A Review of the Factors Affecting Adoption of Precision Agriculture Applications in Cotton Production

Abstract

Precision agriculture (PA) is a modern farming management system adopted throughout the world, which employs cropping practices by observing and measuring the temporal and spatial variability in fields to enhance the sustainability of agricultural production through more efficient use of land, water, fuel, fertilizer, and pesticides. The efficiency of precision agriculture technologies (PAT) in agricultural production mainly depends on the use of site-specific agricultural inputs accurately through decision support mechanisms by observing and measuring the variables such as soil condition, plant health, and weed intensity. Although there have been significant developments in PAT, especially remote sensing as a key source of information available in support of PA in recent years, its adoption has been very slow by farmers due to a variety of reasons. The main aim of this chapter is to provide a critical overview of how recent developments in sensing technologies, geostatistical analysis, data fusion, and interpolation techniques can be used in the cotton production systems to optimize yields while minimizing water, chemical pesticide, and nitrogen inputs and analysis the main factors influencing the adoption of PAT by cotton farmers. Therefore, this chapter includes a compressive literature survey of the studies done on the current use and trends of PAT, and on farm level use of PA in cotton production worldwide.

1. Introduction

Cotton is a very important plant throughout the world. The amount of cotton production in the world is nearly 25 million tons of cotton. Leading cotton-producing countries worldwide in 2022/2023 are announced as China, India, United States, and Brazil. It is estimated that world cotton production will reach 28 million tons with an annual increase of 1.5% until 2030 [1, 2]. While cotton production has steadily increased over the past few years, many issues have also started to emerge with the increase in cotton farming areas because current cotton production methods are not environmentally sustainable. Intensive and incorrect use of technological inputs such as tillage, fertilizers, irrigation, pesticides, and herbicides in cotton agriculture has significantly caused soil and environmental degradation as well as reduced crop profitability [3].

One of the new ways that modern agriculture could potentially maintain or enhance crop yields by minimizing environmental pollution is site-specific application of inputs according to the needs of the crop, which is defined as Precision agriculture (PA) [4]. PA is an umbrella term for using modern data-driven technologies to optimize crop management and improve productivity, efficiency, and sustainability in agricultural production. Therefore, PA can be defined as the application of modern information technologies such as GPS, sensors, drones, Internet of Things (IoT), artificial intelligence (AI), and data analytics in the management of crop production [5]. It is seen that studies on PA have gained importance in recent years. The fact that Internet of Things (IoT), artificial intelligence (AI), remote sensing, and image processing (ImP) techniques have been actively used in agriculture by integrating with geographic information systems (GIS) and geographic position systems (GPS) has brought about important developments in the use of precision agriculture technologies (PAT) in agricultural production [6, 7, 8]. Kırkaya [6] stated that in the future, PAT will be widespread used in crop management practices such as sowing, fertilization, irrigation, and weed control. The author emphasized that PAT had the ability to protect crop health, soil, and the environment by effective and optimized application of inputs.

PAT reduces not only production costs and increases income for the producer but also reduces the negative environmental impact of agricultural chemicals by adjusting input application rates to crop requirements because it can help farmers monitor and control various aspects of their fields, such as soil conditions, crop growth, pest infestation, and water use [9, 10]. However, PA also has some limitations and challenges such as high initial investment and maintenance costs because it needs expensive and complex equipment, such as sensors, drones, satellites, computers, and software, to collect and analyze data and control the farming operations [11, 12, 13]. Therefore, it seems that the PA is not applicable especially in developing countries due to the presence of poor farmers, subsistence farming systems, small farmlands, lack of technical and software knowledge among farmers, and the high cost of application of its technologies.

In cotton agriculture, the adoption of PA technology has been very different than in grain production since cotton needs intensive management processes such as multiple fertilizer applications, multiple plant growth regulator applications, multiple irrigation potential applications, and multiple pesticide applications. The availability of cotton yield sensors later than grain yield sensors affected cotton producers’ adaptation to precision agriculture.

In this chapter, a review of PA techniques and practices used in cotton production is presented along with several considerations and challenges. The advantages and disadvantages of PA, as well as some of the current and future trends and opportunities for the usage of PAT in crop management practices in cotton production are explored.

2. Precision agriculture and its practices in cotton production

Cotton agriculture is known for its intensive crop management practices with higher levels of input including seeds, land management practices, agrochemicals (fertilizers, pesticides, and herbicides), and water, which is negatively influencing farmers’ profit and yield [14]. Also, cotton crop is host to many insects and pests, and enormous amounts of pesticides are used which are hazardous for the environment in the long run, in order to control these insects and pests [15]. When PAT is applied to these management practices, it will be possible to improve the economic and environmental sustainability of cotton production.

Several factors, such as the differences in soil texture and fertility and the occurrence of pests, diseases, and nematodes, can cause spatial variability in the growth and development of cotton crops within a field. PA, which comes from the spatial variability distinctive to each field can be measured and managed with site-specific techniques according to the needs of the crop, PA contributes to more effective use of inputs such as fertilizers, pesticides, tillage, and irrigation water. Effective use of inputs will increase crop yield and (or) quality without polluting the environment [7].

To understand fully how PAT is applied, the tools and techniques that create the infrastructure of this modern form of agricultural management need to be well explained. A diagrammatic representation of the PA components is shown in Figure 1. It can be said that PA is mainly composed of agricultural data collecting, data processing and analysis, data interpretation and decision making, and variable rate application of inputs [8, 16, 17, 18].

Figure 1.

The main components of precision farming [8, 16, 17].

The data collecting, which is the first step of PA, entails gathering as much data as possible about crops, soil, fields, terrain, climate, variables, and resource availability by sensors and innovative techniques. Data collecting can be performed using either proximal sensing or remote sensing techniques by special equipment and software such as sensors, GPS technology, controllers, gateways, drones, satellites, and imaging [8].

Data preprocessing and analysis allow for making accurate decisions during variable rate application of inputs by farm machinery because it contributes to a better understanding of crop dynamics, weather, and soil conditions [19]. Information for data interpretation, decision making, and implementation of crop management practices at an appropriate scale and time can be achieved by preprocessing and transforming the raw data acquired through sensing techniques and GIS software [20, 21, 22].

Data interpretation and decision-making covers choosing the appropriate management tools which give good outcomes in available natural conditions like soil, and environment before using variable-rate devices installed on agricultural equipment. The processes in this phase are considered as very important step in PA [23]. Tantalaki et al. [24] reported that the high volume and complexity of the data caused challenges in successfully implementing PA. They also emphasized that analyzing and interpreting data obtained from ground sensors, unmanned systems, or remote sensing satellites is a significant issue in the successful implementation of PA. The authors state that machine learning techniques, artificial neural networks, support vector machines, decision trees, and random forests, frequently applied for agricultural management purposes, seem promising to cope with agricultural big data, but need to reinvent themselves to meet existing challenges. Also, image segmentation technologies play a significant role in data interpretation and decision making such as plant or weed identification, crop growth stage prediction, crop disease, row detection, and cotton detection in the field [25]. Zhang et al. [26] developed a software used on the smartphone for the real-time detection of cotton diseases and pests in the field. They stated that the developed software could effectively detect the infected area of cotton leaves in the field and provide a technical support for controlling cotton diseases and pests.

Managing field operations can be performed using the information acquired as decision support. Many crop management practices (multiple fertilizer applications, multiple plant growth regulator applications, multiple irrigation potential applications, multiple pesticide applications, etc.) are intensively applied while growing cotton. For this purpose, several agricultural machinery and tools are used for seedbed preparation, sowing, fertilization, pest control weeding, irrigation, and harvesting to reduce labor costs and increase productivity. In PA, these agricultural machinery and tools manage field operations by using technologies such as IoT, AI, remote sensing, and ImP. Recently, numerous robotic systems and variable-rate applicators with human-like capabilities (e.g., precision spraying systems, harvesting robots, shearing robots, grafting machines, weed control systems, transplanting machines, and path planning) have been developed to manage different agricultural activities such as planting, inter-row cultivation, spraying, fertilization, irrigation, and harvesting in crop production [8, 27]. Taylor and Fulton [28] reported that several commercially available sensor-based, variable rate systems exist for efficiently managing inputs to maximize yields or returns. They presented a schematic view of a sensor-based, variable rate application system for liquid products as in Figure 2. A robot, which apply a microdose of herbicide systematically targeting the weeds that have been detected, is seen in Figure 3. It is stated that the total use of herbicides is reduced by as much as 20 times by using this robot because it detects weeds and then targets weeds by moving independently through the field with the help of a camera, GPS sensor, and a solar drive [29]. Remote sensors are usually used to track the soil conditions and plant health. The data obtained from this sensor allows farmers to selectively use (i.e., precisely apply) the exact amount of nutrients, resources, or pesticides necessary for their fields. Grisso et al. [30], who reviewed the variable rate application devices available on the market, discussed the technologies best fit for a cropping system and production management strategy. They presented an “On-the-go” sensor, which measures soil characteristics such as soil moisture content, texture, electrical conductivity, or soil organic matter before planting and adjusting the seeding rate (plant population) as seen in Figure 4. Also, drones and unmanned aerial vehicles systems (UAVs) are used in PA for a variety of tasks such as soil and crop analysis, fertilizer, and pesticide application. Various imaging technologies like hyperspectral, multispectral, and thermal cameras are used in those vehicles, in order to detect and monitor temporal and site-specific changes in plant health and physiology caused by biotic and abiotic stresses [31]. The use of drones and UAVs in precision agriculture is seen in Figure 5.

Figure 2.

Schematic of a sensor-based, variable rate application system for liquid products [28].

Figure 3.

A robot, which applies a microdose of herbicide by systematically targeting the weeds detected [29].

Figure 4.

“On-the-go” sensor (texture, electrical conductivity (EC), or soil organic matter (SOM)) measures soil characteristics before planting and adjusting the seeding rate [30].

Figure 5.

Use of drones and unmanned aerial vehicles systems (UAVs) in precision agriculture [31].

Gemtos et al. [32] stated that a PA system could be divided into three different phases as the acquisition of weather, soil, and crop data; the processing and analysis of the data; and the implementation and adaptation of cultivation practices.

In PA applications, relative observation data and agronomic models were used in order to implement the applications related to tillage and irrigation scheduling, fertilizer management, weed and pest control, soil and crop growth monitoring, and yield estimation. The main aim of PA applications is to apply the targeted rates of fertilizer, seed, and chemicals for soil, crop, and weather conditions by using site-specific knowledge. PAT enable visualization of spatial and temporal variations between fields or within one location and support spatially varying treatments using variable rate application technologies (VRT) installed on farm agricultural field machinery [8, 16, 17, 33]. Variable rate application (VRA) is one of the most important and recent technologies that have been developed recently to accomplish PA. VRA in PA can be map-based or sensor-based. While in map-based VRT, a map of application rates is produced for the field prior to the operation, sensor-based VRT utilize real-time sensors and feedback control to measure the desired properties on-the-go, usually soil properties or crop characteristics, and immediately use this signal to control the variable-rate applicator [33]. Neupane and Guo [34] suggested that the variable rate application of water could reduce water use and improve water use efficiency. Longchamps and Khosla [35] showed that VRA could increase N use efficiency by maintaining productivity and decreasing environmental pollution. Onken and Sunderman [36] determined that the variable rate application of irrigation and fertilization increased cotton yield by 30% when compared to whole-surface application. The usage of PA or site-specific management applications in cotton production fields reduces this variation in yield by recognizing field spatial variability and optimizing variable input use within fields [37]. Huang et al. [38], who reviewed the remote sensing technologies available on the market for weed management, presented in detail information on the development and application of UAVs-based low-altitude remote sensing technology for precision weed management. Lamm et al. [39] developed a real-time robotic weed control system and tested it in commercial cotton fields. The researchers stated that this precision weed control system, which consisted of a real-time machine vision system, a controlled illumination chamber, and a precision chemical applicator, was capable of distinguishing grass-like weeds from cotton plants and applying a chemical spray only to targeted weeds. Allmendinger et al. [40] summarized different commercial technologies and prototypes for precision patch spraying and spot spraying. The authors presented an overview of sensors, applications, and implementation options that should be possible to be controlled via ISOBUS-Connection, as seen in Figure 6. Also, PA facilitates other management decisions making, such as site-specific deep tillage to remove soil compaction, and the equipment guidance where farm equipment follows the same paths for various field operations [41].

Figure 6.

Overview of sensors, application, and implementation options that should be possible to be controlled via ISOBUS-connection [40].

3. Apparatus and instruments in precision agriculture

PA requires special equipment and software to collect and analyze all the information. It uses a range of technologies or diagnostic tools such as GPS, GIS, yield monitors, near-infrared reflectance sensing, remote sensing, IoT sensors, drones, computer vision, LIDAR, big data processing, and artificial intelligence in order to collect and analyze the in-field spatial variability data, and after then, make site-specific management decisions for soils and crops [8, 42, 43].

3.1 Global positioning system (GPS)

GPS, one of the most important parts of PA, enables precise recording of coordinates (latitude and longitude) to accurately map and pinpoint the location of the device or sensor as the data is collected and then aggregates all of these locations and data to create a visual geographic map. GPS is widely used on drones, sensors, tractors, and other farm machinery. GPS enables machinery to operate autonomously and aid in soil testing, tractor driving with a parallel steering system, and VRA for precise seed and fertilizer application.

3.2 Geographic information system (GIS)

GIS, one of the key tools for PA, is a digital mapping system that manages the spatial information collected on the ground. It is also defined as a software that collects, analyzes, and displays spatial data on maps. GIS can help farmers to use various types of data and analytics to improve farmer’s decision making and planning in many ways. For example, GIS can help the farmer to map and monitor the soil characteristics and variability in their fields, such as texture, pH, organic matter, moisture, and fertility. After that, by integrating soil data with other information, such as weather, crop type, and yield, farmers can create soil management zones and apply variable rate inputs, such as fertilizers, pesticides, and irrigation, to each zone according to its specific needs.

3.3 Satellite technology

Satellite technologies, also defined as satellite-based remote sensing, have been utilizing images from space to analyze vegetation indices and identify variations across different areas of the farm. Satellite technologies provide information regarding soil type and condition, crop health, and hydrologic and climatic parameters, which are important for PA (e.g., soil organic carbon, soil moisture, NDVI, leaf area index (LAI), groundwater, and rainfall).

3.4 The Internet of Things (IoT)

IoT is simply defined as a network system of connected devices that may send and receive data over the internet and complete tasks without the need for human intervention. Its main aim is to create an internet-based huge network platform by combining several sensor technologies and networks, in order to understand how information is shared among items all over the world.

3.5 Auto-guidance system

Auto-guidance system is a computer-controlled system that helps farmers guide their tractors or other agricultural equipment along the desired path. The system uses GPS technology to track the equipment’s location and automatically steer it in the desired direction. There are many different types of auto-guidance systems (GPS-based auto-guidance systems, laser-based auto-guidance systems, camera-based auto-guidance systems) available on the market, each with its advantages and disadvantages.

3.6 Precision agriculture-based soil sampling

Soil sampling helps to evaluate the physical and nutrient status of soil in a field to base crop management decisions such as planting, cultivation, fertilization, and irrigation for optimal crop production. Precision soil sampling results in higher fertilizer use efficiency, reduced nutrient loss, and protection of the surrounding natural resources [44, 45].

3.7 Variable-rate technology (VRT)

VRT is a technology which adjusts and applies precise and measured the quantities of the inputs (e.g., fertilizers, pesticides, herbicides, seeds, and water) in agricultural production by considering data that is collected by sensors, maps, and GPS in a given landscape. VRT consists of the machines and systems for applying a desired rate of crop production materials at a specific time and a specific location; a system of sensors, controllers, and agricultural machinery used to perform variable-rate applications of crop production inputs.

3.8 Crop and soil sensors/remote sensing

Crop and soil sensors/remote sensing technologies are mainly used to measure essential soil and crop properties on-the-go in the field. The measurement results obtained from these sensors are used either to control variable rate application equipment in real-time or in conjunction with a global positioning system (GPS) to generate field maps. There are numerous sensor types (e.g., location sensors, optical sensors, multispectral sensors, thermal infrared sensors, laser sensors, electro-chemical sensors, mechanical sensors, dielectric soil moisture sensors, and air flow sensors) on the market to measure crop, soil, and microclimate parameters. Kim and Lee [46], who reviewed the sensors widely used in the market in order to monitor the plant, the soil, and the environmental conditions that directly affect plant growth, presented the electrochemical sensors for monitoring plant health in PA as in Figure 7.

Figure 7.

The electrochemical sensors for monitoring plant health in precision agriculture [46].

3.9 Image-based sensing and unmanned aerial vehicles

Unmanned aerial vehicles (UAV), and unmanned ground vehicles (UGV) are utilized for plant health monitoring, pest control, livestock management, aerial survey, and soil analysis in PA. High-resolution cameras (RGB, multispectral, etc.) are used for the purpose of capturing the images for further investigation [47].

3.10 Crop yield monitoring and mapping

Crop yield monitoring and mapping can be defined as the process of collecting georeferenced data on crop yield and characteristics while the crop is being harvested. It provides the ability to not just estimate yield, but to identify the location in the field where yield is produced. The information obtained during crop yield monitoring and mapping is valuable for a multitude of management purposes, including estimating the amount of nutrients removed by the harvested crop, estimating profitability, developing management zones, and analyzing the impacts of treatments used in on-farm studies. In general, yield monitors provide a realistic estimate of the “relative” yield differences within a field. Yield maps are very useful in providing a visual image which shows the variability of yield across a field [48, 49, 50]. Various methods, using a range of sensors, have been developed for mapping crop yields. Vellidis et al. [49], who evaluate the strengths and weaknesses of commercially available crop yield monitoring and mapping systems, recommended that all potential users should carefully research prospective cotton yield monitoring systems for the following attributes before purchasing: quality of the product, “user-friendliness,” ease of installation, GPS requirements, availability and responsiveness of technical support, skill level required of the picker operator, and time available for downloading data files.

4. Main issues affecting adoption of precision agriculture in cotton production

Although PAT improve the efficiency of agricultural practices by reducing overuse of inputs (seed, fertilizer, pesticides, etc.), thus saving money on input costs, it is seen that adoption of PAT remains relatively low in cotton production. Many studies [e.g., [11, 51, 52, 53, 54, 55, 56, 57]] have been carried out to analyze the factors affecting the adoption of PAT specifically among cotton producers in recent years since it is stated that PAT are generally more profitable with high-value crops, such as cotton [58]. These studies showed that many factors including socio-demographic, economic, institutional infrastructure, etc., affect the adoption of PAT. The most important of these factors are expressed as the lack of digital infrastructure like internet and electricity, education level and purchasing power of farmers, and societal barriers. Pandey et al. [8] presented some common issues affecting the adaption of PA as data management, hardware cost, lack of information, interoperability, connectivity, and environmental variation (Figure 8).

Figure 8.

Some common issues affecting the adaption of precision agriculture [8].

Yield monitors are considered as one of the most important technologies in PA [59]. Also, grid and zone soil sampling and the use of soil survey maps are considered as a significant entry technology into PA [60]. However, the adoption sequence of PAT in cotton production is different from that in grain production because of the lack of reliable yield monitoring technologies for cotton [54, 61]. For example, reliable yield monitors for cotton were not available until 2000, while monitors for grains and oilseeds have been on the market since the early 1990s [62]. Also, in the USDA (US Department of Agriculture) ERS (Economic Research Service), it is stated that yield monitors were used on 72% of the corn area planted in 2010 and 33% of the corn area was mapped using yield monitor-GPS systems, in contrast, it was used on only 4.7% of the cotton area planted in 2007 and only 2.8% of the cotton area planted was mapped with yield monitors [63]. Mooney et al. [64] observed the adoption rate of cotton yield monitors by farms in 2009 as 4%. Larson et al. and Boyer et al. [61, 65] observed the use of yield monitors with GPS in cotton production has risen from 2.8% in 2001 to 19% in 2013. This situation significantly affected the adoption and frequency of PAT in cotton production.

Reuters [66] stated that the most important factor influencing the adoption of cotton yield monitors might be the introduction of on-board module builders on cotton harvesters that are paired with yield monitoring technology. Martin and Varco [67] reported that farmers might find value in combining the two technologies because of reduced equipment and labor expenses associated with the elimination of boll buggies and module builders in the harvest equipment complement. Roberts et al. [68] stated that cotton producers’ first experience in precision agriculture started with precision soil sampling, not yield monitoring. Walton et al. [69], who analyzed cotton farmer decisions regarding the adoption and abandonment of precision soil sampling as a function of farm and farmer characteristics, observed that farmers with high levels of education, large cotton production areas, and digital skills had an optimistic opinion about future of PA and were more likely to adopt precision soil sampling for cotton production. Lambert et al. [54] analyzed the adaptation of precision soil sampling by cotton producers in thirteen southern states in 2013. They stated that farming experience, farm size, land ownership, variable rate fertilizer, management plans, and the use of soil electrical conductivity devices had significant effects on the adaptation of precision soil sampling. Shafi et al. [70] stated that PA has been used for the last few decades to enhance crops’ yield with reduced costs and human effort, although the adoption of these novel techniques by farmers is still very limited owing to the reasons or challenges such as hardware cost, weather variations, data management, literacy rate, connectivity, and interoperability. Esposito et al. [71] reviewed the potential and practical use of the most advanced sensors available in the market for precision weed control. They emphasized that nowadays, especially, PA has rapidly advanced in integrated weed management because of technological innovations in the areas of sensors, computer hardware, nanotechnology, unmanned vehicle systems, and robots that may allow for specific identification of weeds that are present in the field. Lambert et al. [72], who evaluate the factors influencing the timing of grid soil sampling, yield monitoring, and remote sensing adoption by cotton producers using multivariate censored regression, stated that understanding the factors influencing the early adoption of PAT by cotton farmers is important for anticipating technology diffusion over time. They suggested that different factors such as land ownership, farm structure and size, farmer age and education, the purchasing behavior of farmers, and farm location influenced when cotton farmers adopted grid soil sampling, yield monitoring, and remote sensing adoption after these technologies became commercially available. Khanal et al. [73] suggested that special attention is given to the role of farmer expectations, following the adoption of PAT. The researchers observed a significant positive role of meeting “farmer’s expectation” about GPS guidance systems in application decisions and its further diffusion within a cotton farm. Also, they stated that income level, farm size, and farming occupation were other important factors in modeling GPS guidance system adoption and application. Takács-György et al. [74], who stated that the adoption of PAT is slow across the world, emphasized that the application of precision crop production is not easy to understand, it requires much attention, precise work, and a wide range of information. They stated that the slow uptake of some elements of the technology could be partly explained by the problematic questions of shifting such as the need for expertise and precision, requiring the documentation and tracking of the procedures, and extra investment. The authors suggested that all kinds of cooperation and strategic collaborations among the farmers, extension services, and providers are important in the adoption of new technology, such as the forms of joint machine use (e.g., machinery rings) because the individuals make their decisions on the adoption of new technologies on the basis of information coming through these channels. This means that relevant industry players and suppliers affected in the application and marketing of the technology are dominant with regard to the application and adoption. Nair et al. [75] determined that farm size, extension activities, percentage of land owned by a farmer, and the age-education had significant impacts on the choice of the VDTs and VRT. They stated that in particular, younger and more educated farmers were more likely to adopt VDRs and VRT.

A recent study by Paudel et al. [76], who analyzed the duration of PAT adoption that addresses heterogeneity and event dependence between PAT adoptions among the US cotton farmers. Their results indicated that farmers with large farms, a higher share of total cultivated farmland, a higher percentage of income from farming, and farmers using computers for farm management were more likely to adopt PAT. Further, the researchers observed that cotton producers who think that PAT would be valuable in the future and those receiving farming information from university publications were more likely to adopt PAT soon after the technologies become available. In order to increase the adoption of PAT, they recommend the following remarks:

1. Political and legal support could be provided for the dissemination of precision agriculture.

2. University extension programs, private extension services, or international extension agents could provide valuable educational and application assistance to producers to become more familiar with the usage of the PAT.

3. Subsidized capital or financial support could be provided to facilitate the adoption process of farmers because the equipment used in PAT is expensive.

4. Proper documents of environmental or agronomic benefits from precision agriculture might contribute farmers to adopt the PAT.

Overall, we can summarize the main deterrents to the widespread adoption of PA as follows;

1. Considerable investments in time and effort are usually required to learn how to use new technologies in the case of adopting PA.

2. The lack of demonstrated evidence for the economic advantages of adopting PA.

3. Uncertainty in returns and high fixed cost prevents adoption of precision agriculture applications.

4. Farmers’ lack of awareness of the existing precision agriculture technologies in the market.

5. Difficulty in understanding the technologies and interpretation of the data.

6. Farm size, exposure to extension activities, and the age-education have a significant impact on the adoption of PAT.

5. Conclusions

Precision agriculture (PA), which aims to optimize crop yields and reduce waste, while minimizing the impact on the environment by applying crop input and agronomic practices according to the spatial and temporal variability in field conditions and crop requirements, is a new or latest farming practice. It can also be defined as an agricultural application using modern technologies such as GPS, GIS, yield monitors, near-infrared reflectance sensing, remote sensing, IoT sensors, drones, computer vision, LIDAR, big data processing, and artificial intelligence. PA is still in its infancy and its adoption varies greatly although it is the agricultural system of the future and has tremendous benefits. This chapter has given an extensive literature survey on PA and its practices in cotton production along with several considerations and challenges. Also, the information about the main apparatus and instruments used in PA are given in the chapter. Furthermore, the main factors affecting the adoption of PA in cotton production are highlighted. According to the results of the articles reviewed within the scope of this chapter, the adoption sequence of PAT in cotton production is different from that in grain production because of the lack of reliable yield monitoring technologies for cotton. The studies showed that many factors including socio-demographic, economic, institutional infrastructure, etc., affected the adoption of PAT. In the studies, some common issues affecting the adaption of PA are presented as data management, hardware cost, lack of information, interoperability, connectivity, environmental variation, uncertainty in returns from adoption, high fixed cost, farmers’ lack of awareness of the existing PAT in the market, farm size, exposure to extension activities, and the age-education.