Biosystems Engineering最新文献

{"title":"Discrete element modelling and parameter calibration method for a flexible wheat plant with breakable grains","authors":"Yongkang Zhu ,&nbsp;Yanchun Yao ,&nbsp;Xibin Li ,&nbsp;Jiangdong Xu ,&nbsp;Jida Wu ,&nbsp;Duanyang Geng ,&nbsp;Bo Zhao","doi":"10.1016/j.biosystemseng.2026.104405","DOIUrl":"10.1016/j.biosystemseng.2026.104405","url":null,"abstract":"<div><div>To address the limited accuracy of biomechanical representation in Discrete Element Method (DEM) models, this study proposes a discrete element modelling and parameter calibration method for a flexible wheat plant with breakable grains. First, the shape and dimensional parameters of the wheat plant were measured, and a flexible wheat plant model with breakable grains was constructed using the Meta-particle model and the Bonding V2 model. Next, the ranges of the intrinsic parameters, interaction parameters, and bonding parameters of the wheat plant were determined based on mechanical property tests. Parameter calibration was conducted using angle of repose (AOR) tests, grain compression tests, straw three-point bending tests, and tensile tests of wheat ears, in combination with response surface methodology. Finally, drum rotation tests and simulations, as well as impact breakage tests and DEM-MBD co-simulations, were conducted. By comparing the test and simulation results, the accuracy of the DEM model was verified. In the drum rotation test, the relative error between the simulated and measured dynamic angles of repose of the grain-short straw mixture was within 6%. In the impact breakage test, both the simulated and physical wheat straw underwent bending fracture, and the simulated values of the unthreshed rate and breakage rate of the wheat grains were close to the measured values. Validation tests demonstrate that the proposed modelling and parameter calibration method was effective. This study provides a reference for developing an accurate DEM model of a flexible wheat plant that realistically reflects the breakable characteristics of the grains.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104405"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171778","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}

{"title":"Divergent drivers of long-term trends vs. acute outbreaks in harmful algal blooms","authors":"Xianglong Dai ,&nbsp;Siyuan Zhang ,&nbsp;Yinglan A ,&nbsp;Guoqiang Wang ,&nbsp;Jin Wu ,&nbsp;Guangwen Ma ,&nbsp;Kaiji Li ,&nbsp;Shuyu Zeng","doi":"10.1016/j.biosystemseng.2026.104402","DOIUrl":"10.1016/j.biosystemseng.2026.104402","url":null,"abstract":"<div><div>Harmful algal blooms (HABs) have become an environmental issue of global concern due to their wide distribution and sudden outbreak. The existing research mainly focuses on the attribution of the long-term trend of algal blooms, in which eutrophication has been considered as the main driving factor. However, this trend-based analysis framework does not reliably predict the occurrence of specific water blooms, largely due to insufficient explanation of the interaction mechanism between persistent drivers and event triggers. In this study, Hulun Lake was taken as an example to distinguish the red tide driving factors at annual, monthly and daily scales to clarify the interaction between persistence maintenance factors and short-term meteorological trigger factors. On an annual scale, HABs have shifted from localised, low-frequency events to widespread, high-frequency outbreaks, peaking in 2022. Water blooms mainly occurred in July–August, concentrated in the semi-enclosed southwest and northern bays. Total nitrogen and precipitation are key long-term predictors, reflecting the role of eutrophication and hydrological variability. On the monthly scale, HABs were divided into four types according to frequency and severity. This classification shows that meteorological activation and nutrient structure together determine the bloom pattern. HABs are more likely to occur under ' warm, humid, calm and nutrient-rich ' conditions. The key thresholds are: air temperature &gt;19.7 °C (Interquartile coefficient of variation, IQRCV = 9 %), relative humidity &gt;61 %(IQRCV = 21 %), wind speed &lt;3.2 m/s(IQRCV = 37 %). On the daily scale, the formation of HABs is driven by cumulative meteorological effects. When 7-day air temperature &gt;103 °C (IQRCV = 77 %), relative humidity &gt;380 % (IQRCV = 77 %), wind speed &lt;3.0 m/s (IQRCV = 77 %), the risk is further increased. These findings support a multi-scale strategy that combines watershed nutrient control with real-time meteorological monitoring.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104402"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146076945","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}

{"title":"Adaptive synchronous sliding mode levelling system for combine harvester considering track circumference: Co-simulation and experimental verification","authors":"Jinpeng Hu ,&nbsp;Maolin Shi ,&nbsp;Tianle Ma ,&nbsp;Peng Liu ,&nbsp;Xiaoyu Chai ,&nbsp;Guangqiao Cao ,&nbsp;Lizhang Xu","doi":"10.1016/j.biosystemseng.2026.104396","DOIUrl":"10.1016/j.biosystemseng.2026.104396","url":null,"abstract":"<div><div>To address variable track tension, poor cylinder synchronisation, and suboptimal chassis levelling in tracked combine harvesters in hilly terrain, a sliding mode synchronisation levelling control strategy is proposed that integrates theoretical track circumference (TTC) constraints with adaptive cylinder synchronisation control. The hydraulic circuit and operating principle of the four-point levelling chassis are analysed, and a mathematical model is developed to describe TTC variation during levelling. Particle Swarm Optimisation–Backpropagation (PSO-BP) surrogate models are established to capture the relationships among cylinder displacement, tension pulley position, levelling angles, and TTC. Based on these surrogates, the tension pulley position and cylinder extensions are optimised by formulating a constrained objective function and solving it with the Grey Wolf Optimiser (GWO). An adaptive synchronisation sliding mode controller (ASSMC) is then proposed, in which a disturbance observer estimates disturbances in the nonlinear hydraulic system and the synchronisation error is incorporated as a compensation term to improve tracking accuracy. Co-simulation results showed that the proposed strategy reduced levelling time to 1.8 s on a 5° lateral slope and 2.1 s on a 5° longitudinal slope. The cylinder synchronisation error remained below 0.52 mm, with negligible overshoot in cylinder displacement, outperforming conventional PID control. Meanwhile, TTC was maintained within 4580–4600 mm under all tested scenarios. Field tests further confirmed fast and accurate levelling, with body inclination maintained within ±0.2° and track tension satisfying the TTC constraint throughout, validating the effectiveness of the proposed system.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104396"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071123","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}

{"title":"Pre-visual soilborne common root rot disease detection in wheat using UAV multispectral imagery and Deep Neural Networks","authors":"Yiyi Xiong ,&nbsp;Cheryl McCarthy ,&nbsp;Jacob Humpal ,&nbsp;Cassandra Percy","doi":"10.1016/j.biosystemseng.2026.104403","DOIUrl":"10.1016/j.biosystemseng.2026.104403","url":null,"abstract":"<div><div>Common Root Rot (CRR), caused by <em>Bipolaris sorokiniana</em>, is a prevalent soilborne disease that severely impacts wheat production in Australia due to its difficult management. This study is the first to explore the potential of UAV-based multispectral imaging technologies for pre-visual soilborne CRR disease detection and severity classification in wheat across three seasons. Field multispectral imagery data were analysed using five algorithms: Logistic Regression (LR), Random Forest (RF), Support Vector Machines (SVM), eXtreme Gradient Boosting (XGBoost) and Deep Neural Networks (DNN). A Pre-trained DNN model developed from two seasons and validated in a third season achieved 93% accuracy in distinguishing CRR-inoculated wheat at the Z3 stem elongation stage and 79% overall accuracy. Moreover, the pre-trained DNN model classified three severity levels of CRR infection with 67% overall accuracy, which improved to 75% during Z4-Z6 (booting to anthesis) stages. Important Vegetation Indices for CRR disease detection and severity classification were chlorophyll- and RedEdge-based indices (PlantArea, Green, ExG, SCCCI and NDRE). The earliest CRR disease detection was achieved at the Z3 stage, with Z4-Z6 stages proving effective for severity classification. With further refinement, the pre-trained DNN model demonstrated effective validation for third-season disease detection, but not for severity classification. These findings could enable growers to improve field scouting by reducing reliance on labour-intensive manual scouting and subjective assessments, allowing them to adopt more effective disease management strategies and ultimately contributing to more sustainable wheat production.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104403"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171387","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}

{"title":"Teat-Track: A real time tracking method for piglet teat counting","authors":"Wenjie Huang ,&nbsp;Zhenfang Wu ,&nbsp;Ling Yin ,&nbsp;Qiong Huang ,&nbsp;Sumin Zhang ,&nbsp;Delin Mo ,&nbsp;Gengyuan Cai","doi":"10.1016/j.biosystemseng.2026.104413","DOIUrl":"10.1016/j.biosystemseng.2026.104413","url":null,"abstract":"<div><div>Mammary traits in sows significantly affect milk production and piglet survival, making them key indicators in breeding selection. However, manual counting of teats in adult sows is often inefficient and unreliable due to factors such as occlusion, staining, and inconsistent lighting in abdominal imagery. As piglet teat patterns remain relatively stable from birth to maturity, this study proposes a practical, tracking-based approach for automatic teat counting and morphological assessment in piglets. Abdominal videos were acquired on a piglet care platform and analysed using a lightweight object detection model to locate and estimate teat count. To enhance accuracy, a three-stage trajectory association strategy, referred to as Teat-Track, was implemented. Adapted from ByteTrack, this method addresses missed detections caused by occlusion from the umbilical cord and motion blur. This approach reduces detection fluctuations and improves counting stability. Experimental results demonstrated a counting accuracy of 92.2% with a 95% confidence interval of [86.4%, 98.0%], and an average counting time of 1.83 s per video (ranging from 0.8 to 4.6 s). The average per frame processing time was 11.4 ms, confirming its suitability for real-time deployment. Additionally, morphological features such as the standard deviation of teat spacing and the ratio of paired teats were extracted from high-confidence frames. These metrics provide a basis for preliminary phenotypic assessment, offering practical support for automated trait recording in early-stage breeding programmes.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104413"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171394","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}

{"title":"Inverse identification of equivalent mechanical parameters of agricultural materials using NSGA-II and multi-objective optimisation","authors":"Liming Qin ,&nbsp;Zheng Xu ,&nbsp;Yingjie Li ,&nbsp;Wangyi Ye ,&nbsp;Jingbin Li","doi":"10.1016/j.biosystemseng.2026.104404","DOIUrl":"10.1016/j.biosystemseng.2026.104404","url":null,"abstract":"<div><div>Accurate modelling of the impact and rebound behaviour of agricultural materials is critical for numerical simulation and engineering design of postharvest handling systems. However, the strong nonlinearity and condition dependence of impact responses in biological materials make conventional parameter calibration methods inefficient and prone to condition-specific bias. This study proposes a multi-objective inverse identification framework for estimating equivalent mechanical parameters of agricultural materials under free-fall impact conditions by integrating explicit dynamic finite element simulation, machine learning–based surrogate modelling, and evolutionary optimisation. Using broccoli as a representative flexible agricultural material, drop–rebound experiments were conducted at multiple heights to obtain rebound height and coefficient of restitution (COR). An explicit finite element model with an equivalent linear elastic material description and global damping was established, and Latin hypercube sampling was applied to generate simulation datasets. eXtreme Gradient Boosting (XGBoost) surrogate models were trained to efficiently approximate the nonlinear relationships between material parameters, drop height, and impact responses. A three-objective inverse problem was formulated to simultaneously minimise mean prediction error, constrain extreme deviations, and enforce cross-height robustness. The non-dominated sorting genetic algorithm II (NSGA-II) was employed to obtain Pareto-optimal parameter sets, with non-dominated sorting genetic algorithm III (NSGA-III) and Multi-objective evolutionary algorithm based on decomposition (MOEA/D) used for comparison. Results show that NSGA-II achieves superior Pareto front coverage and convergence stability. Sensitivity analysis reveals that the damping coefficient dominates error control, while the elastic modulus primarily constrains high-impact responses. Validation using samples with different masses and independent literature data confirms good robustness and transferability of the proposed framework.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104404"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171762","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}

{"title":"A temporally transferrable approach for quantifying crop residue cover: linking deep learning of UAV images with satellite-based spectral modelling","authors":"Jun Zhang ,&nbsp;Na Dong ,&nbsp;Jiamin Ma ,&nbsp;Hongguang Cai ,&nbsp;Pu Shi","doi":"10.1016/j.biosystemseng.2026.104418","DOIUrl":"10.1016/j.biosystemseng.2026.104418","url":null,"abstract":"<div><div>Accurate monitoring of crop residue cover (CRC) dynamics provides vital information for assessing the impact of diverse agricultural management practices on soil health. However, conventional field-based and remote sensing surveys struggle with insufficient spatial and temporal coverage to capture large-scale CRC dynamics. This study developed a temporally transferable CRC mapping approach, by integrating deep learning of unmanned aerial vehicle (UAV) images with Sentinel-2 multispectral modelling. A modified U-Net image segmentation algorithm with a ResNet-50 backbone was trained to generate multi-temporal CRC ground observations across spring (2024-2025) and autumn (2024) seasons in an agricultural region of northeast China. Independent test showed satisfactory segmentation performance (mPA = 92.02%), outperforming the traditional OTSU method by more than 30%. UAV-derived CRC ground reference was then linked with Sentinel-2 surface reflectance to develop a spectra-based predictive model using partial least squares regression. The model, trained on spring 2024 observations, demonstrated robust transferability, accurately predicting CRC in autumn 2024 (R² = 0.85, RMSE = 12.64%) and spring 2025 (R² = 0.70, RMSE = 10.05%). Shortwave infrared bands (B11, B12) were identified as key predictors, aligning with cellulose/lignin absorption features in crop residues. Multitemporal CRC mapping revealed distinct residue retention patterns between conventional (abrupt clearance) and conservation tillage (persistent coverage). This work establishes a physically meaningful, transferable framework for field-level tillage classification and large-scale monitoring of conservation agricultural practices.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104418"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171760","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}

{"title":"Potential for automatic oestrus detection in grazing cattle through the integration of Global Navigation Satellite System tracking and Bluetooth proximity logging","authors":"Manuel J. García García ,&nbsp;Eseró Padrón Tejera ,&nbsp;M. Pilar Torralbo Muñoz ,&nbsp;Dolores C. Pérez Marín ,&nbsp;Mark Trotter ,&nbsp;Anita Z. Chang ,&nbsp;Francisco Maroto Molina","doi":"10.1016/j.biosystemseng.2026.104400","DOIUrl":"10.1016/j.biosystemseng.2026.104400","url":null,"abstract":"<div><div>Achieving a profitable and sustainable beef cattle operation requires an appropriate reproductive management. Oestrus detection is essential for optimising artificial insemination and/or identifying non-performing cows, amongst other benefits. Traditionally, oestrus detection has relied on visual observation, but this practice poses several challenges, particularly in extensive grazing systems. The aim of this study was to evaluate a sensor system combining GNSS tracking and Bluetooth proximity logging, based on signal strength, to automatically detect oestrus in grazing cows. Fifty-three heifers and three sires were fitted with GNSS collars and Bluetooth ear tags, respectively, and several oestrus indicators were calculated from the data collected by sensors over a period of ten weeks. These indicators included the number of cow-sire proximity records, the signal strength of these records, the time interval between successive records and the spatial characteristics of cow-sire interactions. Several indicators showed significant differences between the day of oestrus and the 14 days before and after oestrus. The number of cow-sire proximity interactions recorded by the system tripled on the day of oestrus. Minimum value of signal strength indicator and time between successive records for the same cow were lower on the day of oestrus. The trajectories defined by the GNSS coordinates of the sire(s) when recording cow proximity were longer (distance and duration) and tended to be less straight on the day of oestrus. A tendency to explore a greater area on the day of oestrus was also observed. The time resolution of data provided by sensors (30-min epochs) may prevent the identification of significant differences in some of the studied indicators. Also, the effects of cow-to-sire ratio and paddock configuration deserve further investigation. Nevertheless, the integration of data from GNSS tracking and Bluetooth proximity logging proved to be useful for the detection of oestrus in grazing cattle.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104400"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385517","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}

{"title":"Maize yield estimation from Sentinel-2 multi-temporal imagery and CANbus data integration: a non-parametric regression approach","authors":"G. Stefanescu Miralles ,&nbsp;A. Biglia ,&nbsp;D. Ricauda Aimonino ,&nbsp;M. Mattetti ,&nbsp;P. Gay ,&nbsp;L. Comba","doi":"10.1016/j.biosystemseng.2026.104401","DOIUrl":"10.1016/j.biosystemseng.2026.104401","url":null,"abstract":"<div><div>In precision agriculture, the assessment and estimation of key crop parameters are crucial aspects for the optimisation of input usage and, as an ultimate goal, for the improvement of yield quality and quantity. In this context, a reliable prediction of yield by remotely sensed imagery is an enabling technology for optimisation. In this work, an innovative method for estimating yield in maize cultivation is presented, which exploits multi-temporal and multispectral Sentinel-2 satellite imagery with supervised Machine Learning (ML) techniques. For model training and validation, yield ground truth experimental data from combine harvesters was used, enabling the yield estimation at sub-field scale. The investigation, which was conducted on five case study plots, involved a preliminary comparison of four ML-based algorithms, trained with raw spectral bands. An assessment of the effect of the training dataset on the yield prediction accuracy was then performed. A set of Vegetation Indices (VIs) and Two Band Indices (TBIs) was also considered for this purpose. Finally, a multi-temporal analysis was conducted, in which the temporal evolution of crop spectral data over the maize growing season was exploited using imageries acquired in different epochs. The obtained results proved that an accurate estimation of maize yield can be reached using a Gaussian process regression model, exploiting multi-temporal features directly provided by the raw spectral bands. The model showed a high accuracy in the estimation of maize yield, even when fed with data acquired during only the maize vegetative phase, thus proving its capacity as a prediction tool.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104401"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171761","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}

{"title":"From hatch to hen: A lifecycle perspective on acoustic-based poultry behaviour and health monitoring","authors":"Hao Zhou ,&nbsp;Qibing Zhu ,&nbsp;Min Huang ,&nbsp;Tomas Norton","doi":"10.1016/j.biosystemseng.2026.104421","DOIUrl":"10.1016/j.biosystemseng.2026.104421","url":null,"abstract":"<div><div>This review presents the first comprehensive synthesis of poultry acoustic monitoring research from a full lifecycle perspective, spanning incubation and the chick stage, rapid growth, and adulthood and reproduction. By situating sound-based monitoring within biological and managerial transitions, it provides stage-specific insights into vocal behaviour, health indicators, and welfare-related acoustic expressions. Sound as a non-contact real-time signal offers clear advantages for precision livestock management. Unlike previous technology- or disease-oriented reviews, this study integrates research from 2000 to 2025 into a unified lifecycle framework for cross-stage comparison. The findings show a shift from individual health assessment in early life to flock-level behaviour and welfare monitoring in later stages, while accurate individual recognition remains challenging. The review compares the evolution of feature extraction, modelling approaches, and deployment strategies across stages, showing that traditional machine learning remains dominant, whereas deep learning is limited by imbalanced lifecycle data, restricted species- and breed-level representation, and high heterogeneity of real-farm acoustic environments. Lifecycle-dependent differences in acoustic features, such as frequency distribution and energy, monitoring targets from individual health to flock welfare and productivity, and analytical strategies from feature-based to deep learning and multimodal approaches highlight the need for unified technical and biological benchmarks. Finally, the review summarises key challenges in methodology, species and breed diversity, and practical deployment, and outlines future directions for standardised, scalable, and interpretable acoustic monitoring frameworks. By establishing a lifecycle-oriented foundation, this work links biological development with technological advances and supports stage-specific and welfare-driven applications in precision poultry farming.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"264 ","pages":"Article 104421"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385516","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}