TY - JOUR AU - Gurrapu, Sai AU - Sikder, Nazmul AU - Wang, Pei AU - Gorentala, Nitish AU - Williams, Madison AU - Batarseh, Feras A. PY - 2021/04/18 Y2 - 2024/03/29 TI - Applications of Machine Learning For Precision Agriculture and Smart Farming JF - The International FLAIRS Conference Proceedings JA - FLAIRS VL - 34 IS - 0 SE - Posters DO - 10.32473/flairs.v34i1.128497 UR - https://journals.flvc.org/FLAIRS/article/view/128497 SP - AB - <p>Recent deglobalization movements have had a transformative<br>impact and an increase in uncertainty on many<br>industries. The advent of technology, Big Data, and Machine<br>Learning (ML) further accelerated this disposition.<br>Many quantitative metrics that measure the global<br>economy’s equilibrium have strong and interdependent<br>relationships with the agricultural supply chain and international<br>trade flows. Our research employs econometrics<br>using ML techniques to determine relationships<br>between commonplace financial indices (such as<br>the DowJones), and the production, consumption, and<br>pricing of global agricultural commodities. Producers<br>and farmers can use this data to make their production<br>more effective while precisely following global demand.<br>In order to make production more efficient, producers<br>can implement smart farming and precision agriculture<br>methods using the processes proposed. It enables<br>them to have a farm management system that provides<br>real-time data to observe, measure, and respond<br>to variability in crops. Drones and robots can be used<br>for precise crop maintenance that optimize yield returns<br>while minimizing resource expenditure. We develop<br>ML models which can be used in combination<br>with the smart farm data to accurately predict the economic<br>variables relevant to the farm. To ensure the accuracy<br>of the insights generated by the models, ML assurance<br>is deployed to evaluate algorithmic trust.</p> ER -