ABSTRACT:Mangrove forest ecosystems fulfil a number of important functions like supporting the conservation of biological diversity by providing habitats, nurseries, and nutrients for animal species. In the Philippines, mangrove forests are declining due to the growth of aquaculture production. Mangrove forests are slowly being replaced by fishponds. An accurate inventory of what are left of these natural resources is important to know how we can conserve and manage them. This study aims to compare the performance of support vector machines (SVM) with random forest (RF) algorithm in automatically classifying mangrove forests using LiDAR data and orthophotographs in an object based approach. The site is a 36 sq. km. coastal area in Manapla, Negros Occidental, Philippines. Various derivatives were created from the LiDAR data like the pit-free canopy height model (CHM) and intensity. The CHM was used in contrast split segmentation to distinguish between ground and non-ground objects. Only the non-ground objects were segmented further knowing that majority of mangroves are tall. Inventory of short mangroves is not yet included in this study. The non-ground objects were further segmented using multiresolution segmentation with the CHM and RGB bands of the orthophoto using a scale of 15. The non-ground class was further separated into four classes namely: mangrove, built-up, other trees, and sugarcane. 120 training points and 30 validation points per class were collected by visual inspection using the orthophoto as reference. Several features of the training objects were computed from both the LiDAR and orthophoto derivatives and used for classification. SVM with radial basis function was used to classify the rest of the image and resulted in an overall accuracy of 95.83%. For mangroves, its precision and recall reached 83.33% and 100%, respectively. In the SVM classification, mangroves were confused with other trees and sugarcane. Another machine learning algorithm, random forest (RF) was used to classify the same area to compare their performance and accuracy. Using the same features, the RF classification achieved an overall accuracy of 99.1667%. For mangroves, the RF classification obtained 100% and 96.70% for its precision and recall, respectively. The RF classifier confused other trees with mangroves which caused the error. The accuracies from both machine learning algorithms show that the RF classifier performed better than the SVM classifier and further implies the potential of using RF in classifying mangroves in other areas.

ABSTRACT:The threat of the ailments related to urbanization like heat stress is very prevalent. There are a lot of things that can be done to lessen the effect of urbanization to the surface temperature of the area like using green roofs or planting trees in the area. So land use really matters in both increasing and decreasing surface temperature. It is known that there is a relationship between land use land cover (LULC) and land surface temperature (LST). Quantifying this relationship in terms of a mathematical model is very important so as to provide a way to predict LST based on the LULC alone. This study aims to examine the relationship between LST and LULC as well as to create a model that can predict LST using class-level spatial metrics from LULC. LST was derived from a Landsat 8 image and LULC classification was derived from LiDAR and Orthophoto datasets. Class-level spatial metrics were created in FRAGSTATS with the LULC and LST as inputs and these metrics were analysed using a statistical framework. Multi linear regression was done to create models that would predict LST for each class and it was found that the spatial metric "Effective mesh size" was a top predictor for LST in 6 out of 7 classes. The model created can still be refined by adding a temporal aspect by analysing the LST of another farming period (for rural areas) and looking for common predictors between LSTs of these two different farming periods.

Abstract. Tangbo River is an important resource in Cebu’s southern town of Samboan for being the site of Aguinid Falls, a known tourist destination. Monitoring the changes in the river’s riparian vegetation is important since it has impacts on its ecological role of helping maintain biodiversity and river water quality. This study aims to detect vegetation index changes along the Tangbo River corridor using three vegetation indices: NDVI, EVI, NDMI, and Tasseled Cap indices, specifically for the years 1998, 2004, 2009, 2016, and 2019. It also aims to monitor the changes in NDVI and EVI values alongside tourism arrivals in Aguinid in 2018.Cloudless Landsat 5 (1998, 2004, 2009, and 2016) and Landsat 8 (2019) imagery were selected. Thirty reference points were plotted along the river with a 30-m distance between each point. Vegetation Indices (VI) and Tasseled Cap values were generated using data from these points and were compared for each selected year. NDVI and EVI values from the same reference points used in Landsat were generated from selected cloudless months of 2018 Planetscope imagery. Inbound tourist records were acquired from the tourism office of Samboan and the tourism arrivals for the year 2018 was then graphed with the Planetscope VI values for better visualization.Landsat imagery showed that there was a general upward trend in the vegetation indices from 1998 to 2019. Tasseled Cap Greenness and Wetness showed an increase in values from 1998–2019 while Tasseled Cap Brightness showed the opposite. Results from Planetscope data for the year 2018 showed that there was an inverse pattern between NDVI and tourism arrivals. Tourism arrivals peaked during the months of April and May based on annual records, while VI values dropped. On the other hand, both VI values peaked towards the last quarter of the year while tourist numbers dropped. This suggests that the pattern of VI values and tourism arrivals seemed to be influenced by seasonal changes rather than with each other. Findings from the study shows that further data collection is required to be able to establish a relationship between tourism and vegetation index values.

ABSTRACT:Mangroves have a lot of economic and ecological advantages which include coastal protection, habitat for wildlife, fisheries and forestry products. Determination of the extent of mangrove patches in the coastal areas of the Philippines is therefore important especially in resource conservation, protection and management. This starts with a well-defined and accurate map. LiDARwas used in the mangrove extraction in the different coastal areas of Negros Occidental in Western Visayas, Philippines. Total coastal study area is 1,082.55 km² for the 14 municipalities/ cities processed. Derivatives that were used in the extraction include, DSM, DTM, Hillshade, Intensity, Number of Returns and PCA. The RGB bands of the Orthographic photographs taken at the same time with the LiDAR data were also used as one of the layers during the processing. NDVI, GRVI and Hillshade using Canny Edge Layer were derived as well to produce an enhanced segmentation. Training and Validation points were collected through field validation and visual inspection using Stratified Random Sampling. The points were then used to feed the Support Vector Machine (SVM) based on tall structures. Only four classes were used, namely, Built-up, Mangroves, Other Trees and Sugarcane. Buffering and contextual editing were incorporated to reclassify the extracted mangroves. Overall accuracy assessment is at 98.73% (KIA of 98.24%) while overall accuracy assessment for Mangroves only is at 98.00%. Using this workflow, mangroves can already be extracted in a largescale level with acceptable overall accuracy assessments.

Abstract. The Department of Agriculture – Region VII reports that many mango orchards in Cebu province are dying because of the absence of required post-harvest attention. Lacklustre yields and erratic pest infestations have driven some farmers and growers to abandon mango orchards. To help revive low-yielding mango orchards, there is a need to distinguish actively bearing mango trees from those that remain dormant throughout the year. Using remote sensing techniques, mango trees from separate orchards in Brgy. Cantipay, Carmen, Cebu were mapped and studied using multi-temporal Sentinel-2 data (from January 2018 through May 2019). Prior to that, a field visit was conducted to survey the area using UAVs and field observation, and in the process, was able to identify an abandoned mango orchard. Pixel-based Normal Difference Vegetation Index (NDVI) values were extracted from each of the 822 geotagged mango trees with an average of 16 trees among 53 divisions. Time series were derived from the average of the NDVI values from each division and plotted per month of extraction from oldest to latest. Clustering was applied to the time series data using Hierarchical Clustering with Ward’s Minimum Variance as an algorithm to determine the divisions with the closest time series. Using the resulting dendrogram as basis, two major clusters were selected based on the value of their distances with each other: Cluster 1 containing 29 Divisions, and Cluster 2 containing 24 Divisions. Cluster 1 contains most of the Divisions in and around the biggest active mango orchard. In contrast, Cluster 2 contains most of the Divisions that are in and around the previously identified abandoned mango orchard. An alternative dendrogram was also created by using Complete Linkage algorithm in Hierarchical Clustering, after which 3 relevant clusters were selected. The second dendrogram highlights the stark difference between Division 1, contained in Cluster 3, from the rest of the other clustered divisions at 2.17 units from the next closest one. Notably, Division 1 is located smack in the middle of the abandoned orchard The remaining clusters, Cluster 2 with 21 divisions containing most of the divisions in the abandoned orchard, is 2.46 distance units away from Cluster 1, which has 31 and hosting most of the divisions in the active mango orchards. Two major clusters emerged from using the two algorithms. Divisions with higher and more variant NDVI values seemed to come from the mango trees which were more active during the fruiting cycle. Divisions from the abandoned mango orchards were observed to have lower and less varied NDVI values because of minimal activity in the trees. Other Divisions clustered under the abandoned orchard could have been juveniles based on their size.