Publication: Terraturtle:
No Thumbnail Available
Date
2024-12
Journal Title
Journal ISSN
Volume Title
Publisher
Don Mariano Marcos Memorial State University – Mid La Union Campus
Abstract
Efforts to protect sea turtles are challenged by the uncertainty of nesting timing and location. This study leverages machine learning to predict the nesting behaviors of Pawikan (sea turtles), improving conservation strategies. Using the Prophet time series forecasting algorithm and historical data, the system estimates nesting periods, egg counts, and locations. Key predictors, including seasonal patterns, lag variables, and moving averages, enhance model accuracy. A user-friendly web platform displays predictions via interactive maps, tables, and graphs. The model achieved high performance, with a Mean Absolute Error(MAE) of 0.0005569 and Root Mean Square Error(RMSE) of 0.000634 for egg count predictions, and an MAE of 0.59 and RMSE of 0.75 for location forecasts. TerraTurtle optimizes resources and strengthens sea turtle protection during critical nesting periods, showcasing the potential of machine learning in conservation
management.
Description
Keywords
Citation
Añonuevo, D. A., Almodovar, K. V., Umbay, D. B., & Yaranon, J. A. C. (2024). Terraturtle: Forecasting pawikan nesting patterns with machine learning algorithm [Unpublished undergraduate feasibility study]. Don Mariano Marcos Memorial State University – Mid La Union Campus.. Lakasa ti Sirib, DMMMMSU Institutional Repository.