Research Article
Towards Automated Environmental Monitoring Using YOLOv8 Variants
Nnanna Ekedebe*
Issue:
Volume 14, Issue 5, October 2026
Pages:
160-166
Received:
13 July 2026
Accepted:
24 July 2026
Published:
18 September 2026
Abstract: Oil spills in the Niger Delta pose a severe environmental threat, yet existing detection methods remain slow, manual and unsuitable for large-scale continuous monitoring. While existing studies have applied individual YOLOv8 variants to oil spill detection, no prior study has systematically benchmarked YOLOv8n, YOLOv8s and YOLOv8m under identical conditions framed around Niger Delta deployment constraints. This study benchmarks three YOLOv8 variants nano, small and medium trained and evaluated under identical conditions. The dataset used is a publicly available Oil Spill Detection dataset from Roboflow Universe, comprising 2,567 images across four classes: object, rainbow, sheen and truecolor. The models were evaluated on a held-out test set of 72 images using mAP@50, mAP@50-95, Precision, Recall and Inference Speed. It was found that YOLOv8m achieved the highest accuracy at 81.95% mAP@50, while YOLOv8n achieved the fastest inference at 6.2ms with 68.66% mAP@50, and YOLOv8s offered no clear advantage over nano. YOLOv8n is recommended for resource-constrained deployment given its speed advantage, while YOLOv8m is recommended where computational resources allow, given its superior accuracy. These findings show that deep learning based detection is a viable and practical approach for automated environmental monitoring in the Niger Delta region, offering a better pathway toward localized, scalable oil spill surveillance in a region that has lacked such tools, helping guide faster cleanup response.
Abstract: Oil spills in the Niger Delta pose a severe environmental threat, yet existing detection methods remain slow, manual and unsuitable for large-scale continuous monitoring. While existing studies have applied individual YOLOv8 variants to oil spill detection, no prior study has systematically benchmarked YOLOv8n, YOLOv8s and YOLOv8m under identical c...
Show More
Research Article
Management Analysis of Rice Husking Residues in the City of Man (Tonkpi Region, Côte d'Ivoire)
Issue:
Volume 14, Issue 5, October 2026
Pages:
167-174
Received:
24 August 2026
Accepted:
7 September 2026
Published:
27 September 2026
DOI:
10.11648/j.ijema.20261405.12
Downloads:
Views:
Abstract: This study analyzes rice husking residues management in the city of Man (Tonkpi Region, Côte d’Ivoire), through a census of husking facilities, a quantification of the residues produced, and an assessment of current management practices. To this end, field observations and a survey were conducted at active rice husking mills in the city of Man, in collaboration with the Association of Rice Husking Machine Owners of Man. A total of 31 mills were surveyed, comprising 9 large semi-industrial mills (29%) and 22 small artisanal mills (71%), spread across 16 neighborhoods. The main residues from husking are husks, bran, and a husk-bran mixture. In large mills, husks and bran are produced separately; while in small mills, an undifferentiated mixture is generated. Over seven months of operation, total byproducts amounted to approximately 1,436.23 metric tons, including 645.71 metric tons of husks and 580.89 metric tons of bran from the large mills, and 209.76 metric tons of husk bran mixture from the small mills. The main recipients of the residues are poultry farmers (47% from large mills) and pig farmers (42% from small mills), as well as crop farmers, fish farmers, and cattle farmers.
Abstract: This study analyzes rice husking residues management in the city of Man (Tonkpi Region, Côte d’Ivoire), through a census of husking facilities, a quantification of the residues produced, and an assessment of current management practices. To this end, field observations and a survey were conducted at active rice husking mills in the city of Man, in ...
Show More
