Saved in:
Bibliographic Details
Main Author: Arazzak, Ridho
Format: Recurso digital
Language:
Published: Zenodo 2026
Online Access:https://doi.org/10.5281/zenodo.18511082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901550247444480
author Arazzak, Ridho
author_facet Arazzak, Ridho
contents <p> </p> <p dir="ltr">Abstract</p> <p> </p> <p dir="ltr">The availability of accurate and granular poverty data down to the sub-district level is often a challenge in regional development planning. Conventional data collection methods tend to be slow, high-cost, and carry the risk of subjectivity. This research introduces a prototype of a poverty monitoring and prediction system in South Solok Regency for the 2020-2023 period using the Google Earth Engine (GEE) platform. By applying the Ordinary Least Squares (OLS) Regression method to the synthesis of disaggregated secondary data, the model successfully achieved an accuracy level (R²) of 0.984. The results of this research not only provide a spatial visualization of poverty trends but also give a projection of the 2024 poverty figures as a basis for evidence-based policy and mitigation of pressure on protected forest areas.</p> <p> </p> <p dir="ltr">Keywords: Google Earth Engine, Poverty, South Solok, OLS Linear Regression, Spatial Intelligence.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18511082
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Democratization of Data: Spatial-Based Poverty Predictive Modeling in South Solok Regency Using Google Earth Engine
Arazzak, Ridho
<p> </p> <p dir="ltr">Abstract</p> <p> </p> <p dir="ltr">The availability of accurate and granular poverty data down to the sub-district level is often a challenge in regional development planning. Conventional data collection methods tend to be slow, high-cost, and carry the risk of subjectivity. This research introduces a prototype of a poverty monitoring and prediction system in South Solok Regency for the 2020-2023 period using the Google Earth Engine (GEE) platform. By applying the Ordinary Least Squares (OLS) Regression method to the synthesis of disaggregated secondary data, the model successfully achieved an accuracy level (R²) of 0.984. The results of this research not only provide a spatial visualization of poverty trends but also give a projection of the 2024 poverty figures as a basis for evidence-based policy and mitigation of pressure on protected forest areas.</p> <p> </p> <p dir="ltr">Keywords: Google Earth Engine, Poverty, South Solok, OLS Linear Regression, Spatial Intelligence.</p>
title Democratization of Data: Spatial-Based Poverty Predictive Modeling in South Solok Regency Using Google Earth Engine
url https://doi.org/10.5281/zenodo.18511082