Remote sensing and machine learning algorithms in geospatial mapping and temporal forecasting of mangrove density distribution

Simple item page
dc.contributor.authorMalaya, Ara Rivina N.
dc.date.accessioned2026-09-18T02:48:24Z
dc.date.available2026-09-18T02:48:24Z
dc.date.issued2023-12
dc.descriptionAbstract Only
dc.description.abstractThis study aimed to develop models for forecasting vegetation indices of the selected mangrove sites in Region 1. The researcher identified the data that can be used for visualization, prediction, and analysis; applied the preprocessing techniques in the dataset; and evaluated the best-performing machine learning algorithms in forecasting mangrove density distribution. Descriptive and applied research designs were employed in the study. Field and satellite data acquired were utilized in forecasting vegetation indices. Application software including Google Earth Pro and Google Earth Engine were utilized in mapping and determining the exact location of the target sites. Programming was also done in Google Earth Engine to extract the satellite data for forecasting and WEKA was used to generate time series analysis for forecasting of vegetation indices. The salient findings of the study are as follows: (1) the mean average of Pangasinan, La Union, Ilocos Sur, and Ilocos Norte are 0.866, 0.592, 0.543, and 0.974, respectively; (2) data cleaning and data transformation were performed to organize the data; and (3) two performance evaluation metrics were applied to identify the best-performing base learner in forecasting vegetation indices. SMOReg had an accuracy of 99.53 and a MAPE score of 2.56, outperforming Linear Regression, Gaussian Processes, and Multilayer Perceptron.
dc.identifier.citationMalaya, A.R.N. (2023). Remote sensing and machine learning algorithms in geospatial mapping and temporal forecasting of mangrove density distribution. [Unpublished Master's Thesis]. Don Mariano Marcos Memorial State University – South La Union Campus, Agoo, La Union. Lakasa ti Sirib, DMMMSU Institutional Repository.
dc.identifier.urihttps://lakasa.dmmmsu.edu.ph/handle/123456789/2617
dc.language.isoen
dc.publisherDon Mariano Marcos Memorial State University - South La Union Campus
dc.sdgSDG 13
dc.titleRemote sensing and machine learning algorithms in geospatial mapping and temporal forecasting of mangrove density distribution
dc.typeThesis
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
MT-SLUC-2023-CGS-MSCS-MalayaARN-ABS.pdf
Size:
1.1 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Master's Theses