MACHINE LEARNING TECHNIQUES IN DETERMINING LAND SUITABLE FOR CEREAL CROPS IN IKERE EKITI, EKITI STATE, SOUTHWESTERN NIGERIA.
Context and background: Agricultural land use planning is vital for sustainable development, requiring modern approaches to address complex challenges. Goal and Objectives: This study aimed at the application of machine learning techniques in determine land suitable for cereal crops in Ikere...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EL-AYACHI
2025-05-01
|
| Series: | African Journal on Land Policy and Geospatial Sciences |
| Subjects: | |
| Online Access: | https://revues.imist.ma/index.php/AJLP-GS/article/view/53174 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Context and background:
Agricultural land use planning is vital for sustainable development, requiring modern approaches to address complex challenges.
Goal and Objectives:
This study aimed at the application of machine learning techniques in determine land suitable for cereal crops in Ikere Ekiti, Ekiti State Southwestern Nigeria. The primary objective was to identify critical factors for sustainable agriculture, and use predictive models for optimal cereal zones using machine learning algorithms.
Methodology:
The methodology involved data acquisition, processing and information presentation. The data acquired involved both the primary and the secondary data, the primary data involved coordinates (Northing, Easting and Height) of points within the study area which was acquired with the aid of Tersus GNSS Receiver. In addition, the secondary data include Landsat Imagery, climate data (temperature and precipitation) and Soil parameters (carbon, phosphorus, potassium, soil pH and soil texture). Moreover, these data were processed with the aid of ArcGIS 10.7 Software and Machine Learning algorithm was used in predicting areas suitable for cereals crops.
Results:
The results revealed significant spatial variations in land suitability across Ikere Ekiti, with the machine learning models successfully identifying highly suitable zones for cereals crops. These findings underscore the importance of incorporating advanced geospatial and machine learning techniques into agricultural planning processes, which can lead to more informed decision-making and sustainable agricultural practices.
|
|---|---|
| ISSN: | 2657-2664 |