Authors :
Oladipe Ebenezer Oluwole; Osaghae Edgar.O; Basaky Fredrick .D.
Volume/Issue :
Volume 8 - 2023, Issue 3 - March
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://bit.ly/40kRQEN
DOI :
https://doi.org/10.5281/zenodo.7825277
Abstract :
- This study is described as a recommendation
system that utilize data from Agricultural development
program (ADP) Kogi State chapters of Nigeria and
employs machine learning approach to recommend
suitable crops to be planted according to input soil and
climate statistics. The purpose of this study is to forecast
agricultural production using machine learning
techniques. The inferred classifier models here
incorporate information from Random forest
classifier,Gradient boost and Keras Regressor with
Gradient boost exhibiting the greatest accuracy of 98.9%.
Forecasts made by machine learning algorithms can now
assist farmers in choosing which plant to cultivate based
on key variables, including temperature, rainfall, and pH
and soil nutrients as nitrogen, phosphorous and
potassium. Therefore, this strategy lessens the financial
losses that farmers experience when they decide to plant
the improper crops. It also helps farmers in their search
for new crop varieties that are suitable for cultivation in
their region.
Keywords :
Machine Learning, Crop Yield, Cultivation, Forecasting, Plantation, Data Mining, Agriculture.
- This study is described as a recommendation
system that utilize data from Agricultural development
program (ADP) Kogi State chapters of Nigeria and
employs machine learning approach to recommend
suitable crops to be planted according to input soil and
climate statistics. The purpose of this study is to forecast
agricultural production using machine learning
techniques. The inferred classifier models here
incorporate information from Random forest
classifier,Gradient boost and Keras Regressor with
Gradient boost exhibiting the greatest accuracy of 98.9%.
Forecasts made by machine learning algorithms can now
assist farmers in choosing which plant to cultivate based
on key variables, including temperature, rainfall, and pH
and soil nutrients as nitrogen, phosphorous and
potassium. Therefore, this strategy lessens the financial
losses that farmers experience when they decide to plant
the improper crops. It also helps farmers in their search
for new crop varieties that are suitable for cultivation in
their region.
Keywords :
Machine Learning, Crop Yield, Cultivation, Forecasting, Plantation, Data Mining, Agriculture.
