Authors : Prabavathi R; Subha P; Bhuvaneswari M; Prithisha V; Roshini K

Volume/Issue : Volume 9 - 2024, Issue 4 - April

Google Scholar : https://tinyurl.com/2drru9u9

Scribd : https://tinyurl.com/3xhncf2s

DOI : https://doi.org/10.38124/ijisrt/IJISRT24APR532

Abstract : Agricultural productivity hinges on soil fertility, influenced by key factors like nitrogen, phosphorus, potassium, pH level, and soil moisture. Yet, achieving optimal crop growth is challenging due to limited farmer knowledge and difficulties in determining precise fertilizer quantities. Conventional soil analysis methods involve manual sampling andcostly lab tests, which are subjective. To address this, aproposed solution integrates IoT-enabled soil nutrient monitoring with machine learning algorithms for croprecommendations. Sensors collect data on crucial parameters like nitrogen, phosphorus, and soil temperature, transmitting it to a cloud-based database. Machine learning analyzes this data to suggest ideal crops, minimizing fertilizer use, reducing labor, and enhancing overall productivity. This innovative approach streamlines crop selection, minimizing unnecessary inputs while maximizing yields. By harnessing IoT and machine learning, farmers gain valuable insights into soil health, enabling precise fertilization and crop selection. This not only boosts agricultural productivity but also contributes to economic growth by fostering sustainable practices andincreased yields.

Keywords : Agriculture Yields, Crop Recommendation, Machine Learning, Soil Behavior Analysis.