eChapters

In 2009, the world celebrated the 200th anniversary of the life and work of Charles Darwin, a transformational scientist who brought about a revolution in our understanding of evolution.  Evolution through natural selection among living organisms leading to the survival of the fittest was a concept which was alien to Christian thought in Darwin’s time, as faith was strong in the divine creation of the living forms of our planet.  Evolution of higher forms of life, including human beings, from fish and other forms of living organisms was an accepted view in ancient Indian thought, as exemplified by the ten forms of manifestation on earth of the Hindu god Vishnu.

“Variety is the spice of life” is a common saying.  Variation is a must for selection to occur.  Today, we are confronted with the prospect of human-induced changes in climate, leading to adverse variations in temperature, precipitation, flood and sea level.  We will have to be prepared for facing the consequences of drought, flood and coastal storms more frequently.

Dashboards play a crucial role in the fields of Machine Learning and Artificial Intelligence by providing a visual and interactive interface through which complex data, model outputs, and performance metrics can be easily understood and monitored. In data-driven environments, where vast amounts of information are processed continuously, dashboards serve as an essential bridge between technical systems and human decision-making. They transform raw data and analytical results into meaningful visual representations, enabling users to interpret insights quickly and effectively. In the context of Machine Learning and Artificial Intelligence, dashboards are used at multiple stages of the workflow. During data exploration and preprocessing, dashboards help visualize trends, patterns, and anomalies in datasets, allowing data scientists to make informed decisions about feature selection and data cleaning. Once models are developed, dashboards

Agriculture has long been at the mercy of the weather, and in today’s datadriven world, harnessing meteorological information is more critical than ever. Weather intelligence—the process of collecting, analyzing, and disseminating weather data—supports decision-making in diverse fields such as aviation, transportation, emergency management, and especially agriculture (Fig 3.1). This chapter explores how advanced data acquisition methods and robust database management techniques underpin agricultural weather intelligence. It covers the variety of data sources available, details strategies for integrating and ensuring the quality of vast datasets, and examines the forecasting techniques that transform raw data into actionable insights for precision forecasting and decision making in food production. Fig. 3.1. Weather Data Acquisition System In this chapter, we not only discuss the technological means by which weather data is collected—from satellites, ground sensors, and IoT networks—but also dive into the structure of weather databases. These repositories house surface weather observations, radar and satellite imagery, upper air measurements, and outputs from weather models. Further, we outline the different forecast types and forecasting methodologies that are essential to interpreting this data, ranging from nowcasting for immediate weather conditions to seasonal forecasting that supports long-term planning. Finally, the role of big data analytics in supporting precision forecasting and optimizing decision-making in agricultural production is examined, highlighting the integration of advanced techniques like numerical

Introduction

The most significant part of the research report is analysis and data interpretation. This chapter presents the analysis of data gathered through the questionnaire designed for the study. The study's primary data was collected from 266 (two hundred and sixty-six) Library and Information Science (LIS) professionals working in the eight-state universities in Kerala. It includes a detailed analysis of major results and pertaining information for arriving at a valid conclusion. It helps to interpret the results of the study from the proper perspective. Based on the set forth objectives and hypotheses formulated, the data collected through questionnaires were tabulated, and statistical analyses have been done to formulate the result of the study.

This chapter presents the analysis and interpretation of data gathered through a structured questionnaire to conduct the current study. Data analysis and interpretation of data is the most significant part of the research report. It contains a detailed analysis of major results about the information for arriving at a valid conclusion. It helps to interpret the results of the study in a proper perspective. Based on the objectives and hypotheses formulated, the data was collected through a questionnaire. Likert’s scale was used to assess the opinions of the respondents. 

Some basic and most common analysis tools used in research are summary statistics. These can be analyzed in Ms-Excel through the following ways.

8.1 Summary Statistics

The following data are the yield (q/ha) of 60 varieties of paddy maintained in a research station for breeding trails:

53 ,74, 89, 65, 88, 65, 45, 70, 25, 80, 75, 85, 47, 63, 78, 44, 42, 51, 59, 86, 76, 48, 30, 38, 67, 78, 74, 68, 58, 59, 36, 76, 89, 48, 67, 69, 35, 46, 89, 75, 79, 56, 42, 41, 60, 65, 68, 69, 61, 63, 95, 94, 85, 83, 76, 71, 68, 62, 64, 62.

Calculate the summary statistics for the study of the data.

Solution: The summary statistics of the data using MS – excel can be obtained / analyzed through following steps:

Step 1: Open Excel sheet and feed the data as given in Fig. 8.1.

Step 2: Go to data menu and select Data Analysis. Sometimes this menu is not available in the data, it can be added through add in → check in, analysis tool pack → go. It will appear as the way showing in Fig. 8.1.

5.1 Introduction

This chapter presents analysis of data collected through the questionnaire survey from agriculture libraries in Maharashtra (Constituent including University Libraries i.e. Government and Affiliated i.e. Private colleges). The purpose of the survey was to explore the status of CRS (Cyber Reference Service), various aspects pertaining to the CRS, and the ICT infrastructure used for the CRS in the agriculture universities and college libraries. It also aimed to obtain agriculture library heads’ perceptions about the CRS, and explore issues and problems affecting implementation and management of the CRS in the agriculture libraries in the Maharashtra state.

Agricultural marketing is a critical component of the economy, influencing the livelihoods of farmers, the operations of traders, and the decisions of policymakers. However, challenges such as price volatility, inefficient supply chains, and inadequate integration of data impede its efficiency. This chapter explores the transformative role of data analytics in addressing these challenges, emphasizing its potential to enhance transparency, optimize decisions, and streamline processes. Traditional data sources, including market prices and production data, are contrasted with emerging sources like remote sensing, IoT, and social media, while the integration of big data characterized by volume, velocity, and variety is discussed. Analytical techniques such as descriptive, predictive, and prescriptive analytics are detailed for their applications in market trend analysis, price forecasting, and supply chain optimization. Advanced models, including ARIMA, LSTM, and Random Forest, are presented alongside market basket analysis to demonstrate their utility in decision-making. The chapter further examines the role of analytics in decision support systems, market timing, and supply chain optimization while addressing challenges like data quality, integration issues, and adoption barriers. By providing a comprehensive framework for leveraging data analytics, this chapter serves as a valuable resource for researchers, practitioners, and policymakers seeking to revolutionize agricultural marketing.

Abstract
Agricultural marketing is a critical component of the economy, influencing the livelihoods of farmers, the operations of traders, and the decisions of policymakers. However, challenges such as price volatility, inefficient supply chains, and inadequate integration of data impede its efficiency. This chapter explores the transformative role of data analytics in addressing these challenges, emphasizing its potential to enhance transparency, optimize decisions, and streamline processes. Traditional data sources, including market prices and production data, are contrasted with emerging sources like remote sensing, IoT, and social media, while the integration of big data characterized by volume, velocity, and variety is discussed. Analytical techniques such as descriptive, predictive, and prescriptive analytics are detailed for their applications in market trend analysis, price forecasting, and supply chain optimization. Advanced models, including ARIMA, LSTM, and Random Forest, are presented alongside market basket analysis to
demonstrate their utility in decision-making. The chapter further examines the role of analytics in decision support systems, market timing, and supply chain optimization while addressing challenges like data quality, integration issues, and adoption barriers. By providing a comprehensive framework for leveraging data analytics, this chapter serves as a valuable resource for researchers, practitioners, and policymakers seeking to revolutionize agricultural marketing.
Keywords: Agricultural Marketing, Data Analytics, Predictive Modeling, Supply Chain Optimization, Market Forecasting, Big Data.

Introduction

The term analytics and data analytics are used inter-changeably. When referring to analytics, it means “analysis of data” or “what can be learnt from an analysis of data”. In an industry like fishing industry, the researchers have been slow to adopt the tools used to portray accurate representations of data. For example, a dashboard with historical data from the past ten or fifteen years displayed on a digital map can enable the researchers to decide the places where fishing can be good. This map can help in locating the points fished during specific seasons. This will enable the researchers to filter the data on various parameters like area, year, season etc. or on any other specific parameter which can give valuable information. Similarly, this type of dashboard can affect the decision making process while fishing, like one can find the monetary value associated with each trip during a specific season or compare the values associated with two different trips to gauge the cost-benefits.

Data Analytics helps in taking most informed decisions in the fishing industry if one of the goals is to increase income while ensuring sustainability. It helps in deciding whether to reduce overhead costs or to increase expenditure to avoid overhead costs in future.

Fisheries sector undergoes continuous changes with introduction of newer technologies evolved through research and development institutions. Statistics per se deals with generation of data, data management, data analysis and information generation from data. There are varied disciplines of fisheries viz., Aquaculture, Fisheries Resource Management, Fish Genetics, Fish Biotechnology, Aquatic Health, Nutrition, Environment, Fish Physiology, and Post-harvest Technology, wherein research on practical aspects is undertaken which affect production and sustainability.

2.1. Open source satellite data

The satellite images have been invaluable information sources for Natural Resource Management. They provide synoptic view of the Earth periodically helping in inventory, surveying, and monitoring in agriculture, hydrology, geology, mineralogy, land cover, land use and environment. Free global satellite image data of spatial resolutions of 1m to 1 km and spectral resolution of single band to hyperspectral are available from an increasing number of sources (Table 2.1).

Data cleaning is one of the most important parts of machine learning. It plays an important role in building a machine learning model. Data quality is a significant aspect to train the ML model. Inaccurate data can have an impact on results. Data quality problems can occur anywhere in information systems. A technique that helps to convert improper data into meaningful data. Machine Learning is datadriven. With the data cleaning techniques, your Machine Learning model will perform better. So, it is important to process data before use. Without quality data, it is unwise to expect a correct output. Data cleaning refers to identifying and correcting errors in the dataset that may negatively impact a predictive model. It is used to refer to all kinds of tasks and activities to detect and repair errors in the data. These problems can be solved by using various data cleaning techniques. The process of fixing or removing incorrect, corrupted, incorrectly formatted, duplicate, or incomplete data within a dataset. When combining multiple data

Data refers to any collection of facts, observations, measurements, or values that are typically numerical, but can also be qualitative. It's raw material that can be processed and organized to provide context, relevance, and meaning. In its raw form, data may not carry any specific meaning and might appear as a series of numbers, text, symbols, or images.

Types of Data

• Quantitative Data: Numerical data that can be measured and expressed with numbers (e.g., height, weight, temperature).

Data Collection and Report Writing

Many a times you may be asked questions like what is the average milk production of deshi cows of your area? What is the average lactation period of CB cows of your area? or maybe what is the impact of AI programme in your area? etc., by your higher officers. How to answer all these questions? All these questions may be answered scientifically if you possess elementary knowledge on statistics. We have to frame a research design and to collect data to answer these questions.

What is Data ?

Data is a collection of facts, such as numbers, words, measurements, observations or even just descriptions of things. Example: 5, Ram, Kilogram, Good, Male, etc. Independently they do not produce any meaning.

These are special types of information, generally obtained through observation, surveys, enquiries or are generated as a result of human activities.

Once you have decided what to study and how to study, you are faced with the task of systematically collecting reliable and valid evidence upon which you can base your findings. Data (singular datum) are facts which are observed and measurable phenomena. The purpose of gathering and summarizing data is to transform them into information. The data collected in the research study may be quantitative or qualitative in nature. Quantitative data can be counted and can be computed. Such as age of a boy, marks scored by a student, distance, etc. Quantitative data are easier for analysis. We also collect qualitative data like sex of a person as Male or Female or Transgender. The qualitative characteristics can be counted, but as such cannot be computed. For example, we may get “Yes’ or “No” to a question to farmers about vaccination of his animals. For this “Yes” or “No” , we may assign 0 to “Yes” and 1 to “No” in an artificial or nominal way to categorise these qualitative data, and go for computation. So, quantitative data are expressed in the form of numerals and are amenable to statistical analysis readily. Whereas, qualitative data are descriptive in nature and can be statistically analysed only after processing and after having them classified into some appropriate categories. Data is required to make a decision in any business situation. The researcher is faced with one of the most difficult problems of obtaining suitable, accurate and adequate data. Utmost care must be exercised while collecting data because the quality of the research results depends upon the reliability of the data. There are basically two sources from which we obtain data for our research works. They are known as primary data and secondary data.

Reliable artificial intelligence depends on accurate, timely and multidimensional livestock data. This chapter examines the transition from manual record-keeping to sensor-based systems that capture physiological, behavioural, production and environmental information. Data sources include wearable devices, IoT monitoring networks, computer-vision systems and environmental sensors. Their applications include monitoring health, welfare, movement, feeding and productivity. The chapter also considers the integration of heterogeneous datasets and persistent challenges involving missing values, noise, interoperability, scalability and system reliability. By connecting data generation with intelligent analysis, it emphasizes that robust acquisition protocols and dependable infrastructure are essential for developing effective, evidence-based and responsive livestock-management systems.

Now we have to learn how to enter numbers and text, how to edit any erroneous entry and then how to do simple calculations. Open empty excel spread sheet by clicking on the start menu in the window tool bars, click on Programs and then click on the Excel menu item.

6.1 Entering Numbers

Numeric entries are constant, can be integers, decimal fractions, integer fractions and scientific nations which can be entered by typing the number in the active cell [cell which can be made active by clicking the mouse on the cell.

6.1 Introduction
Our journey through remote sensing has, thus far, focused on the remarkable capabilities of various platforms and sensors to observe Earth’s atmosphere and surface. From the localized, high-resolution insights provided by groundbased instruments like Wind Profilers and SODARs, to the expansive, global coverage offered by an array of satellite-borne imagers, sounders, radars, and lidars, we’ve seen how a continuous stream of invaluable meteorological data is acquired.
However, the mere act of collecting this data, no matter how sophisticated the technology or comprehensive the observations, represents only the initial phase of its lifecycle. The true power and utility of remote sensing data are unlocked only when it can be efficiently organized, securely preserved, and readily available to the diverse community of meteorologists, climate scientists, researchers, and operational forecasters who rely on it daily. This necessitates a profound understanding of the principles and practices governing data formats, data storage, and data access.
The sheer volume, velocity, and variety of remote sensing data pose significant challenges. Petabytes of information are generated annually, requiring robust infrastructure and standardized methodologies to ensure its integrity, interoperability, and long-term usability. Without effective strategies for managing this deluge of information, the potential of remote sensing to enhance weather prediction, advance climate science, and inform critical decision-making would remain largely untapped. 

Introduction

The biological information that are being generated by research in modern biology worldwide is so huge that it is not possible to manage through conventional file keeping or simple computing. Secondly, analysis of these data certainly needs specific interfaces, software and management facilities. Therefore, such requirements to store, analyze and manage the biological information/data in an appropriate way has led to the origin of a new branch of science called “Bioinformatics”. Here, emphasis will be given on the disciplines of research mostly from which generation of data is made. Broadly, they can be classified as follows.

This chapter deals with data importing, exporting and data manipulations in R. R can import almost all kinds of data format. The basic data format of .txt and .csv and data from other softwares like MS office .xls and .xlsx, spss ……, stata ……., etc. however, we will discuss in this chapter to read and write the basic formats and the .xlsx data which we use the most. Further, we will also discuss the basic data manipulations. For a detailed reading on data manipulation, readers can refer to the first book of the series namely “Data Handling and Manipulation in R”.
2.1. Primary Spectral Data Processing
The original spectra consisting of relative reflectance values of 2151 points (at 1 nm interval) between 350 and 2500 nm were averaged at every tenth-nanometer wavelength interval from 360 to 2490 nm by integration technique. Thus, the new spectra contained reflectance values at 360, 370, 380, 2490 nm, are inclusive. For example, the new reflectance value for 360 nm represented an integrated value of the original reflectance values from 356 to 365 nm, inclusive. Similarly, the reflectance at 400 nm was an integrated reflectance values from 396 to 405 nm, while the reflectance at 2490 nm was an integrated value of reflectance from 2486 to 2495 nm. This was done to reduce the volume of data for analysis and to match it more closely to the spectral resolution of the instrument (3 to 10 nm). This procedure resulted in a new dataset, with reflectance values specified for 214 wavelengths for all samples, which were further processed for noise removal.
2.2. Importing Data in R
We can rerad many format of tabular data in R such as excel, text, csv, etc. In thid book we will be using the csv format. Before reading the data, arrange data in excel/CSV sheet so that spectral data in column is followed by chemical data/ lab data. This will ensure that if any soil property or properties added in next column there is no need to change code for selection of spectral data in R environment.

Abstract

Carrying out effective and sustainable agriculture has become an important issue in recent years. A key to this is the usage of modern technologies for precision agriculture. Recent technological developments allowed envisioning sensor devices with distributed ambient sensory network, which could be a potential technology for monitoring various natural phenomena (weather parameters, soil moisture, etc.) at micro level. As more and more agricultural data are virtually being harvested along with the crops and are being collected/ stored in databases, the same can be used in productive decision making if appropriate data mining techniques are developed/applied. As a case study for this, an experiment was conducted with four consecutive agricultural (Kharif and Rabi) seasons in a semi-arid region of India to understand the crop-weather-environment-pest/diseases relations using wireless sensory and field-level surveillance data on closely related and interdependent pest/disease dynamics of groundnut crop. Association rule and multivariate regression mining techniques/algorithms were propose developed /tailor-made to turn the data into useful information/ knowledge/relations/trends to know crop-weather- environment-pest/disease continuum. These findings have been used for development of prediction models (cumulative and non-cumulative) followed by a web based pest/disease decision support system.

Keywords : Data Mining, Pest/Disease Management, Precession Protection, Wireless Sensor Networks