Predicting Aman Rice Yields in Bangladesh Using Machine Learning
Author Information
Author(s): Taufiqul Islam, Tanmoy Mazumder, Md. Nishad Shahriair Roni, Md. Sadmin Nur
Primary Institution: Khulna University of Engineering & Technology (KUET)
Hypothesis
Which machine learning model is most effective for predicting Aman rice yields in Bangladesh?
Conclusion
The Random Forest model is the most accurate for predicting Aman rice yields under changing climatic conditions.
Supporting Evidence
- The Random Forest model showed the highest accuracy in predicting rice yields.
- Climate projections indicate rising temperatures and slight increases in monsoon rainfall.
- The correlation between rice production and rainfall has decreased significantly over the years.
- Machine learning models can enhance agricultural decision-making and food security.
- Future climate conditions may stress rice production due to higher temperatures.
Takeaway
This study used computers to help farmers know how much rice they can grow in the future, based on weather changes.
Methodology
The study analyzed 52 years of historical data and employed various machine learning models to predict rice yields.
Potential Biases
Potential biases may arise from missing data and the exclusion of socioeconomic factors.
Limitations
The study faced limitations due to the insufficient number of weather stations and reliance on historical data.
Participant Demographics
The study focused on rice production in Bangladesh, with no specific participant demographics provided.
Statistical Information
P-Value
0.0000
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website