eChapters

Agriculture 4.0, otherwise called “Digital Agricultural Revolution”, addresses a change in outlook in agriculture, utilizing state of the art innovations to improve different parts of cultivating tasks. These innovations include the Internet of Things (IoT), Artificial brainpower (Artificial intelligence), Huge Information, distributed computing, Cloud computing, Decision Support System (DSS), high level detecting innovation, and independent robots. Sensors and mechanical technology assume a urgent part in gathering fundamental field information, which is then sent to a neighborhood or cloud server by means of IoT innovation for capacity, handling, and examination. Large information and Artificial intelligence-based strategies can be utilized to change over this information into significant experiences. To work with client connection and informed independent direction, a DSS outfits clients with the fundamental devices to improve the agricultural framework and embrace proper activities.
AI (ML), a subset of Artificial intelligence, has shown extraordinary potential in upgrading different parts of agriculture 4.0. It very well may be characterized as a PC program or framework that can learn explicit errands without being expressly modified to do so. An interaction includes the utilization of a PC to go with choices in light of various information inputs. For this situation, information means a bunch of models. Marked information is frequently utilized for managed learning undertakings (where the model gains from named models), and unlabeled information may be utilized for solo learning assignments (where the model tracks down examples and designs in the information).
ML for sure advantage from a lot of information to accomplish significant exactness in their errands. With regards to farming, acquiring immense and various information can be at times testing yet crucial for the outcome of ML models. IoT sensors are instrumental in gathering a different scope of farming information as they can be decisively sent across fields to catch pertinent data with respect to, for example, soil conditions, Climate factors, crop wellbeing, and animals’ measurements. The inescapable reception of IoT innovation works with constant and continuous information procurement, empowering

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.

Nitrogen Content in Indian Soil Because of tropical and subtropical climates Indian soils have very low nitrogen content and in the majority of cultivated soil it varies from 0.02% to 0.13%. Low levels of N in Indian soil is primarily attributed to climate and secondarily to cropping. Climate plays the dominant role in determining the nitrogen content in soil through the effect of soil organic matter content. Generally heavy textured soils have higher N content than loamy or sandy soils. Other factors remaining the same, total N content in soil decreases with the increase in annual temperature at a given humidity level, on the other hand, it increases with increasing humidity level at a given annual temperature. Maximum N content in soil occurs in the surface layer of soils and decreases with depth in soil profile. The variation of distribution of N content in soil with depth is attributed by varying accumulation of organic matter in soil profile.

Introduction

 India, situated between the latitude of 08004’ and 37006’ N and longitudes of

68007’ to 97025’ E, has a geographical area of 329 Mha. Physiographically, it

can be divided into three broad regions, viz., Peninsula (a triangular Plateau in

the Deccan and South of the Vindhyas), Mountain region of the Himalalayas

(Extra-Penninsula), and the Indo-Gangetic Plain separating these two regions.

Geologically, a great part of the Penninsula is occupied by the gneiss, schists

and other rocks of diverse nature. Red soils (Alfisols) generally predominate in

this region. The western and central parts predominate in basaltic rock having

Black cotton soils of different thickness (Vertisols, Inceptisols). The mountain

region shows the development of marine sediments of all ages, especially, in

north of the Himalayas. The vast Indo-Gangetic and other plains of Pleistocene

origin are composed of alluvium of the great river systems flowing in this

region. The alluvial soils of this region depend on the age of alluvia and degree

of development.

Climatically, India shows three distinct seasons:

 i) Cool and mainly dry winters from November to February

ii) Hot and mainly dry summers from March to June

iii) Monsoon rainy season from mid-June to September.

Fertilizer recommendations are generally made on the basis of soil test. Recommendations of fertilizer for top-dressing are best made on tissue testing.

SOIL TEST

A number of approaches have been adopted to increase the precision of soil-test values in making fertilizer recommendations. Four most important ones are discussed.

Low-Medium-High Approach

Making fertilizer recommendations based on soil test for a nutrient involves conducting a large number of ?eld experiments on soils similar to those which are intended for making recommendations. For an individual nutrient (say P for example) experiments are conducted with graded doses of P on a crop for which the fertilizer recommendations are to be made. Thus, agronomic experiments are to be conducted for each crop on each kind of soil. The response curve can then be divided into three sections: a, low soil-test value and high response to fertilizer zone; b, medium soil-test value and medium response to fertilizer zone; and c, high soil-test values and no response to fertilizer zone. In India, this was done

1.1 The relation between man and the earth’s resources

The balance between the demand which a community of plants or animals makes on its environment and the ability to satisfy those demands is not the static equilibrium of a laboratory balance with equal weights on either side. It is more like the unstable balancing of a circus acrobat - a series of swings and overcorrections, resulting in an oscillation on either side of the true balance point. Thus a species of wild life increases in number according to the availability of its food supplies, but then goes beyond the optimum number. The natural correcting factors of starvation or migration reduce the population, but there is an overcorrection, and soon the cycle starts again with increasing numbers.

1.1.1 The Malthusian Thesis

In primitive societies the human population also oscillates about a mean as the limiting factors of starvation, disease, and war, maintain an uneasy balance against the natural tendency to increase. A serious imbalance arises when man learns how to modify the limiting factors, but allows the natural increase to go unchecked. The essence of the Malthusian Thesis is that the resulting instability is the inevitable order for mankind. The thesis is named after the English political economist Thomas Malthus who first gave it formal expression in MALTHUS (1966). In an age when significant improvements in health, hygiene, and the standard of living were just becoming possible, Malthus aroused great argument when he pointed out that these very improvements could lead to mi sery through overpopulation. The key point of Malthus’s argument is that population increases in what he called geometric ratio, what today we would call an exponential curve, because whenever there is an increase in population there are more people to produce the next generation, so the rate of population growth accelerates - in modelling terms a positive feedback loop. On the other hand, when we increase food production there is no feed-back loop, the best we can hope for is for a constant linear increase. The natural sequence is therefore for food demand to increase faster than food supply, leading at some point to food shortage.

Background and Technology Intervention

Managed Aquifer Recharge (MAR) describes planned storage and treatment of water in aquifers which can provide cheapest form of new safe water supply for towns and small communities (British Geological Survey, 2006). It is a part of a groundwater manager’s tool which is useful for replenishing and re-pressurising depleted aquifers, controlling saline intrusion or land subsidence as well as improving water quality through filtration and chemical and biological processes. MAR can enhance volumes of groundwater abstracted through different package of measures and restore groundwater balance. It also plays a vital role in smoothing out supply and demand fluctuations, stabilizing over-exploited groundwater levels, reducing evaporation losses and runoff, maintaining environmental flows in streams and rivers, improving water quality and augmenting the reuse of waste and storm water. In recent times, MAR uptake has been very limited.

Calcareous soils

In arid regions, calcareous soils are developed from limestone or marl parent materials. The content of calcium and magnesium carbonate may be as high as 60 to 70 per cent of the total soil mass. In calcareous soil lime content may vary from a small amount in some places in the profile to appreciable amounts throughout the profile.

Calcium carbonate coatings occur in sand, silt and clay size fractions of calcareous soils. In sub soil, large amounts of lime forms hardpan under high water tables.

In general, pH of the soil increases to alkaline pH with increasing the proportion of water to soil ratio. This may happen in part from a reduction of CO₂ pressure. The dilution of salts in soil solution also permits greater hydrolysis of calcium clay. The dilution of calcium carbonate with production of hydroxyl ions may lead to higher pH as:

Introduction

In classification of irrigation water, it is assumed that the water will be used for average conditions with respect to soil texture, infiltration rate, drainage, quantity of water used, climate and salt tolerance of the crop. Large deviations from the average for one or more of these variables may make it unsafe to use what, under average conditions, would be a good water; or may make it safe to use what, under average conditions, would be a water of doubtful quality. The relationship to average conditions must be kept in mind in connection with the use of any general method for the classification of irrigation water.

However, the quality of irrigation water is evaluated, mainly by the quantity of dissolved salts, proportion of anions, monovalent and divalent cations, sodium adsorption ratio, residual sodium carbonate, potential salinity, specific ion toxicity, proportion of magnesium, calcium in water etc.

Introduction

Salinity in India is a major issue affecting the sustainability of irrigated as well as non-irrigated areas particularly in the states of Rajasthan, Gujarat, Haryana, Uttar Pradesh, West Bengal and Orissa. Salt affected soils are unproductive unless excess salts are reduced or removed. These soils occur most extensively in arid and semi-arid climates, but these soils are also found in coastal sea areas where soils are unundated by ocean or sea water. Soils are said to be saline if they contain an excess of soluble salts and sodic or alkali if they contain an excess of sodium salts. Again soils are said to be saline-sodic or saline-alkali if they contain appreciable amounts of both soluble salts and sodium. The impact of salinity manifests itself in several ways. As the salinity increases, not only does the productivity decline but sensitive crops also go out of cultivation and are replaced by salt-tolerant, low value crops and other plant species.

In whole of the world, about 6 to 7 m ha of agricultural land is becoming unproductive every year due to one or the other reasons (Gupta, 2018a). This is, however, more so in case of developing countries (Gupta, 2003). Productive lands are utmost important to meet the countryís growing needs for food, fodder, fuel wood, medicinal herbs and timber.

Managing soil organic matter is of paramount importance in sustainable crop production. Human interventions always lead to a decrease in soil organic matter content and biological activity. Therefore, even for maintaining moderate levels of organic matter in soils, sustained efforts should be in place. Such sustained efforts should include adopting high-residue crops in rotation and ensuring regular return of residues to soils.

It is all the more difficult to maintain the organic matter content in well aerated soils and soils of hot and arid regions, because in these soils added materials decompose rapidly. However, in comparison, it may not be so difficult to maintain the organic matter levels in fine-textured soils with restricted aeration and in soils of cold temperate regions.

19.1. Measures that Decrease Soil Organic Matter Content

Introduction

Increasing fresh water demands for ever growing population and it has increased by 600% over the past 100 year (Wada, et. Al, 2016) the annual increment rate 1.8 % whereas the present growth rate is less, only 1 % but this figure may be optimistic. The global water demands will grow significantly over the next two decades in all three components as: Industry, domestic and agriculture (U.N, 2018) industry and domestic demand will grow faster than agriculture, but agriculture demands will remain largest (U.N, 2018). The global water demands for all purpose will increase 20% to 30% by 2050, up to 5,500 to 6,000 km3 per year (Burek et.al, 2016), whereas, agricultural demands will increase by 60% by 2025 (Alexandrators and Bruinsma, 2012).

Introduction

Manures are obtained from the plant residues, green manure, compost and animal wastes that are used as source of plant nutrients. They release nutrients after their decomposition. They essentially function as sustenance to the crops. They help in the proper cultivation of crops. The addition of manure enables the soil to hold more water. Organic manures have acids that dissolve the nutrients in the soil and make them available to the plants. manures can be grouped into bulky organic manures and concentrated organic manures. Brief dissection about manure given blow flow chart.

Bulky Organic Manure

Bulky organic manures are those materials of plant and animal origin, which contain small percentage of nutrients when added to the soil have tendency to decrease bulk density and to increase soil volume, thus providing better physical conditions for plant growth especially in coarse textured soils and also provide essential nutrients in smaller quantities than the chemical fertilizers. Characteristics of bulky organic manures:

The word “Manure” is originated from the French word “Manoeuvrer” which refers to “work with soil”. The word Manure is also originate from Latin word “Manu” (hand) and operate (to work). Manures are the substances which are organic in nature, capable of supplying plant nutrients in available form, bulky in nature having low analytical value and having no definite composition and most of them are obtained from animal and plant waste products. Formerly, the word in use was “Dung ”in English (at present fertilizer).

The resources on the land have started showing sign of faster depletion owing to the population explosion, over exploitation of mineral and water resources and also the improper exploitation and the related wasting of the natural resources. Hence a time has come to search for more and more newer natural resources amongst which the ocean resources gain supreme importance as this treasure is yet to be hunted due to the non - availability of suitable technology for the same.

Such ocean resources mainly include the mineralogical and biological resources. The ocean biological resources, their birth, growth, population and migration greatly depend as chlorophyll content, total dissolved oxygen, total suspended solids, salinity etc. These parameters which constitute the marine environment drastically change in a quick span of time owing to the dynamically changing marine forces.

Abstract

GIS in marine fisheries has taken off much later than its application in land. But the strides made in this field since 1990’s has been quite significant, as many serious mapping studies and modeling initiatives have been recorded. With the third dimension added to the 2D spatial data, the marine GIS have all the ingredients of making it a fertile domain for research for decades to come. Most of the studies and products pertaining to GIS in fishery management had been revolving around mapping of habitats, geo-referencing of catch and effort data and modeling linking oceanographic and biogeochemical factors with living resources. Satellite remotely sensed information like ocean colour can act as a surrogate to fish biomass. Further remotely sensed SST, wind and other parameters can be effectively modeled to predict fish abundance, their habitat and related aspects. This manuscript pours into the various products and outputs based on GIS in marine fisheries around the world and the Indian initiatives.

Key words: GIS, marine resources, oceanography, primary productivity and climate change

1.0 Introduction

Geographic Information Systems (GIS) have been one of the most prolific scientific enhancements in recent past, which by virtue of out of box expansion of traditional database concept have opened up an entirely new vista of knowledge and opportunities. It’s probably one such unique application where information collation and analysis happen hand in hand resulting in palpable mining of data in perspective. A formal introduction to GIS would define it as a collection of computer hardware, software, data and personnel designed to collect, store, update, manipulate, analyze and display geographically referenced information. By virtue of its conceptualizations, there are no single GIS; systems can be assembled in an infinite number of ways. This is one such field, which probably always seeks the frontiers of innovations in the fields of ICT and modeling.

2.1 INTRODUCTION

Mass flow and diffusion are processes which cause the redistribution of many components within the soil profile. They are usually investigated because they cause a redistribution of materials such as fertilizers and pesticides which are added to the soil, or because of the need to reduce salt concentrations to levels safe for crop growth. This has given an economic incentive to the investigations, but the processes are also basic to our understanding of the development of soil properties. For example, diffusion is the main process for the movement of gases into and out of the soil, which in turn affects many soil properties (Chapter 7), and mass flow of water is an important cause of the formation of horizons in soil profiles (Chapter 8). Hence there are both academic and economic reasons for attempting to understand the way the processes operate in soils.

Over the last few years our understanding has increased considerably. It is the purpose here to give the principles which have been evolved in this recent work, and to discuss their application. It will also be shown that many problems remain to be solved.

Diffusion means a spreading out, and is caused by random thermal motion, as is the Brownian movement of colloidal particles observable under the microscope. In unstirred liquids, which are our main concern in this chapter, all the molecules and ions of the solvent and solute have this random movement (molecules and ions in gases and some solids behave similarly). As a result of this motion, which occurs randomly in all directions, any irregularities in the concentration of a solution or mixture of gases eventually disappear.

Mass Production of Bacterial Inoculants

Strain Selection and Improvement

In biofertilizer technology, strain selection occupies the foremost criteria, so as to explore its biological potentialities for the beneficiary crop. The selected strain used in biofertilizer production must be efficient to grow fast besides retain desirable potentialities of biological activities, which should be present in desired high numbers and must be stable. The strain must be improved periodically so as to sustain the productivity.

Increasing crop productivity while reducing resource consumption is a central objective of modern agriculture. This chapter examines how artificial intelligence can support crop yield improvement through data-driven analysis, prediction, and decision-making. AI models can integrate information from soil, weather, crop growth, remote sensing, IoT sensors, and historical yield records to identify important factors influencing productivity. Machine learning and deep learning approaches can support yield forecasting, crop selection, fertilizer and water optimization, and precision management. The chapter also considers AI-enabled genomic selection, market intelligence, and intelligent farm management. Challenges such as data availability, implementation cost, connectivity, farmer training, and model reliability are discussed alongside future opportunities including edge AI and explainable AI.