elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Modelling complex investment decisions in Germany for Renewables with different machine learning algorithms

Frey, Ulrich J. and Klein, Martin and Deissenroth, Marc (2019) Modelling complex investment decisions in Germany for Renewables with different machine learning algorithms. Environmental Modelling & Software. Elsevier. doi: 10.1016/j.envsoft.2019.03.006. ISSN 1364-8152.

Full text not available from this repository.

Abstract

Investment decisions in renewable energies are known to be influenced by many diverse drivers, e.g. social, political, geographic, economic and psychological. Non-comprehensive models are problematic since missed interactions might introduce bias. We implement a robust modelling approach by (1) using a large data set with 1.4 million solar installations and (2) three different machine learning algorithms (deep neural networks, gradient boosting, random forests). Generalized linear models serve as baseline and comparison. A high prediction accuracy can be achieved on the county level with deep neural networks (adjusted R2 = 0.86) and gradient boosting (adjusted R2 = 0.87). The most important drivers are population per county, followed by type of urbanisation and social variables like unemployment, with varying degree of importance for the different machine-learning algorithms. Our approach points out both differences and agreements across methods and therefore a higher confidence in their interpretation

Item URL in elib:https://elib.dlr.de/127150/
Document Type:Article
Title:Modelling complex investment decisions in Germany for Renewables with different machine learning algorithms
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Frey, Ulrich J.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Klein, MartinUNSPECIFIEDhttps://orcid.org/0000-0001-7283-4707UNSPECIFIED
Deissenroth, MarcUNSPECIFIEDhttps://orcid.org/0000-0002-9103-418XUNSPECIFIED
Date:2019
Journal or Publication Title:Environmental Modelling & Software
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1016/j.envsoft.2019.03.006
Publisher:Elsevier
ISSN:1364-8152
Status:Published
Keywords:investment decisions; solar installation; renewable energy; deep learning; machine learning; Germany
HGF - Research field:Energy
HGF - Program:Technology, Innovation and Society
HGF - Program Themes:Renewable Energy and Material Resources for Sustainable Futures - Integrating at Different Scales
DLR - Research area:Energy
DLR - Program:E SY - Energy Systems Analysis
DLR - Research theme (Project):E - Systems Analysis and Technology Assessment (old)
Location: Stuttgart
Institutes and Institutions:Institute of Engineering Thermodynamics > Systems Analysis and Technology Assessment
Deposited By: Frey, Ulrich
Deposited On:23 Aug 2019 15:38
Last Modified:03 Nov 2023 09:16

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.