GEOSPATIAL CROP YIELD MODELLING IN FUTA FARM

Elufisan Paul Tomilola ()
Additional contact information
Elufisan Paul Tomilola: Department of Surveying and Geoinformatics, Ajayi Crowther University Oyo, Oyo State.

Malaysian Journal of Geosciences (MJG), 2023, vol. 8, issue 1, 82-92

Abstract: This research aims to geospatially model crop yield in a FUTA farm to enhance productivity and management practices. Primary and secondary data were collected for seven planting seasons (2014-2021), including maize seeds, NPK fertilizers, urea used, harvesting dates, and yield measurements. GNSS observation was used to determine planting boundaries, while satellite imagery and climate records were used for secondary data. The study examined the vegetation indices (NDVI and GCI) of the farm between 2012 and 2022. Then, Artificial Neural Network (ANN) was used to model crop yield in the study area using the primary and secondary data and the NDVI, and GCI values. Result showed that Vegetative indices (NDVI and GCI) showed an increase between 2014 and 2016, while between 2017 and 2019, there was a decrease. In 2021, there was an increase in vegetative indices values, indicating healthier crops. The decline in crop yield between 2017 and 2019 was not coincidental, but it is believed that the decline in crop health is responsible for the corresponding reduction. The ANN model had a regression coefficient of 0.73282, and the coefficient of determination was 0.5176. The maximum and minimum crop yield values were 24.7 and 25.26 in 2016, and 5 and 4.01 in 2018, respectively. It was observed from that the minimum value of difference is -9.883708757 while the maximum value of difference is 1.451557122. The root means square error (RMSE) and the Mean Absolute Error (MAE) are 0.4296 and 0.2947, respectively. Modelled crop yield values were close to actual yield values, except for 2017 when a large difference was observed due to herdsmen invasion into the school farm. Since, the model showed close correlations with actual yield values, making it a recommended model for predicting crop yield in the study area.

Keywords: Crop Yield; NDVI; GCI; Artificial Neural Network (ANN) (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://myjgeosc.com/archives/1mjg2024/1mjg2024-82-92.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zib:zbnmjg:v:8:y:2023:i:1:p:82-92

DOI: 10.26480/mjg.01.2024.82.92

Access Statistics for this article

Malaysian Journal of Geosciences (MJG) is currently edited by Dr. Rodeano Roslee

More articles in Malaysian Journal of Geosciences (MJG) from Zibeline International Publishing
Bibliographic data for series maintained by Zibeline International Publishing ( this e-mail address is bad, please contact ).