The impacts of climate change on agricultural production are becoming more severe, leading to increased food insecurity. Adopting more progressive methodologies, like smart farming instead of conventional methods, is essential for enhancing production. Consequently, livestock production is swiftly evolving towards smart farming systems, propelled by rapid advancements in technology such as cloud computing, the Internet of Things, big data, machine learning, augmented reality, and robotics. A Digital Twin (DT), an aspect of cutting-edge digital agriculture technology, represents a virtual replica or model of any physical entity (physical twin) linked through real-time data exchange. A DT conceptually mirrors the state of its physical counterpart in real time and vice versa. DT adoption in the livestock sector remains in its early stages, revealing a knowledge gap in fully implementing DTs within livestock systems. DTs in livestock hold considerable promise for improving animal health, welfare, and productivity. This research provides an overview of the current landscape of digital transformation in the livestock sector, emphasizing applications in animal monitoring, environmental management, precision agriculture, and supply chain optimization. Our findings highlight the need for high-quality data, comprehensive data privacy measures, and integration across varied data sources to ensure accurate and effective DT implementation. Similarly, the study outlines their possible applications and effects on livestock and the challenges and limitations, including concerns about data privacy, the necessity for high-quality data to ensure accurate simulations and predictions, and the intricacies involved in integrating various data sources. Finally, the paper delves into the possibilities of digital twins in livestock, emphasizing potential paths for future research and progress.

A lightweight strawberry detection and localization algorithm plays a crucial role in enabling the harvesting robot to effectively harvest strawberries. The YOLO model has often been used in strawberry fruit detection for its high accuracy, speed, and robustness. However, some challenges exist, such as the requirement for large model sizes, high computation operation, and undesirable detection. Therefore, the lightweight improved YOLOv5s-CGhostnet was proposed to enhance strawberry detection. In this study, YOLOv5s underwent comprehensive model compression with Ghost modules GCBS and GC3, replacing modules CBS and C3 in the backbone and neck. Furthermore, the default GIOU bounding box regressor loss function was replaced by SIOU for improved localization. Similarly, CBAM attention modules were added before SPPF and between the up-sampling and down-sampling feature fusion FPN–PAN network in the neck section. The improved model exhibited higher mAP@0.5 of 91.7% with a significant decrement in model size by 85.09% and a reduction in GFLOPS by 88.5% compared to the baseline model of YOLOv5. The model demonstrated an increment in mean average precision, a decrement in model size, and reduced computation overhead compared to the standard lightweight YOLO models.

The optimal indoor environment is associated with comfortable temperatures along with favorable indoor air quality. One of the air pollutants, particulate matter (PM), is potentially harmful to animals and humans. Most farms have monitoring systems to identify other hazardous gases rather than PM due to the sensor cost. In recent decades, the application of environmental monitoring systems based on Internet of Things (IoT) devices that incorporate low-cost sensors has elevated extensively. The current study develops a low-cost air quality monitoring system for swine buildings based on Raspberry Pi single-board computers along with a sensor array. The system collects data using 11 types of environmental variables along with temperature, humidity, CO₂, light, pressure, and different types of gases, namely PM₁, PM_2.5, and PM₁₀. The system is designed with a central web server that provides real-time data visualization and data availability through the Internet. It was tested in actual pig barns to ensure stability and functionality. In addition, there was a collocation test conducted by placing the system in two different pig barns to validate the sensor data. The Wilcoxon rank sum test demonstrates that there are no significant differences between the two sensor datasets, as all variables have a p-value greater than 0.05. However, except for carbon monoxide (CO), none of the variables exhibit correlation exceeding 0.5 with PM concentrations. Overall, a scalable, portable, non-complex, low-cost air quality monitoring system was successfully developed within a cost of USD 94.

Monitoring the energy inputs and outputs in pig production systems is crucial for identifying potential imbalances and promoting energy efficiency. Therefore, the objective of this study was to measure the energy input, output, and losses during the growing–finishing phase of pigs from 1 September to 1 December 2023. A Livestock Environment Management System (LEMS) was used to measure the temperature, humidity, airflow, and water consumption levels inside the barn, and a load cell was used to measure the body weight of pigs. Furthermore, a bomb calorimetric test was conducted to measure the energy content of pigs’ manure. While calculating energy balance in the experimental barn, it was found that energy from feed and water contributed approximately 81% of the total input energy, while the remaining 19% of energy came from electrical energy. Regarding output energy, manure, and body weight accounted for about 69%, while around 31% was lost due to pig activities, maintaining barn temperature and airflow, and illuminating the barn. In conclusion, this study suggested methods to calculate energy balance in pig barns, offering valuable insights for pig farmers to enhance their understanding of input and output energy in pig production.

Pork accounts for 34% of global meat consumption, following poultry and beef. Intensive pig farming has expanded to meet increasing demand, but space constraints and poor environmental conditions can negatively affect pig welfare. This study aimed to investigate pigs’ spatial preferences in response to environmental factors in an experimental pig barn. Six 60-day-old Yorkshire pigs were observed for 60 days. Indoor temperature (IT), relative humidity (IRH), and CO₂ concentration (ICO₂) were measured hourly, and pig positions were recorded using an RGB 2D-IP camera. Pearson correlation analysis was performed using SPSS. IT ranged from 14.3 °C to 25.1 °C, IRH from 78.9% to 96.5%, and ICO₂ from 1038 to 1850 ppm. A strong negative correlation was found between IT and IRH (r = −0.89), while IT and ICO₂ were uncorrelated (r = −0.01). Pigs showed a clear preference for sections with lower IT, supporting previous findings on thermal preference. Structural features, such as two-wall enclosures, also influenced stay frequency. These results suggest that optimizing barn structure and improving ventilation and manure management can support thermal comfort and improve welfare in intensive pig farming systems.