CROP YIELD PREDICTION USING MACHINE LEARNING SATELLITE DATA

Author(s): Nikita Deshmukh, Dr. Nita Goswami, Rana Jay Bharatbhai

Publication #: 2506013

Date of Publication: 08.06.2025

Country: India

Pages: 1-8

Published In: Volume 11 Issue 3 June-2025

Abstract

Crop yield prediction plays a crucial role in agricultural planning, food security, and economic stability.

Traditional yield estimation methods are often labor-intensive, time-consuming, and limited in accuracy. This

study focuses on the use of Machine Learning (ML) algorithms integrated with satellite data to enhance crop

yield prediction. Satellite imagery provides valuable environmental indicators such as NDVI, rainfall,

temperature, and soil moisture, which influence crop growth. By training ML models like Random Forest,

Support Vector Machines, and Gradient Boosting on historical crop yield and remote sensing data, the system

can identify patterns and predict yields with improved accuracy. The model’s ability to analyze real-time and

large-scale data makes it suitable for diverse regions and crop types. This technology empowers farmers,

researchers, and policymakers with timely insights, aiding in better resource allocation, risk management, and

strategic planning. The integration of ML and satellite data offers a scalable, efficient, and data-driven approach

to modern agriculture.

Keywords: remote sensing, Supervised Learning, Time series analysis, Geospatial Data, Vegetation Index.

Download/View Count: 61

Share this Article