# Thermodynamical Material Networks for Modeling, Planning, and Control of Circular Material Flows

arXiv: https://arxiv.org/abs/2111.10693 · HTML: https://mlsanity.com/paper/2111.10693/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2021.

## Built on by (most cited first, 4 of 4)

- [Synchronized Object Detection for Autonomous Sorting, Mapping, and Quantification of Materials in Circular Healthcare](https://mlsanity.com/paper/2405.06821/) (2024)
- [Circular Microalgae-Based Carbon Control for Net Zero](https://mlsanity.com/paper/2502.02382/) (2025)
- [Visual Material Characteristics Learning for Circular Healthcare](https://mlsanity.com/paper/2309.04763/) (2023)
- [CiRL: Open-Source Environments for Reinforcement Learning in Circular Economy and Net Zero](https://mlsanity.com/paper/2505.21536/) (2025)

## Abstract (arXiv)

Waste production, carbon dioxide atmospheric accumulation, and dependence on finite natural resources are expressions of the unsustainability of the current industrial networks that supply fuels, energy, and manufacturing products. In particular, circular manufacturing supply chains and carbon control networks are urgently needed. To model and design these and, in general, any material networks, we propose to generalize the approach used for traditional networks such as water and thermal power systems by using compartmental dynamical thermodynamics and graph theory. The key idea is that the thermodynamic compartments and their connections can be added, removed or modified as needed to achieve a circular material flow. The design methodology is explained and its application is illustrated through examples. In addition, we provide a physics-based definition of circularity and, by implementing a nonlinear compartmental control, we strengthen the connection between "Industry 4.0" and "Sustainability". The paper source code is publicly available.