Global positioning system

GPS is a satellite network-based positioning/navigation system which reveals positional information via the latitude, longitude and elevation of a location. Such information collected by GPS receivers facilitates high-accuracy field mapping for farmers and researchers on boundaries, water bodies and infested/problematic areas, as well as understanding of the relationship and interactions with other attributes within and outside the boundaries of given fields. Site-specific, precision application of water, nutrients and chemicals such as pesticides and herbicides are also made possible and efficient for increased productivity at reduced costs (Ghosh and Kumpatla, Reference Ghosh and Kumpatla2022).

Having established a geofence by defining a closed polygon referring to a geographic area on earth, the real-time positioning of an animal can be tracked/monitored with the use of a satellite navigation device, which is commonly referred to as a GPS receiver. Alerts can be triggered by a location-aware device whenever the animal crosses the geofence (Ilyas and Muneer, Reference Ilyas and Muneer2020). Radio-frequency identification, wireless sensor networks and the low-power wide area network are other technologies that can be used for geofencing in livestock management (Ilyas and Muneer, Reference Ilyas and Muneer2020). UAVs are great enhancements for real-time livestock monitoring (Ilyas and Muneer, Reference Ilyas and Muneer2020).

Geophysics

Geophysics involves generation of data/information on features and conditions beneath the surface of the earth via surface measurement of relevant physical quantities. Near surface geophysics (typically within a depth range of 0–2 m) has been shown to have present and potential useful applications in agriculture; including site infrastructure assessment, environmental investigations and hydrologic monitoring, as well as detection of soil horizons, soil compaction, soil salinity, and mapping of hardpan layer, and soil texture in site-specific agriculture (Allred et al., Reference Allred, Daniels and Ehsani2008; Mohammed et al., Reference Mohammed, El Mahmoudi and Almolhem2022).

Furthermore, groundwater availability and quality assessment, quality/efficiency improvement soil surveys, delineation of spatial changes in soil properties, soil drainage class mapping, soil salinity assessment, determination of clay-pan depth, measurement of micro variability in soil profile horizon depths, estimation of herbicide partition coefficients in soil, identification of subsurface flow pathways, mapping of flood deposited sand depths on farmlands, soil water content determination, soil nutrient monitoring from manure applications, plant root biomass surveying, bedrock depth determination in glaciated landscape with thin soil cover and farm field and golf course drainage pipe detection are applications of geophysics in agriculture (Toushmalani, Reference Toushmalani2010); many of which affect livestock production and management directly or indirectly. Geophysical methods which are being widely used in agriculture include the electrical resistivity tomography, electromagnetic and ground penetrating radar methods; giving rise mostly to depth sections and contour maps.

Peralta et al. (Reference Peralta, Cicore, Marino, Da Silva and Costa2015), using geophysical and other measurements, showed that apparent electrical conductivity (ECa), which favours site-specific management in soils for livestock production, can also serve as a potential pasture yield estimator. They reported high spatial heterogeneity of some of the related soil properties in soils used for livestock production.

Underground water sources can be located for livestock drinking water via geophysical surveys. Geophysical surveys can also be utilized for identifying suitable areas for farm buildings/structures, ponds, pastures, roads, fences, etc., in farm planning/design. Geophysical methods and soil geochemistry can facilitate assessment of nutrient availability/deficiencies, thereby guiding fertilizer application and nutrient supplementation, enhancing proper animal nutrition.

Geographic information systems

Geographic information system (GIS) comprises of tools for the collection, storage and retrieval of data at will, as well as analysing, transforming and manipulating spatial and non-spatial data, and presenting them through intuitive and illustrative maps for specific purposes (Burrough, Reference Burrough1986; Burrough and McDonnell, Reference Burrough and McDonnell1998; Gomiero, Reference Gomiero2013; Soomro, Reference Soomro2015; Delgado et al., Reference Delgado, Vandenberg, Neer and D'Adamo2019). GIS, used along with other technologies such as remote sensing (RS), GPS, AI, computational systems, data analytics and digital technologies has become very crucial in precision farming and sustainable food production; in monitoring crops and implementing efficient and effective management practices towards improving crop and livestock productivity (Kumar et al., Reference Kumar, Karaliya and Chaudhary2017; Ghosh and Kumpatla, Reference Ghosh and Kumpatla2022). GIS and RS have been reported to be efficient for prevention of universal ecological hazards (Dukiya, Reference Dukiya2021; Bimrew, Reference Bimrew2022).

GIS can be used to create a complete livestock geo-database, which can be very useful in providing easy accessibility to information about availability/abundance of different animal species in any location (Senapati et al., Reference Senapati, Paikaray, Das and Swain2016). Geodatabase can also be created for exotic, local and/or cross breeding farms as well as semen stations, frozen semen laboratories, good animal rearing sites, etc. (Senapati et al., Reference Senapati, Paikaray, Das and Swain2016). Also, monitoring and integration of the progress and coverage/extent of implementation of livestock insurance and other programmes can be achieved with the aid of GIS (Senapati et al., Reference Senapati, Paikaray, Das and Swain2016).

GISs and RS tools can be highly valuable in the conservation of AnGRs through habitat mapping, biodiversity assessment as well as monitoring and surveillance of land use that may impact animal habitats (McManus et al., Reference McManus, Hermuche, Paiva, Ferrugem-Moraes, Barros de Melo and Mendes2014, Reference McManus, Hermuche, Paiva, Guimarães, Osmar, Junior and Blackburn2021; Duruz et al., Reference Duruz, Flury, Matasci, Joerin, Widmer and Joost2017). Cringoli et al. (Reference Cringoli, Rinaldi, Musella, Veneziano, Maurelli, Di Pietro, Frisiello and Di Pietro2007) had used GIS to study the spatial structure of livestock (cattle, water buffaloes and sheep) populations to unravel the role of sheep as reservoir for the transmission of cystic echinococcosis to cattle and water buffaloes.

Furthermore, it can help in identifying threats to genetic resources and implementing timely conservation measures (Duruz et al., Reference Duruz, Flury, Matasci, Joerin, Widmer and Joost2017). This information is critical for developing strategies to mitigate these impacts and ensure the long-term survival of vulnerable populations. An example of this is a Web-GIS-based platform called GENMON which is designed to assess the degree of endangerment to farm animal species (Jelokhani-Niaraki and Omidipour, Reference Jelokhani-Niaraki and Omidipour2023).

By leveraging GIS and RS technologies, conservationists can enhance their understanding of AnGRs, optimize conservation strategies and contribute to the sustainable management of biodiversity for future generations.

Remote sensing

RS is a technical process of acquiring information about distant objects via technological means without physical contact. It is very useful for data/information (spectral, temporal and spatial) acquisition, exploration, surveillance, management and inventory in crop and animal production, and other fields, as well as in environmental monitoring and biodiversity conservation (Mancino et al., Reference Mancino, Nolè, Ripullone and Ferrara2014; Senapati et al., Reference Senapati, Paikaray, Das and Swain2016; Guerini et al., Reference Guerini, Kuplich and Quadros2019; Weiss et al., Reference Weiss, Jacob and Duveiller2020). Simultaneous acquisition of data from large areas is made possible with RS (Guerini et al., Reference Guerini, Kuplich and Quadros2019). RS when combined with GPS, GIS and other relevant tools is efficient for soil mapping, crop growth monitoring, estimation of soil moisture and fertility, detection of biotic (pests and diseases) and abiotic (drought and flood) stresses and yield estimation (Ghosh and Kumpatla, Reference Ghosh and Kumpatla2022).

Biomass and pasture evaluation, which can be useful in predicting the beginning or peak of vegetation growth as well as monitor vegetation dynamics via vegetation indices (VIs) such as soil adjusted vegetation index and normalized difference vegetation index, can be determined with the use of RS (Hu et al., Reference Hu, Gou, Tsunekawa, Cheng and Hou2022; Rhodes et al., Reference Rhodes, Perotto-Baldivieso, Reeves and Gonzalez2022). This can also impact large-scale forage production and assessment (da Silva et al., Reference da Silva, Salami, da Silva, Silva, Monteiro and Alba2020; Wijesingha et al., Reference Wijesingha, Astor, Schulze-Brüninghoff, Wengert and Wachendorf2020; Rhodes et al., Reference Rhodes, Perotto-Baldivieso, Reeves and Gonzalez2022).

RS and GIS have been applied to human and animal health in identifying localized species–habitat correlations and employing high spatial resolution satellite data to upscale to regional control programmes (Hay et al., Reference Hay, Packer and Rogers1997; Curran et al., Reference Curran, Atkinson, Foody and Milton2000; Griffiths et al., Reference Griffiths, Lee and Eversham2000). Factors such as habitat fragmentation, patch proximity, species' richness and/or climatic factors influence disease vector distribution and can be represented using remotely sensed imagery (Boone et al., Reference Boone, McGwire, Otteson, DeBaca, Kuhn, Villard, Brussard and St. Jeor2000; Hay, Reference Hay2000; Thomson and Conner, Reference Thomson and Conner2000). This has enhanced risk-based control strategies. McKenzle et al. (Reference McKenzle, Morris, Pfelffer and Dymond2002) developed a statistical model using logistic regression for identification of geographic and habitat factors associated with the risk of the presence of a possum TB hot spot on a farm.

Multi-criteria decision analysis

Since much earlier, decision support systems have been useful in making complex animal health management decisions at both farm and larger coverages through provision of useful information, promotion of deliberation and analyses of the available options (Morris et al., Reference Morris, Sanson, McKenzie and Marsh1993; Sprague, Reference Sprague, Sprague and Watson1993).

Multi-criteria decision analysis (MCDA) approach is an advanced model consisting of fast running, error-free analytical hierarchy process (AHP), fuzzy AHP; statistical approach (frequency ratio model), etc. (Rana and Moniruzzaman, Reference Rana and Moniruzzaman2023). GIS-based multi-criteria decision-making approach and other features of GIS such as soil type distribution, soil texture mapping, buried deep underground water level distribution, soil fertility distribution, soil pollution distribution, hydraulic conductivity of soil (Ks), slope (S), soil texture (ST), depth to water-table (DTW), electrical conductivity of groundwater (ECw), climate conditions, topography and satellite data are now being used by researchers for sustainable land use planning; studying to identify and utilize the various interactions, dependences and impacts of the interacting factors (Ghosh and Kumpatla, Reference Ghosh and Kumpatla2022).

AHP at present is being widely used together with the combination of GIS and RS approaches for locating appropriate sites for various purposes, such as cropland (Akram et al., Reference Akram, Mondal and Bandyopadhyay2018; Uddin et al., Reference Uddin, Mohiuddin, Ahmed, Rahman, Karim and Saha2020; Hossen et al., Reference Hossen, Yabar and Mizunoya2021; Mostafiz et al., Reference Mostafiz, Noguchi and Ahamed2021); route alignment planning (Singh and Singh, Reference Singh and Singh2017) and determination of groundwater potential zones (Alikhanov et al., Reference Alikhanov, Juliev, Alikhanova and Mondal2021; Singh et al., Reference Singh, Hasnat, Rao and Singh2021; Rana et al., Reference Rana, Hossain, Huq, Islam, Das, Ghosh, Mukhopadhyay, Das Gupta and Kumar Singh2022). RS and GIS are also used for climatic assessment of forest (Mondal et al., Reference Mondal, Thakur and De2022) and urban areas (Gazi and Mondal, Reference Gazi and Mondal2018), forest coverage tracking (Mondal et al., Reference Mondal, Thakur, Ghosh, De and Bandyopadhyay2018; Thakur et al., Reference Thakur, Maity, Mondal, Basumatary, Ghosh, Das and De2020) and soil erosion measurements (Bag et al., Reference Bag, Mondal, Dehbozorgi, Das, Bandyopadhyay, Pham, Al-Quraishi and Cuong2022) among other uses.

Several researchers in different parts of the world have studied the use of combinations of MCDA/AHP, RS and geospatial techniques to locate suitable sites for livestock production/farming; e.g. in Ghara-Aghch region, central Iran (Amiri et al., Reference Amiri, Shariff, Tabatabaie and Alam2012), Fujian in China (Peng et al., Reference Peng, Chen, Li, Bai and Pan2014), Dire district, Southern Ethiopia (Terfa and Suryabhagavan, Reference Terfa and Suryabhagavan2015), Hangzhou metropolitan area, China (Qiu et al., Reference Qiu, Zhu, Pan, Hu and Amable2017), Ghayen Plain in Iran (Rajabi et al., Reference Rajabi, Ajorlo and Dehghani2020), Bale lowlands of Ethiopia (Balew et al., Reference Balew, Legese, Kunbushu, Nega, Alebel, Kerbesh, Md Mijanur and Rubenstein2022), Faridpur district of Bangladesh (Rana et al., Reference Rana, Moniruzzaman and Howlader2023), etc.

Rana and Moniruzzaman (Reference Rana and Moniruzzaman2023) used GIS-based MCDA and RS techniques to locate ideal land for livestock (sheep, goats, buffalo and cow) production in the Northwestern part of Bangladesh. They used geospatial tools to combine eight thematic/geographical layers (slope, land use and land cover, soil types, rainfall, water accessibility, road distance, relative humidity and average temperature) in the suitability analysis for livestock production; measuring the weight of each criterion with AHP, which is an MCDA approach. They produced a map that depicted low, medium, high and excellent sites for raising cattle.

Balew et al. (Reference Balew, Legese, Kunbushu, Nega, Alebel, Kerbesh, Md Mijanur and Rubenstein2022) reported that climate change and human factors, as well as lack of sufficient environmental and rangeland policies, disaster mitigation strategies and good management had negatively affected rangeland resources of the Bale lowlands, Ethiopia. In their study, they employed GIS-based MCDA and RS techniques to identify suitable rangeland for cattle, sheep, goat and camel production in the Bale lowlands; using land-use and land-cover, rainfall, water accessibility, slope and soil types for the suitability analysis.

Bioinformatics

Biostatistics is the application of statistical techniques in collecting, presenting, analysing and interpreting biological data, particularly in the field of biology (life sciences), medicine and public health. Biostatistics has found important applications in livestock production and management. In veterinary medicine and animal science, it facilitates and enhances tracking and interferencing of populations, through statistical analysis of evidence-based data of various animal diseases and disorders; gives rise to accurate sample testing and disease diagnosis, thereby enhancing health monitoring and treatment; facilitates availability of essential animal health information through statistical data; removes bias as well as improves analysis, resulting in better, dependable inferences, conclusions and decision making; and enhances better animal health care (Nisanka, Reference Nisanka2022).

Modern data analytics and ML tools make exploration of environmental sensor data, clustering using farm traits and categories, and identification of causality and variable importance achievable (Neethirajan, Reference Neethirajan2020; Pitesky et al., Reference Pitesky, Gendreau, Bond and Carrasco-Medanic2020; Wen et al., Reference Wen, Li, Xue, Jia, Gao, Li and Huo2021; Quintana-Ospina et al., Reference Quintana-Ospina, Alfaro-Wisaquillo, Oviedo-Rondon, Ruiz-Ramirez, Bernal-Arango and Martinez-Bernal2023a). When dealing with large data sets, data mining tools (e.g. commercial Oracle Data Miner, IBM SPSS Modeler, SAS Enterprise Miner and Microsoft SQL Server Analysis service, as well as Open-source R and Orange, etc.) are required to reveal patterns, relationships and insights. Data mining techniques include regression, decision trees, clustering, classification, association rule mining and neural networks (Aggarwal, Reference Aggarwal2015; Bramer, Reference Bramer and Mackie2016; Quintana-Ospina et al., Reference Quintana-Ospina, Alfaro-Wisaquillo, Oviedo-Rondon, Ruiz-Ramirez, Bernal-Arango and Martinez-Bernal2023b).

Quintana-Ospina et al. (Reference Quintana-Ospina, Alfaro-Wisaquillo, Oviedo-Rondon, Ruiz-Ramirez, Bernal-Arango and Martinez-Bernal2023a) evaluated the effects of temperature, relative humidity, thermal humidity index, management and farm-associated factors on body weight (BW), BW gain, feed conversion ratio and mortality of broilers raised to 35 days under commercial tropical conditions; employing correlation analyses, one-way ANOVA and ML. Ozturk et al. (Reference Ozturk, Kecici, Serva, Ekiz and Magrin2023) determined the best non-linear growth function, among a selected four; Gompertz, Logistic, Von Bertalanffy and Brody, for Kivircik lambs as well as the growth parameters for different sexes, birth types and birth seasons.

Biotechnology

Utilization of biotechnology is immensely improving animal nutrition, genetics, health, etc. (Van Eenennaam, Reference Van Eenennaam2016; NTNU, Reference NTNU2022). Gene editing has employed advanced technologies, such was clustered regulatory interspersed short palindromic repeats/associated protein 9 (CRISPRs/Cas9) for detection and elimination of possible genetic disorders in animals and biological systems. Biotechnology has also been applied in gene therapy, where DNA is used as a therapeutic disease treatment agent (Agina, Reference Agina2022); involving the repair of mutated cells as has been expressed in the treatment of cancer and cystic fibrosis. Other emerging and advancing applications are molecular diagnostics (PCR, RT-PCR, nanoPCR, biosensors, proteomics, nanotechnology), production of virus vectored vaccines and DNA vaccine technology, among others.

Internet of things

IoT refers to a network of uniquely identifiable interconnected devices embedded with sensors, software and other technologies, that communicate with themselves and other such networks over the internet. IoT also involves collection and cloud-storing of data by connected devices, which are processed for common goals using intelligent algorithms. IoT has found very laudable applications in livestock production and management; including animal location, tracing and tracking, as well as farm monitoring, healthy food production, improved security management, etc. (Ashraf et al., Reference Ashraf, Syed, Muhammad and Mujahid2017; Ilyas and Muneer, Reference Ilyas and Muneer2020; Kays and Wikelski, Reference Kays and Wikelski2023; Mishra and Sharma, Reference Mishra and Sharma2023). Meanwhile, there is still potential for much more.

The applications of AI and ML have enhanced knowledge and understanding of animal behaviour and discomfort, disease prevention and management, and the efficiency of decisions that impart farmers' economy (Mishra and Sharma, Reference Mishra and Sharma2023). Techniques based on ML are being explored for predicting disease–biomolecule associations with multi-view data sources (Yulian et al., Reference Yulian, Xiujuan, Bo and Fang-Xiang2021). Quantitative geneticists and animal breeders are also progressively exploring deep learning (DL) in genomic predictions (Junjie et al., Reference Junjie, Cedric, Kenneth and Juan2021). Digital twin technology is an AI-based advancement in cattle production for better efficiency and cost effectiveness (Mishra and Sharma, Reference Mishra and Sharma2023). Internet of Animals is also a very promising emerging application of IoT (Kays and Wikelski, Reference Kays and Wikelski2023).

Ilyas and Muneer (Reference Ilyas and Muneer2020) proposed a smart livestock tracking and geofencing solution by creating a geographical safe zone for cattle using IoT and (General Packet Radio Service) GPRS, where the cattle are assigned dedicated IoT sensors, enabling them to be remotely monitored and managed. This smart system collects the location, well-being and health data of the livestock.

Unmanned aerial vehicles (UAVs)

UAVs are small aircraft, which are also known as mini flying robots, miniature pilotless aircraft or drones designed to fly without human pilot. They operate via mutual collaboration of aircraft bodies, ground control station and sensor support. UAVs are efficient, easy to use and maintain, able to reach remote locations within minimum time and effort, capable of vertical take-off and landing as well as long-term flight and surveillance; and without risk of loss or damage to human life. They have made the collection of outdoor aerial images possible, or easier as the case may be, and have enhanced monitoring and analysis (Bentley, Reference Bentley2018; Scharf, Reference Scharf2019; Gül et al., Reference Gül, Güzey, Yıldırım and Keskin2021; Hossain, Reference Hossain2022; Kaşlı, Reference Kaşlı2022; Turğut and Şeker, Reference Turğut and Şeker2022).

The UAV technology facilitates several, diverse modern livestock production and management operations, such as health and behaviour monitoring; zoonotic disease monitoring; detection, counting and tracking of farm animals; early diagnosis of diseases; grazing land search and monitoring; habitat improvement; search and rescue; AI, ML and DL applications; welfare risk management; real-time tracking; conservation management; smart farming with IoT; surveillance and reporting of potential threats as well as improved treatment and farm management (Koh and Wich, Reference Koh and Wich2012; Hodgson and Koh, Reference Hodgson and Koh2016; Hodgson et al., Reference Hodgson, Mott, Baylis, Pham, Wotherspoon, Kilpatrick and Koh2018; Al-Thani et al., Reference Al-Thani, Albuainain, Alnaimi and Zorba2020; Alanezi et al., Reference Alanezi, Shahriar, Hasan, Ahmed, Sha'aban and Bouchekara2022; Ergün and Ergün, Reference Ergün and Ergün2024). Meanwhile, Ergün and Ergün (Reference Ergün and Ergün2024) opined that the application areas can still be expanded to get the best of the technology. Also, to fully unlock the full potentials of UAVs in wildlife research, regulatory frameworks and ethical guidelines need to be appropriately set to allow their usage (Christie et al., Reference Christie, Gilbert, Brown, Hatfield and Hanson2016; Hodgson and Koh, Reference Hodgson and Koh2016; Duporge et al., Reference Duporge, Spiegel, Thomson, Chapman, Lamberth, Pond, Macdonald, Wang and Klinck2021).

Sensor technologies, artificial intelligence and UAVs

Sensor technologies, which have been reported to save time and energy are useful in livestock precision farming practices pertaining to individual animal behaviour, grazing conditions (livestock grazing behaviour and rangeland resources), health conditions and forage intakes (Bimrew, Reference Bimrew2022). Biosensors or simply sensors have been reported to be useful in easy, affordable and quick field assessment of animal health and welfare as well as diagnosis of animal disease-causing organisms (Vidic et al., Reference Vidic, Manzano, Chang and Jaffrezic-Renault2017; Dukiya, Reference Dukiya2021; Tewari et al., Reference Tewari, Jain, Brar, Prasad and Prasad2021). In livestock production and management, it is essential to assess and monitor rangeland resources for better management and utilization. Rangeland serves as grazing land for domestic animals and wildlife. Due to varying environmental conditions and management practices, forages and pasture vary in abundance, species and chemical composition (Bimrew, Reference Bimrew2022). Meanwhile, measurement accuracy, repetitive data, inadequacy of knowledge and skill in developing countries, limited applicability in tropical climate, among other factors have been reported as limitations to the use of sensors (biosensors) (Bimrew, Reference Bimrew2022). Sensors have been used to study the predictability of lifetime resilience and productive life span of dairy cows (Mücher et al., Reference Mücher, Los, Franke and Kamphuis2022).

According to Mücher et al. (Reference Mücher, Los, Franke and Kamphuis2022), animal detection using AI-based remotely sensed imagery has very strong potential for enhancing effective and efficient monitoring of cattle herds in extensive and remote beef production systems. They also reported UAVs to be useful and promising in assessing traits which are connected to resilience in cattle, such as individual cattle and postures detection. Furthermore, UAV-borne RS has been used for grassland biomass estimation in grassland monitoring and mapping with multispectral imaging (Hakala et al., Reference Hakala, Viljanen, Honkavaara, Näsi, Niemeläinen and Kaivosoja2018).

Li and Jia (Reference Li, Jia, El-Askary, Erguler, Karakus and Chaminé2022) worked on producing an estimation model for pasture health using multispectral imagery, which can perform livestock management automatically when rooted into electronic shepherding system. They investigated VIs using the Sentinel-2 MSI imagery, thereby proposing a class-based regression model for the growing, matured and grazed grassland, obtained from support vector machine classification, which led to an improved correlation between the canopy chlorophyll content index and the above-ground biomass. They used in situ data samples for the research, while ground truthing was done with the use of UAV. They developed an improved regression model which supports better grazing intensity estimation and guidance of livestock rotation cycles.

Mücher et al. (Reference Mücher, Los, Franke and Kamphuis2022) investigated the detection, counting, identification and characterization of posture of individual cows in grassland production systems via remotely sensed imagery data sets from satellites, manned aircrafts and UAVs, as well as DL techniques.

Precision livestock management

Precision livestock management (PLM) is an integration of sensor technologies, including on-animal sensors such as real-time tracking and motion sensors, automated feeders, body weighing scales and milk extractors, environmental monitoring equipment (such as weather stations) and RS applications; with digital documentation, systematic ranching operations recording for financial analysis, inventory management and production assessments incorporated for well- informed decisions (Wathes et al., Reference Wathes, Kristensen, Aerts and Berckmans2008; Berckmans, Reference Berckmans2014; Bailey et al., Reference Bailey, Trotter, Tobin and Thomas2021; Nyamuryekung'e, Reference Nyamuryekung'e2024). With machine vision, non-invasive animal monitoring is achievable with fixed sensors.

PLM within IoT has tremendous capacity for enhanced traceability and real-time livestock production/management information which can greatly increase the efficiency of ranchers in managing their very complex production systems, and even positively impact the entire food chain (Nyamuryekung'e, Reference Nyamuryekung'e2024). PLM has evolved tremendously in recent times with the use of bio-sensors, data analytics, automation power, AI, ML, robotics, etc.

Precision livestock farming technologies based on advances in sensor-based high-throughput phenotyping and AI have greatly enhanced the accuracy of genomic predictions, discovery of novel traits and understanding of genotype by environment interactions, as well as selection of animals with superior and better environmentally adapted qualities (Pérez-Enciso and Zingaretti, Reference Pérez-Enciso and Zingaretti2019; Fuentes et al., Reference Fuentes, Gonzalez, Tongson and Dunshea2022). Precision breeding techniques, such as marker-assisted selection and genomic selection enable precise breeding decisions, thereby enhancing the accuracy of prediction of animal genetic potentials.