Predicting Orange Harvest Using Image Analysis and RandomForestRegressor

EasyChair Preprint no. 13705

Abstract

AI in agriculture offers numerous benefits, from increased productivity and efficiency to waste reduction and sustainable practices. This revolutionary technology processes large volumes of data, providing valuable insights on climate, plant health, water management, and logistics. AI also enables the automation of agricultural tasks, such as harvesting and pesticide spraying, making the process more efficient and cost-effective (RENDA, 2023, SCHMIDHUBER, 2015). The "Prediction of Orange Harvest Based on Flowering Image Analysis" is a fascinating and innovative topic that combines agriculture with modern technology. This study aims to develop efficient methods to predict orange production using images of tree flowering. Flowering is a crucial indicator of the productive potential of an orange tree, yet the relationship between flowering and final fruit production is complex and influenced by many factors, including climatic conditions, tree health, and agricultural practices. (REZENDE, 2004 , ELISANDRA 2005, WILLIAMS, 1969)

Keyphrases: deep learning, predicting orange, RandonForest

@Booklet{EasyChair:13705,
  author = {Alessandro Akira Saito and Milton Faria Jr},
  title = {Predicting Orange Harvest Using Image Analysis and RandomForestRegressor},
  howpublished = {EasyChair Preprint no. 13705},

  year = {EasyChair, 2024}}