eChapters

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.

Remote sensing is emerged as an important application of science in all fields for collection of information from a far. This chapter describes the fundamental concepts of remote sensing, electromagnetic radiation (EMR), the interactions between EMR and earth surface features, satellites etc.

8.1 What is Remote Sensing?

Remote sensing is nothing but acquiring information about an object without touching the object itself. In other words, remote sensing is the acquisition of information about an object or phenomenon, without making physical contact with that object. In present era, the term generally refers to the use of aerial sensor technologies to detect and classify objects on the Earth by means of propagated signals. As remote sensing is obtaining information about objects without making physical contact with them, remote sensing can be described as ‘reconnaissance from a distance’, ‘teledetection’ or a form of the common phrase ‘look but don’t touch’.

More information, more accurate and timely decision. In present high tech world, the more information you have it is easier to make an accurate decision. The information comes in many different ways, from reports to digital photos. A new way to analyze data is a geographic information system (GIS). GIS allows to bring all types of data together based on the geographic and locational component of the data. GIS is a useful tool for seeking innovative ways to solve the problems.

9.1 What is GIS?

A geographic information system (GIS) is a system designed to capture, store manipulate, analyze, manage and present all types of geographically referenced data. GIS can be defined as a computer-based system for digital entry, storage, transformation, analysis and display of spatial data. A geographic information system integrates hardware, software and geographically referenced data for further analysis. GIS allows users to interpret the georeferenced data in many ways that reveal relationships, patterns and trends.

7.1 Introduction

The current atmospheric CO₂ concentration is the highest during last 650,000 to 800,000 years (Luthi et al., 2008), and also probably in the last 20 million years (Pearson and Palmer, 2000). Since last two decades, it is increasing at a rate of about 2 ppm/yr with the current concentration of 389 ppm in 2010 (WMO, 2011). The current trend of energy use based on fossil fuel consumption may raise it to 900 - 1100 ppmby the end of 21^st century (Kiehl, 2011).

Global warming is the most prominent environmental issue across the world. It is caused by the increased concentration of greenhouse gases (GHGs) in the atmosphere and leads to a phenomenon widely known as ‘greenhouse effect’. Amongst various sources of greenhouse effect, agriculture is considered a major contributor primarily through the emission of greenhouse gases such as methane, nitrous oxide and carbon dioxide.

Vegetation is a key component in hydrologic modeling. Transpiration, a component in hydrologic cycle, is contributed by vegetation. Most of the hydrologic model thus includes vegetation as a parameter. For accurate and appropriate model output, first requirement is good quality data. Most of the time, the data on vegetation is confusing, as in literature various researcher have used different values for common vegetation parameters. Here some common parameters of some important crops, which yield good quality results, are given.

Kharif crops are generally sown during last week of May and first week of June, while rabi crop are sown during last week of November and first week of December. But this period will vary from region to region as well as depends on variety of crop.

Introduction

A system is a simplified version of reality and is defined as a collection of interrelated parts that work together. Most systems share certain common characteristics. These common characteristics include the following:
Systems have a structure that is defined by its parts and processes. Systems are generalizations of reality.
Systems tend to function in the same way as nature. This involves inputs getting changed in a process and realization of new outputs.
The various parts of a system have functional as well as structural relationships between each other.
Owing to the functional relationships that exist between the parts there is a flow and transfer of some type of energy and/or matter. In case of information systems there is a flow of information in the structure.
The parts that make up a system show certain degree of integration. In other words the parts work well together.

Introduction

In a technology that consistently maintains a fantastic development curve with capabilities doubling up year-to-year, freezing the hardware specification is not easy or very meaningful. GIS (not geography) owes to its genesis and progress to the developments in information technology front. It may be asserted that any and all upgrade in the hardware industry will only add to its own ability to effectively process more and more data and handle more complex routines. The personal computers of today are seen to be adequate to run typical GIS software. A reference hardware specification is discussed here. GIS software development is an involved process but then the software developers have made good use of hardware capabilities available and have released upgrades consistently. Hardware developments are such that they defy a static spcification. However a reference specification as on 2009. An overview of various software packages used in the past as well as present is attempted. ESRI released a new version in 2002 and claimed that their ArcGIS is an “integrated collection of GIS software products for building a complete GIS that enable users to deploy GIS functionality wherever it is needed, in desktops, servers, or custom applications; over the Web; or in the field.” The details are discussed below. While a number of software overviews are available, this text is not aimed at providing a tutorial to any of the software packages nor do the comparisons made are to promote any particular software. Similarly, it is presumed that the reader is familiar with the hardware elements and functionality. Lot of information about the software packages are available on their respective web sites and the reader is exhorted to look for current, additional and in depth information required in the pages. A brief discussion on Liveware or human resource can be found at the end of the chapter.

Introduction

All spatial data stored in a GIS are associated with a map projection, either implicitly (so-called “unprojected” data stored with raw longitude, latitude coordinates) or explicitly (where the data have been transformed into a known map projection). Map projections are a particularly important feature of spatial data because they introduce error and distortion, since a sphere cannot be transformed to a plane without some stretching and twisting of the sphere’s surface.

The typical GIS package supports anywhere from 5 to 50 map projection types, and most projections may be modified or customized by varying their parameters. This flexibility is important for two reasons First, in order to use two or more layers together in a GIS for visualization or analysis, all data must be projected in the same way. Second, certain types of analyses, such as the measurement of area, are only valid when using certain types of projections (and conversely, are completely wrong when using an inappropriate projection).

Any living organism in its natural habitat is called a wildlife. It may be plant animal or a microbe. The significance of wild life lies in setting up the balance of population in nature by maintaining food chains and food webs. It acts as the gene banks in relation to breeding of plants and animals for introduction of desirable characters such as high yield of economic product and resistance to diseases. The scientists are performing studies to screen and select useful genes in economically important organisms.

Air is one of the most important constituents of man’s environment. It is calculated that a roan breathes about 22,000 times a day inhaling about 16 kg of air by weight. Air is present everywhere and its entrance from one place to another cannot be checked. Clean and pure air is very essential for the health and survival of man.

El Nino is the name given to the occasional development of warm ocean surface waters along the coast of Ecuador and Peru. When this warming occurs the usual upwelling of cold, nutrient rich deep ocean water is significantly reduced. El Nino normally occurs around Christmas and lasts usually for a few weeks to a few months. Sometimes an extremely warm event can develop that lasts for much longer time periods. In the 1990s, strong El Ninos developed in 1991 and lasted until 1995, and from fall 1997 to spring 1998.

Introduction

Data are the most critical element of a GIS. It is reported that more than two thirds of the time and expenditure to develop a GIS is spent on data collection and organization. Understanding and appreciating the criticality of data is of paramount significance to practice GIS. This chapter is complementary to database concepts chapter discussed in Level II and deals with the fundamentals to start with and the concepts of building an information organization.

Data - A Definition and Certain Points to Ponder

“Data” are defined as a body of facts or figures, which have been gathered systematically for one or more specific purposes.”

Introduction

The concept of database is the approach to information organization in computer-based data processing. (Date, 1995 and Everest, 1986).

A Geographic Information System is as good as the data contained in it. Accurate and efficiently organized data are critical to the durability of the system. Data collection, capture and organization will occupy much of the time in building a GIS solution. The analysis potential of a GIS will depend on the database. It is essential to understand database concepts to practice GIS. It is erroneous to view these GIS databases as mere stores of information. The database is used to abstract very specific sorts of information about reality and organize it in a way that will prove useful during subsequent analysis. The database should be viewed as a representation or model of the world developed for a very specific application.

Conversion of real world geographical variation into discrete objects is done through data models. They represent the linkage between the real world domain of geographic data and computer representation of these features. Data models discussed here are for representing the spatial information.

Introduction

Data input or capture is the operation of encoding the data and incorporating in the database. The creation of a clean error free digital database is a complex and critical task determining the very usefulness of a GIS. GIS data represent not only where the graphic or cartographic features occur, but also the associated attributes of them.

Data input to a geographical information system involves

(a) Entering the spatial data (digitizing);

(b) Entering the non-spatial, associated attributes and

(c) Linking the spatial to the non-spatial data.

At each stage necessary verification and checking procedures shall be deployed to ensure an error free database.

Introduction

The GIS database is a model of real world. It goes without saying that there is an inherent discrepancy between GIS database and the real world it represents. This is so because all models are fraught with cognitive issues and remain as approximations. To realize the objectives of a GIS, geographical data collected, entered and processed are to be sufficiently error free and reliable.

Errors can be statistical errors like mistakes, wrong inputs or faulty field surveys or system errors like excessive tolerances or high RMS error. The spatial database has further problems in the sense that the real world phenomena are not always intrinsically discrete. For instance where is the bank of a shallow river? Where is the boundary between two soil types? These are but a few questions revealing the fuzzy nature of geographic data. Many soil scientists, geographers have noticed that carefully drawn boundaries or iso-lines on maps in general give misrepresentations of change that are often gradual, vague or fuzzy. Traditional cartography as a medium of spatial data handling had a solution to such problems. But now when digital data are handled, they need to be stored with certain precision. Moreover, the spatial variation of natural phenomena is not just a local noise function or inaccuracy that can be removed by collecting more data or by increasing the precision measurement but is often a fundamental aspect of nature that occurs at all scales. (Goodchild, 1980; Mark and Aronson, 1984). This means residual unmapped variation is a remarkable problem in geographical information processing. It is therefore a prerequisite to fully understand how errors arise or propagated in GIS and what might be the effects of errors on output.

The Global Environmental Issues

 
Expansion of the scale of human activity in recent years has put so much strain on the natural environment of this planet that in some cases nature can no longer recover. The nature’s ability though recovers damage or harmful effects in one part of the world do not stop in the very area and keeps going beyond national borders and become environmental problems on a global scale, but in a limited manner.

1.1. Characteristics and categories
                
1.2. Litter
    Patterns of accumulation
    Successional trends
    Seasonal variations
    Fluctuations in accumulation

1.3. Dissolved organic matter
    Sources of DOM
    Fluxes of DOM

1.4. Woody detritus

1.5. Soil organic matter

2.1. The Physical environment
    Light
    Soil temperature
    Water dynamics

2.2. Chemical environment
    Production of phytotoxins

2.3. Biological environment
    Trophic dynamics
    Community structure
    Biodiversity

Topology building

Boolean operations

Query and model building

Customization

Introduction

At human scales, the world consists of objects, events, processes, and a background environment. Cognition is about knowledge: its acquisition, storage and retrieval, manipulation, and use by humans and other intelligent creatures. Cognition includes sensation and perception, thinking, imagery, reasoning and problem-solving, memory, learning, and language. Cognitive structures and process are part of the mind, which emerges from a brain and nervous system inside of a body that exists in a social and physical world. Spatial cognition deals with the cognition of spatial properties of the world, including location, size, distance, direction, shape, pattern, movement, and inter-object relations. GIS design will be largely influenced by spatial cognition.