Justus Caspers

Mr. Justus Caspers

TU Berlin
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 July 2024 in Journal of Industrial Ecology
Verified
Journal Article
Open access
NHNicolas Hübner
Nicolas Hübner
JCJustus Caspers
Justus Caspers
VCVlad Constantin Coroamă
Vlad Constantin Coroamă
MFMatthias Finkbeiner
Matthias Finkbeiner
Rapid advancements in artificial intelligence (AI) are driving transformative changes in many areas, with significant environmental implications. Yet, environmental assessments for specific applications are scarce. This study presents an in‐depth life cycle assessment of “Foodforecast,” a machine learning (ML) cloud service designed to reduce food waste in bakeries by optimizing sales forecasting. It covers four impact categories: global warming, abiotic resource depletion, cumulative energy demand, and freshwater eutrophication. The assessment includes both the direct environmental impacts of the ML model and the underlying system hardware, as well as the indirect benefits of avoided bakery returns compared to traditional ordering methods, using real‐world case study data. In 2022, “Foodforecast” led to an average 30% reduction in bakery returns, primarily bread and rolls, according to sales reports. The associated environmental benefits significantly outweighed the system's direct impacts by one to three orders of magnitude across impact categories and return utilization scenarios. The study identifies support activities such as service maintenance during deployment as major direct impact factors, surpassing those from cloud compute for ML operations. Data processing and inference dominate the latter, while the much‐discussed ML training plays a minor role. The environmental consequences of AI are complex and dual sided. This case study demonstrates that AI might provide environmental benefits in certain contexts, yet results are constrained by methodological challenges and data uncertainties. There remains a need for further holistic LCAs across different ML applications to inform decision‐making processes and ultimately guide the responsible use of AI.

28 February 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
JCJustus Caspers
Justus Caspers
ESElisabeth Süßbauer
Elisabeth Süßbauer
VCVlad Coroama
Vlad Coroama
Matthias FinkbeinerMatthias Finkbeiner
Matthias Finkbeiner
Consumer behavior can significantly influence the environmental impact of products. Takeaway food and beverage packaging can be assumed to be an example of this effect, as consumers directly affect its disposal or, in the case of reusable packaging, the reuse rate. While possible environmental impacts of takeaway food and beverage packaging are comprehensively discussed in available Life Cycle Assessment (LCA) studies, consumer behavior is not extensively considered. Thus, a literature review was used to analyze existing LCAs of takeaway food and beverage packaging regarding three aspects: (i) the extent to which consumers are considered in the use phase, (ii) the inclusion of littering, and (iii) the consideration of consumer behavior in the End-of-Life (EoL) phase. The analysis shows that none of the reviewed LCAs includes all reviewed aspects of consumer behavior, and that the depth of implementation varied significantly. We conclude that, currently, the topic is not adequately considered in available LCAs and future studies need to address it more widely. This is especially important for the comparison of single-use and reusable takeaway packaging, as consumer behavior significantly influences the environmental impact of both systems. Finally, we argue why a method that includes littering on takeaway packaging needs to be developed.

23 October 2020 in Sustainability
Verified
Journal Article
Open access
PDF file
SLSergej Lisowski
Sergej Lisowski
Markus BergerMarkus Berger
Markus Berger
JCJustus Caspers
Justus Caspers
KMKlaus Mayr-Rauch
Klaus Mayr-Rauch
GBGeorg Bäuml
Georg Bäuml
Matthias FinkbeinerMatthias Finkbeiner
Matthias Finkbeiner
The United Nations Sustainable Development Goals (SDGs) cannot be met without the private sector. In order to contribute to the fulfillment of the SDGs, companies have to identify their influence and select relevant SDGs. However, so far no research has been conducted on the influence of companies or industries at the most concrete level in the SDG framework—the 247 SDG indicators. In this paper, a criteria-based approach to select relevant environmental SDG indicators for the automobile industry is developed. The three criteria—environmental impact, direct impact, and automobile impact—are defined. By means of a qualitative analysis, 31 influenceable indicators are selected and substantiated by an empirical analysis of the automobile industry’s impact. These indicators belong to 12 SDGs and demonstrate the broad influence of the automobile industry. The outcome of this study is a structured procedure for selecting relevant environmental SDG indicators. This procedure can be applied by companies and can also be adapted to other economic sectors. Finally, it is possible to quantify the level of influence of the selected indicators and thus measure the contributions of companies or economic sectors to the fulfillment of the SDGs.

12 February 2025 in Cleaner Engineering and Technology
Verified
Journal Article
Open access
JCJustus Caspers
Justus Caspers
PBPauline Bade
Pauline Bade
MFMatthias Finkbeiner
Matthias Finkbeiner

7 July 2025 in Journal of Cleaner Production
Verified
Journal Article
Open access
JCJustus Caspers
Justus Caspers
MFMatthias Finkbeiner
Matthias Finkbeiner

9 October 2020 in MÜLL und ABFALL
Verified
Journal Article
Closed access
ESElisabeth Süßbauer
Elisabeth Süßbauer
HWHenning Wilts
Henning Wilts
SOSarah Julie Otto
Sarah Julie Otto
JSJennifer Schinkel
Jennifer Schinkel
KWKlara Wenzel
Klara Wenzel
SJSvenja Jürgens
Svenja Jürgens