KEYWORDS: Image classification, Sand, Data modeling, Water, Random forests, Ocean optics, Global Positioning System, Education and training, Ecosystems, Animal model studies
The marine habitats of the Philippines are diverse and ecologically important and while they support a wide range of species and provide important ecosystem services, they remain inadequately mapped on a nationwide scale. This study maps sand, corals, and seagrass in Boracay Island (Malay, Province of Aklan) and Sta. Cruz Islands (Zamboanga City) using deglinted and land-masked Sentinel-2 imagery and Random Forest classification in Google Earth Engine. Ground truth data for Boracay Island were gathered using geotagged validation points, while for Sta. Cruz Islands, a continuous video from a towed camera and GPS tracks were collected and subsequent geotagged images were produced. These data were used for training and testing the benthic classification model. Results indicate high coral coverage in both locations, with more than 90% overall accuracy. This methodology demonstrates an automated benthic habitat classification framework that can be adapted to the entirety of the Philippines.
Due to limited ground instruments and lack of direct satellite measurements, local studies related to PM (particulate matter) estimation are often limited only to the Metro Manila area in the Philippines. This study explores the use of satellite data to produce PM models for the country using Artificial Neural Network (ANN). Monthly concentrations of NO2, SO2, CO, O3, HCHO, and H2O for a period of five years (2019 to 2023) were acquired from Sentinel-5P’s Tropospheric Monitoring Instrument while in-situ PM data were from the Air Quality Monitoring Stations of the Department of Environment and Natural Resources. Results showed that integrating SO2, CO, O3, and H2O as inputs produced the best-performing PM2.5 model with an R of 0.281 and RMSE of 6.64 while incorporating HCHO and H2O yielded the best-performing PM10 model with an R of 0.307 and RMSE of 21.1. Low correlations indicate that these inputs capture only a portion of the variability in PM, suggesting a complex relationship between gases and PM that may not be fully captured by the models. Using these models, sample PM maps for the whole Philippines were generated.
Palawan is considered "the last frontier" of the Philippines; in light of this, the province receives special attention from the national and international community. Despite this, there are still numerous issues that need to be addressed, including illegal burning activities. Based on reports and satellite image analyses, slash-and-burn (kaingin) farming is pervasive in Palawan. Burned areas are easily detected from optical satellite images using the Normalized Burn Ratio (NBR) or similar indices. However, the usefulness of optical imagery is severely limited by persistent cloud cover, especially in upland areas where kaingin is commonly practiced. This study focuses on the utilization of Sentinel-1 SAR data in monitoring the burned areas due to its ability to penetrate clouds, smoke, and haze. Radar burn and vegetation indices such as Radar Burn Difference (RBD), Radar Burn Ratio (RBR), Radar Vegetation Index (RVI), and Radar Forest Degradation Index (RFDI) were used to detect the burned areas. These were then cross-validated with the NBR layer. RBD index yielded better results compared to other radar burn and vegetation indices in mapping the burned areas. Additionally, the RBD using the VH polarization band provided detailed delineation of burned areas than that using the VV polarization band. In the operational monitoring of burned areas, the synergistic use of burned indices from optical and SAR images is recommended.
Slash-and-burn agriculture or kaingin is a method of clearing and burning of forest for the planting of agricultural and agro-forestry crops. Observed effects of kaingin are destruction of forests, grassland fires due to uncontrolled or accidental fires, degraded soil, cultivation leaching, massive erosion and landslide. This study utilizes Fire Information for Resource Management System (FIRMS), Moderate Resolution Imaging Spectroradiometer (MODIS) Active Fire and Thermal Anomalies, Fire CCI (European Space Agency Fire Climate Change Initiative), and MODIS Burned Area for a study period of 2015 to 2022. Results show that both fire and burn products capture the burning season in Palawan, occurring in April and March with high fire pixel counts, concurrent to its climate’s dry season. La Niña affected the trend across datasets wherein declines in fire pixel count during the years 2021 and 2022 were observed. The use of fire and burnt product depicted fire schemes across vegetation types. Clusters are assessed per vegetation type revealing fire incidents occurred predominately over shrublands with low intensity and temperature fire, and long duration of burns; and open forests with intense and high temperature fires with varying duration of burning. Moreover, density of fire occurrences are highest in the municipalities of Sofronio Espanola, Bataraza, Rizal, Quezon, Culion, Roxas, Aborlan, Taytay and Narra. Synergestic use of fire and burned area products is instrumental in understanding the quality and characteristics of fire; fire descriptors and schemes are crucial for fire management strategies.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.