Skip to main content

Advertisement

SpringerLink
Log in

Spatial analysis and predictive modeling of energy poverty: insights for policy implementation

  • Published:
Environment, Development and Sustainability Aims and scope Submit manuscript

Abstract

Understanding and alleviating energy poverty is critical for sustainable development. This study harnesses a suite of Machine Learning (ML) algorithms to predict Multidimensional Energy Poverty Index (MEPI) and to highlight the spatial distribution of energy poverty. We assess the predictive accuracy of Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), Multiple Linear Regression (MLR), and XGBoost models. The RF model outperforms others, achieving an R2 value of 0.92 and a Pearson Correlation Coefficient (PCC) of 0.97 on the testing dataset, indicative of a highly accurate prediction capability. XGBoost also demonstrates strong predictive power with corresponding values of 0.88 and 0.94, respectively. Our spatial analysis, revealing significant clustering of energy poverty with a Global Moran’s I value of 150.39, indicates that energy poverty is not only geographically concentrated but also intricately linked to socio-economic factors such as income levels, access to education, and nutritional status. These insights underscore the necessity of region-specific and socio-economically informed policy interventions. The results inform targeted interventions, particularly highlighting the critical roles of education and nutrition in mitigating energy poverty. The RF model’s accuracy rate of 92% on the testing set suggests that improvements in these sectors could significantly influence MEPI scores. The integration of ML and spatial analysis offers a nuanced and actionable understanding of energy poverty, paving the way for targeted, evidence-based policy formulation aimed at achieving SDG7: ensuring access to affordable, reliable, sustainable, and modern energy for all.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

(Source: Author)

Fig. 3

(Source: Author)

Fig. 4
Fig. 5

(Source: Author)

Fig. 6

(Source: Author)

Fig. 7
Fig. 8

(Source: Author)

Fig. 9

(Source: Author)

Fig. 10

(Source: Author)

Fig. 11

(Source: Author)

Fig. 12

(Source: Author)

Fig. 13

(Source: Author)

Fig. 14

(Source: Author)

Fig. 15

(Source: Author)

Fig. 16

(Source: Author)

Fig. 17

(Source: Author)

Fig. 18

(Source: Author)

Similar content being viewed by others

Data availability

The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.

Abbreviations

ANN:

Artificial Neural Network

CO2 :

Carbon dioxide

CRS:

Coordinate Reference System

DDS:

Household Dietary Diversity Score

DOE:

Department of Energy

FCS:

Food Consumption Score

GHS:

Ghana Cedis

GIS:

Geographic Information Systems

GSS:

Ghana Statistical Service

HFIA:

Household Fuel Insecurity Access

IEA:

International Energy Agency

IREA:

International Renewable Energy Agency

LEAD:

Low-Income Energy Affordability

MAE:

Mean Average Error

MAPE:

Mean Absolute Percentage Error

MEP:

Multidimensional energy poor

MEPI:

Multidimensional Energy Poverty Index

ML:

Machine learning

MLP:

Multilayer Perceptron

MSE:

Mean Squared Error

NSE:

Nash–Sutcliffe Coefficient

PCA:

Principal Component Analysis

PCC:

Pearson Correlation Coefficient

RMSE:

Root Mean Squared Error

ROC:

Receiver Operating Characteristic Curve

SDGs:

Sustainable Development Goals

UN:

United Nations

WHO:

The World Health Organization

WI:

Willmott’s Index

WMA:

Wa Municipal Assembly

References

Download references

Funding

The authors have no relevant financial or non-financial interests to disclose.

Author information

Authors and Affiliations

  1. Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, 21211, USA

    Sidique Gawusu

  2. School of Economics and Management, Nanjing University of Science and Technology, Nanjing, China

    Seidu Abdulai Jamatutu

  3. School of Energy and Power and Engineering, Nanjing University of Science and Technology, Nanjing, China

    Xiaobing Zhang

  4. Global Development Institute, School of Environment, Education and Development, University of Manchester, Manchester, UK

    Solahudeen Tando Moomin

  5. Department of Urban Design and Infrastructure Studies, Faculty of Planning and Land Management, SD Dombo University of Business and Integrated Development Studies, Bamahu-Wa, Ghana

    Abubakari Ahmed

  6. Structural and Fire Engineering Division, Department of Civil, Environmental and Natural Resources Engineering, Luleå University of Technology, 97187, Luleå, Sweden

    Rhoda Afriyie Mensah & Oisik Das

  7. Department of Economics, School of Liberal Arts and Social Science, Ghana Institute of Management and Public Administration, Accra, Ghana

    Ishmael Ackah

Authors
  1. Sidique Gawusu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seidu Abdulai Jamatutu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaobing Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Solahudeen Tando Moomin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Abubakari Ahmed
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Rhoda Afriyie Mensah
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Oisik Das
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Ishmael Ackah
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Sidique Gawusu: Conceptualization, writing—original draft, software, methodology, visualization, data curation, investigation, project administration. Seidu Abdulai Jamatutu: Writing—review and editing, and investigation. Xiaobing Zhang: Writing—review and editing. Solahudeen Tando Moomin: Writing—review and editing. Abubakari Ahmed: Writing—review and editing, and investigation. Rhoda Afriyie Mensah: Writing—review and editing. Oisik Das: Writing—review and editing. Ishmael Ackah: Writing—review and editing.

Corresponding authors

Correspondence to Sidique Gawusu or Abubakari Ahmed.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix: Zones and energy poverty

Appendix: Zones and energy poverty

The analysis of energy poverty across the different zones revealed distinct patterns in the distribution of households classified as “Energy Poor” and “Not Energy Poor” (see Fig. 20). Within the core zone, out of a total of 286 households, 172 were categorized as experiencing energy poverty, while 114 were classified as not experiencing energy poverty. This suggests a concentration of energy poverty within the core zone, highlighting a higher prevalence compared to non-energy poverty (Table 

Table 5 Exploratory data analysis of selected variables
Full size table

5).

On the other hand, the fringe zone, consisting of 489 households, showed a higher incidence of energy poverty, with 263 households identified as “Energy Poor” and 226 as “Not Energy Poor”. These findings emphasize the spatial disparities in energy poverty within the municipality, with both the core and fringe zones exhibiting significant energy poverty rates (Figs.

Fig. 19
figure 19

(Source: Author)

Distribution of MEPI according to the different Zones

Full size image

19,

Fig. 20
figure 20

(Source: Author)

Classification of MEPI according to the different Zones

Full size image

20,

Fig. 21
figure 21

(Source: Author)

Classification of zones

Full size image

21,

Fig. 22
figure 22

(Source: Author)

Sensitivity analysis of selected parameters

Full size image

22,

Fig. 23
figure 23

(Source: Author)

Residuals versus predicted MEPI values

Full size image

23,

Fig. 24
figure 24

(Source: Author)

Histogram of residuals versus predicted MEPI values

Full size image

24,

Fig. 25
figure 25

(Source: Author)

Q–Q plot of predicted MEPI values

Full size image

25,

Fig. 26
figure 26

(Source: Author)

Visual representation of MEPI data across the geographic area

Full size image

26). Addressing the specific challenges faced in these zones through targeted interventions could play a crucial role in mitigating energy poverty and fostering sustainable development.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gawusu, S., Jamatutu, S.A., Zhang, X. et al. Spatial analysis and predictive modeling of energy poverty: insights for policy implementation. Environ Dev Sustain (2024). https://doi.org/10.1007/s10668-024-05015-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10668-024-05015-4

Keywords

Search

Navigation