia Wang, Xiaobo Sun","doi":"10.1016/j.biosystemseng.2025.104211","DOIUrl":"10.1016/j.biosystemseng.2025.104211","url":null,"abstract":"<div><div>In view of the problems with the widely used single-channel linear fertiliser spreading blade, including obvious operational pulsation, a narrow fertiliser spreading width at low speeds, an irregular overlap of the fertiliser coverage area, and poor fertiliser distribution uniformity at high speeds, a double-channel inclined fertiliser spreading blade structure was designed in this research. Based on the discrete element method (DEM), the mechanism of fertiliser spreading by blades under different blade declination angles, blade inclination angles, disc rotation speeds and machine forward speeds was analysed, and the influences of each factor on the coefficient of variation <em>Cv</em> of fertiliser distribution and the effective width <em>B</em> of fertiliser spreading were analysed and summarised; the best blade fertiliser spreading performance was attained when the blade declination angle and inclination angle were 10° and 14° respectively, the disc rotation speed was 350 rev min<sup>−1</sup>, and the machine forward speed was 1.3 m s<sup>−1</sup>. At this moment, the coefficient of variation of the fertiliser distribution <em>Cv</em> was 15.17 %, and the effective width of the fertiliser spreading <em>B</em> was 9 m. In comparison with the initial foliar fertilisation, the <em>Cv</em> was decreased by 35.42 % and the <em>B</em> was increased by 28.57 %. It is shown that the discrete element method can effectively model the process of fertiliser spreading and predict the motion behaviour of fertiliser particles, and it is also shown that the use of this blade in fertiliser spreading machine can effectively improve the quality of fertiliser spreading operation.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104211"},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modelling and strip application validation of granulated straw based on DEM 基于DEM的粒状秸秆建模及条形应用验证

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-18 DOI: 10.1016/j.biosystemseng.2025.104216

Guibin Chen , Zhengdao Liu , Jiaying Wan , Fuzeng Yang , Qingjie Wang , Jin He , Zhijie Liu

{"title":"Modelling and strip application validation of granulated straw based on DEM","authors":"Guibin Chen , Zhengdao Liu , Jiaying Wan , Fuzeng Yang , Qingjie Wang , Jin He , Zhijie Liu","doi":"10.1016/j.biosystemseng.2025.104216","DOIUrl":"10.1016/j.biosystemseng.2025.104216","url":null,"abstract":"<div><div>Granulating surface straw and returning it to the field in conservation tillage can prevent straw blockage, effectively improve sowing quality, and enhance soil fertility. However, straw modelling methods must be updated for accuracy to guide the optimal engineering of mechanised strip applications. This study elucidates granulated straw's particle size and length distribution through mathematical statistical analysis. The differential in tangential and normal compression loads is ascertained via uniaxial compression, three-point bending, and shear examinations. The contact parameters amongst straw particles are calibrated using the cylinder lifting technique. A novel approach is introduced for constructing and calibrating an anisotropic bidirectional bonding model tailored explicitly for materials exhibiting significant discrepancies in tangential and normal load. Utilising the Box-Behnken test design, mathematical models correlating bonding parameters with tangential and normal loads are developed. The study further investigates the effects of variations in interaction parameters on the assessment of the load, culminating in the identification of an optimal set of bonding parameters. Simulation outcomes from uniaxial compression and three-point bending tests revealed deviations from actual target values by 5.9 % and 2.4 %, respectively, with consistent deformation patterns observed. During the validation phase of mechanised straw-breaking strip application, the average discrepancy of test outcomes is recorded at 8.6 %, affirmatively simulating the roller device's field mechanised straw-breaking strip application process. This research offers technical backing for the swift establishment of anisotropic material models and the optimisation design of key components of agricultural machinery.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104216"},"PeriodicalIF":4.4,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A multi-posture adaptive method for measuring goat bodies dimensions using 3D point clouds in real-world applications 一种基于三维点云的多姿态自适应山羊体尺寸测量方法

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-14 DOI: 10.1016/j.biosystemseng.2025.104214

Yi Sun , Qifeng Li , Weihong Ma , Daniel Morris , Hao Guo , Xiangyu Qi , Mingyu Li , Chunjiang Zhao

{"title":"A multi-posture adaptive method for measuring goat bodies dimensions using 3D point clouds in real-world applications","authors":"Yi Sun , Qifeng Li , Weihong Ma , Daniel Morris , Hao Guo , Xiangyu Qi , Mingyu Li , Chunjiang Zhao","doi":"10.1016/j.biosystemseng.2025.104214","DOIUrl":"10.1016/j.biosystemseng.2025.104214","url":null,"abstract":"<div><div>Body dimensions are recognised as critical indicators in the processes of fattening and breeding goats. However, manual measurement methods are both time-consuming and labour-intensive, often inducing significant stress in the animals and compromising their healthy growth. To address these concerns, a non-contact, high-throughput body measurement system for goats has been developed utilising multi-view three-dimensional point clouds. It employs an arched-channel device equipped with three depth cameras to collect three-dimensional point clouds. Firstly, a Multi-View Filter Reconstruction Processing Pipeline is proposed to filter, down-sample, segment, register, extract and reconstruct the surface of the target point cloud. Secondly, a Directional Positioning Continuous Segmentation Algorithm is introduced to identify key regions of the goat's body for precise segmentation. Finally, body dimensions are calculated from the identified key regions. The average error rates of various measurements, including body height, body oblique length, chest girth, chest depth, chest width, abdominal girth, abdominal depth, and abdominal width are 1.30 %, 2.73 %, 1.89 %, 2.43 %, 3.37 %, 2.11 %, 2.94 %, and 2.59 %, respectively. This algorithm provides a scientific and accurate way to measure the key body dimensions of goats. This algorithm demonstrates generalisability and robustness, being unaffected by environmental conditions or the diverse postures of the goats. This automated method for measuring goat body dimensions offers an efficient means of collecting phenotypic data during goat fattening, providing a convenient approach to precise and high-throughput body dimension assessments in goat breeding.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104214"},"PeriodicalIF":4.4,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144279294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A rapid calibration method for the discrete element model of straw fodder particle mixtures based on the UVE-PLS-GD algorithm 基于UVE-PLS-GD算法的秸秆饲料颗粒混合物离散元模型快速标定方法

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-13 DOI: 10.1016/j.biosystemseng.2025.104193

Ziqing Xiao , Haiqing Tian , Chunxiang Zhuo , Kai Zhao , Yang Yu , Qiaofei Mu , Xiaoyu Xue

{"title":"A rapid calibration method for the discrete element model of straw fodder particle mixtures based on the UVE-PLS-GD algorithm","authors":"Ziqing Xiao , Haiqing Tian , Chunxiang Zhuo , Kai Zhao , Yang Yu , Qiaofei Mu , Xiaoyu Xue","doi":"10.1016/j.biosystemseng.2025.104193","DOIUrl":"10.1016/j.biosystemseng.2025.104193","url":null,"abstract":"<div><div>The accuracy of parameter settings for straw fodder particle mixtures, which include straw rind, pith, bracts, and dust, is crucial for in-depth research on the mechanical behaviours of straw, such as motion, collision, and separation between particles. This study proposes a method for the rapid calibration of the discrete element model for straw fodder particle mixtures, based on the Uninformative Variable Elimination-Partial Least Squares-Gradient Descent (UVE-PLS-GD) algorithm. The UVE-PLS-GD algorithm and traditional experimental methods were used to calibrate the numerical simulation parameters of individual particles in the mixture, followed by comparative validation. The experimental results indicated that both methods identified the factors significantly affecting the repose angle, in the following order: JKR surface energy coefficient between bracts and rind, bracts and pith, pith and rind, pith and pith, rind and rind, and bracts and dust. The relative errors between the repose angles obtained from the numerical simulations using the UVE-PLS-GD algorithm and traditional experimental methods and those from the physical experiments were 0.37 % and 0.45 %, respectively, verifying the accuracy of the calibrated numerical simulation parameters. Among them, the parameters obtained using the UVE-PLS-GD algorithm resulted in the smallest error, and the optimal combination of significant factor parameters were 0.1337, 0.0862, 0.1339, 0.1238, 0.1254, and 0.1186. This study demonstrated that the UVE-PLS-GD algorithm can significantly improve both the accuracy and speed of calibrating the discrete element model for particles, and the calibrated numerical simulation parameters can provide data support for the motion and separation of mixtures.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104193"},"PeriodicalIF":4.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Regional airflow velocity control to meet the diverse requirements of unevenly distributed maize threshing mixtures 区域气流速度控制，以满足玉米脱粒混合物分布不均匀的多样化要求

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-13 DOI: 10.1016/j.biosystemseng.2025.104210

Meng Zhang , Chao Cheng , Jun Fu , Zhi Chen , Luquan Ren

{"title":"Regional airflow velocity control to meet the diverse requirements of unevenly distributed maize threshing mixtures","authors":"Meng Zhang , Chao Cheng , Jun Fu , Zhi Chen , Luquan Ren","doi":"10.1016/j.biosystemseng.2025.104210","DOIUrl":"10.1016/j.biosystemseng.2025.104210","url":null,"abstract":"<div><div>Cleaning is a critical operation in maize production. Uneven lateral distribution of maize threshing mixture on the cleaning sieve surface is a common issue, which can lead to material overload or underload in certain regions, severely impacting the quality of the cleaning operation. This paper designs a combined cleaning fan, consisting of three fans that can independently control their speed, achieving precise airflow control over three regions of the cleaning sieve surface. A monitoring device is designed to detect the load distribution of maize threshing mixture in real-time, providing signals for the control of the combined fan. Material load, vibration frequency of the cleaning sieve, and sieve opening are used as the input layer, while fan speed serves as the output layer. A Gradient Boosting Regression (GBDT) fan speed prediction model is established to provide a data model for the precise control of the combined fan. A control system for the combined fan is developed, adjusting the fan speed in real-time based on model calculations. Cleaning performance tests showed that the combined fan control system precisely adjusted fan speed according to changes in material load, enabling differentiated operations for unevenly distributed threshing mixture, thereby achieving lower loss rates and impurity levels. Compared to traditional fans, the combined fan demonstrated superior operational performance. The combined cleaning fan improved airflow mismatch caused by uneven threshing mixture distribution, significantly enhancing maize cleaning performance. It also provides a valuable reference for the cleaning operations of other crops and the intelligent development of agricultural machinery.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104210"},"PeriodicalIF":4.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mechanisation of ring-furrow fertiliser application for orchards: A multi-segment arc trajectory and its control method 果园环沟施肥机械化：多段弧线轨迹及其控制方法

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-12 DOI: 10.1016/j.biosystemseng.2025.104213

Xudong Li , Xinhua Zhu , Jiahan Liang , Zhengyang Zhu , Binghui Li , Huiqing Guo

{"title":"Mechanisation of ring-furrow fertiliser application for orchards: A multi-segment arc trajectory and its control method","authors":"Xudong Li , Xinhua Zhu , Jiahan Liang , Zhengyang Zhu , Binghui Li , Huiqing Guo","doi":"10.1016/j.biosystemseng.2025.104213","DOIUrl":"10.1016/j.biosystemseng.2025.104213","url":null,"abstract":"<div><div>Ring-furrow fertiliser placement is a precise near-root application method for orchards. However, it is still unclear what kind of fertiliser application trajectory is more conducive to precise near-root fertiliser placement and smooth mechanical operation and by what means it can be precisely controlled. Therefore, this study proposed a fertiliser application method based on a multi-segment arc trajectory that was evaluated by the accuracy of near-root fertiliser placement, and a root pruning coefficient. A control model for the transverse motion of the furrow opener was constructed and a novel method of segmental proportional-integral-derivative (PID) control was adopted to control the electro-hydraulic system for the ring-furrow trajectory. The results indicated that the multi-segment arc trajectory had outstanding advantages, with a smooth furrowing speed without abrupt changes, a fertiliser-root contact coefficient more than 1.5 times that of the traditional straight furrow trajectory, and a root pruning coefficient not exceeding 8.13 %. Field tests showed that the correlation coefficients between actual and target displacement curves of the furrow opener's transverse telescopic motion were >0.99, with the root mean square error (RMSE) of 0.010 m and 0.011 m, respectively, for the plant spacing of 1.3 m and 2.3 m. The control system enabled precise control of the multi-segment arc trajectory for accurate near-root fertiliser placement with smooth mechanical operation and good adaptability to plant spacings and heavy-load conditions. The study laid a theoretical foundation for developing mechanised ring-furrow fertiliser application technology in orchards.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104213"},"PeriodicalIF":4.4,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimation of tunnel fan operating conditions for a laying hen house based on the ventilation resistance characteristics 基于通风阻力特性的蛋鸡鸡舍隧道风机运行工况估算

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-11 DOI: 10.1016/j.biosystemseng.2025.104194

Zhihao Zhang , Yang Wang , Baoming Li , Haiqing Peng , Hao Zhu

{"title":"Estimation of tunnel fan operating conditions for a laying hen house based on the ventilation resistance characteristics","authors":"Zhihao Zhang , Yang Wang , Baoming Li , Haiqing Peng , Hao Zhu","doi":"10.1016/j.biosystemseng.2025.104194","DOIUrl":"10.1016/j.biosystemseng.2025.104194","url":null,"abstract":"<div><div>Tunnel-ventilated laying houses need adequate ventilation rates to abate heat stress in hot climates. However, due to the underestimation of the ventilation resistance caused by the caged-hen occupied zone (COZ), the differential static pressure (DSP) of fans determined empirically is lower than the actual value, resulting in insufficient ventilation rate in the laying house. In this study, field measurements of the ventilation rate and DSP were conducted with various operating fans in a commercial layer house. A ventilation resistance curve was developed according to the results of computational fluid dynamics (CFD) simulations on the DSP distribution. The ventilation rate was estimated by the number of operating fans, resistance curve and fan performance curve. When the number of operating fans increased from 16 to 24, the fan ventilation rate decreased by 24.56 %, and the fan DSP increased from 41.6 to 67.7 Pa. The resistance caused by COZ contributed more than 60 % to the fan DSP. The DSP distribution near the fan was not uniform. The measured fans and fan DSP measuring point were in the low DSP area, resulting in the predicted ventilation rate being lower than the measured ventilation rate. The error of ventilation rate predicted by the in situ fan performance curve (E 3.47 %–6.51 %; RMSE 8.7) was higher than that predicted by the designed fan performance curve (E 0.77 %–4.72 %; RMSE 4.49). This study provides a methodological basis for accurately developing the ventilation resistance curve of the tunnel ventilated laying house.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104194"},"PeriodicalIF":4.4,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Method for estimating single-leaf photosynthesis in crops considering few-shot learning and uncertainty prediction 基于少次学习和不确定性预测的作物单叶光合作用估算方法

IF 4.4 1区农林科学

Biosystems Engineering Pub Date : 2025-06-10 DOI: 10.1016/j.biosystemseng.2025.104212

Miao Lu , Haoling Liu , Huimin Li , Yongxia Yang , Zhangtong Sun , Pan Gao , Jin Hu

{"title":"Method for estimating single-leaf photosynthesis in crops considering few-shot learning and uncertainty prediction","authors":"Miao Lu , Haoling Liu , Huimin Li , Yongxia Yang , Zhangtong Sun , Pan Gao , Jin Hu","doi":"10.1016/j.biosystemseng.2025.104212","DOIUrl":"10.1016/j.biosystemseng.2025.104212","url":null,"abstract":"<div><div>Accurate and efficient assessment of single-leaf photosynthetic rate (<em>A</em><sub>L</sub>) is essential for applications in crop yield assessment, stress perception, and biological breeding. However, existing <em>A</em><sub>L</sub> prediction methods typically require extensive training data and often rely on point estimation, which poses challenges for few-shot learning and high-reliability predictions. To alleviate this dilemma, a comprehensive <em>A</em><sub>L</sub> estimation model was developed in this study. Using the combination of meta-learning (ML) and multilayer perceptron (MLP), the model initially constructed a base prediction model and then fine-tuned it for unseen tasks. Compared to the current popular methods, the proposed model achieved higher prediction accuracy with fewer training samples. Introducing only about 5 % of new samples from the dataset was sufficient to achieve satisfactory predictive performance. Additionally, this study introduced quantile regression (QR) method to obtain the 95 % confidence interval of <em>A</em><sub>L</sub>, mitigating the limitations of high reliability in predictions. Finally, by employing Gaussian kernel density estimation (GKDE) to derive the probability density under each environmental condition, we constructed an <em>A</em><sub>L</sub> prediction model with reliable uncertainty estimation capabilities. Through detailed validation using multiple datasets from various species and interpretability analysis, the proposed method has proven to be universally applicable and reasonable. This research highlights the high generalization ability of ML-MLP for unseen datasets and extends <em>A</em><sub>L</sub> predictions from point estimation to interval prediction by QR-GKDE, thereby facilitating the researches on crop cultivation. This research significantly enhances precision agriculture by providing robust methodologies for crop monitoring and stress perception.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"257 ","pages":"Article 104212"},"PeriodicalIF":4.4,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0