Analysis of Drone-Camera Imagery-Based Mangroves Ecosystem Using Machine Learning Techniques and Artificial Intelligence Techniques

Coastal and carbon-storing, mangrove ecosystems are under threat by human activities and climate change impacts. This research employs drone-based imagery and ML-AI algorithm-driven approaches to design an ML-AI-based tool for evaluating the ecological state of mangrove environments. Using high-resolution drone imagery of study areas and applying image preprocessing along with KMeans clustering and Random Forest classification the study identifies healthy and degraded mangrove regions. The performance here proves that Random Forest outperforms the other classifiers when it comes to ecosystem classification, especially in identifying the health of the mangroves. The methodology created represents a cheap and efficient means of monitoring the environment which must be useful for conservation purposes. Thus, the results emphasize the prospect of the synergy between drone imagery and ML/AI for ecosystem surveillance and management.

Mangrove ecosystems, drone imagery, machine learning, artificial intelligence, KMeans clustering, Random Forest, environmental monitoring, conservation, image classification, ecosystem assessment.

1. X. Liu et al. (2024). Extraction of 10 m Resolution Global Mangrove in 2022. Remote Sensing, 16(15), 2723. [Google Scholar] [Crossref]

2. P. Y. Dhirendra et al. (2024). Advancing Hyperspectral Image Analysis with CTNet: An Approach with the Fusion of Spatial and Spectral Features. Sensors, 24(6), 2016. [Google Scholar] [Crossref]

3. Álvaro Agustín Chávez-Durán et al. (2024). Forest Canopy Fuel Loads Mapping Using Unmanned Aerial Vehicle High-Resolution Red, Green, Blue and Multispectral Imagery. Forests, 15(2), 225. [Google Scholar] [Crossref]

4. M. Kobe et al. (2024). Automated Workflow for High-Resolution 4D Vegetation Monitoring Using Stereo Vision. Remote Sensing, 16(3), 541. [Google Scholar] [Crossref]

5. K. Chan-Bagot et al. (2024). Integrating SAR, Optical, and Machine Learning for Enhanced Coastal Mangrove Monitoring in Guyana. Remote Sensing, 16(3), 542. [Google Scholar] [Crossref]

6. S. M. Win, S. Tsuyuki, & Z. Guo. (2024). Improving Land Use and Land Cover Information of Wunbaik Mangrove Area in Myanmar Using U-Net Model with Multisource Remote Sensing Datasets. Remote Sensing, 16(1), 76. [Google Scholar] [Crossref]

7. Y. Wang et al. (2023). Evaluation of Mangrove Restoration Effectiveness Using Remote Sensing Indices: A Case Study in Guangxi Shankou Mangrove National Natural Reserve, China. Frontiers in Marine Science. [Google Scholar] [Crossref]

8. P. Lemenkova, & O. Debeir. (2023). Time Series Analysis of Landsat Images for Monitoring Flooded Areas in the Inner Niger Delta, Mali. Artificial Satellites, 58(4), 278–313. [Google Scholar] [Crossref]

9. Y. Xu et al. (2023). Incorporation of Fused Remote Sensing Imagery to Enhance Soil Organic Carbon Spatial Prediction in an Agricultural Area in Yellow River Basin, China. Remote Sensing, 15(8), 2017. [Google Scholar] [Crossref]

10. Z. Zhang et al. (2023). Monitoring of 35-Year Mangrove Wetland Change Dynamics and Agents in the Sundarbans Using Temporal Consistency Checking. Remote Sensing, 15(3), 625. [Google Scholar] [Crossref]

11. D. P. Anang et al. (2023). Decision Tree and Random Forest Classification Algorithms for Mangrove Forest Mapping in Sembilang National Park, Indonesia. Remote Sensing, 15(1), 16. [Google Scholar] [Crossref]

12. M. H. Pham et al. (2022). Mangrove Health Assessment Using Spatial Metrics and Multi-Temporal Remote Sensing Data. PLoS One, 17(12). [Google Scholar] [Crossref]

13. Anonymous. (2021). A Neural Network Method for Classification of Sunlit and Shaded Components of Wheat Canopies in the Field Using High-Resolution Hyperspectral Imagery. Remote Sensing, 13(5), 898. [Google Scholar] [Crossref]

14. Anonymous. (2021). Recent Advancement in Mangrove Forests Mapping and Monitoring of the World Using Earth Observation Satellite Data. Remote Sensing, 13(4), 563. [Google Scholar] [Crossref]

• A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya
• AI-Powered Facial Recognition Attendance System Using Deep Learning and Computer Vision
• A Comprehensive Review on Brain Tumour Segmentation Using Deep Learning Approach
• A Scalable Retrieval-Augmented Generation Pipeline for Domain-Specific Knowledge Applications
• Predictive Maintenance in Semiconductor Manufacturing Using Machine Learning on Imbalanced Dataset