Tools
Tools
Shittu, Oyinkansola (2023) Soil Degradation Prediction and Classification using Digital Soil Maps:Boosting Nigerian Food Security. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (7MB) | Preview |
Preview |
PDF (Configuration manual)
Download (5MB) | Preview |
Abstract
The global threat to food security in recent years and the uncertainties around it motivated this research. The experiment is channelled towards assisting the Nigerian government in the plan to improve farmers economic well-being and food security in Nigeria. In this research, eight machine learning models were developed to predict and classify soil pH and soil textures using the Nigerian digital soil map (two for prediction and six for classification). The models are support vector machine for regression, random forest for regression, k-nearest neighbour (2), support vector machine, non-parametric Naive Bayes (2) and Random forest. Soil PH has been rated high as one of the key indicators of soil organic carbon which in turn, scientists have mentioned is one of the main indicators of soil degradation.The developed models successfully predicted and classified both soil pH and soil texture with very high accuracy and negligible errors. Randomforest was found to be the best of the models for both prediction and classification at accuracy of 1 and relative mean square error of 0.006 and all the developed models outperformed the benchmarked existing models on the evaluating metrics.This successful high performance models confirmed the Nigerian soil map dataset can be used to predict and classify soil degradation with the aim of the Nigerian government educating farmers on suitable crops for each soil type to improve the farmers economic power and indirectly resolving the continuous farmers- herders clashes over farm lands.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Mulwa, Catherine UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science S Agriculture > S Agriculture (General) > Farming Industry H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry > Plant products industry |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 10 Jan 2025 16:40 |
| Last Modified: | 10 Jan 2025 16:40 |
| URI: | https://norma.ncirl.ie/id/eprint/7304 |
Actions (login required)
 |
View Item |