Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 7;15(1):24266.
doi: 10.1038/s41598-025-07584-4.

AI driven automation for enhancing sustainability efforts in CDP report analysis

Ramya Rangarajan  1 , Tamilarasi Kathirvel Murugan  2 , Logeswari Govindaraj  1 , Venyaa Venkataraman  1 , Krithik Shankar  1
Affiliations

AI driven automation for enhancing sustainability efforts in CDP report analysis

Ramya Rangarajan et al. Sci Rep. .

Abstract

The need for sustainable practices in supply chains is becoming increasingly critical, as businesses face pressure to reduce their carbon footprint while maintaining operational efficiency. This paper proposes a novel hybrid approach that combines Genetic Algorithms (GA) with Long Short-Term Memory (LSTM) networks to optimize supply chain sustainability. The proposed system leverages publicly available Carbon Disclosure Project (CDP)-reported data to predict emissions and optimize resource allocation. The primary objective of this research is to develop a cost-effective, scalable solution that reduces emissions, improves operational efficiency, and ensures regulatory compliance within supply chains. The hybrid model consists of two main components: LSTM networks for predictive modeling of emission trends and GA for optimization of supply chain processes. LSTM is used to forecast future emissions based on historical data, while GA optimizes resource management, including transportation choices and energy consumption, to minimize emissions and operational costs. The system employs a multi-objective optimization approach, addressing the simultaneous goals of emission reduction, operational efficiency, and compliance with environmental regulations. The experimental results demonstrate the effectiveness of the proposed approach. A 23.67% reduction in total emissions was achieved, with the most significant improvements in indirect emissions. The system also improved operational efficiency by 10.98%, while ensuring 100% compliance with environmental regulations, eliminating any penalties. The hybrid GA-LSTM framework offers valuable insights for businesses seeking to meet sustainability targets and provides a practical, data-driven method for improving supply chain performance. The proposed system is not only applicable to large corporations but can also be scaled for use in small and medium-sized enterprises, offering a pathway for widespread adoption of sustainable practices across industries.

Keywords: Carbon disclosure project; Emissions optimization; Genetic algorithm; Long short-term memory; Resource efficiency; Sustainability.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Consent for publication: All authors have read and approved the manuscript.

Figures

Fig. 1
Fig. 1
Proposed system framework.
Fig. 2
Fig. 2
Process flow of the CDP.
Fig. 3
Fig. 3
Comparisons of emissions before and after optimization.
Fig. 4
Fig. 4
Fitness score vs. generations.
Fig. 5
Fig. 5
Emission vs. renewable energy usage.
Fig. 6
Fig. 6
Transportation emissions vs. efficiency.
Fig. 7
Fig. 7
Multi-objective optimization.
Fig. 8
Fig. 8
Comparison of emission reduction.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Cordero, D., Juiz, C., Mory, A., Bermeo, V. & Andrade, D. Model for the intent to adopt green IT in the context of organizations. IEEE Access10, 65636–65657. 10.1109/ACCESS.2022.3184727 (2022).
    1. Akhtar, I., Kirmani, S., Jameel, M. & Alam, F. Feasibility analysis of solar technology implementation in restructured power sector with reduced carbon footprints. IEEE Access9, 30306–30320. 10.1109/ACCESS.2021.3059297 (2021).
    1. Savazzi, S., Rampa, V., Kianoush, S. & Bennis, M. An energy and carbon footprint analysis of distributed and federated learning. IEEE Trans. Green Commun. Netw.7(1), 248–264. 10.1109/TGCN.2022.3186439 (2023).
    1. González-González, J., García-Méndez, S., De Arriba-Pérez, F., González-Castaño, F. J. & Barba-Seara, Ó. Explainable automatic industrial carbon footprint estimation from bank transaction classification using natural language processing. IEEE Access10, 126326–126338. 10.1109/ACCESS.2022.3226324 (2022).
    1. Hans, M., Hikmawati, E. & Surendro, K. Predictive analytics model for optimizing carbon footprint from students’ learning activities in computer science-related majors. IEEE Access11, 114976–114991. 10.1109/ACCESS.2023.3324725 (2023).

LinkOut - more resources