Trends and Patterns in Tea Yield Prediction using Machine Learning Algorithms – a Bibliometric Analysis

Abstract

The application of machine learning (ML) in agriculture has transformed yield prediction, enhancing productivity and optimizing resource utilization. Predicting yields has become a focal area of research due to its vital role in addressing challenges such as natural disasters, market fluctuations, and effective agricultural planning. Among various crops, tea yield prediction is particularly significant, with India being one of the world's largest tea exporters [11, 13]. This study conducts a bibliometric analysis to examine the convergence of tea yield prediction and ML techniques. It aims to provide a detailed bibliometric overview and highlight research gaps for future exploration. The analysis entails collecting bibliographic data from trusted sources like Scopus, Web of Science, PubMed, or Google Scholar and evaluating it based on [7]. The data spans from 2015 to 2024. Through bibliometric analysis, the study seeks to offer valuable insights into: a) prevailing research trends and significant contributions in the field, b) emerging areas and gaps in tea yield prediction using machine learning, and c) the geographic and institutional factors shaping progress in this area. Tea yield prediction through machine learning (ML) involves using advanced computational methods to estimate the quantity of tea that can be harvested from a specific area, considering various influencing factors such as weather conditions, soil health, irrigation practices, crop diseases, and pest infestations. ML enables the creation of predictive models that offer more accurate, dependable, and timely forecasts than traditional approaches, resulting in improved management of tea farming operations.