An analysis of Data mining techniques, multidimensional modelling on agriculture
Namrata Kumari*
Research Scholar, Dept. of Computer Science & IT, Magadh University, Bodh Gaya, Bihar, India
Email- namratakrishnasinha@gmail.com
Abstract - This articles analysis the “An analysis of Data mining techniques, multidimensional modelling on agriculture.” The sole method for using and obtaining knowledge from large data sets is data mining. Samples are taken in increments from various locations within a bag. A consignment can contain up to 30 bags, of which one must be selected at random from each bag. For consignments containing 50 bags, however, samples of the Magadh division blocks in Bihar must be obtained from each bag. additionally to investigate how changing weather affects agriculture and how data mining in government platforms is formed. Whether there is a positive correlation between weather changes and agricultural and big data mining. Results shows that the Big Data mining has positive co-relation (r=.8) on weather changing on agriculture. The results confirms the hypothesis.
Keywords: Data mining, Agriculture, Bugs, Climate change, and Algorithms.
INTRODUCTION
With less space available for farming, there is an urgent need to produce more food to feed the world's expanding population. Let's examine in more detail how agtech, or agricultural technology, and big data can be used to address this issue in this post. Traditionally, agriculture has been viewed as an intuitive field where knowledge is passed down through the generations. However, the issues of today—such as the shifting climate and the loss of arable land—are more complicated and pressing in nature1. In order to feed the world's expanding population, we must greatly increase food production. Regrettably, a significant portion of farmlands have been lost to increasing urbanization and climate change.
Through data mining, new patterns are found in massive data sets. It is the process of dissecting data from many angles and condensing it into knowledge that is helpful, all without having any restrictions on the kinds of data that can be examined. Extracting knowledge from an existing data set and transforming it for advanced use is the aim of the data mining process.
The data may be accessed via a relational database, data warehouse, text file, or web server log. Understanding the right data mining techniques is necessary for effective data analysis2. This paper's goal is to apply various data mining techniques to the agricultural domain with regard to the quality assessment of groundnuts in order to develop a model that can be applied to the decision-making process when purchasing any of the 16 notified agricultural commodities, such as cotton, oilseeds, and pulses, in accordance with Fair Average Quality Norms.
Predictive and descriptive tasks are the two categories into which data mining tasks fall. While descriptive data mining establishes and elaborates the general features of the data in the database, predictive data mining is used to anticipate the direct values based on patterns found from existing results. A small number of database fields or variables are used in prediction in order to forecast the future values of other relevant variables.3. The use of predictive data mining techniques is becoming widespread. Agriculture can benefit from extrapolations made with predictive data mining tools.
The benefits of big data for agricultureTechnology forces like IoT, big data, analytics, and cloud computing are being looked to by business executives and governments to help combat the stresses of rising food demand and climate change.
The initial stage of this process, data collection, is aided by IoT devices. Real-time data is collected straight from the ground with the help of sensors that are plugged into tractors, vehicles, fields, soil, and plants. In order to identify trends, analysts secondly combine the vast volumes of data gathered with other data accessible on the cloud, such as pricing models and meteorological data.
Ultimately, these trends and understandings help to manage the issue. They assist in identifying current problems, such as operational inefficiencies and poor soil quality, and develop prediction algorithms that can raise an alarm even before a problem arises.
Big data on the agriculture farm- Big data applications have a vast potential, and we have only just started to scratch the surface4. Farming practices may alter significantly as a result of the capacity to track tangible objects, gather data in real time, and predict scenarios. Let's examine a few scenarios where big data can be beneficial.
1. Feeding a growing population- One of the main issues that even governments are working to resolve is this one. Increasing the yield from the current farmlands is one strategy to accomplish this. Farmers can access detailed information on water cycles, fertilizer needs, rainfall trends, and other topics thanks to big data5. This helps them to make informed choices about when to harvest and what crops to sow for maximum profitability. In the end, wise choices increase agricultural yields.
2. Using pesticides ethically- The adverse consequences of pesticide administration on the ecology have made it a controversial topic. By advising farmers on the best pesticides to use, when to apply them, and in what quantities, big data helps them better manage this. Farmers can comply with regulatory rules and prevent the abuse of chemicals in food production by regularly monitoring it. Furthermore, since weeds and insects don't kill crops, this increases profitability.
3. Optimizing farm equipment- To improve fleet management, businesses such as John Deere have incorporated sensors into their farming machinery and implemented big data applications. This degree of monitoring, which notifies users of tractor availability, service due dates, and fuel refill warnings, can be a lifesaver for large farms. This basically ensures the long-term health of farm equipment and optimizes its usage.
4. Managing supply chain issues- According to McKinsey, annually, one-third of the food produced for human consumption is lost or squandered. a terrible reality given that the sector finds it difficult to close the supply-demand gap6. Reducing the cycles of food delivery from the producer to the market is necessary to address this. Big data can track and optimize delivery truck routes, which can lead to improvements in supply chain efficiency.
Environmental Data Mining- The process of obtaining knowledge from massive volumes of environmental data is known as environmental data mining. Environmental information management systems, recommender systems, decision support systems, environmental data analytics, and other related fields are all part of this multidisciplinary field that combines computer science with environmental sciences. In order to better evaluate and comprehend environmental processes and systems, a group of learners is trained sequentially on the dataset in the relatively new field of environmental data mining based on ensemble learning7. Nevertheless, how ensemble methods might be applied to enhance the performance of a particular method is still poorly understood.
An Using big data successfully to address problems facing the farming sector. This will make it easier to see how big data solutions can have a significant, practical influence. Big data is used by Digital Transmission Network to increase yields and profitability. Customers can obtain market intelligence and agricultural information solutions from DTN, a Schneider Electric business. Farmers and commodity traders can use DTN to get the most recent weather and pricing information to run their businesses more effectively8.
The enterprise resource planning (ERP) system, financial applications, GIS, agronomy packages, and sensing applications are just a few examples of the complex networks of data sources that DTN must manage in order to provide customers with real-time information. However, the current method used by DTN to connect these systems was becoming too costly to maintain.
DTN spent a lot of money on a cutting-edge data integration solution that allowed it to combine data from several sources without writing a lot of proprietary code. Now that it has a clear and uniform set of interfaces, DTN can accurately anticipate by combining field-based agronomic and meteorological data. Based on these projections, farmers can use DTN to increase yields and reduce expenses9. Digital Transmission Network has developed into an information hub for a networked farming and agribusiness community and has quickly become an industry standard for agribusiness information sharing.
The Hindi-language Biahr Krishi software (Digital Transmission Network) is an agriculture software created especially for Bihar farmers. It seeks to increase their incomes while supporting them on their path to more inventive and better farming10. This agriculture software in Bihar, which includes text and video on all aspects of agriculture, will guarantee that every farmer in the state has access to the newest technologies in agriculture. The Agri app, then, is a farmers' app that aids in keeping farmers informed about the finest agricultural and farming techniques. The software, which is among the top agricultural mobile applications in India, also discusses the best practices for crop management, productivity, and protection.
Bihar Krishi Yantra Yojana (BKYY)- The goal of this program is to improve farmers' financial status by incentivizing them to purchase new equipment11. Farmers in Bihar will receive financial support from the Bihar government through this initiative, which will subsidize agricultural machinery purchases up to 80.00%.
BKYY InVivo uses big data to empower precision farming- The top member of the BKYY agricultural cooperative organization is InVivo. Its subsidiary, BKYY, is the pioneer in agronomic information systems in Bihar. In Bihar, 20% of cooperatives and 30% of retailers utilize its software. BKYY sought to combine all of its data, including five years' worth of meteorological data, satellite and drone photos, and soil kinds, in order to make deft judgments more quickly, even though it has created numerous mobile applications to aid farmers in their day-to-day operations. Their goal is to employ technology to address the 21st-century food-related issues. Giving farmers in Bihar an 80% discount on the purchase of agricultural machinery is the primary goal of the Krishi Yantra discount Scheme Bihar 2024.
The Bihar government's Bihar Krishi Yantra Yojana seeks to subsidize agricultural tools financially12. Farmers that use this program can acquire agricultural equipment at a discounted price and receive subsidies. Subsidies for a large variety of equipment, with percentages ranging from 40% to 80%, are available for tractors, combines, trolleys, bulldozers, seed drills, seeding tools, and irrigation equipment. The direct transfer of these subsidies to farmers' bank accounts makes it easier for them to buy better equipment.
Farmers who want to use cutting-edge instruments to improve and modernize their agricultural methods might profit from the Bihar Krishi Yantra Yojana. They may now affordably access cutting-edge equipment, which increases output and makes agricultural duties easier. This program is essential to the growth of the agricultural sector since it empowers farmers in Bihar and encourages higher productivity.
Machinery for Various Crops: Grants are available for machinery related to maize, sugarcane, jute, and horticulture.
HYPOTHESIS
to gather and categorize reviews according to various techniques for maximizing the impact of weather on agriculture, such as multidimensional modeling and correlation analysis.
METHODOLOGY
In order to attain high precision and high generality with regard to data points, the study is creating appropriate data models. In order to find state-of-the-art in algorithms, technique, and problem domains, data mining for environmental analysis was conducted. The WEKA toolbox has been used to evaluate the method for data gathering and storage. The information gathered comes from publicly available data, which focuses on maximizing the positive correlation between multidimensional climate modeling and agricultural impurities (such as dust, dirt, stones, lumps of earth, chaff, stem/straw, or any other kind of impurity), damaged pods, shriveled and immature pods, pods of different varieties, shelling (kernels/pods), and moisture content government platform.
Large-scale meteorological data mining makes the effects of climate change on agriculture more irreversible. The test and tools employ predictive data mining to forecast how crops, fertilizers, and pesticides will be used in the future. Big data mining is used to determine how much money will be made for crop growth and function. Moreover, increasing numbers of samples are drawn from various areas of a bag. A consignment can contain up to 30 bags, of which one must be selected at random from each bag. For consignments containing 50 bags, however, samples of the Magadh division blocks in Bihar must be obtained from each bag.
RESULTS
The weather has an optimal impact on agriculture, as demonstrated by the results of multidimensional modeling and correlation analysis. Up to thirty bags in a shipment will be used to study how the weather is changing and how it affects agriculture using data mining on government platforms. The impact of weather variations on agriculture is positively correlated with big data mining. The impact of weather changes on agriculture is positively correlated (r=.8) with big data mining. The BKYY sophisticated agronomic Data Crop algorithm enables the optimum decision-making process by utilizing various forms of data.
With Data Crop, users can forecast yields and monitor crop progress throughout the year. a fact that has had amazing outcomes in wheat production. At the moment, Data Crop is used to manage 80.00% of the agricultural land in Bihar that is used for wheat cultivation. BKYY intends to extend this to additional crops and nations. The use of analytics in agriculture has been steadily rising, and the market is anticipated to continue expanding. Data mining has becoming more popular in many industries, and the agricultural sector needs to focus on it as well. Agglomerative clustering, DBSCAN, EM algorithms, and K-Means are a few examples of data mining techniques that we think can benefit the agricultural industry.
CONCLUSION
Big data in agriculture: the cloud and its future. Farming success used to be mostly based on advantageous natural forces, but that is no longer the case. Big data and cloud computing have made it possible for farmers to have access to enough information to make informed decisions. Because data centers and storage are now available on a "pay-as-you-go" basis, cloud computing has democratized the availability of enormous processing power. As a result, knowledge warehouses containing information on plant nutritional requirements, irrigation methods, weather, and other farming approaches may now be combined.
Farmers may increase their output and profitability by modifying their production in response to market demand with the help of BKYY apps. These days, a farmer may micromanage farming and all that goes along with it. In fact, by adjusting a few variables, it is possible to forecast the outcome even before crops are planted. The agriculture industry can be genuinely transformed by big data, but only if it has access to a cloud-based ecosystem that has the necessary tools and software to connect different data sources. To help farmers make decisions, these technologies ought to be able to compile information on a wide range of topics, including climate, agronomy, water, farm equipment, supply chains, weeds, and nutrients.
Multimedia modeling By providing a unified set of self-service applications for data integration and data integrity, Data Fabric accomplishes that. It enables real-time data streaming from several sources and aids in the extraction of critical insights based on reliable, high-quality data. Big data mining using multimedia modeling nowadays. The amount of rainfall and the climate throughout the year determine whether the agriculture sector succeeds or fails. Even though technology is used extensively in agriculture, data mining techniques are still not widely used in India's agricultural industry. Particularly when it comes to using massive amounts of data to create predictive models, not many studies have been conducted up to this point.
REFERENCES