Artificial Intelligence: An Emerging Approach for Intensive Livestock Farming
Priya1, Chaithra S N, Vivek Sahu, Pratibha
1PhD Scholar, Livestock Production and Management Section, Indian Veterinary Research Institute, Bareilly (243122), UP, INDIA
Several thousand years ago, man started domesticating animals for their own benefits. Since then, we have always relied on our intuition, sensory signals, and collective knowledge to make effectual animal production decisions. Historically, animal husbandry has always been dispersed, on a scale that individual animal is kept by individual man and only a few individuals can get together and manage them. And until a decade ago, most animal farmers did not have access to present-day technologies such as high-speed internet, smart phones and cheap computing power. Now, both these conditions are changing quickly. Many farmers are coming together with a common view of rearing the animals and use the common resources in a sustainable way. Their familiar interest for the enhanced animal production with the better animal welfare makes them to reach various advanced technologies so that they can remotely monitor the farm animals with minimum invasion.
One should clearly understand that the major hurdle in achieving enormous output in animal farming is acquisition of data. There is almost impossibility to obtain accurate data on a farm related to daily and routine farm operations. Farms, especially large ones, don’t know how much an individual cow eats, how much she moves, how much she drinks, her body temperature, stress levels, optimum housing conditions, sickness, etc. Without precise, smart, real-time data, the task of managing individual cows is nearly impossible. But emerging digital technologies could fill that data gap.
Secondly, today, more than half the global population is connected to the internet either through smartphones or computers. This means that computing power is now easily accessible by millions of animal farmers. Also, there is more advancements in technology in different fields. Everyday new technology is coming up for the benefit of humans and their ease.
Because of all above stated reasons, artificial intelligence plays an important role in achieving higher gains and increased production from the animals. Under the current situations, it would be interesting to review the most recent advancement on artificial intelligence and to analyze the possibilities of transferring these results into fields with an interest in enhanced animal production and their upliftment in terms of welfare.
In simple terms, Artificial Intelligence (AI) can be defined as a technology which mimics human intelligence through the application of algorithms that can perform a series of tasks and are built into computers, software, apps and all other forms of technologies. Big data plays a key role in applying advanced technologies to animal farming practices and offers a scalable solution to store vast amounts of data on a remote server. This extensive data is used by advanced AI and Machine learning (ML) algorithms to analyze, predict and notify farmers in case there is something abnormal. Therefore, in the context of animal farming, sensors, big data, and advanced AI & ML algorithms go hand in hand to provide a complete solution.
To sum it all up, artificial intelligence allows easy data entry on farm records, monitoring farm activities, analyzing economic performance, improving animals’ health, improving soil richness. All these features and solutions strive towards ‘smart farming’.
Artificial intelligence technologies can be used for disease prediction. In this scenario, the possibility of using seasonal climate forecasts as predictive indicators in disease early warning system (EWS) is an interest of focus as the geographic and seasonal distribution of many infectious diseases are associated with climate. Therefore, Geographic Information system (GIS), remote sensing (RS) and Global Positioning system (GPS) are the three commonly used veterinary geo-informatics technologies employed in this digital era for rapid communication of data for better management of animal diseases. Animals are purchased for various reasons, such as breeding purposes, and there always exists the occurrence of an exotic animal disease and zoonotic disease. For supervising the chance of controlling the disease and reducing its economic and social impact on the whole country, early recognition of a serious or exotic animal disease is one of the most important factors. Diseases often affect an animal’s body temperature, and inflammation caused by infection or injury may be visible at specific spots in an animal’s body. One of the challenges in measuring body temperature is the lack of a true gold standard. Each body temperature measurement location has either physical, logistical, or physiological limitations. In addition, many physiological and environmental factors affect body temperature. Thus, the inherent variation in body temperature can make detection of outliers challenging. Thermal imaging has been proven to work as a diagnostic tool for some animal diseases. The temperature in the gluteal region of dairy cattle increases when an animal becomes ill; this can be detected in thermal images even before the disease is detected clinically. Examination for a disease using this method can be done with no physical contact with the animals.
Effective decision making in animal farming
Over the last decade, there have been several key studies dedicated to reporting on how the application of decision support systems (DSS) in animal farming improves production and systems management. The application of decision support systems (DSS) using AI technologies have been utilized in areas such as, farm planning, animal management, sustainable use of resources, disease management, etc.
There are varying data types that can be used in an animal farm setting, such as weather indices, animal growth parameters, etc. Advances in the use of technology (e.g. sensor hardware, satellites, drones, proximal sensing, etc.) and the development of online and offline systems to house this data (cloud systems) has resulted in more efficient and accurate DSS.
Core AI technologies
So far, we’ve discussed the reason for decision support systems (DSS) in livestock sector, how to develop them, as well as the common techniques used. In this next section, we’re going to discuss the practical application of core AI technologies and how they can improve decision making, as well as the level of data quality.
Data mining, artificial neural networks (ANNs), Bayesian networks (BNs) and support vector machines (SVMs) are the core AI technologies that have been developed to assist in the analysis of data collected across the livestock sector. Below we provide a brief definition of the key technologies, as well as suggestions for their usage.
Data mining
Although a relatively new development, data mining is the process of collating multiple sets of data, analysing that data from differing perspectives and then summarising the findings into useful and accessible information. The process of data mining is data cleaning, data integration, data selection, data transformation, data mining, pattern evaluation and knowledge presentation.
Artificial neural networks (ANNs)
Artificial neural networks (ANNs) are built upon the premise of the biological processes of the human brain. This model consists of several layers, such as input, middle and output layers. Examples of the application of ANNs in an agricultural environment include crop development modelling, pesticide and nutrient loss assessments, soil retention estimates, prediction of potential diseases and the fertility of hen eggs.
Bayesian networks (BNs)
A Bayesian network (BN) is an approach developed that represents both the beliefs and knowledge through probabilities. This method is particularly popular for use on extremely complex systems; either in their structure or functionality.
Support vector machines (SVMs)
Support vector machines (SVMs) are a relatively new development in the field of supervised machine learning methods. SVMs have been utilised across the livestock sector for varying purposes, including to classify livestock sector, to detect and forecast demand and supply for animal protein.
In brief, AI or advanced technologies can help in achieving the targeted livestock production across the globe for fulfilling the future man needs. Moreover, such technologies minimize the man power requirement by effectively monitoring of animals and ensure better animal health throughout the production process.
https://www.frontiersin.org/articles/10.3389/fvets.2021.715261/full
