GIS Systems for Precision Agriculture and Site-Specific Farming

Abstract

An increase in population and economic cost in managing agriculture limits the crop area and production. An increase in population also results in drastic changes in climate, heat stress, and drought, which limits crop productivity. Food is the main source for all living beings but it has become a very tedious process for the farmers to monitor the crops regularly when the cultivated area is very large (in acres). Precision agriculture (PA) is a future farming management system that will change the style of farming. It is a strategy that utilizes information technology and geographical information to find the changes in the field and to ensure the best possible use of inputs to maximize the yield with optimum health. It is a forthcoming approach that is going to modify the style of farming to assure profitability, sustainability, and environment. A larger area of land will definitely have variations in the type of soil, soil moisture content, availability of nutrients, etc. So the farmers have to precisely determine the type of input to be given and the quantity to be given exactly can be determined with the help of remote sensing (RS), global positioning system (GPS), and geographical information system (GIS). The most expensive resources like fertilizers, herbicides, pesticides, and even water resources can be used more effectively with the information provided by GIS. Ultimately, the farmers will maximize their yield by reducing their operating expenses, which increases their profit. So this chapter focuses on the use of geospatial technologies in precision farming. RS and GIS play a vital role in implementing and monitoring the farming works at a large scale. Handheld devices like smartphones with inbuilt GPS can be used to map the fields and help the farmers in getting site-specific information and more accurate solutions for their problems. The spatial content retrieved can also be used to monitor the growth of the crop, manage disease, estimate the yield, and map the soil and weed. The yield data is recorded and stored in the database at regular intervals with positional data which is received from the GPS unit. GIS software can be used to produce yield maps. The data collected through remote sensing technologies, which is a point data converted into spatial data using GIS techniques, will reflect the positions of all the zones. The spatial data obtained will determine the problem that appears in various zones in turn helps the farmers make effective decisions to solve problems, which leads to an increase in the overall production of the farm. The data collected will be in raster or vector format. In the case of raster format, imaginary grids are developed and points in the map are differentiated with various colors. So the user can identify easily and differentiate the characteristics. In the case of vector format, x-axis and y-axis coordinates are used to assign a particular point in the map. Once the mapping of spatial data is done, it is compared with the results with ground data. It helps in identifying the area with high content of nutrients in the soil or the area which is highly infested with insects. Hence the information collected using remote sensing and GIS will help to make site-specific decisions with respect to the usage of fertilizers, disease and herbicides, irrigation etc. The data collection will be useful in the future by storing it in a systematic manner. The focus of this chapter is to discuss the usage of remote sensing in agriculture, plan the estimation of crop yield and cropland, and find the opportunities and challenges in the usage of GIS in precision farming. This chapter identifies various geospatial technologies used for precision farming and collecting and analyzing the geospatial data for better decision-making, which maximizes the yields. This study also gives an analysis of the application of remote detecting techniques in homepage farming for measuring crop development and production fluctuation based on the literature review. According to the results two classification approaches, namely pixel-based and object-based, are presented. Image processing techniques including vegetation indices, segmentation, and classification were used in this research. The models presented in the chapter are suggested to be used for crop monitoring and supporting decision-making. Yield data gathering is also highlighting in this chapter.