Description:DESCRIPTIONS
Smart farming allows us to monitor plant growth and adjust system settings in real time. Consequently, plant growth can be enhanced and the farmer can obtain support. The integration of the digital and physical worlds is aided by Internet of Things (IoT) designs based on application-specific sensor data readings and improved processing. In this research, we propose the creation and evaluation of an intelligent agricultural system based on an AI-powered prediction platform. We are constructing a sophisticated base for this system. Currently, 85 percent of the world's freshwater resources are consumed by agriculture. As the global population grows and people consume more food, agriculture will continue to consume the vast majority of the world's freshwater resources. It is time to develop plans based on solid scientific evidence and technical progress. The importance of IoT in agricultural applications is growing as a result of the success of theoretical research over the past decade. As the Internet of Things (IoT) expands, more IT solutions are being employed in agriculture as part of precision agricultural approaches that help manage water resources more efficiently. It is possible to use any combination of technical, agronomic, management, and other approaches. Scientists have experimented with simple to complex irrigation systems in an effort to reduce the amount of water required for a wide variety of crops. Thermal imaging, the Crop Water Stress Index, and direct soil water readings are a few of the water-saving methods that have been implemented in irrigation systems. Precision agriculture is founded on the premise that farmers should maximise their investments and yields while also taking into account the dynamic nature of their natural environment. This concept emerged during a time of intense competition in agricultural productivity. It altered how people tilled, planted, fertilized, irrigated, and sprayed pesticides. Precision agriculture is necessary if we are to address agricultural production issues pertaining to productivity, environmental impact, food security, and sustainability. Because the global population is growing, there must be a substantial increase in the amount of food grown without a reduction in the nutrient content of the food. Precision agriculture is crucial for these reasons. Recent advances in sensor technology for smart farming and irrigation systems, as well as the advent of Internet of Things (IoT) technologies that can be utilised to build these systems, have made these advancements possible. We will discuss how "IoT in Agriculture" can be used to facilitate the transitions preceding digital transformations. We are thrilled to discover a concept for an IoT-based intelligent irrigation architecture that predicts soil moisture using machine learning. This will enable us to obtain more precise results. In this study, we propose a novel EDGE-Fog-IoT-Cloud platform for a future Internet of Things-based smart agricultural architecture. After we've seen the big picture of the architecture, we can discuss its execution. This platform's primary objective is to demonstrate how well artificial intelligence can assist farmers in making water-saving irrigation decisions. Today's farmers are losing time, money, and lives by not keeping up with technological advancements in their industry. Because the farmer cannot read or write, teaching him new skills is difficult. Farmers need a computerised system to help them monitor and manage their land. The automated system must be able to respond to questions on a variety of topics, such as how to properly irrigate the field, how to deal with potential environmental threats, and how to choose and apply fertilisers. Internet of Things enables the discovery of at least one of the best solutions in these situations. The Internet of Things (IoT) is a cutting-edge new technology that offers innovative solutions to some of the obstacles to agricultural modernization. Research institutes and logical organisations are increasingly turning to the Internet of Things as they seek answers and solutions to a diverse array of problems. This paper examines in detail several agricultural technologies, including embedded systems, sensor-based systems, the Internet of Things (IoT), and the IoT in conjunction with machine learning. It was discovered that adopting a smart farming system was both feasible and cost-effective in terms of precision farming's optimal utilisation of water resources. This article aimed to design a new intelligent agricultural architecture based on EDGE, fog, and IoT Cloud technologies. Using machine learning and other open source technologies, we demonstrated the significance of artificial intelligence techniques to the growth of precision agriculture. Future research directions include collecting the physical parameters of our own farming system to create our dataset and utilising the data from these sensors and weather forecast information to develop an algorithm that predicts soil moisture for the following days. During data ingestion, you should also monitor how well the server's hardware is performing. During this time, we focused on the limitations of AI methods, specifically the tradeoff between training speed and accuracy, which could be problematic for machine learning. To maximise the potential of transfer learning, therefore, additional research is required.

, Claims:CLAIMS
1. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) States it is the groundwork for future research.

2. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said it is a cutting edge technology.

3. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said this paper attempts to explain the concept, and assess its impact.

4. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said this paper has many applications.

5. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said that this paper discusses the major advantages and how it can improve.

6. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said that it is a smart system.

7. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said that we analyzed and discussed various aspects.

8. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said that in this research, we focused on using ML and IoT technology to achieve accurate results.

9. PROBABILISTIC METHOD IN APPLIED MATHEMATICS FOR FARMING SYSTEM TRACKING THROUGH MACHINE LEARNING AND THE INTERNET OF THINGS(IOT) of claim 1, wherein said that in recent years ML and IoT has become popular around the world.