The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach
Reducing humans' ecological footprint (ECF) is critical for guaranteeing a sustainable future and sustaining the planet's health for future generations. Consequently, sustainability policies and development aim to minimize ECF and guarantee a sustainable future. This study analyzes the eff...
Published in: | DISCOVER SUSTAINABILITY |
---|---|
Main Authors: | , , , , , |
Format: | Article |
Language: | English |
Published: |
SPRINGERNATURE
2024
|
Subjects: | |
Online Access: | https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001345949600003 |
author |
Kumaran Vikniswari Vija; Ridzuan Abdul Rahim; Senadjki Abdelhak; Kanaan Abdulkarim M. Jamal; Esquivias Miguel Angel |
---|---|
spellingShingle |
Kumaran Vikniswari Vija; Ridzuan Abdul Rahim; Senadjki Abdelhak; Kanaan Abdulkarim M. Jamal; Esquivias Miguel Angel The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach Science & Technology - Other Topics; Environmental Sciences & Ecology |
author_facet |
Kumaran Vikniswari Vija; Ridzuan Abdul Rahim; Senadjki Abdelhak; Kanaan Abdulkarim M. Jamal; Esquivias Miguel Angel |
author_sort |
Kumaran |
spelling |
Kumaran, Vikniswari Vija; Ridzuan, Abdul Rahim; Senadjki, Abdelhak; Kanaan, Abdulkarim M. Jamal; Esquivias, Miguel Angel The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach DISCOVER SUSTAINABILITY English Article Reducing humans' ecological footprint (ECF) is critical for guaranteeing a sustainable future and sustaining the planet's health for future generations. Consequently, sustainability policies and development aim to minimize ECF and guarantee a sustainable future. This study analyzes the effects of gross domestic product (GDP), financial development, renewable energy, share of global forest area, and technological innovations on the ECF of the Indonesian economy from 1990 to 2020. The Autoregressive Distributed Lag approach is applied to observe the varying levels of influence across variables. The findings show significant short-term links between GDP, income inequality, technological advancements, and ECF, and statistically significant long-term relationships between GDP, share of forest area, and technological innovation. The machine learning approach uses neural networks and regression as its parametric models to analyze the data for prediction. Both models can predict how the parameters interacted with ECF, with neural networks making more accurate predictions. The study reveals that economic growth intensifies ECF, whereas income equality decreases it. Technological advancements and forest expansion benefit the environment by reducing the footprint. These insights can provide policy recommendations to minimize ECF in Indonesia and strengthen the efforts to achieve a sustainable future. SPRINGERNATURE 2662-9984 2024 5 1 10.1007/s43621-024-00585-9 Science & Technology - Other Topics; Environmental Sciences & Ecology gold WOS:001345949600003 https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001345949600003 |
title |
The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach |
title_short |
The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach |
title_full |
The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach |
title_fullStr |
The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach |
title_full_unstemmed |
The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach |
title_sort |
The impacts of income inequality, forest area, and technology innovations on ecological footprint in Indonesia: ARDL and ML approach |
container_title |
DISCOVER SUSTAINABILITY |
language |
English |
format |
Article |
description |
Reducing humans' ecological footprint (ECF) is critical for guaranteeing a sustainable future and sustaining the planet's health for future generations. Consequently, sustainability policies and development aim to minimize ECF and guarantee a sustainable future. This study analyzes the effects of gross domestic product (GDP), financial development, renewable energy, share of global forest area, and technological innovations on the ECF of the Indonesian economy from 1990 to 2020. The Autoregressive Distributed Lag approach is applied to observe the varying levels of influence across variables. The findings show significant short-term links between GDP, income inequality, technological advancements, and ECF, and statistically significant long-term relationships between GDP, share of forest area, and technological innovation. The machine learning approach uses neural networks and regression as its parametric models to analyze the data for prediction. Both models can predict how the parameters interacted with ECF, with neural networks making more accurate predictions. The study reveals that economic growth intensifies ECF, whereas income equality decreases it. Technological advancements and forest expansion benefit the environment by reducing the footprint. These insights can provide policy recommendations to minimize ECF in Indonesia and strengthen the efforts to achieve a sustainable future. |
publisher |
SPRINGERNATURE |
issn |
2662-9984 |
publishDate |
2024 |
container_volume |
5 |
container_issue |
1 |
doi_str_mv |
10.1007/s43621-024-00585-9 |
topic |
Science & Technology - Other Topics; Environmental Sciences & Ecology |
topic_facet |
Science & Technology - Other Topics; Environmental Sciences & Ecology |
accesstype |
gold |
id |
WOS:001345949600003 |
url |
https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001345949600003 |
record_format |
wos |
collection |
Web of Science (WoS) |
_version_ |
1818940500871217152 |