1 / 19

Seminar Report (1) (1)

The use of big data analytics in agriculture

Kinu
Télécharger la présentation

Seminar Report (1) (1)

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Seminar Report On The use of big data analytics in agriculture Submitted By Guide Name: Raypura Kinu H. Name: Dr.J.V.Suthar Reg.no.: 3060822048 (Asst. Prof. CAIT, AAU Anand) Semester: III Sign: College of Agricultural Information Technology Anand Agricultural University Anand – 388 110 Page 1 of 19

  2. Index Sr. Contents Page No. No. 1. Introduction 3 2. Objectives 5 3. Methodology 6 4. Results 9 5. Discussion 11 6. Recommendations 16 7. References 19 Page 2 of 19

  3. Introduction 1. ABSTRACT  Agriculture plays significant role in almost every country economy in the world. It is identified that agriculture produces huge amount of data with wide velocity and wide range of variety in each second. Analyzing these data and taking decisions depending on the data is highly difficult by using traditional tools and techniques. Hence not only large amount of products but also fertilizers, labor and other resources are wasted. Big data analysis is the best way to explore the data. Presenting the discussion on how big data analytics and how its tools use in the field of agriculture is the main aim of this paper. Big data provides farmers granular data on rainfall patterns, water cycles, fertilizer requirements. This enables them to make smart decisions, such as what crops to plant for better profitability and when to harvest. Big data analytics is the process of using advanced analytic techniques to extract valuable insights from large and complex datasets. In recent years, big data analytics has become increasingly important in the agricultural industry, as it can be used to improve crop yields, reduce costs, and make more informed decisions. Big data analytics is still a relatively new technology, but it has the potential to revolutionize the agricultural industry. As the technology continues to develop and become more affordable, it is likely that we will see even more innovative and effective uses of big data analytics in agriculture in the years to come. 2.BIG DATA A complex and massive collection of data which is hard to process by applying traditional data processing techniques or on-hand database management tools is referred as ‘big data’. These data are available on heterogeneity structures which are structured or unstructured or semi? structured. Data which is having pre-defined structure is called structured (banking information), data without pre? defined format is unstructured (text files, audio) and the semi? structured is data that are able to convert from unstructured to structured using available descriptions (xml document). Also big data is characterized by 3Vs to 4Vs which is meant by Volume, Variety, Velocity and Veracity. Each dimension has an opportunities to advance taking decisions as well as challenges for data management. Volume – amount of data generated Variety – variation of data with respect to the time Velocity – how speed data is generated and processed Veracity – availability and accountability Page 3 of 19

  4. The characterizing of the big data as bad, good or undefined is depended on incompleteness, inconsistence, atency, deception, ambiguity and approximations. 3. BIG DATA ANALYTICS  As mentioned in eariler, the complexity of big data is very huge which is unable to process using commonly used software tools. Also data sizes are continously increasing and changing from time to time. Hence, the used technique for analyzing data is called big data analytics. The process of collecting, keeping and analyzing the data with the aim of revealing hidden patterns, unknown correlations and other facts is called big data analysis. Analyzing big data is needed analytical capabilities as well as optimal processing power. In big data analysis, raw format data are converted into standard format with the support of tools. This is a process of information gathering, data analysis, visualization and scheduling. Big data analytics in agriculture can be studied under two major areas: smart farming and precision agriculture. The idea of farming management that is including about measuring, observing and responding is called precision agriculture.it is needed collection of data, analyzing and processing the gathered information. It uses big data tools for maximizing the productivity while using minimum number of resources. Global Positioning System (GPS), Geographic Information System (GIS), and Variable-rate Technology (VRT) are some of the technologies used in Precision Agriculture. Precision agriculture gives not only great challenges but also great opportunities for Computer Scientists specially who are working in the field of data analysis. Smart farming explains the relationships among functions, variables, and concepts. This is concentrated on the big data analytics applications including agricultural value chain and business processes. Page 4 of 19

  5. Objectives To increase the agricultural production towards the increasing world’s population  To reduce the expenses on agricultural farming.  To identify the problems of facing the famers in India.  To increase the market for the Agricultural products of India all over world.  To identify the climatic seasons changes.  To Forecast and historical weather information fine-tuned for agricultural decisions. Page 5 of 19

  6. Methodology 1 .Big Data Applications  Big data applications are being used in different industries. Fed BP Disaster response was an application for the government’s [USA government] response in the disaster situation. This was built in 2010 when oil rate flow was a key issue. BP and independent groups presented changeable estimates preventing efforts to manage the level and range of the U.S. Government’s response. NIST analyzed the estimates and formed actionable intelligence on which to support the final reaction [12]. Applications in oil and gas business could be Equipment maintenance to prevent failure, production optimization, price optimization, safety and compliance. Oil and gas companies have big competition in their field, and facing regular change. Firms need to increase their production volumes and at the other hand they also want the healthy, safety and low risk environment. From exploration and production of the oil, leading companies are using big data for new business values, reduce cost and increase production [13]. Website of Whitehouse consists of all speeches of Barrack Obama. Aim was to find the influence of these speeches on the election. A scrapper was made to collect all speeches from the website. Hadoop and Map reduce both are used for parallel processing of these speeches. Study finds the most spoken or referred words, most referenced countries, personalities and also focus on internal and foreign affairs. According to [14], these all things are the basis for the influence on the elections. A. Different tools used for the data Analytics: - At Present, the tools that can be used for the analysis of the Agricultural data can be listed. The Usage of the different tools that can be used for analytics can be listed below. 1. Tool :- language R Use: - software environment for statistical computing and graphics Remarks: - Graphical facilities for Agriculture data analysis and display either on-screen or on hardcopy. 2. Tool :- Hadoop Use: - Open-source software framework for distributed storage of very large datasets on computer clusters. Remarks: - software framework for distributed storage of the collected large agriculture data set 3. Tool :- Python Use: - for data manipulation and analysis Remarks: - To manipulate the Agricultural data. 4. Tool :- Visualization Tools :- a) Tableau, b) D3, c) Data wrapper Use :- Information that has been abstracted in some schematic form, including attributes or variables for the units of information Remarks : - By using these tools visualization of the pattern is clear. At present, high-tech tools are raising the bar, enabling farmers to crunch massive amounts of data collected through sensors to predict the best time to plant, what type of seed to use, and where to plant in Page 6 of 19

  7. order to improve yields, cut operational costs, and minimize environmental impact. John Deere’s Farm Sight, Monsanto’s Field Scripts, and Pioneer’s Field360 are among the tools that allow farmers to collect planting and yield data from motorized farm equipment and input this information into a database that, when aggregated with multiple sources of anonymized data, produces detailed prescriptions. B . Role of big data in agriculture : -  Sustainability, global food security, safety, and improved efficiency are some of the critical issues that are being addressed by big data applications in agriculture. Undoubtedly, these global issues have extended the scope of big data beyond farming and now cover the entire food supply chain. With the development of the Internet of Things, various components of agriculture and the supply chain are wirelessly connected, generating data that is accessible in real-time. Primary sources of data include operations, transactions, and images and videos captured by sensors and robots. However, extracting the full potential of this data repertoire lies in efficient analytics. The development of applications related to risk management, sensor deployment, predictive modeling, and benchmarking, has been possible due to big data. Technology and input suppliers are the traditional players who offer their platforms and solutions to the farmers. Data privacy and security risks compel farmers to form coalitions to benefit from their data, creating a close and proprietary environment. Big data also attract start-ups, private firms, non-agricultural tech companies, and public institutions. The organization of the stakeholders determines the infrastructure of big data solutions – either proprietary or an open-source system. The development of big data applications in agriculture will result in either the farmers becoming franchisers in integrated long supply chains or a scenario in which farmers collaborate with suppliers and the government to engage in short supply chains. Page 7 of 19

  8. C. big data analytics transforming agriculture :- Boostingproductivity– Data collected from GPS-equipped tractors, soil sensors, and other external sources has helped in better management of seeds, pesticides, and fertilizers while increasing productivity to feed the ever-increasing global population. Access to plant genome information– This has allowed the development of useful agronomic traits. Predicting yields– Mathematical models and machine learning are used to collate and analyze data obtained from yield, chemicals, weather, and biomass index. The use of sensors for data collection reduces erroneous manual work and provides useful insights on yield prediction. Risk management– Data-driven farming has mitigated crop failures arising due to changing weather patterns. Food safety– Collection of data relating to temperature, humidity, and chemicals, lowers the risk of food spoilage by early detection of microbes and other contaminants. Savings– AI and data analytics-driven farming generate significant savings for the agriculture industry. Page 8 of 19

  9. Result  The results of studying the use of big data analytics in agriculture can yield valuable insights into how this technology is impacting various aspects of farming. Here are potential results and findings that might emerge from such a study: Improved Crop Yield and Quality: Farmers leveraging big data analytics experience improvements in crop yield and quality due to better- informed decision-making. Precision farming practices, guided by data analytics, contribute to optimized planting, irrigation, and harvesting techniques, leading to increased productivity. Enhanced Resource Efficiency: Big data analytics helps in the efficient use of resources such as water, fertilizers, and pesticides. Smart irrigation systems, driven by real-time data, reduce water wastage, and optimized nutrient application leads to better resource utilization. Predictive Crop Disease Management: The use of data analytics enables the prediction and early detection of crop diseases and pest infestations. Farmers can take proactive measures, reducing the reliance on chemical treatments and minimizing the impact on crop health. Precision Agriculture Adoption: Farmers increasingly adopt precision agriculture practices, tailoring their approach to individual crops and fields. Data-driven insights facilitate the customization of planting density, seed varieties, and cultivation methods, leading to more sustainable and efficient farming. Streamlined Supply Chain and Market Integration: Integration of big data analytics in agriculture streamlines the supply chain, from production to distribution. Farmers can align their production with market demands, reducing waste and ensuring timely delivery of agricultural produce to consumers. Increased Adoption of Smart Farming Machinery: Data analytics plays a crucial role in the adoption of smart and autonomous farming machinery. Automated tractors, drones, and other equipment guided by real-time data contribute to increased operational efficiency on the farm. Challenges in Data Security and Privacy: The study may reveal challenges related to data security and privacy, especially concerning the collection and sharing of sensitive farm-related data. Page 9 of 19

  10. Addressing these challenges is crucial for ensuring the responsible and ethical use of big data in agriculture. Need for Farmer Education and Training: Results may highlight the importance of farmer education and training programs to ensure effective utilization of big data analytics tools. Bridging the knowledge gap is essential for widespread adoption and maximizing the benefits of data- driven farming practices. Policy Implications: The study may identify areas where policy interventions are needed to support the integration of big data analytics in agriculture. Governments and regulatory bodies may need to develop frameworks that encourage responsible data use while addressing concerns related to data ownership and access. Environmental Impact Assessment: Assess the environmental impact of data-driven farming practices. Are there measurable reductions in the use of agrochemicals, water, and energy? The results of such a study can provide a comprehensive understanding of the current state of big data analytics in agriculture, its impact on farming practices, and the challenges and opportunities associated with its widespread adoption. These findings can guide future research, policy development, and technological innovations in the agricultural sector. Page 10 of 19

  11. Discussion 1. Big data analytics in climatic changes discovery : -  In India the direct impact of climate change would be effect plant growth development and yield due to change in rainfall and temperature .Increase in temperature would reduce crop duration, increase crop respiration rate change the pattern of pest attack and new equilibrium between crop and pest hasten mineralization in soil and decrease fertilization use efficiency. Many crops have become adapted to the growing season, day lengths of the middle and lower latitudes and may not respond well to the much longer days of the higher summers. In warmer, lower latitude regions, increased temperate may accelerate the rate at which plant release CO2 in the process of respiration, resulting in hastened maturation and reduced yield. 2. Actual Seasons:-  Sowing Season: May to July. Sowing Season: October to December.  Harvesting Season: February to April. Harvesting Season: September to October. 3. Proposed Seasons :- By collecting the data of rainfall and temperature of last 5 years we can analyze the data by using different big data analytics tools to get the exact change in the Indian agricultural climate. 4. The Data that are collected can be used for the following conditions:- Historic weather patterns Plant breeding data and productivity for each Strain Fertilizer specifications and Pesticide specifications Soil productivity data Water supply data Market spot price and futures data Page 11 of 19

  12. Capturing data live analysis of data 5. Big data analytics in climatic changes discovery :- In India the direct impact of climate change would be effect plant growth development and yield due to change in rainfall and temperature .Increase in temperature would reduce crop duration , increase crop respiration rate change the pattern of pest attack and new equilibrium between crop and pest hasten mineralization in soil and decrease fertilization use efficiency. Many crops have become adapted to the growing season, day lengths of the middle and lower latitudes and may not respond well to the much longer days of the higher summers. In warmer, lower latitude regions, increased temperate may Page 12 of 19

  13. accelerate the rate at which plant release CO2 in the process of respiration, resulting in hastened maturation and reduced yield. 6. Sensors used for the data collection : -  Different sensors used for the data collection Sensor for climatic changes detection Sensor for pesticide control detection Page 13 of 19

  14. Sensor for moisture control detection 7. Proposed Framework for the solution to Agricultural problems : -  The data can be sent to the Agri bank to get the appropriate solution regarding Pesticide Usage  Seed Usage  Crop Diagnosis  Temperature and climate  Loan Request  Rain fall 8. Benefits of this Framework: Sensor for disease detection Page 14 of 19

  15. Using drowns to capture image The data in the form of pictures can be captured through our smart phones can be sent to the bank. The Agricultural bank contains necessary tools to analyze the data and within a short period, the farmer gets the solution to his problem. All the fertilizers and pesticides that are used by the farmers can be supplied by the Agricultural bank only. All the Agricultural loans issuing can be done according to the data contains in the bank. By using this approach the right farmer will get the loan. Crop Insurance issues can be easily solved by this frame work. Crop damage by the natural calamities can be easily estimated by using this frame work. Fraud in the loan issuing matters can be reduced because all the accurate land records can be kept in this bank Page 15 of 19

  16. Recommendations   Big data analytics in agriculture can play a crucial role in optimizing farming operations, increasing productivity, and improving overall sustainability. Here are some recommendations for implementing big data analytics in agriculture: Data Collection and Integration: Collect diverse data sources, including weather patterns, soil conditions, crop health, machinery performance, and market trends. Integrate data from various sensors, satellite imagery, and other sources to create a comprehensive dataset. IoT and Sensor Technology: Deploy IoT devices and sensors to collect real-time data from the field. Use sensors for monitoring soil moisture, temperature, humidity, and other relevant parameters. Implement precision agriculture techniques to optimize resource use. Remote Sensing and Satellite Imagery: Utilize satellite imagery for monitoring crop health, identifying disease outbreaks, and assessing overall field conditions. Integrate remote sensing technologies to provide a bird's-eye view of large agricultural areas. Predictive Analytics: Implement predictive analytics to forecast crop yields, disease outbreaks, and optimal planting/harvesting times. Use historical data to identify patterns and make informed decisions about crop management. Machine Learning and AI: Apply machine learning algorithms to analyze large datasets and derive insights. Develop models for predicting pest infestations, crop diseases, and recommending optimal crop varieties. Supply Chain Optimization: Use big data analytics to optimize the entire agricultural supply chain, from production to distribution. Page 16 of 19

  17. Improve logistics and reduce waste by accurately predicting demand and optimizing transportation routes. Farm Management Systems: Implement farm management systems that leverage big data analytics to assist farmers in decision- making. Provide user-friendly interfaces for farmers to access and interpret the data. Data Security and Privacy: Establish robust security measures to protect sensitive agricultural data. Ensure compliance with data privacy regulations to build trust among stakeholders. Collaboration and Knowledge Sharing: Encourage collaboration among farmers, researchers, and technology providers to share insights and best practices. Foster a culture of continuous learning and adaptation to new technologies. Scalability and Flexibility: Design systems that are scalable to accommodate the growing volume of agricultural data. Ensure flexibility to adapt to evolving technologies and agricultural practices. Education and Training: Provide training programs to farmers and agricultural professionals on using big data analytics tools. Foster a better understanding of the benefits and applications of big data in agriculture. By implementing these recommendations, the agriculture sector can harness the power of big data analytics to make more informed decisions, increase efficiency, and contribute to sustainable and productive farming practices. Page 17 of 19

  18. Conclusion   In the review paper, the notion of introducing big data to agriculture has been discussed with its driving factors and what visible constructive changes have been observed, after its initiation to the field as compared to the traditional methods. Given the variety of data required for performing big data analytics we also explore the various sources, methods and techniques for obtaining data. An agronomy-based framework for performing agricultural analytics has also been explained. Also, with the recent development in the field of technology, platforms and tools. Integrating them with big data analytics and implementing them in the field of agriculture has also been introduced, explained and reviewed in detail. Finally, a few challenges have been discussed, with possible solutions to overcome it. Following that, there is a representation of comparison table of various agricultural areas with its data sources and the techniques that can be applied to it. Nevertheless, the increase in big data and big data analytic with its adoption to open standards have immense potential to boost more research and development towards smart agriculture. Having said that we do not want to challenge the existing and traditional agricultural niches implemented by the farmers and agriculturists. But instead motivate and enhance the ongoing methods for producing higher quality products, generate more revenue for the business and plan sustainably without affecting the natural resources. Page 18 of 19

  19. References  https://www.researchgate.net/publication/344042695  https://www.researchgate.net/publication/339102917  http://nebula.wsimg.com/c877e0cda4fa92b8d611b726f8dbe8d4 Page 19 of 19

More Related