DETECTION AND SPATIAL ANALYSIS OF LAND-USE: A CASE OF BUTUAN CITY WITH HISTORY OF MAJOR INFORMAL SETTLEMENTS

This study detects the significant informal settlements in Butuan City proper. It determines the growth rate in 15 years with the given five-year interval. Machine learning algorithms and spatial analysis were applied to obtain the possible locations of informal settlement buildings. The projected locations of informal settlement buildings were validated thru aerial image validation using Remote Sensing and GIS-based techniques in ArcGIS software. Eight (8) barangays satisfy all the informal settlement building characteristics during the aerial validation process and ground-truthing, namely, Golden Ribbon, Holy Redeemer, Limaha, New Society, Ong Yiu, Port Puyohon, San Ignacio, and Tandang Sora. The eight (8) barangays were manually digitized from the given 5-years interval from 2005, 2010, 2015, and 2010. The value of the major informal settlement buildings area was computed to excel. The area growth rate was calculated using the growth rate formula. This study showed that the significant informal settlement in the study area increased. Among the eight (8) focused barangays, Tandang Sora ranked the highest informal settlements growth from 2005 to 2020. Its area increases up to 178.52%, a total of 24,608.43 square meters. Finally, the results revealed that the area of informal settlement buildings in Butuan City from 2005-2020, in 15-years, its value increases up to 9.74%, a total of 19,172.88 square meters.


INTRODUCTION
In most developing countries, informal settlements are such a great feature in towns and cities. The most common ones are slums and squatters. The land is scarce, and urban land becomes even more. Squatting and lack of access to land is one of the most challenging factors for the urban poor. Many people in developing countries must find shelter in the market. The public sector cannot offer affordable land or housing. With this, policies are there to reduce the informal settlements, but still a failure. The trend is rising. Now, over-urbanization has become a big problem (Huerta, 2019).
In the Philippines, urbanization is rising, and one of the prominent aspects of this is informal settlements. They have become a national problem because it is expanding. The vacant lands owned by the government along coasts, riverbanks, creeks illegally claim both publicly and privately owned property (Asm Amanullah, 2011). These people claiming these properties are informal settlers because they live in lands without the consent of the property owners or the government. They lived in dangerous areas such as railways or even under bridges. Some of them lived in government infrastructure projects; protected/forest areas (except for indigenous peoples), lands for Priority Development (APDs), other government/public lands, or facilitation households with the status rent-free without permission from owners. In the province of Agusan del Norte, informal settlers account for 58 percent and 85 percent of Butuan City households (Navarro et al., 2014) The objective of this study is to detect the land use with prominent informal settlers in Butuan City. It also aims to utilize a machine-learning algorithm to detect informal settlement areas in Butuan City and produce maps of central informal settlement area locations.
This study is beneficial to the government of Butuan City in assessing the situations of the informal settlers who frequently live in dangerous locations in the most environmentally and geographically hazardous areas. Thus, the study played an essential role in the development planning in the city to detect and map the informal settlers.

Data Acquisition
Data acquisition involves gathering information on the informal settlers, including readily available datasets from appropriate offices, internet downloadable data, and other reliable sources.

nDSM Generation
Digital Terrain Model (DTM) (Baghdadi, Zribi, 2017) and Digital Surface Model (DSM) were requested to the Caraga Center for Geo-informatics (CCGeo). These data were used to generate nDSM or Normalized Digital Surface Model for getting the elevation of features within the study area using ArcGis software.

Segmentation
Segmentation is commonly used to separate more important things, such as objects, into smaller segments. In eCognition Developer, segmentation is any process that produces new picture objects or changes the morphology of existing image objects based on specific criteria. It means that segmentation can be subdividing, merging, or reshaping (Baatz et al., 2001).

Classification
The Classification algorithm uses class descriptions to categorize picture objects. It examines the class description to see if an image object may be a member of a class. Without a class description, classes are considered to have a membership value of one (Baatz et al., 2001).

Downloading Satellite Data
Google Earth satellite imagery was downloaded for the study area. Four (4) different year images with five-year intervals were downloaded in 2005, 2010, 2015, and 2020.

Image Rectification
Using ArcMap 10.8 software, the correct coordinates of downloaded satellite imagery have been set using the georeferencing tool.

Spatial Analysis
The spatial analysis process was used to validate the focused area using satellite imagery from 2020 google earth imagery. It was composed of aerial image validation and ground-truthing. Thru this process, the researcher can quickly identify whether the projected areas were building or vegetation. Furthermore, additional parameters are being applied by manual aerial image validation. The physical characteristics of the informal settlement are derived through visual interpretation, integrated, and combined with GIS analysis of the provided dataset. In determining the necessary information to describe informal settlement, visual interpretation of the image and review of various literature was made to develop indicators specific to local conditions.

Image Digitation in ArcGis
Digitizing in GIS is converting geographic data either from a hardcopy or a scanned image into vector data by tracing the features. During the digitizing process, features from the traced map or image are captured as coordinates in either point, line, or polygon format. Manual digitizing was performed on the projected prominent informal settler to calculate the area's growth using four different images from Google Earth 2005, 2010, 2015, and 2020. The digitized area calculation was performed in excel, and the growth rate percentage was calculated using Equation 1 (Patrick Campbell, 2020).

Infrastructure Growth Rate (IGR) Statistical Method
The digitized area calculation was performed in excel, and the growth rate percentage was calculated using Equation 1 Growth Rate = (Vpresent-Vpast))/Vpast x 100 where: Vpresent = present value Vpast = past value

Aerial Image Validation
Aerial image validations were used to validate the support vector machine algorithm projected informal settlements results in Ecognition developer. In visually identifying the non-building and building, other informal settlement characteristics (Table 1) were considered during the process. The results of the Support Vector Machine (SVM) algorithm in identifying the informal settlements are mainly projected in this area. The areas were validated through aerial image validation in visual interpretation of the image and review of various literature to identify the other aspect qualified as informal settlements. The visual interpretation of aerial images is not automated. However, it requires expert knowledge, systematic search, and additional data to ensure adequate identification of the target features.
Typically, the informal settlements in Butuan are characterized by the following properties (through visual interpretation):

Ground Truthing
Location of the informal settlement in eight (8) barangays namely; Golden Ribbon, Holy Redeemer, Limaha, New Society, Ong Yiu, Port Puyohon, San Ignacio, and Tandang Sora. They were identified based on the SVM algorithm. The following informal settlements areas were digitized manually and were first validated using aerial image validation. The extent of the settlement was used as a reference in ground truth data collection.  Figure 1 shows the map of the area using the Support Vector Machine (SVM) classification algorithm in E-cognition developers. Projection of the informal settlement buildings through the algorithm condition that the Formal Housing Concepts site all buildings for informal settlements study. It has 2.75 m in height from the ground, which is one of the characteristics of informal settlement buildings. From the classification result, only eight (8) barangays in Butuan City proper projected a major informal settlement, namely, Golden Ribbon, Holy Redeemer, Limaha, New Society, Ong Yiu, and Port Puyohon, San Ignacio, and Tandang Sora. The said barangays were subjected to aerial object-oriented image analysis and ground-truthing.

Classified Area as Informal Settlements
The informal settlement location was identified using a support vector machine algorithm and spatial analysis. Figure 2 to Figure  9 shows the digitized location of informal settlements of eight barangays. These locations were validated through groundtruthing and random interviews with the residents. Field validation and interviews reveal that private individuals claimed most of the detected informal settlements area.     Figure 11 shows the thematic map area from 2005-2020, and Table 3 shows the informal settlement growth in percentage in Limaha. From 2005 up to the year 2010, the informal settlement descended to 38.00%. There was an increase of 10.00% from the year 2010-2015.
In the year 2015-2020, the growth had declined to 11.87%. Lastly, from 2005 to 2020, there was a drastic downfall of informal settlements to 40.00%. Figure 12 shows the thematic map area from 2005-2020 in the Brgy. New Society Village. Port Poyohon thematic area map in the year 2005-2020 is shown in Figure 14. The growth rate of the informal settlement of people from the year 2005 -2020 (Table 6)    From the year 2015 to 2020, there was an increase to 39.34%. Lastly, from the year 2005 to 2020, it has an increased to 88.40%.
San Ignacio thematic area map in the year 2005-2020 is shown in Figure 15. There was a 50.23% increase in residence from 2005-2010 (Table 7). From the year 2010 to 2015, there was a decline of 25.22%. Furthermore, from 2015 to 2020, there was a drastic increase of 79.40%. Generally, in the year 2005 to 2020, the informal settlement increased to 101.53%. Figure 16 shows the thematic map area from 2005-2020 in Brgy.
Tandang Sora. Table 8 Figure 18 shows the location of the informal settlements of the eight (8) barangays in Butuan City. Figure 19 reveals the rate of change of the eight (8) barangays) in Butuan City. On the other hand, the most common reason for the informal settlement is that they do not own a piece of land to settle formally.
The summary of the overall growth of areas of central informal settlements locations in Butuan City for each year intervals 2005-2010, 2010-2015, and 2015-2020 (Table 10 and Figure 20). In five-year intervals, there was a change of area occupied by informal settlers, which may be increased or decreased.

CONCLUSION
The machine learning algorithm, precisely the Support Vector Machine (SVM) algorithm in E-cognition developer, helps locate the possible major informal settlement buildings areas. It lessens the time when it comes to manual digitizing. Remote Sensing and GIS-based techniques help in validating the possible informal settlement areas.
The results of the study reveal that the significant informal settlement in the study area increased. Among the eight (8) identified barangays, Tandang Sora ranked as the highest informal settlement's growth from 2005 to 2020. Its area increased up to 178.52%, a total of 24608.43m 2 . The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLVI-4/ W6-2021Philippine Geomatics Symposium 2021, 17-19 November 2021