A Machine Learning Framework for Predicting Crop Production in Support of SDG13 Climate Action

Shidling, Amrit Laxmanasa (2023) A Machine Learning Framework for Predicting Crop Production in Support of SDG13 Climate Action. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Drought, a prolonged dry period in the natural climate cycle that will lead to reduced agricultural productivity. Current research utilizes machine learning techniques for drought classification, However, There is a need to develop precise crop production prediction models to address the impact of climate change. Addressing climate change to ensure food security is a challenge. This research proposes an advanced machine-learning framework to encourage better agriculture productivity. The proposed framework combines drought prediction factors with a crop production rate prediction model. A combination of soil moisture, drought information and crop production information consisting of Corn, Oats, Rice, Soybean and Wheat production data are used to train the machine learning regression Model. Data Preprocessing and Correlation Analysis techniques are applied to train four models namely, Linear Regression, XGBoost Regression, Random Forest Regression and Feed Forward Neural Networks. The results of the four models are presented in this research work based on Mean Squared Error(MSE), Mean Absolute Error(MAE) and R2 (Coefficient of Determination) value. Cross-validation technique like K-folds is applied to assess the performance and generalizability of models. This research shows promise for Random Forest, Feed Forward Neural Network and XGBoost in encouraging farmers to decide on crop selection and agricultural efficiency.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Stynes, Paul UNSPECIFIED
Uncontrolled Keywords:	Crop Production; Regression; Random Forest; XGBoost; Cross Validation
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	22 May 2025 16:10
Last Modified:	22 May 2025 16:10
URI:	https://norma.ncirl.ie/id/eprint/7611

Actions (login required)

View Item