eChapters

Artificial insemination (AI) is the deposition of the semen or male germ cells (spermatozoa) in the female genital tract by artificial means (instruments). Artificial insemination includes collection of semen from the male, preservation, handling and deposition into the female reproductive tract hygienically replacing natural mating by a male. In India this technique is gaining momentum in chickens due to improved animal husbandry practices and economic considerations, initiated by IVRI, Izatnagar and JNKVV, Jabalpur. In many parts of the world, turkey, ducks, goose and guinea fowl are bred solely by AI. Chicken species are endowed with the behaviour and capacity of each male to mate several females and also 25 to 40 times a day. Further, the process of ovulation in birds is almost daily and stimulated by intensity and duration of light.

In modern poultry managemental practices of using cages, environmentally controlled houses and breeding and hybridization techniques employed for developing highly economical chickens, selection for faster growth and heavy body weight in broilers, which has led to loss of fertility and hatchability and use of dwarf female parents in broiler industry have demanded the use of AI in poultry.

1. AI with liquid semen

The ampoule is thawed in ice water for 6-7 minutes. Then, the ampoule is dried and cut. The semen is drawn in a sterilized glass pipette (40-42 cm x 5 mm length diameter) fitted to a sterile glass/plastic syringe (2-5 mL) filled with 1 mL of semen with a rubber connecter. Artificial insemination is done by recto-vaginal method after securing cow/buffalo in standing position in the trevis.

The first buffalo AI progeny is reported at Allahabad in August 1943. Although AI is commonly used as a tool of breeding in buffaloes and complaints have appended that conception rate is not satisfactory. There are differences in the anatomy of the sexual organs, sexual physiology and general breeding behaviour that have to be known and taken into consideration when the same technique of AI used in cattle is applied in buffalo breeding. It explains the lower semen production capacity of male buffaloes compared to the cattle bulls. The buffalo bull’s penis is shorter and thinner than penis of the cattle bull. There is a pronounced tapering of the penile end and glans penis is rather poorly developed. The thrust is shorter and less forceful than the bulls. The sheath is tighter and closer to the abdomen than zebu cattle. These anatomical differences are of significance in the semen collection work and type of artificial vagina to be used. The weight of testis and epididymidis in the male buffalo is only ¼ of what it is in cattle. In addition, the seminal vesicles and the prostate are considerably smaller.

Artificial insemination technology is a valuable tool to inseminate 2000 to 3000 does by frozen semen instead of breeding 40 to 50 does by natural service in a year. Goat semen may be stored and frozen more successfully than ram semen. The buck will be sexually mature at 6-7 months of age.

Artificial insemination in horses is being practiced since many years in Russia and China for genetic up-gradation. The equine artificial insemination industry has evolved a system in which mares are inseminated with fresh or cooled semen (500 million motile sperm) every 48 hours until estrus is no longer detected or until ovulation is detected by trans-rectal palpation or ultrasonography of ovaries respectively. The advantages of AI include:

Artificial insemination (AI) technique in pigs is being performed since several decades in many countries but not widely accepted technology as in cattle due to reasons like sub-standard method of semen cryopreservation and lower fertility rate. The main idea is to increase the breeding efficiency by utilization of superior boars. The number of boars needed for breeding purposes can be reduced by use of AI and reduced transmission of infectious diseases. A minimum of 15 to 20 sows can be inseminated after dilution over a 2 days period with an ejaculate from a boar. Artificial insemination had considerable impact worldwide in its application to commercial pig production. The main advantage of using fresh liquid boar semen is that fertility is maintained even with low number of spermatozoa in the inseminate. AI provides unique opportunity for the genetic improvement of pig industry. Using fewer than 1 million sperm cells per breeding unit can achieve conception rates with liquid semen similar to those with frozen thawed semen containing approximately 15 million sperm and reduced fertility makes cryopreservation an uneconomical option in boars.

Artificial insemination Technology is a high cost and labour intensive technique in sheep and In India, sheep are reared by economically weaker sections of the society and any advanced technique may take much time to reach their flocks.  Considerably more research work has been done in AI with sheep than with goats. However, the equipment and techniques are very similar for the two species. Goat semen may be stored and frozen more successfully than ram semen.

Advantages and limitations of artificial insemination

Artificial insemination is the first great biotechnology applied to improve reproduction and genetics of domestic animals. Artificial insemination includes the collection of semen from the male, semen assessment for quantity and quality, dilution with extender, preservation and then insemination. Artificial insemination (A.I.) is a breeding technique where semen with living sperm is deposited into the reproductive tract of a female who is in estrus by use of instruments. Artificial insemination is the most important single technique widely used worldwide to upgrade the genetic makeup of the farm animals. Artificial insemination can be performed in most of the domestic animals like cow, buffalo, mare, sow, bitch, queen cat, lambs, does etc. Due to invention of frozen semen technology, the extended semen doses can be preserved for years together and permit wide spread use of superior germplasm. Artificial insemination is a powerful tool mostly employed for livestock improvement. The advantages and limitations of frozen semen technology are enlisted below:

9.1. Introduction

The human population of the world will reach nearly 10 billion by 2050, boosting agricultural order-in a situation of humble financial development (FAO, 2017). At present, approximately 37.7% of total land surface is being utilized for crop production. From employment generation to contribution to National Income, agriculture sector is contributing a significant role in economic prosperity of the developed nations and is playing an active part in the economy of the developing countries as well. The growth of agriculture has resulted in a significant increase in the per-capita income of the rural community. Thus, a greater emphasis on agricultural sector is the need of the hour. For countries, like India, the agricultural sector accounts for 18% of GDP and provides employment to 50% of the country’s workforce. Development in the agricultural sector will enrich the rural development which will lead toward rural transformation and ultimately the desired structural transformation (Mogili and Deepak, 2018; Shah et al., 2019). The role of Artificial Intelligence (AI) has been obvious in the agricultural sector recently. The sector needs the impetus from AI based technology to maximize its yield including improper soil treatment, disease and pest infestation, big data requirements, low output, and knowledge gap between farmers and technology.

Artificial Intelligence (AI), Machine Learning and Data Analytics seem to be invading all the fields to bring in efficiencies in those respective fields. However, Toxicology field seems to be lagging behind in these areas although there is a huge scope to use these advanced technologies.

AI, data analytics and machine learning can be used for creating toxicology databases on chemicals, predictive modelling and AI for risk assessment, amongst other applications. One such effort was carried out for use of AI in creating a BOT, a ToxBot, for conducting risk assessments on chemicals which helped in gaining lot of efficiencies. The ToxBotwhich was created helped in conducting risk assessments and reducing time for such risk assessments from48 hours to 15 minutes. This also ensured using a uniform database, consistent output and helping toxicologists in arriving at unform conclusions. To begin with, the sponsors need to be very clear about the objective and expected outcome of the AI solution. The first step in creating these AI solutions is creation of a datasbase. While, creating AI solutions for risk assessment two aspects are important- source of Toxicology thresholds and the other one to derive exposure to population to assess safety. Creating a Toxicology data base for deriving thresholds is tedious. Toxicology studies generate huge data on multiple chemicals, drugs and botanicals. However, these data are scattered, not uniformly documented, and there is lack of efforts to compile them. Each constituent has data on each end point and these data are spread across multiple species. Hence the Toxicology data on each constituent has variables such as species, routes, doses, duration and end points. The efforts start with creating a complete Toxicological profile including all available data on each end point in each species by specific route of administration. These profiles then form the basis of a data base, which then enable to derive safety thresholds. The other database or system is to derive the exposure. This depends on the type of product, daily dose, frequency, route, concentration of chemical and the target population. These can be populated through an exposure matrix. For Al, these data need to be documented in uniform manner for subjecting it to Machine Learning and creating AI solutions. The AI experts would then be required to understand the entire process of the desired outcome and how the dataare used, at what points. This helps them in creating an algorithm. Once the algorithm and coding is created, the product is ready to be tested.

At a compound annual growth rate (CAGR) of 7.6%, the global poultry industry expanded from $352.02 billion in 2022 to $378.84 billion in 2023. Global production of chicken meat was projected to reach 103.4 million metric tons in 2023, primarily as a result of rising output in China, India, Brazil, and the US. India is currently the world’s second-largest egg producer (138.3 billion eggs in 2022–2023), trailing only China. It is also the world’s fifth-largest broiler producer (producing 4.99 metric tons (MT) in 2022–2023), behind China, the United States, Brazil, and the Russian Federation.

Introduction

The term "artificial intelligence" was originally coined in 1956 at a conference hosted by Dartmouth College. While the aspirations and dreams of the attendees were sky-high, the reality was sobering. The thought of citizens in space or self-driving cars within a decade was ancient science fiction. The building blocks of the required computing infrastructure, as well as AI, notably deep learning and statistical machine learning methods, were not even in the distant future. The aim was to create an artificial brain for a machine, where the "brain" is the so-called "expert system", a software program that can integrate a large knowledge base and use it to solve problems in the same manner that a human expert could. The intellectual merits and achievements of a few AI systems designed solely to narrowly excel in a specific problem became the actual problem of the nascent field.

This chapter integrates case studies, scientific examples, and policy perspectives to illustrate how AI and ML can transform agricultural weather intelligence. The discussion spans from advanced predictive models in developed nations to emerging applications in technology-limited regions, while also addressing the urgent need for resilient crisis management systems in the face of natural and human-caused conditions. Advanced scientific techniques can not only optimize food production and resource management but also play a critical role in recovery efforts during times of crisis. Agriculture is intrinsically linked to the natural world—a domain defined by fluctuating weather patterns, seasonal shifts, and unpredictable environmental factors. Today, Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing how we analyze and predict weather patterns, and their applications in agriculture are far-reaching (Fig. 5.1). From forecasting crop yields and fishery conditions to managing plantations and monitoring livestock health, these technologies are creating a paradigm shift in agricultural weather intelligence. Scientific organizations worldwide are leveraging AI and ML to refine predictive models, enable multi-variate analysis, and provide advanced warning systems for extreme events such as droughts, tsunamis, earthquakes, and even crises caused by human-made conflicts. Emerging nations with rapidly growing technological capabilities stand to benefit immensely from these innovations, tailoring solutions to local challenges while contributing to global food security and crisis resilience.

Introduction
Antimicrobial resistance (AMR) has emerged as a critical global health threat, diminishing the effectiveness of antibiotics against bacterial infections. Conventional strategies to counter AMR—including antibiotic stewardship programs and the development of new drugs—are often slow, expensive, and labor intensive. However, artificial intelligence (AI) and machine learning (ML) present ground breaking alternatives to address this challenge. By leveraging advanced computational techniques, AI can significantly speed up the discovery of novel antibiotics, enabling researchers to identify promising drug candidates more efficiently than traditional methods. Additionally, ML algorithms enhance treatment optimization by analyzing patient data to recommend personalized antibiotic regimens, reducing misuse and resistance risks. AI also strengthens surveillance systems by processing vast datasets— such as genomic sequences and electronic health records—to detect emerging resistance patterns in real time. These capabilities allow for proactive interventions, helping healthcare providers and policymakers stay ahead of AMR outbreaks. Together, AI and ML offer a transformative approach to mitigating AMR, combining speed, precision, and scalability to combat one of the most pressing medical challenges of our time.
AI in Antibiotic Discovery
One of the most promising applications of AI in AMR mitigation is in antibiotic discovery. Traditional drug development is costly and time-consuming, often taking over a decade [1]. Machine learning models can analyse vast datasets of chemical compounds to predict their antibacterial properties. For example, researchers at MIT used deep learning to identify halicin, a novel antibiotic effective against drug-resistant bacteria. AI-driven platforms can also repurpose existing drugs, reducing the time needed for clinical trials [2].
Fig. 1: AI cyclic interface in antibiotic discovery
Predictive Analytics for Resistance Patterns AI-powered predictive analytics enables early detection of antimicrobial resistance (AMR) patterns by processing clinical, genomic, and epidemiological data. Machine learning models analyse electronic health records (EHRs) [3] and bacterial genome sequences to identify emerging resistance threats in real time. These predictive insights allow hospitals to take proactive measures— such as optimizing antibiotic prescriptions—before resistant strains spread. Beyond clinical settings [4], AI models assist public health agencies in forecasting outbreaks and strategically deploying resources. By integrating large-scale datasets, these systems enhance surveillance, enabling faster, datadriven decisions to curb AMR progression. This approach not only improves patient outcomes but also supports global efforts in combating antibiotic resistance through smarter, pre-emptive interventions [5].

1. Introduction
Studies on soil health and agricultural growth are increasingly using artificial intelligence (AI) and machine learning (ML) techniques. With the help of these technologies, it is possible to analyse vast amounts of data and gain insightful knowledge that will help to boost crop yields and optimise agricultural practises (Neethirajan, 2020). Applications of AI and ML to research crop development and soil health have enormous potential to revolutionise agriculture. In order to increase soil health and crop yield, farmers and researchers can use these technologies to analyse massive datasets, generate precise forecasts, and optimise farming practises. Overall, artificial intelligence (AI) and machine learning (ML) provide useful tools that can support efficient and sustainable agriculture, solving global concerns in food availability and the sustainability of the environment. Unquestionably, technical developments have significantly increased the productivity and efficiency of many industries, including agriculture. The advent of words like “big data,” “data analytics,” “artificial intelligence,” “Internet of Things,” “erosion modelling,” “smart farming,” and “machine learning” are just a few examples of this technological revolution (Almoussawi et al., 2022). Digital soil mapping (DSM) uses computational models to infer regional and temporal shifts of soil types and properties based on soil observations, prior knowledge, and relevant environmental variables in order to create and populate spatial soil information systems. The supply chain for agricultural production is extremely intricate (Lamichhane et al., 2019). The way our food is produced, distributed, and consumed is changing as a result of AI. When planning crop rotations, planting times, water and nutrient management, pest and disease control, optimal harvesting, food marketing, product distribution, food safety, and other agriculture-related tasks throughout every step of the food supply chain, researchers use powered by AI tools to supply advice and expertise. In “Harnessing AI to transform agriculture and inform agricultural research,” Peters et al. (2020) presented a summary of the most recent developments, difficulties, and prospects for AI technology in agriculture. They use the four main elements of the food system—production, distribution, consumption, and uncertainty—to show the possibilities of AI. They come to the conclusion that agricultural businesses are excellent candidates for using AI and other technologies. In “AI down on the farm,” Sudduth et al. (2020), examined a number of case studies in which machine learning (ML) has been used to model various aspects of agricultural production systems and give data that can be utilised to make management decisions at the farm level. These research efforts involve providing data, essential for creating precise and effective irrigation systems and improving tools for suggesting the best nitrogen fertilisation rates for maize. Traditional crop health monitoring techniques need a lot of work and time. Using AI to monitor and detect potential crop problems or nutrient deficits in the soil is an effective method. Applications to analyse plant health trends in agriculture are being created with the aid of deep learning. These AI-powered tools are essential for improving our understanding of soil quality, crop pests, and disease in plants (Virnodkar et al., 2020).

Millets have potential as both food and fodders crops. Foods made from millet are abundant in micronutrients and necessary amino acids for regulatory functions. Since, millets were traditionally grown under adverse conditions, a great amount of polymorphism was preserved, making millet crops naturally resistant to abiotic and biotic stresses. Using data-driven technology to increase genetic gain in breeding operations can improve traditional breeding. Artificial intelligence can be used to create varieties that are adapted to certain soil and climatic conditions. In order to achieve breeding goals, machine learning (ML) is crucial in data mining and analysis, providing information for decision-making. We have been able to generate information on interesting genes using data mining and allele identification methods. For the exploitation of the natural variation and the identification of target genes, advances in high-throughput sequencing for the detection of genetic variations as well as the role of phenomics in genomics-assisted breeding can be employed. QTLs and marker-trait correlations can be identified via genome-wide association analyses. Multiple loci and genes that control agronomic traits have can be studied by comparative and functional genomics. Model selection is crucial for ML algorithms in smart breeding, which depends on knowledge in genotype, phenotype, and G×E interaction to be handled through computer science.

Climate change affects livestock through heat stress, water scarcity, unstable feed supplies, altered disease patterns and extreme weather. This chapter examines how artificial intelligence supports climate-smart and sustainable animal husbandry. Machine learning, predictive analytics and IoT-enabled monitoring can optimize feeding, detect disease, assess welfare and improve the use of water, energy and other resources. Intelligent technologies can also assist in reducing greenhouse-gas emissions and developing adaptive production strategies. The chapter evaluates the contribution of AI to productivity, climate resilience and environmental responsibility while addressing problems such as insufficient data, limited infrastructure, implementation costs and ethical concerns. Future integration with sustainable agricultural frameworks is also discussed.

9.1 Introduction

The increase in world’s population and respective food demand has brought the global concern. The climate change alone has put a tremendous burden on the farming communities, and has become the major challenge to feed the burgeoning population. It has been estimated that by the end of the year 2050, the global population will be around 10 billion, meanwhile, the food demand will also be increased by 70-100 %. The traditional method of agricultural practices are not sufficient enough to meet the rising food demand. Therefore, to meet the increasing food demand, agriculture is intensified by the use of chemical fertilizer, pesticides, herbicides, which deteriorat the soil health. Thus, new automated/ mechanised systems have been introduced into the agriculture sector to ensure precision farming. These systems are quick in action, and satisfing the requirements along with generation of billions of employment worldwide. In a developing country like India, 65-70 per cent of the total population resides in rural areas, of which, most of the households are dependent on agriculture. The agriculture sector in India accounts for 18 per cent of the country’s GDP, and provide employment to 50 per cent of the total work force. The agriculture sector is one of the most sensitive sectors of Indian economy which supports all other sectors, and spreading its benefit to the far-reaching areas. Therefore, it becomes important for the developing country like India to develop agriculture sector to boost-up the rural economy.

With the advent of technology, a rapid transformation has been occurred in various industries, while agriculture remains the least digitized. Though, the application of aircraft/ drones in agriculture for fertilizer/ pesticides applications, image capturing, access to real-time quality data has adopted in some developed countries like Australia, USA, Japan, and some of the European countries. Moreover, these unmanned aerial vehicles could provide data of soil health, monitor crop health, assist in irrigation scheduling, yield estimation, and weather data analysis too. However, such development in agriculture is still lacking in developing countries. The agriculture development in the modern era could be done by taking the biological information and agricultural knowledge through integration of modern agriculture information technology with traditional agricultural practices. These knowledge integrations with mobile internet, cloud computing, and machine learning could enable to control the agricultural production system over stressed climate condition easily. Thus, Artificial Intelligence (AI), which is a sort of machine intelligence, an inbuilt set of programme and algorithms similar to the human brain in the current world is gaining more attention in agricultural application for precision farming.

Artificial intelligence (AI) uses multiple technologies that equip machines to sense, comprehend, plan, act, and learn with human-like levels of intelligence. Fundamentally, AI systems perceive environments, recognize objects, contribute to decision making, solve complex problems, learn from past experiences, and imitate patterns. AI technologies such as deep learning allow computer systems to understand a problem, learn from examples, and make predictions.

The AI has a tremendous potential to solve the diverse application problems in the field of domestic animal breeding and management. Till date, most of the studies have been focused on animal behaviour (Valletta, et al., 2017), cognition (Lake et al., 2017), animal welfare (Neethirajan, 2021), individual identification (Norouzzadeh et al., 2018), growth or body condition scoring (Zin et al., 2020), disease detection and its monitoring (Kumar et al., 2021), precision farm management (Radun et al., 2021) etc. particularly in the pigs, poultry and cattle species. These AI based applications primarily involves data generation, data processing, use of gadgets / IoT devices, development of smart machine learning algorithms and their integration to attain precision to solve various issues in animal husbandry. Having said that, very few works have been carried out with respect to applications of AI in domestic animal breeding, and major problems like breed identification, genomics- based animal selection criteria and breeding decision, are yet to be automated. Moreover, there are some bottlenecks in application of AI in animal breeding, like the lower accuracy of a decision/outcome and large cost involved in creating AI based infrastructure.

Introduction
Loss of arable land due to population expansion, urbanization and climate change have substantially impacted agricultural production, driving the need to exploit advanced techniques for enhancing sustainable crop production (Bren d’Amour et al. 2017). The yield and productivity of plants are influenced by both their genotype and the growing environment, which govern the performance indices or phenotype (Reynolds et al. 2020). Conventional plant breeding plays a crucial role in ensuring food and nutritional security for the ever-growing global population by harnessing genetic diversity and selecting plants with superior agronomic traits (Singh et al. 2019). However, identifying plants with superior agronomic traits and novel genes (quantitative trait loci or QTLs) through conventional breeding is akin to finding a needle in a haystack (Bohra et al. 2022). Furthermore, the conventional breeding approach is time-consuming and often associated with linkage drag due to extensive inter-crossing/hybridization among elite, wild, and common landraces (Beaver and Osorno 2009). Despite these challenges, classical breeding does develop new plant varieties with improved traits that can withstand climate extremes. Nevertheless, the duration of breeding cycles required to successfully complete the breeding program remains a major bottleneck, taking around 7-9 years to develop an improved variety (Pratap et al 2021).
Efforts have been made to revamp conventional breeding techniques by exploiting molecular markers (Ribaut et al. 2010). These markers effectively capture genetic variations across large populations at an early plant developmental stage. Additionally, the use of molecular markers in plant breeding significantly reduces the time required to screen plant genotypes with desired traits. Otherwise, achieving this task would take 2-3 years (Amiteye et al. 2021). Molecular marker-based techniques, such as marker-assisted selection (MAS), markertrait association (MTA), and genome- wide association studies (GWAS), have become routine tools. They help predict and develop genetic models for plants containing desired traits (Bohra et al. 2020). Furthermore, plant breeders have successfully integrated these molecular markers with genomics, phenomics, transcriptomics, proteomics, metabolomics, and epigenomics approaches (Malik

Agriculture is the support for the sustainable health and economic growth of the country. With the frequent changes in climatic conditions and increase of global population, it is important to come up with new varieties and nutrient rich crops. In this context, underutilized and neglected millets, considered as “nutri-cereals” or “smart foods” due to better adaptation in diverse environmental stresses and tolerance to insect pests and diseases, also a staple crop for hunger-stricken areas. Millet production is limited by the lack of intensive farming and deployment of genetic tools for trait and nutrition improvement. The recent advancement in machine learning (ML) and Artificial Intelligence (AI) technologies are key to depict plant response to environmental perturbation in huge data sets. Therefore, precision agriculture or smart farming is necessary to explore the genetic makeup of the neglected millets. AI has a substantial potential to handle numerous challenges in the formation of knowledge-based farming systems. The next agricultural revolution would emphasize more on farm machinery using AI integrated with the Internet of Things (IoT). In Smart agriculture, deep learning facilitates fast and interesting data analysis and provides support to researchers and farmers by the outcomes generated from the analysis. Here, we emphasize on the advancement of AI and its application to monitor the underutilized and neglected millets quality, yield and disease assessment. This chapter summarizes how AI can contribute to the improvement of sustainable productivity and quality of underutilized and neglected millet.

Genetic improvement creates permanent, heritable gains in milk production, growth, fertility, disease resistance and environmental adaptation. This chapter explains how artificial intelligence complements conventional phenotypic and pedigree-based selection by analysing large genomic and performance datasets. Machine-learning models reveal genotype-phenotype relationships, predict breeding values and support earlier, more reliable selection. Applications include genomic selection, precision breeding, reproductive technologies, bioinformatics and digital twins. AI can reduce generation intervals and improve the efficiency of breeding programmes, but its success depends on data quality, representative populations and interpretable models. Ethical concerns, genetic diversity and long-term sustainability must also be considered when designing AI-supported breeding systems.

Genetic improvement creates permanent, heritable gains in milk production, growth, fertility, disease resistance and environmental adaptation. This chapter explains how artificial intelligence complements conventional phenotypic and pedigree-based selection by analysing large genomic and performance datasets. Machine-learning models reveal genotype-phenotype relationships, predict breeding values and support earlier, more reliable selection. Applications include genomic selection, precision breeding, reproductive technologies, bioinformatics and digital twins. AI can reduce generation intervals and improve the efficiency of breeding programmes, but its success depends on data quality, representative populations and interpretable models. Ethical concerns, genetic diversity and long-term sustainability must also be considered when designing AI-supported breeding systems.

Currently, the milk production of country is 221.06 million tonnes (2021 22) and the target is 300 million tonnes by 2023-24. The livestock sector contributed nearly 5.21% of total gross value added (GVA) and 28.36% of the agriculture and allied sectors GVA. Thus, there is a huge gap between demand and supply, therefore with the requirements of better yield from the dairy animals, we need more better and advanced options. Artificial intelligence (AI) is one of such options which can be exploited in dairy industry. Artificial Intelligence can be a game-changer for the dairy farming in India and it can emerge as a tool that empowers farmers in monitoring, forecasting as well as optimizing the farm animal growth. It can predominantly change the scenario of dairy farmers by maintaining the health, physiological and physical conditions of dairy-cows. This knowledge-based technology has a huge potential and could confront the loopholes in dairy farming and thus indirectly can strengthen the dairy industry. In dairy farming AI has multiple applications like monitoring the activities of the dairy-cows, boosting the milk production and farm productivity, detection of mastitis in dairy-cows and developing the smart cow houses powered by image analysis.

AI enables the dairy farmers to determine whether the cow is ill, ready to breed or has become less productive. The AI also sends alerts to the farmer about the change in the cow’s behavior allowing human intervention where needed. Regular 24x7 monitoring of dairy animals is the key for successful dairy farming, however, traditional methods of monitoring relied on visual observation, but it was not very efficient due to the lack of time and human resources. Without AI, it would be almost impossible for the farmer to keep a watchful eye on every cow in the herd. Artificial Intelligence components of the dairy automation system process the collected data to provide insights on the heat stress, change in feeding efficiency and the estrus of the cow. Diseases like sub-clinical mastitis, one of the more common diseases in the dairy industry, cost the Indian dairy industry one billion dollars annually. Eventually, it provides new hope and open prospects for the overall quality and progress in the dairy industry through a profitable business approach in dairy farming

What is Artificial Intelligence

‘Artificial’ is taken to mean a property of a human-made machine. ‘Intelligence’ will be that when something is able to perform a new action or change its state to achieve the optimal response it could perform given external inputs. This term is coined by- John McCarthy (American computer and cognitive scientist) during 1956 So, AI is basically a machine able to mimic human intelligence by having the ability to predict, classify, learn, plan, reason and perceive.

AI is an emerging technology in the field of agriculture. AI-based equipment and machines, has taken today’s agriculture system to a different level. This technology has enhanced crop production and improved real-time monitoring, harvesting, processing and marketing . The latest technologies of automated systems using agricultural robots and drones have made a tremendous contribution in the agro-based sector. Various hi-tech computer-based systems are designed to determine various important parameters like weed detection, yield detection and crop quality and many other techniques.

Introduction 
In the past, literacy in reading, writing and mathematics was considered the basis of establishment in society. With this knowledge, anyone could run all the businesses of his professional life efficiently because no technical skills other than typewriter and general computer knowledge were required. In present set up, this general knowledge is no longer enough to perform any task smoothly today. In this age of science and technology, the old concept of literacy is no longer applicable. Three other types of literacy or skills have now been added to the past concept of literacy: information literacy, technological literacy and human literacy. In this age of technology, people cannot keep themselves functional in this digitized world by practical knowledge of analog equipment alone. In present days, people live and work on the constant flow of big data, connections, and instant information flowing from every click and touch of a device. Technology is not static. Evernew technological advancement brings tides of data before people, therefore, they need data literacy to read, analyze and use them. Technological literacy gives them grounding in coding and engineering principles, so they know how their machines tick. Ultimately, human literacy teaches them the humanities, communication and design, allowing them to work in human environments. Artificial intelligence (AI) is now a fact of everyday life in our modern hightech societies. There are many definitions of AI and each of those definitions has been revised over time. Presently, most definitions state that AI solves complex cognitive problems associated with human intelligence or that AI helps as many people as possible through smartphones or healthcare, or even that AI recognizes problems and creates solutions for the benefit of technology, people, and society. However, the core concept of AI has continuously been to create machines that were capable of thinking like humans. It took about 200,000 years for human intelligence to evolve from natural to artificial and only 10 years to cut ties with the Earth and move to the clouds. During the creation of AI, mankind learned a lot about what it means to be human, how human intelligence is structured, and how humans learn and acquire expertise. With more predictive power, more efficiency and the ability to deliver better results than humans, AI is rapidly moving aside from humans into the world of expertise. However, it is impossible to imagine that someone else will replace Homo sapiens at this moment, but its probability cannot be ruled out in the days to come. The day, when mankind, in the course of time, will immerse in the world of knowledge, robotics becomes an essential part of the human body and existence, the existence of mankind is sure to be threatened. In October 2017, Saudi Arabia granted citizenship to humanoid Sofia. Perhaps this is a new breed of human being brought about by technology in the 21st century. Just as the message of the first driverless car aroused a lot of curiosity among mankind and now that curiosity has disappeared completely, it is likely that the arrival of many Sophia’s will make the environment very normal in the coming days. So here comes AI – Artificial Intelligence, the driving force behind Sophia or Driverless cars. The very simple definition of artificial intelligence is -the intelligence displayed by machines. Today, in this age of science and technology, we can say that anything imaginable by humans can be done with the help of machines. Sundar Pichai, CEO Google and Alphabet in his article “The promise of AI for India and the World” opined that every technology shift is an opportunity to advance scientific discovery, accelerate human progress and improve lives. AI will do this on an unprecedented scale and India is uniquely positioned to play a leading role.

Artificial Intelligence (AI) technology is increasingly used in our everyday lives. It is used in a variety of industries from gaming, journalism/media, to finance, as well as in the research fields from water resources to robotics. In this chapter concept and applications of AI are discussed in brief.

6.1 Historical Background

After World War II, a number of people worked independently on intelligent machines. The English mathematician Alan Turing was the first who explained the concept of intelligent machines through a lecture in 1947. He stated that intelligent machines could be developed by programming computers rather than by building machines. Since late 1950 many researchers are working on intelligent machines, mostly on programming computers

The artificial intelligence (AI) world is quickly growing as it reaches several different industries. You currently will see AI used for many different purposes from agriculture to automotive; with the passage of time you will see even more of it. Agriculture is one of the most important branches of the IT industry. Agriculture is an important industry and is a big part of our economy’s base. In terms of annual sales, the agricultural industry contributes to our economy almost 17%.AI is becoming a technical advancement that boost and protects crop yield, as climate change and populations rise. Here in this chapter basics of Artificial Intelligence have been discussed how it can be related to agriculture.

1. Introduction

Artificial Intelligence has become most prominent in current generation. Every field is utilizing Artificial Intelligence for their better results and which also result in saving a lot of time. As Artificial intelligence is boosting different sectors to increase the productivity and efficiency and its utilization across different sectors like in the field of CIVIL Artificial Intelligence can be used to analyze the structures of buildings, dams etc., and Artificial Intelligence solutions are assisting in so many ways to overcome the traditional challenges in every field.

I. What is Artificial Intelligence

Artificial Intelligence is one of the most prominent field of Computer Science Engineering which attempts to redefine the tasks which are carried out by humans in their daily life with better results and maximum accuracy. Artificial Intelligence is actually meant to ease the work of human where the word artificial states the work done without any human interference and intelligence states the capabilities like human brain to perform tasks. The field artificial Intelligence has given so many definitions from time to time which can be typically stated as

Artificial Intelligence (AI) is technology which can store, retrieve, manipulate, manufacture, transmit or receive, analyze any digital information and can apply machine vision for increasing efficiency and workability of the system. The AI permits systematically scope of ‘3S’ i.e. Safety, Security and Surveillance, which is also known as manmade intelligence. In fact, it needs more reliable and accurate data or information for processing and correction for predicting performance of any system and devices.

Artificial intelligence is founded on the idea that human intelligence may be described in such a way that a computer can simply imitate it and carry out tasks ranging from simple to sophisticated. Artificial intelligence is assisting several agricultural sectors in increasing output and efficiency. In every industry, AI technologies are assisting in overcoming traditional hurdles.

AI intervention in agriculture is assisting farmers in increasing their farming efficiency while reducing harmful environmental impacts. The agriculture business has embraced AI with open arms in order to improve overall results. The way food is produced is changing as a result of artificial intelligence. Incorporating AI technology into agriculture aids in the control and management of any unwelcome natural occurrence.

1.1 Introduction

Since the beginning of humankind, we have thrived as a species due to our unique capabilities. These skills have developed and progressed over the centuries to the point that, in recent decades, we have been able to build machines that can imitate our intelligence, as far as we comprehend it. A novel type of world may lie ahead of us.

Artificial intelligence is the future, and the future is here." - Dave Waters

Artificial intelligence (AI) refers to the replication of human intelligence in computers, which are programmed to think and behave in a manner similar to humans. Literacy, logic, problem-solving, perception, and linguistic appreciation are all manifestations of cognitive abilities. Artificial Intelligence refers to the development of computer systems, computer-controlled robots, or software that are designed to exhibit intelligent behavior similar to that of the human mind. The term artificial intelligence is composed of the word "Artificial," which denotes something created by humans rather than existing naturally, and "Intelligence," which refers to the capacity to gain and utilize knowledge and skills.AI is achieved by the analysis of patterns in the human brain and the evaluation of cognitive processes. The culmination of these studies leads to the creation of sophisticated software and systems with advanced intelligence. The term AI was coined by McCarthy et al. 2006 while working on Dartmouth summer research project in which they proposed that machines have the capability to emulate "every facet of learning or any other characteristic of intelligence."

Abstract

Natural sunlight is the cheapest source available, but for horticulture it is not always attainable in sufficient quantities. Therefore, the use of artificial light has become very common in order to increase production and quality. Under artificial lighting technologies, LED lighting is one of the technology that can help in producing crops and flowers in a more effective and sustainable way around the world. The benefits of LEDs are that the spectrum and intensity can be selected and adjusted, the energy efficiency is higher than most conventional light sources and their small size, durability, long lifetime, cool emitting temperature, and the option to select specific wavelengths for a targeted plant response make LEDs more suitable for plant-based uses than many other light sources. These advantages, coupled with new developments in wavelength availability, light output, and energy conversion efficiency, can bring about a revolution in horticultural lighting. Light quality plays a major role in the appearance and productivity of ornamental and food specialty crop species. Far-red light, for example, is important for stimulating flowering of long-day plants (Deitzer et al., 1979; Downs, 1956) as well as for promoting internode elongation (Morgan and Smith, 1979). Blue light is important for phototropism (Blaauw and Blaauw-Jansen, 1970), for stomatal opening (Schwartz and Zeiger, 1984), and for inhibiting seedling growth on emergence of seedlings from a growth medium (Downs, 1956). The interactions are complex and continue to be unraveled at the molecular level (Devlin et al., 2007), but much of our understanding of these responses comes from studies with narrow-waveband lighting sources, in which LEDs provide obvious advantages. Thus, one potential role of LEDs in horticulture could be to enhance desired characteristics for specific crops. The artificial LED lightings increase the possibility of year-round production of ornamental plants, which will subsequently increase the income of growers related to ornamental industry. Light-emitting diodes pave the way for a better understanding of the interaction between light and pests, diseases, natural enemies and plants, as they make possible the use of very narrow wavelengths. LEDs as an option for reducing the use of growth retardants and obtaining better product quality in ornamental pot plants. Production of secondary metabolites increase with higher blue light ratio. Secondary metabolites production are increased and act against Reactive Oxygen Species (ROS) and pathogens, precondition the plant for environmental changes so they can cope with stress more efficiently.

12.1. Introduction

Artificial Neural Networks (ANNs) are computational models inspired by the way biological neural networks in the human brain process information. They consist of interconnected nodes or “neurons” arranged in layers: an input layer, one or more hidden layers, and an output layer. Each neuron in the network processes data and passes the results to the next layer. ANNs are designed to recognize patterns, learn from data, and make predictions or classifications based on that learning.

In an ANN, the connections between neurons are weighted, meaning each connection has a strength or value that determines the influence of one neuron on another. Through a process called training, the network adjusts these weights to minimize errors in its predictions. This is typically done using techniques like backpropagation, where the error is propagated backward through the network to update the weights (Abiodunet al., 2018).

ANNs are highly versatile and have been applied across various domains, including image and speech recognition, natural language processing, and decision-making systems. Their ability to model complex relationships in large datasets makes them a crucial component in the field of machine learning and artificial intelligence (Ahmed et al., 2023).

INTRODUCTION

There is growing concern in both the scientific community and the general public over the possibility of important climatic changes due to increases in relatively active gases in the atmosphere, a phenomenon commonly referred to as “climate change.” In the past century, the activities of a rapidly expanding and industrializing human population have added significant quantities of heat retaining gases to the atmosphere. For example, the Intergovernmental Panel on Climate Change (IPCC) estimates that by 2100 increases in greenhouse gases will likely lead to an increase in temperature of between I0⁰ C and 3.50⁰ C (Houghton et al., 1996) and an increase in sea level of between 13 and 94 cm (Warrick et al., 1996). The IPCC also reports that warmer temperatures will most likely intensify the hydrological cycle, leading to an increase in the precipitation intensity and number of storm events (Houghton et al., 1996). Our results of this study also agree with it.

INTRODUCTION

Artificial Neural Network (ANN) is a branch of the field in computer science known as “Artificial Intelligence (AI)”. The field goes by many names, such as connectionism, parallel distributed processing, neuro-computing, machine learning, and artificial neural networks. A tremendous growth in interest of this computational mechanism has occurred since Rumelhart(1986) rediscovered a mathematically rigorous theoretical framework neural network. Traditional (physically-based) modeling of physical processes tries to explain the underlying processes. On the contrary, the data-driven models are based on a limited knowledge of the modeling process and rely on the data describing input and output characteristics. Data-driven models are based on pure relationships between input and output data and not the physical principle linking input and output. They offer real advantages over conventional methods, including the ability to handle large amounts of dynamic, non-linear or noisy data and such tools can be especially useful when the underlying relationship are not fully understood. Data-driven modeling uses results from such overlapping fields as data mining, artificial neural networks, rule-based type approaches such as expert systems, fuzzy logic concepts, and machine learning systems.

Artificial neural networks are suited to problems where relationships between the variables to be modeled are not well understood. Mathematically, an ANN may be treated as a universal approximator. The ability to learn and generalize ‘Knowledge’ from sufficient data pairs make it possible for ANN to solve large-scale complex problems such as non-linear modeling, pattern recognition, classification, control and others – all of which find application in water resources management today. Since the early nineties, ANNs have been successfully used in water management area such as rainfall-runoff modeling, stream flow prediction, groundwater modeling, water quality, hydrologic time series, and reservoir operation.

The artificial neural network (ANN), a data driven model, is inherently suited to the problems that are mathematically difficult to describe. An ANN is a flexible mathematical structure that is capable of identifying complex nonlinear relationships between input and output data sets, where explicit knowledge of the internal processes is not available. In this chapter general structure of ANN is described and also explained briefly with a case study.

7.1 What is Artificial Neural Network?

An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous system, such as brain process the information. An ANN is an adaptive (Adaptive means that the system parameters are changed during operation i.e. training phase), most often nonlinear system that learns to perform a function (an input/output map) from data. In more practical term, neural networks are non-linear statistical data modeling tools. They can be used to model complex relationships between inputs and outputs or to find out patterns in the data.

Introduction

Global diversity in domestic animals and aquatic organisms is considered to be under threat worldwide. Worldwide 11 % birds, 25 % mammals and 34 % of fish species are threatened (Lovell-Badge, 2001; Vemuganti and Balasubramanian, 2002) and aquatic ecosystem is becoming more vulnerable to disasters due to run off from agriculture and industrial sources, oil spills or sudden environmental changes leading to total elimination of stocks from different ecosystems. The multifarious human activities in open waters have threatened the fish diversity all round the world. Fish worldwide are in crisis. The effective population sizes in fish hatcheries are getting smaller and smaller that causes loss to farmers worldwide. The World Resources Institute has reported that nearly 70 percent of the world’s marine fish stocks are over fished or are being fished at their biological limit. Apart from fish, across all live stock species there is a shrinking pool of genetic diversity. For instance, the effective population size for all dairy cattle breeds is less than 60 animals. To preserve the gene pool of unique populations by protecting them from extinction, loss of genetic variability (inbreeding) and dilution due to inter breeding with unrelated populations (hybridization) gene banks or germplasm repository can play a vital role. Germplasm repositories in fisheries could be used for: 1) restoration of threatened species, 2) brood stock improvement through genetic modification of a targeted population, and 4) information and technology development including gene pool database management.

The artificial seed production technique was first used in clonal propagation to cultivate somatic embryos placed into an artificial endosperm and constrained by an artificial seed coat. Today artificial seeds represent capsules with a gel envelope, which contains not only somatic embryos but also axillary and apical buds or stem and root segments (Vdovitchenko and Kuzovkina, 2011).

The prime requirements for preparation of artificial seeds are high frequency somatic embryogeniccalli, synchronous embryo development and maximum conversion of embryos into plants. Success in production of synthetic seeds mainly depends on how best callus development and plantlet regeneration are achieved. However, over time the morphogenetic competence of differentiated cultures declines (Lynch and Benson, 1991). Therefore, the primary goal of synthetic seed production is to produce somatic embryos that resemble more closely to the true seed embryo in storage and handling characteristics so that they can be utilized as a unit for clonal propagation and germplasm conservation. Synthetic seeds may be hydrated or dehydrated and may be quiescent or not. Encapsulation of micropropagules enables to satisfy the requirements of synthetic seed development. The gelling agents used for encapsulation for production of synthetic seeds act as protective cover. The encapsulated synthetic seeds also contain growth nutrients, plant growth promoting microorganisms (mycorrhizah, Rhizobium, etc.), and/or other biochemical constituents necessary for optimal embryo-to-plant development (Fig. 4.1). Fungicides may also be used in the liquid gelling medium to protect them during storage and germination in vitro and in vivo.

Introduction

1. The condition has been reported the world wide in growing broiler chickens.
2. The affected birds show clinical signs usually during 4 - 5 weeks of age. The clinically affected birds are smaller, listless with ruffled feathers, pale head and shrunken comb. Severely affected birds have distended abdomen, which restricts their normal movement. Death may occur suddenly, and not all the broilers which die of the condition have ascites. The incidence of the disease varies between 2 to 20%.

Ascorbic acid (vitamin C) is present in almost all fresh fruits and vegetables in varying quantities ranging from 0.02 to 1.0 mg per g fresh weight. It is most abundantly found in bittergourd and berries.

The method for estimation of ascorbic acid is given here below as described by Albrecht (1993). It is an easy and simple method based on titration technique.

Fruit, vegetables and their products are important sources of ascorbic acid. Aonla, guava and citrus fruits are good sources of Vitamin C (Ascorbic acid).Ascorbic acid is sensitive to heat, light and oxygen but is stable in acidic
 media. The methods for estimation of Ascorbic acid are based on the reduction of 2,6 -dichlorophenol - indophenol dye by ascorbic acid and those based on the reaction of dehydroascorbic acid with 2,4- dinitrophenylhydrazine. However,the 2,6 -dichlorophenol - indophenol dye reduction method is most commonly used in the estimation of ascorbic acid in fresh fruit and vegetables and their processed products.
2,6 dichlorophenol - indophenol visual titration method
The dye, which is blue in an alkaline solution and red in an acid solution, isreduced by ascorbic acid to a colorless form. The reduction is quantitative and specific for ascorbic acid in solutions in the pH range of 1-3.5.
Reagents
i. 3% Metaphosphoric acid (HPO3) solution:Dissolve 3g sticks/ pelletsofMetaphosphoric acidin a volumetric flask and make volume to 1oo ml with glassdistilled water.

Explant

The tissue obtained from plant to be cultured is known as Explant. It may include the parts of shoots, leaves, stems, roots, flowers and callus.

Maintenance of Aseptic Environment

All culture vessels, media and instruments used in handling tissues as well as the explants must be sterilized. The importance is to keep the air surface and floor free of dust. All operations are carried out in laminar air-flow, a sterile cabinet.In general, the methods of elimination of these sources of infection can be grouped under different categories of sterilization procedures: 

7.1. Introduction

In the modem lifestyle, people are extremely busy in their work and lack the time to cook their own foods. They mainly depend upon processed and packaged food for their nutritional intake. So it becomes essential that the packaged products should be safe, hygienic and shelf stable. To preserve the food for long duration, thermal processing is most suitable method. Aseptic packaging is a form of thermal food processing. Aseptic packaging can be defined as the filling of sterile containers with a commercially sterile product under sterile conditions and then sealing the containers so that reinfection is prevented; that is, they are hermetically sealed. 

Aseptic packaging is a specialized and advanced method used to extend the shelf life of perishable foods without the need for refrigeration. This technique involves sterilizing both the food product and the packaging material separately and then filling and sealing the product in a sterile environment. Aseptic packaging has transformed the food industry, allowing products such as dairy, juices, soups, and sauces to remain fresh and safe at room temperature for extended periods. The ability to maintain product quality, nutritional value, and safety while reducing reliance on cold storage has made aseptic packaging a preferred choice in both food manufacturing and distribution. The process of aseptic packaging is both complex and precise, as it requires thorough sterilization of every component to ensure food safety. Packaging materials, typically a combination of paper, plastic, and aluminum, are carefully selected to withstand high temperatures while providing an effective barrier against contamination. This chapter explores the principles of aseptic packaging, its significance in food preservation, and the advanced technologies and materials used to achieve and maintain sterility in packaged foods.

Vegetative propagation enables horticulturists to multiply plants while retaining desirable genetic characteristics of selected mother plants. This chapter covers important methods including cuttings, layering, budding, grafting, division, and specialized vegetative structures. The physiological basis of rooting, wound healing, callus formation, compatibility, and environmental requirements is discussed. Grafting and budding are particularly important for combining desirable scion characteristics with suitable rootstock traits such as vigor, disease resistance, stress tolerance, and adaptation. Proper sanitation and selection of healthy propagation material are emphasized to minimize pathogen transmission. Modern techniques such as rooting hormones, mist chambers, protected propagation, and clonal multiplication further improve the efficiency and uniformity of vegetative propagation.

The inorganic residue remaining after the destruction/burning of organic matter in foodstuffs is called ash. Ash contents in food commodities roughly represent the mineral contents, however, some minerals are likely to be lost due to volatilization or some interaction between constituents during ashing. Estimation of ash content is also used as a measure to judge the quality of fruit products. The presence of high ash content or low alkalinity of the suggests the presence of adulterants in the sample. Similarly, the presence of a high amount of acid-insoluble ash indicates the presence of sand and other silicious matter in the food products.
Principle
Organic matter is burnt off at as low a temperature as possible. Heating is done in stages, first to char the product thoroughly and finally to ash it at 550ºC in a muffle furnace. The inorganic material left after burning organic matter is cooled and weighed.
Apparatus
* Silica Crucibles
* Muffle furnace
* Desiccator
* Balance

Botany: The ash gourd(Benincasa hispida) belonging to the family cucurbitaceae is an annual creeping vine that can either climb structures or be allowed to spread out on the ground. This plant features large green leaves and thick stems covered with coarse hairs. The showy, golden yellow blooms appear early in the summer, and female flowers give way to round or spherical fruits. Young ash gourds are covered with a soft down that disappears with maturity. Fully matured gourds have a white, waxy coating covering the surface.

Field preparation:The field selected for seed production must not have been sown with ashguard in the previous season. This is done to avoid volunteer plants that cause admixture.After proper ploughing, at a spacing of 2.5 x 2 m distance take pits having 45 cm length, width and height. Ten days after that, apply 10 kg FYM and urea 30 g. Super phosphate 72 g and potash 19 g per pit. Then mix the above nutrients with soil and fill the pits and level them.

Soil and climate:Soil with neutral pH must be selected. Loam or clay loam soils are best suited. Higher organic matter will lead to production of vigorous seed.Seed is very sensitive to whether. Hence selecting the right season is necessary. Though ashgourd can grow through out the year, seed crop should be grown such that the seed matures in cool dry climate. This will facilitate proper ripening of fruits and reduce the pest and disease infection. Seasons are selected with this idea in mind. In