A dual encounter logarithmic path neural network for precision carbon emission monitoring and mitigation

Mohammad Barr; Tawfeeq Shawly; Ahmed A. Alsheikhy; Sahbi Boubaker; Mohammad Barr; Tawfeeq Shawly; Ahmed A. Alsheikhy; Sahbi Boubaker

doi:10.3934/math.2026400

AIMS Mathematics

2026, Volume 11, Issue 4: 9655-9685. doi: 10.3934/math.2026400

Previous Article Next Article

Research article

A dual encounter logarithmic path neural network for precision carbon emission monitoring and mitigation

1.
Department of Electrical Engineering, College of Engineering, Northern Border University, Arar 91431, Saudi Arabia; Email: mohammed.barr@nbu.edu.sa
2.
Department of Electrical Engineering, Faculty of Engineering at Rabigh, King Abdulaziz University, Jeddah 21589, Saudi Arabia; Email: tshawly@kau.edu.sa
3.
Department of Computer and Network Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah 21959, Saudi Arabia; Email: aaalsheikhy@uj.edu.sa, sboubaker@uj.edu.sa

Received: 19 January 2026 Revised: 06 March 2026 Accepted: 19 March 2026 Published: 10 April 2026
MSC : 68T07, 68T10, 68T20

Monitoring and reducing carbon footprints are crucial for achieving sustainability and effectively tackling climate change. Given the urgent global need to address climate change and to participate in Saudi Arabia's Vision 2030, we present DeepCarbonNet (EcoNet), a novel deep learning (DL) framework to monitor, analyze, and reduce carbon emissions. The framework is built using a new Dual Encounter Logarithmic Path Neural Network (DELPNN) architecture, including a novel Spatial Encounter Pathway (SEP), which processes high-resolution satellite images through a Logarithmic Convolutional Encoder (LCE) to extract multi-scale spatial features, and a new Temporal Encounter Pathway (TEP), which processes sequential Internet of Things (IoT) sensor and energy consumption data via a Gated Logarithmic Recurrent Unit (GLRU) and a central Feature Fusion Operator (FFO) that integrates the spatial and temporal features using cross-attention mechanisms and projects them into a logarithmic latent space to capture intricate, non-linear emission dynamics. This approach enables the precise capture of spatial and temporal dependencies within carbon emission data, achieving an outstanding level of accuracy. The simulation experimental results demonstrated that EcoNet attains a high accuracy of 98.7% in estimating carbon footprints after training the model on two public datasets. Furthermore, the model employed a reinforcement learning (RL)-based optimization strategy, enabling a 29.4% reduction in emissions through adaptive mitigation techniques. EcoNet was designed to adapt to changing conditions and promote environmental sustainability continuously. Beyond monitoring, EcoNet achieved a 32.8% improvement in energy efficiency. Additionally, the framework demonstrated robust performance across weather conditions, with 97.0-98.7% accuracy and an accuracy of emission intensities between 94.2–99.1%. These results showed that EcoNet is a solution for artificial intelligence (AI)-driven environmental sustainability, which offers immediate practical value for industrial monitoring, smart city management, logistic services to reduce fuel consumption, and national sustainability programs.
- DeepCarbonNet,
- climate change,
- sustainability,
- carbon emission,
- carbon footprint monitoring,
- emission reduction optimization,
- real-time monitoring,
- logistics
Citation: Mohammad Barr, Tawfeeq Shawly, Ahmed A. Alsheikhy, Sahbi Boubaker. A dual encounter logarithmic path neural network for precision carbon emission monitoring and mitigation[J]. AIMS Mathematics, 2026, 11(4): 9655-9685. doi: 10.3934/math.2026400

Related Papers:

Abstract

Monitoring and reducing carbon footprints are crucial for achieving sustainability and effectively tackling climate change. Given the urgent global need to address climate change and to participate in Saudi Arabia's Vision 2030, we present DeepCarbonNet (EcoNet), a novel deep learning (DL) framework to monitor, analyze, and reduce carbon emissions. The framework is built using a new Dual Encounter Logarithmic Path Neural Network (DELPNN) architecture, including a novel Spatial Encounter Pathway (SEP), which processes high-resolution satellite images through a Logarithmic Convolutional Encoder (LCE) to extract multi-scale spatial features, and a new Temporal Encounter Pathway (TEP), which processes sequential Internet of Things (IoT) sensor and energy consumption data via a Gated Logarithmic Recurrent Unit (GLRU) and a central Feature Fusion Operator (FFO) that integrates the spatial and temporal features using cross-attention mechanisms and projects them into a logarithmic latent space to capture intricate, non-linear emission dynamics. This approach enables the precise capture of spatial and temporal dependencies within carbon emission data, achieving an outstanding level of accuracy. The simulation experimental results demonstrated that EcoNet attains a high accuracy of 98.7% in estimating carbon footprints after training the model on two public datasets. Furthermore, the model employed a reinforcement learning (RL)-based optimization strategy, enabling a 29.4% reduction in emissions through adaptive mitigation techniques. EcoNet was designed to adapt to changing conditions and promote environmental sustainability continuously. Beyond monitoring, EcoNet achieved a 32.8% improvement in energy efficiency. Additionally, the framework demonstrated robust performance across weather conditions, with 97.0-98.7% accuracy and an accuracy of emission intensities between 94.2–99.1%. These results showed that EcoNet is a solution for artificial intelligence (AI)-driven environmental sustainability, which offers immediate practical value for industrial monitoring, smart city management, logistic services to reduce fuel consumption, and national sustainability programs.

References

[1]	The evidence is clear: the time for action is now. We can halve emissions by 2030, The Intergovernmental Panel on Climate Change (IPCC). Available from: https://www.ipcc.ch/2022/04/04/ipcc-ar6-wgiii-pressrelease/?utm_source = chatgpt.com.
[2]	Kingdom of Saudi Arabia, Saudi Vision 2030. Available from: https://www.vision2030.gov.sa/media/rc0b5oy1/saudi_vision203.pdf.
[3]	L. F. W. Anthony, B. Kanding, R. Selvan, Carbontracker: Tracking and predicting the carbon footprint of training deep learning models, arXiv: 2007.03051, 2020, 1–11.
[4]	S. Budenny, V. Lazarev, N. Zakharenko, A. Korovin, O. Plosskaya, D. Dimitrov, et al., Eco2AI: Carbon emissions tracking of machine learning models as the first step towards sustainable AI, Adv. Stud. Artif. Intell. Mach. Learn., 106 (2023), s118–s128. https://doi.org/10.1134/S1064562422060230 doi: 10.1134/S1064562422060230
[5]	N. Cooper, A. White, IPCC report: urgent climate action needed to halve emissions by 2030, World Economic Forum. Available from: https://www.weforum.org/stories/2022/04/ipcc-report-mitigation-climate-change/?utm_source = chatgpt.com.
[6]	New IPCC report: Emissions can be halved by 2030, United Nations: Regional Information Center for Western Europe. Available from: https://unric.org/en/new-ipcc-report-emissions-can-be-halved-by-2030/?utm_source = chatgpt.com.
[7]	Saudi Green Initiatives, Vision 2030. Available from: https://www.vision2030.gov.sa/en/explore/projects/saudi-green-initiative?utm_source = chatgpt.com.
[8]	Efficiency for a better future, more sustainable resources, Saudi Energy Efficiency Center. Available from: https://www.seec.gov.sa/en.
[9]	H. Cho, E. Ackom, Artificial intelligence (AI)–driven approach to climate action and sustainable development, Nat. Commun., 16 (2025), 1228, 1–12. https://doi.org/10.1038/s41467-024-53956-1 doi: 10.1038/s41467-024-53956-1
[10]	B. G. Kang, Y. Nam, Responsible artificial intelligence for climate action: A theoretical framework for sustainable development, Sustain. Mach. Intell. J., 8 (2024), 1–13. https://doi.org/10.61356/SMIJ.2024.88101 doi: 10.61356/SMIJ.2024.88101
[11]	J. Liu, G. Liu, H. Zhao, J. Zhao, J. Qiu, Z. Y. Dong, Real–time industrial carbon emission estimation with deep learning–based device recognition and incomplete smart meter data, Eng. Appl. Artif. Intell., 127 (2024), 107272. https://doi.org/10.1016/j.engappai.2023.107272 doi: 10.1016/j.engappai.2023.107272
[12]	N. Priya, K. Srinidhi, T. Kousalya, Carbon footprint monitoring system using machine learning and deep learning techniques, 12th International Conference on Advanced Computing (ICoAC) (2023), Chennai, India, 2023, 1–8. https://doi.org/10.1109/ICoAC59537.2023.10250070
[13]	C. P. Ezenkwu, S. Cannon, E. Ibeke, Monitoring carbon emissions using deep learning and statistical process control: a strategy for impact assessment of governments' carbon reduction policies, Environ. Monit. Assess., 196 (2024), 1–15. https://doi.org/10.1007/s10661-024-12388-6 doi: 10.1007/s10661-024-12388-6
[14]	H. Pan, C. Wu, Bayesian optimization + XGBoost based life cycle carbon emission prediction for residential buildings—An example from Chengdu, China, Build. Simul., 16 (2023), 1451–1466. https://doi.org/10.1007/s12273-023-1024-2 doi: 10.1007/s12273-023-1024-2
[15]	J. Rao, Y. He, Forecasting the energy intensity of industrial sector in China based on FCM–RS–SVM model, Environ. Sci. Pollut. Res., 30 (2023), 46669–46684. https://doi.org/10.1007/s11356-023-25511-w doi: 10.1007/s11356-023-25511-w
[16]	M. Fattah, S. R. Morshed, S. Y. Morshed, Multi–layer perceptron–Markov chain–based artificial neural network for modelling future land–specific carbon emission pattern and its influences on surface temperature, SN Appl. Sci., 3 (2021), 359, 1–22. https://doi.org/10.1007/s42452-021-04351-8 doi: 10.1007/s42452-021-04351-8
[17]	H. Jahangir, H. Tayarani, S. S. Gougheri, M. A. Golkar, A. Ahmadian, A. Elkamel, Deep learning–based forecasting approach in smart grids with microclustering and bidirectional LSTM network, IEEE T. Ind. Electron., 68 (2021), 8298–8309. https://doi.org/10.1109/TIE.2020.3009604 doi: 10.1109/TIE.2020.3009604
[18]	A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, et al., An image is worth 16x16 words: Transformers for image recognition at scale, Adv. Neural Inform. Process. Syst. (NeurIPS), 33 (2020), 4846–4858.
[19]	X. Zhang, C. Song, J. Zhao, Z. Xu, X. Deng, Spatial–temporal causality modeling for industrial processes with a knowledge–data guided reinforcement learning, IEEE T. Ind. Inform., 20 (2024), 5634–5646. https://doi.org/10.1109/TII.2023.3333921 doi: 10.1109/TII.2023.3333921
[20]	EDGAR–Emissions database for global atmospheric research, European Commission. Available from: https://edgar.jrc.ec.europa.eu.
[21]	EarthData, OCO–2, NASA. Available from: https://www.earthdata.nasa.gov/data/platforms/space–based–platforms/oco–2.
[22]	M. C. Chiu, Y. L. Tu, M. C. Kao, Applying deep learning image recognition technology to promote environmentally sustainable behavior, Sustain. Prod. Consump., 31 (2022), 736–749. https://doi.org/10.1016/j.spc.2022.03.031 doi: 10.1016/j.spc.2022.03.031
[23]	B. Wang, L. Hua, H. Mei, Y. Kang, N. Zhao, Monitoring marine pollution for carbon neutrality through a deep learning method with multi–source data fusion, Front. Ecol. Evol., 11 (2023), 1257542, 1–19. https://doi.org/10.3389/fevo.2023.1257542 doi: 10.3389/fevo.2023.1257542
[24]	W. Saetang, S. C. Arayalert, S. Kajornkasirat, J. Kongcharoen, A. Saeliw, K. Puangsuwan, et al., Eco–friendly office platform: Leveraging machine learning and GIS for carbon footprint management and green space analysis, Sustainability, 16 (2024), 9424, 1–20. https://doi.org/10.3390/su16219424 doi: 10.3390/su16219424
[25]	B. U. M. Enriquez, M. Rangel–Ayala, Y. Kumar, J. E. Garcia, J. F. Gomez–Aguilar, S. Khandual, et al., Multifunctional arthrospira platensis biomass derived carbon dots: Sensing/removal of heavy metal ions, high–power light–emitting devices, and some machine learning assisted approaches for solid state sensor, J. Environ. Chem. Eng., 13 (2025), 5. https://doi.org/10.1016/j.jece.2025.117827 doi: 10.1016/j.jece.2025.117827
[26]	W. Ajbar, M. Cervantes–Bobadilla, J. A. Hernández–Pérez, J. E. Solis–Perez, J. F. Gómez–Aguilar, J. García–Morales, et al., Expert system for the parabolic trough collector control through classical and conformable transfer functions in ANNi–PSO, Expert Syst. Appl., 280 (2025). https://doi.org/10.1016/j.eswa.2025.127343 doi: 10.1016/j.eswa.2025.127343

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)