eChapters

Introduction

Food supply is a major concern in the near future as the human population touches 9 billion in 2050 and therefore, more food has to be produced. This has to be achieved in the face of climate change amounting to constant pressure of biotic and abiotic stresses. However, Swaminathan (2007) opined that science and technology can play a very important role in stimulating and sustaining an evergreen revolution leading to long-term increases in productivity without associated ecological harm. Rice is considered as global grain since it is consumed by more than half of the world population. In India rice supplies calorie requirement to more than 70 per cent of its population. This is evident from the fact that rice is cultivated in all the 30 states and 5 union territories of the Indian subcontinent of diverse ecologies ranging from below sea level to mountainous regions. Though India tops in rice acreage (43.61 mha) its productivity of 3.19 t/ha (rough rice) is far below world average of 4.12 t/ha and that of Asia’s average of 4.19 t/ha (Shobharani et al., 2010). This low productivity is mainly due to unfavourable ecologies of the varied ecosystems which, rice encounters during critical stages of its growth. Salinity and submergence are major abiotic stresses, next to drought, limiting rice production in South East Asia including India.

In India nearly 8 mha are salt affected of which 2 mha are coastal saline and 3.4 mha are sodic (Singh, 1994). Rice is predominant crop in these areas especially in vast stretches of eastern and western coasts of India. The presence of salts, in excess to plant growth, in the soil solution makes the soil detrimental to crop growth. The source of the excess salt may be from soil or irrigation water. The content and composition of salts (ions) in tandem with types of soil and weather conditions prevailing during the crop period decides the severity of salt stress. Similarly, f lash floods or short-term submergence regularly affect rice growing areas in South and Southeast Asia. Even more favorable irrigated areas experience flooding problems during the monsoon season. It is also prevalent in rainfed lowlands where most of the present day rice varieties do not survive complete submergence for more than a week. In India 30% of the rice growing area is prone to such menace resulting in severe yield losses (Neeraja et al., 2007).

Introduction

Global warming directly ref lects on rising sea levels due to melting of ice caps and natural expansion of sea water as it becomes warmer. Consequently, areas adjoining the coast and wetlands could be frequently flooded and the distribution pattern of monsoon rains may alter, through more intense downpours, storms and hurricanes. The meteorological data available at the Annamalai University, for the tail end of the Cauvery river delta region of Tamil Nadu State, India, shows that the average annual rainfall during the last 10 years segment has increased by 233 mm compared to the average of the previous 10 years segment (1588 mm and 1355 mm, respectively). In contrast, annual evaporation has reduced by 453 mm (2153 mm and 1700mm, respectively) (Kathiresan, 2011). The year 1990 was the hottest year in the last century with all other five of the warmest years in the century falling within the last 22 years. This trend indicates that f lash floods in wetlands and droughts in uplands have become more frequent. Such a changing climate warrants reinforcement of climate resilience in farming to protect the livelihoods of farmers and the biodiversity. The sub-project of the National Agricultural Innovation Project implemented by Annamalai University in Tamilnadu, sponsored by ICAR has identified three types of clusters in each of the four disadvantaged districts, based on the prevailing agro-ecology viz. wetland clusters, rainfed upland clusters and coastal shore farming clusters. The constraints for farming and livelihoods in these clusters are identified as frequent floods, inundation, drought, weed problems, crop failure, and lack of diversification (Kathiresan, 2009a and Kathiresan, 2010). Farming systems that would be resilient to such climatic and farming constraints designed through rigorous institutional and on-farm experiments (Kathiresan, 2007; Kathiresan, 2009b and Kathiresan, 2012) were disseminated for adoption by the farmers in these clusters.

Coastal areas are defined as the interface or transition areas between land and sea, including large inland lakes. Coastal areas are diverse in function and form, dynamic and do not lend themselves well to definition by strict spatial boundaries.

Economic importance of coastal areas

Many of the world’s major cities are located in coastal areas, and a large portion of economic activities are concentrated in these cities. The coastal zone is an area of convergence of activities in urban centres, such as shipping in major ports, and wastes generated from domestic sources and by major industrial facilities. Many of the world’s most productive agricultural areas are located in river deltas and coastal plains, which contribute for national economic growth.

7.1 Economics and Valuation of ghgs emissions

Since the late 20^th century, it has been largely accepted that cause of high concentration of GHGs in atmosphere is induced by human activities. Greenhouse gas emissions and related climate change has opened up debate on overall economic losses and ways to reduce these loses. Moreover, apart from curbing monetary losses; the global political leaders as well as reputed economists are looking towards making money by saving the emissions. Recently, the researchers have started to emphasize on the actual value added to the ecosystem by curbing emissions, discrete of the economic benefits. This section will discuss the economics and ecosystem services related to the management of GHG emissions.

Origin

The initiative to curb the emissions started in 1992 with the United Nations Framework Convention on Climate Change (UNFCCC) at the Earth Summit in Rio de Janeiro. The Convention took place from 3 to 14 June, 1992. The UNFCCC is an international environmental treaty designed to “stabilize greenhouse gas concentrations in the atmosphere at a level that would prevent dangerous anthropogenic interference with the climate system”. The UNFCCC had non-binding limits on greenhouse gas emissions for individual countries and the framework was only meant for formulating precise international treaties (called “Protocols” or “Agreements”). It contained no execution mechanisms, however, it considered some negotiations and suggestions to formulate the action plans and regulation guidelines under UNFCCC to fulfill the objective of reduction of GHG emissions to the desired level.

What is mitigation of GHGs emission? We must be clear about the answer of this fundamental question. In simple term, the mitigation of GHGs emission is the way or means by which the emission of those gases could be reduced. As we know from the previous chapters of this book that the GHGs emission could be occurred from natural as well as anthropogenic activities. Natural activities included volcanic eruptions, ocean current fluctuations, continental drifts which are responsible for emission of huge amount of CO₂ and other GHGs. The reduction of emissions from those natural activities is beyond our capabilities. However, the human induced emissions of GHGs emission could be reduced. We studied in previous chapters that fossil fuel burning, industrial and energy sector pollution, deforestation, land use change and agricultural could contribute to GHGs emission considerably. Mitigation techniques are different for each of those sectors that governed by lot of interrelated factors. In actual sense, the mitigation of GHGs emission should includes all the measures that can curtail the anthropogenic emission from all sectors. But that is out of the scope of this book. In this book, we specifically address the mitigation principles, options and efficiency of different techniques/ practices in agriculture only.

In that aspect, the mitigation of greenhouse gases emissions in agriculture is defined as “the means and ways by which emissions of GHGs could be reduced from agriculture”. The ways and means actually referred to the techniques and practices and their amalgamation in agricultural sector both in production, processing and consumption aspects. So, mitigation is not only a techniques or combination of techniques it is actually an integrated approach for reducing greenhouse gases emission from agricultural systems. Primarily, there are two complementary approaches for mitigation of GHGs emissions from agriculture. Those two approaches are (i) supply-side and (ii) demand- side options or pathways. The supply-side approaches includes scientific land- use-changes, improvement of crop management, better livestock management practices, enhancing carbon storage in biota, soil carbon sequestration, significant substitution of fossil fuel by bio-fuels and use of renewable energy in agriculture. On the other hand, demand side approaches, taken in to account of shifting in the dietary pattern from non-vegetarian to vegetarian, curtail down the food loss and waste, and reducing the supply-chains (Figure 6.1). We can see, most of the approaches in supply-side are technology driven, while, approaches in demand-side are socio-economical and or policy driven. In this chapter we would thoroughly discuss the principles of mitigation, options of mitigation, mitigation cum adaptation approaches to reduce GHGs emission and climate change and few strategies to cope up with the vagaries of climate change.

5.1 Impact of climate change on agriculture

Climate change has both positive and negatively impact on agriculture, food security and land degradation. Climate change could exacerbate the land degradation processes by increases in rainfall intensity, drought frequency and severity, dry spells, f looding, heat stress, sea-level rise and permafrost thaw. The 1/4^th of ice-free land area in the world is prone to human-induced anthropogenic degradation (Certini and Scalenghe, 2011; Hooke et al., 2012). Soil erosion rate is 20-100 times faster than that of soil formation in agricultural field. The erosion rate is least is zero-tillage (non-disturbed field) and maximum at conventional intensive tillage practices. Climate change further exacerbates the land degradation. The permafrost areas, dry-lands, low-lying coastal regions, river deltas are more vulnerable. The occurrence of drought in dry-land was increased by around 1% per year during 1961-2013 periods. On an average 380-620 million people globally experienced desertification who lived in dry-land areas (1980s and 2000s) in South and East Asia, North Africa, Middle East, Sahara region, and Arabian peninsula. Moreover, people who are already living in degraded/ desertified regions are more negatively affected by climate change.

Specifically, the land surface air temperature has increased about twice as much as the global average temperature since the pre-industrial era. The land-surface air temperature has increased relatively higher than the world’s average surface (land and ocean) temperature since the pre-industrial era (1850-1900). The average land-surface air temperature has enhanced by 1.53°C (1.38-1.68°C), whereas, world’s surface (including land and ocean) air temperature has enhanced by 0.87°C (0.75-0.99°C). Subsequently, global warming triggered the frequency, intensity and duration of heat waves and related damage. The direct and indirect impacts of climate change on global agriculture is summarised below for an overall idea about the importance of the issues.

The measurement of greenhouse gases (GHGs) has been started during middle of the last century. Initially, CO₂ and water vapour were measured with other common meteorological variables like temperature, sunshine hours, rainfall, humidity etc., for monitoring the weather condition and pollution. The absolute or relative concentrations of gasses in atmosphere are used to measure basically for monitoring purpose. However, limited studies were dealt with actual gaseous exchanges of fluxes. The concern about gaseous flux measurement and GHGs-exchanges started after 1900s when people got concerned about anthropogenic pollution, environmental sustainability and climate change issues. The GHGs-exchanges in earth-atmosphere systems primarily occur due to change in meteorological variables, soil responses and physiological activities of crops. If we are interested for environmental data inventories, then absolute GHGs concentrations of atmosphere at a specific time is required. However, presently researchers, students, environmentalists, climate scientists are primarily interested for quantitative data on GHGs fluxes and or GHGs-exchanges. They want to know what and how much quantity of a particular GHG is emitting from unit area at unit time.

Flux refers to the amount of any gas emitted per unit area per unit time. The dimension of that is M A^-11 T^-1. (Where, M= Mass/ Quantity; A= Area; T= Time). The SI unit of flux is g m²s^-1. Therefore, flux is a vector. It has magnitude as well as direction. As for example positive flux of CO₂ from earth surface means, CO₂ is moving out from earth surface to atmosphere. If it moves in opposite direction then the flux would be negative. In that case CO₂ gas may be absorbed by the soil surface from adjacent atmosphere. Similarly, GHGs fluxes of earth surface are either positive or negative. Generally, positive GHGs flux refers to emission of GHGs from earth to atmosphere and vice versa.

3.1 Chemistry of greenhouse gases (ghgs)

Greenhouse gases (GHGs) are atmospheric-gases that have capabilities to absorb and radiate-back the infrared (IR) radiation in the earth-atmosphere system (Figure 3.1). In this process the atmospheric-gases absorb and radiate- back IR radiation in lower atmosphere effectively emitting and absorbing heat energy heat energy. They maintain the heat budget of earth-atmosphere and keep our plant warm. If we typically see the chemistry of those gases, the key point is that they should have dipole moments. This is the property which makes them capable to absorb and radiate-back the range of IR radiation. In a molecule when valence-electrons are not equally shared in a bond between the two atoms, a slight positive charge is developed above one atom and a negative charge on the other atom. That charge difference of the different atoms in a molecule generates the dipole moment. For instance, in water vapour (H₂O- vapour), an unequal sharing of electrons and or separation of charge causes dipole moment. In H₂O, the centre has a positive charge at the hydrogen atoms and negative charges are located on the oxygen atom. The magnitude of dipole- charges, vibration and stretching of O-H bond generates certain frequency of the oscillating dipole moment that actually regulates the absorption capacity of IR radiation by H₂O vapour.

Climate change is caused by both natural as well as anthropogenic causes and it has been changing since the inception of earth-atmosphere (Figure 2.1). In a broader sense, anthropogenic activities (human activities) also must be considered as natural one in longer time scale as human and their activities are also a part of natural-ecosystem-functions. Among the natural phenomena, volcanic eruptions and continental drifts significantly affect the earth’s precipitation and temperature. A huge volume of CO₂ is released due to volcanic eruption at a little span of time-period which heated up the earth-atmosphere. Climate variability is primarily governed by rise in sea temperature, movement of warm water from the Western Pacific towards Peru, and El Nino which occurs at an intervals of 3-7 years. Climate variability also influenced the alteration in temperature and precipitation world wide. And persistent climate variability cause long term climate change. Therefore, basically three drivers that causes climate change are, the alteration in the energy of sun received by earth-atmosphere (natural causes), variations of ref lectivity of earth-surface- atmosphere system (natural as well as anthropogenic causes) and fluctuations in the greenhouse effect (natural as well as anthropogenic causes).

1.1 Weather

Firstly, what is weather? Simply, the conditions in the atmosphere above the earth is called weather. It refers to the conditions such as wind, rain and temperature, prevailing at a particular location during periods of hours or days. We often ask “what’s the weather like today”? Any individual can answer to this question as it requires only a short term experience or say exposure to the atmosphere. The TV news forecasters predict weather each day and inform about the temperature, cloudiness, humidity, or possibility of storm in the next few days. Weather is localised, say, it’s a hot and cloudy weather in one part of the country and dry and windy on the other part.

1.1.1 What are the factors that influence weather?

Before we try to understand the factors that influence weather, we must understand what the components that describe a weather conditions are? Is it the rains, or the air temperature or both? The answer to this question is not so easy, and it’s a bit complicated. There are many components that constitute weather. Weather components include rain, cloud cover, sunshine, winds, hail, snow, sleet, storms, thunderstorms, heat waves and many more. These components are sometimes referred as weather parameters or climate elements. Each of these components define weather patterns of a particular area. These components determine the status of local atmospheric conditions. Again, as a basic definition, weather is the state of the atmosphere and majority of weather phenomena occur in the lowest layer of the atmosphere, called as the troposphere. Does it mean that ground conditions such as the topography, water bodies and vegetation of a particular area has nothing to do with it? No, it is not so. The state of the atmosphere is subjected to various processes taking place not only in the atmosphere but also in the ocean, the sea-ice, the vegetation, etc. Weather parameters or the components of weather form a sequence of events, and the influences are far reaching and they do not remain solely in the atmosphere. For example, terrestrial radiation impacts the air temperature, air pressure and humidity. The terrestrial location also influences the cloud formation. The clouds may or may not turn into precipitation depending on the outcome (cloud or rain), which is by and large governed by troposphere. Likewise, a lack of precipitation affects not only weather conditions, but also soil moisture conditions that may result in lowering of water levels (ground water table) in soil. Wind speed and direction are governed by the atmospheric pressure and air temperature. So, all these parameters or components are interrelated and the weather conditions are the outcome of their interactions. Therefore, we can say that, the three main components of weather are temperature, precipitation and solar radiation. These components are influenced by different factors.

In this Chapter the precision farming/ Agriculture is discussed along with its steps of implementation. It also includes how artificial Intelligence plays role to perform precision farming/ agriculture in various way along with its scope, limitation and challenges.

Introduction

The primary source of livelihood is agriculture in India, where two thirds of India’s population, services and the private sector account for the remainder. Agricultural land accounts for about 43 percent of the geographical area of India. In earlier days, India was largely dependent in terms of food imports, but over the years, the country’s production of grain and seeds was self-sufficient, and this effort led to the formation of the Green Revolution. In fact, there was strong effort to achieve food self-sufficiency. This trend has continued up to now and continuous improvements have occurred. Precision agriculture or precision farming means the right thing to do, in the right way, on the right place and at the right time. Precision agriculture is expected to suit the agro-climate activities to improve application precision. Farming land has declined a bit in the last 40 years but the number of farmers has increased. According to the 2010–11 Agriculture Census, a total of 138.35 million operating holdings were estimated (single farmers) and 159,59 million hectares were covered by operations.

Precision agriculture is a management technique that collects, processes and analyzes temporary, spatial and individual data and integrates this with other information in order to support management decisions based on an estimated variability to enhance efficiency of use of agricultural production resources, productivity, quality, profitability and sustainability. Precision Agriculture manages every input of crop production (fertilizer, specifically found calestone, herbicide, seeds, insecticide, etc. Reduce waste, boost income and maintain efficiency Place. Precision Agriculture adapts soil and crop management carefully to suit the different field conditions.

Introduction

The conventional approach of the human person for plant classification is comparing the color and shape of the leaves, but by using Artificial Intelligence analysis can provide quicker and more detailed results by analyzing the morphology of the leaves and provides more details about the leaf properties. Species Recognition has been a very important part of agriculture and there are thousands of species in plants which can be identified by a single person and even if it does so It will take a huge lot of time to do it.

In this chapter we will discuss and built a project related to identify species in flower with an image. In this project we will be using Artificial Intelligence different branches like machine learning, deep learning and computer vision to build such an amazing project. So, let’s begin

Introduction

In agriculture, plant diseases have always been a major problem, as they cause crop quality to decrease, resulting in yield. Plant disease has a range of effects from minor symptoms to serious damages in whole crop areas, which lead to high financial costs and significantly impact the agricultural economy, particularly in developing countries dependent on a single crop or on a few crops.

Various approaches have been developed to detect disease in order to avoid significant losses. Causal agents have been precisely defined by methods developed in molecular biology and immunology. However, for many farmers these techniques are inaccessible and require detailed knowledge of the field or substantial time and energy to be used. According to the United Nations Food and Agriculture Organization, most farms in the world are small and family-owned in developed countries. Such families provide food for a significant proportion of the population of the planet. However, hunger and food insecurity are not rare and there is restricted access to markets and services. For the above reasons, a great deal of work has been undertaken in order to establish methods that are sufficiently reliable and available to most farmers. Where Plant disease is an essential factor contributing to a major decline in plant production quality and quantity. Plant disease identification and classification are a significant role in improving plant production and economic development.

In this chapter of machine learning algorithms we will cover the basic algorithms of machine learning with their implementation using dataset and discuss their pro’s and cons of algorithms for better understanding and how to use them in any project or with any dataset to get an correct result which can useful for research or study.

Key Component

We defined a data set composed of audio, images and binary labels that provided an understanding of how we could train a model from snippets to classifications. This sort of problem is one of many kinds of machine learning problems when we try and predict a specified unknown label given known inputs, provided that a dataset of examples for which labels are known is called supervised learning. Let’s discus what are the major key components we have to get there

In this chapter we will cover all the basics libraries and some frameworks of machine learning, deep learning and computer vision. We will discuss all about their use with an example and instruction which will states the commands to install to those libraries for building any project in our system. So let’s begin

What is a Library?

Library is an aggregate of features and methods that allow you to take many actions without getting your own code written.

For instance, the libraries that you have to know are if you work with data, numpy, scipy, pandas, etc. They have very simple data processing functions that save you time for small tricks.

In this chapter we will talk about the tools which are required to make project in artificial intelligence. All this bellow discussed tools are uses python programming language for making any project in any respective field. We have discussed about how anyone can install and use the tools to built a real time project in artificial Intelligence.

Using Python IDE

To download and install Python visit the official website of Python https://www.python.org/downloads/and choose your version. We have chosen Python version as per requirement all the codes in this book were on python version 3.6 as you can see in the Fig. 7.1.

In this chapter we will look at the Expert system which can guide and assist an individual once it is provided with the enough Knowledge to do so. Here we will discuss about expert system and its architecture with proper steps of making an expert system in any field by several tools which are available to do so. For expert systems the most important is Knowledge Engineering which is the collection of Knowledge from an expert and Engineering it in such a form that a machine could understand it.

Introduction

One of the pioneering fields of AI study is Expert Systems (ES). It is proposed by researchers in the computer science department of Stanford University. An expert system is a computer system which emulates a human expert’s decision-making skills. Expert systems are developed by reasoning through information structures, representing laws, rather than through traditional procedural code, in order to overcome complex problems.

Expert Programs use professional expertise systematically to address human expert problems. An expert is an individual with experience in a specific field. The expert has expertise or special credentials which most people do not learn or care about. An expert can solve or solve problems more effectively than people can solve. Expert System actually emulates all these qualities of expert and solve the problem in a better way and fast.

Today, Expert System (ES) is used in the fields of finance, research, engineering, technology, medicine and many others where there is a well-defined problem area. The fundamental principle is that an expert method should also define the steps to illustrate why a problem can be solved. Unless an individual can justify his reasoning for Expert System.

Introduction

Agriculture has played an important role in the global economy in recent years. The further growth of the population is leading to a gradual decrease in the area of the agricultural land and further growing stresses on the farm system. Agricultural food production methods are rising in demand for successful and healthy. Innovative sensoring and motive technologies and advanced information and communications systems and Artificial Intelligence must supplement conventional agricultural management methods to speed up farm productivity growth more accurately, thereby promoting the production of high-quality and high-performance agriculture. Computer vision monitoring systems have become valuable tools in farm operations over the past decades, and their use has increased significantly.

What is Computer Vision?

Computer vision can be characterized as a field of AI for extracting information from digital images. The type of data obtained from an image may be different from recognition, navigational space measurements or applications of increased reality.

The applications of computer vision can also be described. Computer vision builds algorithms that recognize and use the quality of pictures for other purposes.

Deep learning emerged as a serious contender in the field from a 10-year explosive computational development. Deep learning is therefore a special form of machine learning, the algorithms of which are based on the structure and function of the human brain.

Machine learning VS Deep learning

Deep learning is arguably the most efficient form of machine learning. This is so important because they know the best way to solve the problem and how to fix everything. The following is a description of deep learning and machine Learning:

As we know there are different branches of artificial Intelligence and machine Learning of one of them which has become a most advance and widely used branch of artificial Intelligence in every field of this generation whether it may be either electronics, civil, mechanics, Bioengineering, medical or agriculture etc., In this chapter we will study about machine learning and its types with the most common algorithms of machine learning which are being mostly used in different scenarios and their implementation using python language has been discussed in the implementation part of this book. Here we will also see where machine learning can be used.

i. Introduction

Machine learning is a subset of Artificial Intelligence and one of the most important part of artificial Intelligence. It is a field of Computer science which is totally differs from traditional computational approaches. In traditional approaches, a set of instruction is explicitly provided to the algorithm to solve any problem. Whereas in Machine Learning is a domain of an AI which uses a statistical analysis and can enables a system to always learn from its data without any external inputs in order to give an essential output. Due to this machine learning makes computers in advance to make model which provide decision based on input data.

Machine Learning involves a lot of algorithms which usually based on their requirements and functionalities to use where and when. To make a machine learning model we always require the data on which model can be made. Machine learning uses the algorithm which continuously learns from the data available as training data. A machine learning model is generated after the training of algorithm from the data. After the training completes, when trained model is provided with other real-life data then you can get an essential outcome. For example, in figure 3.1 Machine learning Model we use a predictive algorithm and make a model by providing it with some data, and later on we can receive prediction’s based on real data as input.