Global Journal of Science Frontier Research, A: Physics and Space Science, Volume 23 Issue 1

fertilizer, chemicals, pesticide, lime, gypsum, and irrigation water. By creating a Zones Map from specified data layers such as Topography, Satellite Images, Soil Sampling, High-Density Sensors and Cameras, Applied Datasets of Yield, VRA maps can be employed for any agricultural field. Data visualization leads to new ideas, and analytics helps to solve problems by creating solutions and writing prescriptions agronomists. CropX captures raw data from global soil sensors and integrates it with topography/soil maps, weather forecasts data, satellite imagery, hydraulic models, crop models, user inputs, data from the controllers, and agricultural equipment such as sprayers, tractors & harvesters, and then ingests it to a centralized platform running on Elastic Compute Cloud (Amazon EC2) instances. It then analyses and saves satellite imagery, agronomical data, and insights in the cloud storage. It uses SNS to transfer messages between services. The Service provides crop-specific and growth-stage-specific insights and recommendations, such as advising farmers when, where, and how much to irrigate, fertilize and spray (CropX, n. a.) . c) Microsoft Azure Farm Vibes. AI (Project Farm Vibes, n.a.) is Microsoft’s open-source Multi-Modal Geospatial ML Models for Agriculture and Sustainability. There are three main components of FarmVibes.AI. The first one consists of data ingestion from sources such as satellite imagery (RGB, SAR, multispectral), drone imagery, weather data, custom sensor data (such as weather sensors), and more. The input data is pre-processed for building ML models with ease based on parameters that can be specified. The inbuilt notebooks are used to tune the models to achieve a level of accuracy for the specific parts of the world or seasons. The library includes data for detecting practices (for example, harvest date detection in the country for a particular crop), estimating climate impact (both seasonal carbon footprint and long-term sustainability), microclimate prediction, and crop identification. The artificial intelligence arm of Farm Vibes has three parts, namely, Async Fusion, which pairs sensors and satellite imagery to create nutrient heat and soil moisture maps; Space Eye, which removes clouds from satellite imagery; Deep MC, which uses sensor data and weather forecasts to predict the temperatures and wind speeds of a farm’s microclimate; and a “what if” analysis tool that predicts effect on the soil’s carbon sequestration abilities based on variances in farming methods. i. Use Case-Bayer Bayer’s Climate Field View™is a data integration tool that provides yield analysis, field region reports, field health imagery, and manual seed scripts. As per the company’s report, the Software is being used on more than 180 million farming acres across more than 20 countries. Microsoft and Bayer have entered into a strategic partnership to build a new cloud-based set of digital tools and data science solutions to enable the rapid development of agriculture food tech applications by the combination of modern cloud technology and adding a layer of data (Digital Farming, n. a.) . V. C hallenges Soil fertility has severely degraded in many parts of the world due to intensive agriculture, increasing use of fertilizers and pesticides, over-grazing, water pollution, deforestation, salinization, and accumulation of non-biodegradable waste. Climate change due to global warming further aggravates land degradation, soil erosion, and soil fertility. Natural disasters like flooding and landslides are being witnessed more frequently worldwide. Severe soil degradation can reduce crop yield by over 50% (FAO, 2019) . At the same time, Food and Agriculture Organization of the United Nations has estimated that the world population will exceed 9 billion by 2050, and the world will lose about 250 million crop- production acres due to urbanization and soil degradation from excessive tillage and other farming practices (Wilde, 2021) . Food loss and waste (FLW) in production, postharvest and consumption stages are 24, 24, and 35 percent, respectively, accounting for more than 80 per cent of food wastage in these stages, which is quite alarming (Li et al, 2017) . The agriculture analytics market is expected to grow to $2.27 billion by 2027, at a CAGR of 17.5% from 2020 to 2027. The key factors driving the growth are rising pressure to meet global demand for food, especially in the current world environment of food shortage due to the COVID epidemic, climate changes, and war. This environment has led to an increasing need for improved farm productivity that is possible only by the use of Knowledge Agriculture deploying modern tools and technology of AI and predictive analytics to improve the yield and cut down the losses of 1.2 billion tonnes globally; 40% of all food is never eaten when both farming and post-farming are taken into account, as per WWF-UK (WWF, 2021) . Going with cloud-based technologies and applying big data in the agribusiness chain will reverse the trend of farmers selling their land for choosing employment in the service sector and make the agriculture business profitable. The lack of technical know-how among farmers, the fragmented agriculture industry, and need for heavy capital investment for Knowledge Agriculture, lack of standardization for data management and data aggregation may hamper the growth of this market. Further, political compulsions, farmers’, and trade unions’ lack of trust in industrialists and solution providers are significant impediments. One of the most significant challenges is discovering stable business and operational frameworks for private-public © 2023 Global Journals 1 Year 2023 24 Global Journal of Science Frontier Research Volume XXIII Issue ersion I VI ( A ) Data-Driven Knowledge Agriculture: A Paradigm Shift for Enhancing Farm Productivity & Global Food Security